ADAS audio automotive availability estimation business cloud consumer electronics context-aware deep learning digital TV education functional safety gaming HMI human detection ieeexplore image processing infotainment internet of things keynote lighting control market research networks recommendation RSSI smart homes software framework user experience user interface user monitoring
2024 |
Bjelica, Milan Z Making Smart Systems Safe and Secure: Caveats and Blueprints from the Automotive Industry ConferenceM32 2024 International Conference on Smart Systems and Technologies (SST), IEEE, 2024, ISBN: 979-8-3503-8639-4. Abstract | Links | BibTeX | Tags: automotive, consumer electronics, cybersecurity, functional safety @conference{SST2024, title = {Making Smart Systems Safe and Secure: Caveats and Blueprints from the Automotive Industry}, author = {Milan Z. Bjelica}, doi = {10.1109/SST61991.2024.10755316}, isbn = {979-8-3503-8639-4}, year = {2024}, date = {2024-10-17}, booktitle = {2024 International Conference on Smart Systems and Technologies (SST)}, publisher = {IEEE}, abstract = {Smart systems and technologies continue to proliferate across industry domains. The introduction of digital technologies and complex software in the consumer industries, such as the Internet or media distribution, was a success story. However, the introduction of software-defined approaches in safety and security-critical industries, such as smart cities, factories or mobility, presents many caveats. In the talk, we are dissecting the blueprints for safe and secure developments in the automotive industry, applied to automated and autonomous driving. The audience would be offered a comprehensible overview of how modern standards, such as ASPICE, ISO 26262 and ISO 21434 can be applied in companies to construct a compelling safety and security case for road vehicles and their items. Caveats and key challenges around software complexity will be presented, giving ideas on how to bridge the gap between the agility and somewhat ad-hoc practices of present-day software engineers, with the rigor required to deliver safe and secure solutions. }, howpublished = {M32}, keywords = {automotive, consumer electronics, cybersecurity, functional safety}, pubstate = {published}, tppubtype = {conference} } Smart systems and technologies continue to proliferate across industry domains. The introduction of digital technologies and complex software in the consumer industries, such as the Internet or media distribution, was a success story. However, the introduction of software-defined approaches in safety and security-critical industries, such as smart cities, factories or mobility, presents many caveats. In the talk, we are dissecting the blueprints for safe and secure developments in the automotive industry, applied to automated and autonomous driving. The audience would be offered a comprehensible overview of how modern standards, such as ASPICE, ISO 26262 and ISO 21434 can be applied in companies to construct a compelling safety and security case for road vehicles and their items. Caveats and key challenges around software complexity will be presented, giving ideas on how to bridge the gap between the agility and somewhat ad-hoc practices of present-day software engineers, with the rigor required to deliver safe and secure solutions. |
Bjelica, Milan Z Designing a safe autonomous vehicle computer - where we are, where we should be and a hands-on example ConferenceM32 2024 IEEE International Conference on Consumer Electronics (ICCE), IEEE, 2024, ISBN: 979-8-3503-2413-6. Abstract | Links | BibTeX | Tags: ADAS, automotive, functional safety @conference{ICCE2024, title = {Designing a safe autonomous vehicle computer - where we are, where we should be and a hands-on example}, author = {Milan Z. Bjelica}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10444258}, doi = {10.1109/ICCE59016.2024.10444258}, isbn = {979-8-3503-2413-6}, year = {2024}, date = {2024-01-05}, booktitle = {2024 IEEE International Conference on Consumer Electronics (ICCE)}, publisher = {IEEE}, abstract = {In the last two years, we have witnessed the increased push to legislators to approve the robotaxi vehicles in several cities in the USA for commercial use, with two permits Issued, and one revoked. The endeavor to proliferate self-driving vehicles proves to be very hard, since the technology stack required, dominated by software, presents extreme challenges In safety critical design and certification according to practices laid out in ISO 26262 and ISO 21448 SOTIF. In this tutorial we would contrast the due diligence in automotive functional safety with the real-world design challenges and what has been deployed on roads. We would discuss legal debates around the technology shortcomings following the first lawsuits regarding the casualties caused by the car autopilots. Finally, we would work out in a hands-on example a process of designing a safe autonomous vehicle computer for a traffic jam pilot function, witnessing all the challenges first hand.}, howpublished = {M32}, keywords = {ADAS, automotive, functional safety}, pubstate = {published}, tppubtype = {conference} } In the last two years, we have witnessed the increased push to legislators to approve the robotaxi vehicles in several cities in the USA for commercial use, with two permits Issued, and one revoked. The endeavor to proliferate self-driving vehicles proves to be very hard, since the technology stack required, dominated by software, presents extreme challenges In safety critical design and certification according to practices laid out in ISO 26262 and ISO 21448 SOTIF. In this tutorial we would contrast the due diligence in automotive functional safety with the real-world design challenges and what has been deployed on roads. We would discuss legal debates around the technology shortcomings following the first lawsuits regarding the casualties caused by the car autopilots. Finally, we would work out in a hands-on example a process of designing a safe autonomous vehicle computer for a traffic jam pilot function, witnessing all the challenges first hand. |
2023 |
Kaštelan, Ivan; Popović, Miroslav; Bjelica, Milan Z A Learning Model for Lifelong Education of Computer Engineers Journal ArticleM22 IEEE Access, 11 , pp. 101296 - 101308, 2023, ISSN: 2169-3536. Abstract | Links | BibTeX | Tags: consumer electronics, education @article{Access2023, title = {A Learning Model for Lifelong Education of Computer Engineers}, author = {Ivan Kaštelan and Miroslav Popović and Milan Z. Bjelica}, doi = {10.1109/ACCESS.2023.3314760}, issn = {2169-3536}, year = {2023}, date = {2023-09-13}, journal = {IEEE Access}, volume = {11}, pages = {101296 - 101308}, publisher = {IEEE}, abstract = {It has been noted that education advances at a much slower rate than modern technologies. Rapid development of modern technologies has led to the increasing need for high quality engineers, but the Universities usually do not keep the same pace. This increases the importance of lifelong learning for engineers, especially those working in quickly developing disciplines such as computer engineering and specialized software for consumer and automotive technologies. The objective of this paper is to propose a learning model suitable for application in lifelong learning setting, aimed at agile education of engineers in the computer engineering field. One example course that follows this learning model is presented in detail. The learning model was applied in courses offered to computer engineers working in consumer and automotive industries. Learning effectiveness of the proposed model was measured by summative assessment in the courses. Experiences from learners that were collected in the end-of-course surveys provide insight into positive and negative aspects of this learning model. The overall feedback received from learners was positive and this may indicate that the proposed learning model has advantages over existing models used in lifelong education.}, howpublished = {M22}, keywords = {consumer electronics, education}, pubstate = {published}, tppubtype = {article} } It has been noted that education advances at a much slower rate than modern technologies. Rapid development of modern technologies has led to the increasing need for high quality engineers, but the Universities usually do not keep the same pace. This increases the importance of lifelong learning for engineers, especially those working in quickly developing disciplines such as computer engineering and specialized software for consumer and automotive technologies. The objective of this paper is to propose a learning model suitable for application in lifelong learning setting, aimed at agile education of engineers in the computer engineering field. One example course that follows this learning model is presented in detail. The learning model was applied in courses offered to computer engineers working in consumer and automotive industries. Learning effectiveness of the proposed model was measured by summative assessment in the courses. Experiences from learners that were collected in the end-of-course surveys provide insight into positive and negative aspects of this learning model. The overall feedback received from learners was positive and this may indicate that the proposed learning model has advantages over existing models used in lifelong education. |
Bjelica, Milan Z; Mrazovac, Bojan Reliability of Self-Driving Cars: When Can We Remove the Safety Driver? Journal ArticleM21 IEEE Intelligent Transportation Systems Magazine, 15 (4), pp. 46-54, 2023, ISSN: 1939-1390. Abstract | Links | BibTeX | Tags: automotive, functional safety, reliability @article{BjelicaITSM2023a, title = {Reliability of Self-Driving Cars: When Can We Remove the Safety Driver?}, author = {Milan Z. Bjelica and Bojan Mrazovac}, url = {https://ieeexplore.ieee.org/document/10056924}, doi = {10.1109/mits.2023.3244271}, issn = {1939-1390}, year = {2023}, date = {2023-07-01}, journal = {IEEE Intelligent Transportation Systems Magazine}, volume = {15}, number = {4}, pages = {46-54}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, abstract = {Self-driving cars and other vehicles are being increasingly demonstrated, released, and deployed on roads. Yet only a handful of special-case vehicles have obtained a permit to go fully driverless, and our passenger cars still require drivers at the steering wheel to correct the car if something goes wrong. Safety drivers, which operate autonomous vehicles in testing phases, upon occasions were unable to correct the faulty behavior of their vehicles, inducing accidents and, unfortunately, casualties. This article proposes a method to analyze the reliability of autonomous vehicles applying the classical reliability theory and software reliability growth models (SRGMs). This method is then applied to real-world data to get some predictions on what is really needed to safely remove the driver and go fully driverless.}, howpublished = {M21}, keywords = {automotive, functional safety, reliability}, pubstate = {published}, tppubtype = {article} } Self-driving cars and other vehicles are being increasingly demonstrated, released, and deployed on roads. Yet only a handful of special-case vehicles have obtained a permit to go fully driverless, and our passenger cars still require drivers at the steering wheel to correct the car if something goes wrong. Safety drivers, which operate autonomous vehicles in testing phases, upon occasions were unable to correct the faulty behavior of their vehicles, inducing accidents and, unfortunately, casualties. This article proposes a method to analyze the reliability of autonomous vehicles applying the classical reliability theory and software reliability growth models (SRGMs). This method is then applied to real-world data to get some predictions on what is really needed to safely remove the driver and go fully driverless. |
Bjelica, Milan Z; Milošević, Milena; Petrović, Vladimir; Bjeković, Ognjen; Popović, Ivan Software platforms in next-generation vehicles: trends, varieties and challenges ConferenceM32 2023 Zooming Innovation in Consumer Technologies Conference (ZINC), IEEE, 2023, ISBN: 979-8-3503-4772-2. Abstract | Links | BibTeX | Tags: automotive, software framework @conference{ZINC2023, title = {Software platforms in next-generation vehicles: trends, varieties and challenges}, author = {Milan Z. Bjelica and Milena Milošević and Vladimir Petrović and Ognjen Bjeković and Ivan Popović}, doi = {10.1109/ZINC58345.2023.10174228}, isbn = {979-8-3503-4772-2}, year = {2023}, date = {2023-05-29}, booktitle = {2023 Zooming Innovation in Consumer Technologies Conference (ZINC)}, publisher = {IEEE}, abstract = {The new frontline in next-generation vehicles is tied to the concept of Software-Defined Vehicles (SDVs). One or several domain controllers handle the complete set of functionalities, including powertrain control, battery management, assisted driving, infotainment, and more. In this panel, we are contrasting actual approaches in complex software designs in vehicles coming from the industry and academia, and try to understand the trends and challenges for the future developments and aspiring suppliers. We are also challenging the robustness of such stacks against failures and discuss fault tolerance and functional safety mechanisms which should be built in.}, howpublished = {M32}, keywords = {automotive, software framework}, pubstate = {published}, tppubtype = {conference} } The new frontline in next-generation vehicles is tied to the concept of Software-Defined Vehicles (SDVs). One or several domain controllers handle the complete set of functionalities, including powertrain control, battery management, assisted driving, infotainment, and more. In this panel, we are contrasting actual approaches in complex software designs in vehicles coming from the industry and academia, and try to understand the trends and challenges for the future developments and aspiring suppliers. We are also challenging the robustness of such stacks against failures and discuss fault tolerance and functional safety mechanisms which should be built in. |
Bjelica, Milan Z Systems, Functions and Safety: A Flipped Approach to Design for Safety BookM11 Springer International Publishing, 2023, ISBN: 978-3-031-15822-3. Abstract | Links | BibTeX | Tags: automotive, functional safety @book{BjelicaSpringer2023, title = {Systems, Functions and Safety: A Flipped Approach to Design for Safety}, author = {Milan Z. Bjelica }, url = {https://link.springer.com/book/10.1007/978-3-031-15823-0}, doi = {10.1007/978-3-031-15823-0}, isbn = {978-3-031-15822-3}, year = {2023}, date = {2023-03-01}, volume = {1}, number = {1}, publisher = {Springer International Publishing}, abstract = {This textbook provides up-to-date content in the fields of system engineering, system safety and functional safety, with up-to-date examples from the automotive, industrial and aerospace domains, with respect to the growing complexity of the field and the increased utilization of complex hardware and software in vehicle designs. The book covers practical functional safety insights concerning the required standards (e.g. IEC 61508, IEC 62061, ISO 13849, ISO 26262), but also inherent system safety process as a key factor towards the mitigation of systematic faults. Readers will be equipped with a broad understanding of safety and functional safety, with balanced theoretical and practical views in this area. The book covers the specific topics of introduction to system engineering, overall system safety and its relation to functional safety. Functional safety is introduced in all the required concepts, terminology and safety analysis methods. Basic fault-tolerance concepts are covered, including the design considerations to achieve functional safety. The book also gives an introduction to the required system safety processes and the applications of relevant functional safety standards.}, howpublished = {M11}, keywords = {automotive, functional safety}, pubstate = {published}, tppubtype = {book} } This textbook provides up-to-date content in the fields of system engineering, system safety and functional safety, with up-to-date examples from the automotive, industrial and aerospace domains, with respect to the growing complexity of the field and the increased utilization of complex hardware and software in vehicle designs. The book covers practical functional safety insights concerning the required standards (e.g. IEC 61508, IEC 62061, ISO 13849, ISO 26262), but also inherent system safety process as a key factor towards the mitigation of systematic faults. Readers will be equipped with a broad understanding of safety and functional safety, with balanced theoretical and practical views in this area. The book covers the specific topics of introduction to system engineering, overall system safety and its relation to functional safety. Functional safety is introduced in all the required concepts, terminology and safety analysis methods. Basic fault-tolerance concepts are covered, including the design considerations to achieve functional safety. The book also gives an introduction to the required system safety processes and the applications of relevant functional safety standards. |
Mrazovac, Bojan; Bjelica, Milan Z Human-Centric Role in Self-Driving Vehicles: Can Human Driving Perception Change the Flavor of Safety Features? Journal ArticleM21 IEEE Intelligent Transportation Systems Magazine, 15 (1), pp. 117-125, 2023, ISSN: 1939-1390. Abstract | Links | BibTeX | Tags: automotive, functional safety, human detection @article{BjelicaITSM2023b, title = {Human-Centric Role in Self-Driving Vehicles: Can Human Driving Perception Change the Flavor of Safety Features?}, author = {Bojan Mrazovac and Milan Z. Bjelica}, url = {https://ieeexplore.ieee.org/document/9773320}, doi = {10.1109/mits.2022.3169597}, issn = {1939-1390}, year = {2023}, date = {2023-01-01}, journal = {IEEE Intelligent Transportation Systems Magazine}, volume = {15}, number = {1}, pages = {117-125}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, abstract = {Autonomous vehicles are expected to generate significant revenues for the global economy in the next decade. Recently, industry experts warned that autonomous vehicles are losing momentum. Self-driving is stalling. Fusing human sentiment and driving perception into a holistic approach to the development of human-centric autonomous vehicles could regain the market’s trust. In this article, we try to explain why the traditional approach to self-driving vehicles, which focuses only on perfecting vehicle performance, sends engineers back to the whiteboard.}, howpublished = {M21}, keywords = {automotive, functional safety, human detection}, pubstate = {published}, tppubtype = {article} } Autonomous vehicles are expected to generate significant revenues for the global economy in the next decade. Recently, industry experts warned that autonomous vehicles are losing momentum. Self-driving is stalling. Fusing human sentiment and driving perception into a holistic approach to the development of human-centric autonomous vehicles could regain the market’s trust. In this article, we try to explain why the traditional approach to self-driving vehicles, which focuses only on perfecting vehicle performance, sends engineers back to the whiteboard. |
2022 |
Simić, Đorđe; Stefanović, Stefan; Dankulov, Marija Mitrović; Stepanenko, Dimitrije; Bjelica, Milan Z Autonomous mobility: appropriate tools and verification practices ConferenceM32 2022 IEEE Zooming Innovation in Consumer Technologies Conference (ZINC), 2022, ISBN: 978-1-6654-8374-2. Abstract | Links | BibTeX | Tags: ADAS, automotive @conference{BjelicaZinc2022, title = {Autonomous mobility: appropriate tools and verification practices}, author = {Đorđe Simić and Stefan Stefanović and Marija Mitrović Dankulov and Dimitrije Stepanenko and Milan Z. Bjelica}, doi = {10.1109/ZINC55034.2022.9840668}, isbn = {978-1-6654-8374-2}, year = {2022}, date = {2022-05-25}, booktitle = {2022 IEEE Zooming Innovation in Consumer Technologies Conference (ZINC)}, abstract = {A panel of distinguished speakers from both industry and academia, discuss autonomous mobility “from within”. What is required to develop autonomous mobility solutions? Which algorithms are needed? Can we rely upon those solutions in realistic environments? Can we simulate the real world so that we can perform adequate laboratory pre-verification and validation? Institute of Physics Belgrade, SYRMIA LLC, and University of California San Diego discuss together with session presenters to answer the questions above!}, howpublished = {M32}, keywords = {ADAS, automotive}, pubstate = {published}, tppubtype = {conference} } A panel of distinguished speakers from both industry and academia, discuss autonomous mobility “from within”. What is required to develop autonomous mobility solutions? Which algorithms are needed? Can we rely upon those solutions in realistic environments? Can we simulate the real world so that we can perform adequate laboratory pre-verification and validation? Institute of Physics Belgrade, SYRMIA LLC, and University of California San Diego discuss together with session presenters to answer the questions above! |
Pavković, Bogdan; Marinković, Vladimir; Đorđević-Čegar, Dragana; Bjelica, Milan Z Safety done right: Systems, Software, Standards and Attitudes ConferenceM32 2022 IEEE Zooming Innovation in Consumer Technologies Conference (ZINC), 2022, ISBN: 978-1-6654-8374-2. Abstract | Links | BibTeX | Tags: automotive, functional safety, safety culture @conference{ZINC2022b, title = {Safety done right: Systems, Software, Standards and Attitudes}, author = {Bogdan Pavković and Vladimir Marinković and Dragana Đorđević-Čegar and Milan Z. Bjelica}, doi = {10.1109/ZINC55034.2022.9840691}, isbn = {978-1-6654-8374-2}, year = {2022}, date = {2022-05-25}, booktitle = {2022 IEEE Zooming Innovation in Consumer Technologies Conference (ZINC)}, abstract = {In this panel, we discuss the common pitfalls with new developments and solutions in safety-critical industries. Those industries are now increasingly getting digitized and starting to depend on complex hardware/software/mechanical configurations, often with centralized control by a computer. What should newcomers know when embarking on projects in autonomous mobility, Industry 4.0 and other disciplines? How to create safe solutions? Which role is played by hardware and software designs there? What about the standards and the required compliances? What about attitudes and understanding of safety in the teams? }, howpublished = {M32}, keywords = {automotive, functional safety, safety culture}, pubstate = {published}, tppubtype = {conference} } In this panel, we discuss the common pitfalls with new developments and solutions in safety-critical industries. Those industries are now increasingly getting digitized and starting to depend on complex hardware/software/mechanical configurations, often with centralized control by a computer. What should newcomers know when embarking on projects in autonomous mobility, Industry 4.0 and other disciplines? How to create safe solutions? Which role is played by hardware and software designs there? What about the standards and the required compliances? What about attitudes and understanding of safety in the teams? |
2021 |
Lazić, Nemanja; Ponoš, Milica Z; Bjelica, Milan Z; Anđelić, Tihomir; Pešić, Jasmina Automotive safety: ActivityView enabled split-screen ConferenceM33 2021 29th Telecommunications Forum (TELFOR), 2021, ISBN: 978-1-6654-2585-8. Abstract | Links | BibTeX | Tags: automotive, HMI, ieeexplore, infotainment, user experience @conference{2021tf1, title = {Automotive safety: ActivityView enabled split-screen}, author = {Nemanja Lazić and Milica Z. Ponoš and Milan Z. Bjelica and Tihomir Anđelić and Jasmina Pešić}, doi = {10.1109/TELFOR52709.2021.9653251}, isbn = {978-1-6654-2585-8}, year = {2021}, date = {2021-11-23}, booktitle = {2021 29th Telecommunications Forum (TELFOR)}, abstract = {In-Vehicle Infotainment systems are representatives of a new generation of multimedia in vehicle systems. As the name proposes, the main goal of these systems is to provide entertainment and informational content to the driver and passengers. Automotive industry is undergoing dramatic changes nowadays and there is a lack of standards for what operating system should be applied to certain vehicle display. Availability of Android operating system (AOS) on most of the modern portable devices and ability to re-use existing tested and reliable applications, encourage automotive industry to integrate AOS in vehicles, usually in head unit display. The goal is to build systems that will be easy to handle. It will impose minimal distraction of the driver. One way to achieve higher safety level while in traffic is by allowing driver to manipulate two or more applications simultaneously. This work is based on expanding multimedia system in the vehicle based on Android operating system so it can show two or more apps at the same time while using this new Android component called ActivityView. In this paper we argue that with this software component, interaction with central information display is going to be more efficient and safety will be enhancedas well.}, howpublished = {M33}, keywords = {automotive, HMI, ieeexplore, infotainment, user experience}, pubstate = {published}, tppubtype = {conference} } In-Vehicle Infotainment systems are representatives of a new generation of multimedia in vehicle systems. As the name proposes, the main goal of these systems is to provide entertainment and informational content to the driver and passengers. Automotive industry is undergoing dramatic changes nowadays and there is a lack of standards for what operating system should be applied to certain vehicle display. Availability of Android operating system (AOS) on most of the modern portable devices and ability to re-use existing tested and reliable applications, encourage automotive industry to integrate AOS in vehicles, usually in head unit display. The goal is to build systems that will be easy to handle. It will impose minimal distraction of the driver. One way to achieve higher safety level while in traffic is by allowing driver to manipulate two or more applications simultaneously. This work is based on expanding multimedia system in the vehicle based on Android operating system so it can show two or more apps at the same time while using this new Android component called ActivityView. In this paper we argue that with this software component, interaction with central information display is going to be more efficient and safety will be enhancedas well. |
Ponoš, Milica Z; Lazić, Nemanja; Bjelica, Milan Z; Anđelić, Tihomir; Manić, Milan Z One solution for integrating graphics in vehicle digital cockpit ConferenceM33 2021 29th Telecommunications Forum (TELFOR), IEEE, 2021, ISBN: 978-1-6654-2585-8. Abstract | Links | BibTeX | Tags: automotive, HMI, ieeexplore, infotainment @conference{2021tfb, title = {One solution for integrating graphics in vehicle digital cockpit}, author = {Milica Z. Ponoš and Nemanja Lazić and Milan Z. Bjelica and Tihomir Anđelić and Milan Z. Manić}, doi = {10.1109/TELFOR52709.2021.9653214}, isbn = {978-1-6654-2585-8}, year = {2021}, date = {2021-11-23}, booktitle = {2021 29th Telecommunications Forum (TELFOR)}, publisher = {IEEE}, abstract = {The accelerated development of the automotive industry and the impact of consumer technologies has contributed that many car manufacturers are switching from analogue to digital cockpits. Cockpits nowadays consist of a safety critical and a non-critical parts. The critical part of the system is the one that is necessary for safe driving, while the non-critical part of the system represents additional functionalities that make driving easier and more comfortable, but without them safe driving is possible. Each part of the system is displayed on a separate screen in a specific part of the cockpit. There are usually three displays - Central Information Display (CID) that represents non-critical part of the system, digital control panel - Cluster and Head-up display (HUD) that represent critical part of the system. These displays are controlled by two operating systems, which are connected by the hypervisor. A hypervisor is a concept that enables two operating systems to run simultaneously on one SoC in real- time. When critical and non-critical parts of a system are connected, it brings many safety issues. One of the problems is that sometimes information that is not necessary for safe driving, such as: information about an incoming call, the current song being played, is displayed on the Cluster. Displaying this information can affect the safety of Cluster operations. Therefore, it is necessary to somehow separate processing and displaying important from less important information for safe driving. In this paper we present one solution for displaying the maps information from the non- critical part of the system, on screen layer above Cluster that represents safety-critical part of the system.}, howpublished = {M33}, keywords = {automotive, HMI, ieeexplore, infotainment}, pubstate = {published}, tppubtype = {conference} } The accelerated development of the automotive industry and the impact of consumer technologies has contributed that many car manufacturers are switching from analogue to digital cockpits. Cockpits nowadays consist of a safety critical and a non-critical parts. The critical part of the system is the one that is necessary for safe driving, while the non-critical part of the system represents additional functionalities that make driving easier and more comfortable, but without them safe driving is possible. Each part of the system is displayed on a separate screen in a specific part of the cockpit. There are usually three displays - Central Information Display (CID) that represents non-critical part of the system, digital control panel - Cluster and Head-up display (HUD) that represent critical part of the system. These displays are controlled by two operating systems, which are connected by the hypervisor. A hypervisor is a concept that enables two operating systems to run simultaneously on one SoC in real- time. When critical and non-critical parts of a system are connected, it brings many safety issues. One of the problems is that sometimes information that is not necessary for safe driving, such as: information about an incoming call, the current song being played, is displayed on the Cluster. Displaying this information can affect the safety of Cluster operations. Therefore, it is necessary to somehow separate processing and displaying important from less important information for safe driving. In this paper we present one solution for displaying the maps information from the non- critical part of the system, on screen layer above Cluster that represents safety-critical part of the system. |
Popić, Srđan; Teslić, Nikola; Bjelica, Milan Z Simple Framework for Efficient Development of the Functional Requirement Verification-specific Language Journal ArticleM22 Advances in Electrical and Computer Engineering (AECE), 21 (3), pp. 11-20, 2021, ISSN: 1582-7445. Abstract | Links | BibTeX | Tags: software engineering @article{2021ro, title = {Simple Framework for Efficient Development of the Functional Requirement Verification-specific Language}, author = {Srđan Popić and Nikola Teslić and Milan Z. Bjelica}, doi = {10.4316/AECE.2021.03002}, issn = {1582-7445}, year = {2021}, date = {2021-08-31}, journal = {Advances in Electrical and Computer Engineering (AECE)}, volume = {21}, number = {3}, pages = {11-20}, abstract = {This paper presents the framework for the creation of various domain-specific languages for verification of the functional requirements. When it comes to Requirement Engineering and the process of Validation and Verification of the requirements, there are plenty of tools for modeling, analyzing, and validating the requirements. It comes as a full-blown set of applications for validation of the requirements. But the set of the verification tools is either too complex or usable in a narrow domain. From the customers' point of view, there is a need for another independent requirement verification. This tool enables the creation of the custom verification in a way that allows users (either clients or developers) to verify requirements. It follows the IEEE guides, standards, and best practices to check all aspects of the software requirements that are neither implemented nor checked by the validation process: correctness, completeness, traceability, dependency, importance, and uniqueness. Tool implements design patterns specific to the verification process, thus enabling the faster implementation of the language. The concept can be used for development of the verification-specific language with any type of requirement representation, which will be shown by a few examples.}, howpublished = {M22}, keywords = {software engineering}, pubstate = {published}, tppubtype = {article} } This paper presents the framework for the creation of various domain-specific languages for verification of the functional requirements. When it comes to Requirement Engineering and the process of Validation and Verification of the requirements, there are plenty of tools for modeling, analyzing, and validating the requirements. It comes as a full-blown set of applications for validation of the requirements. But the set of the verification tools is either too complex or usable in a narrow domain. From the customers' point of view, there is a need for another independent requirement verification. This tool enables the creation of the custom verification in a way that allows users (either clients or developers) to verify requirements. It follows the IEEE guides, standards, and best practices to check all aspects of the software requirements that are neither implemented nor checked by the validation process: correctness, completeness, traceability, dependency, importance, and uniqueness. Tool implements design patterns specific to the verification process, thus enabling the faster implementation of the language. The concept can be used for development of the verification-specific language with any type of requirement representation, which will be shown by a few examples. |
Bjelica, Milan Z Reliability Estimation for a Central Vehicle Computer with Upgradeable Software Components Masters Thesis University of Applied Sciences - FH CampusWien, 2021. BibTeX | Tags: automotive, functional safety, reliability @mastersthesis{2021fh, title = {Reliability Estimation for a Central Vehicle Computer with Upgradeable Software Components}, author = {Milan Z. Bjelica}, editor = {Peter Krebs}, year = {2021}, date = {2021-06-11}, address = {Vienna, Austria}, school = {University of Applied Sciences - FH CampusWien}, keywords = {automotive, functional safety, reliability}, pubstate = {published}, tppubtype = {mastersthesis} } |
Bjelica, Milan Z My Big, Fat, Safe Software Stack: Functional Safety for Complex Software for Next-Generation Vehicles ConferenceKeynoteM32 ECBS 2021: 7th Conference on the Engineering of Computer Based Systems, ACM, 2021, ISBN: 978-1-4503-9057-6, (Keynote). Abstract | Links | BibTeX | Tags: automotive, functional safety, software framework @conference{ecbs2021, title = {My Big, Fat, Safe Software Stack: Functional Safety for Complex Software for Next-Generation Vehicles}, author = {Milan Z. Bjelica}, doi = {10.1145/3459960.3461563}, isbn = {978-1-4503-9057-6}, year = {2021}, date = {2021-05-27}, booktitle = {ECBS 2021: 7th Conference on the Engineering of Computer Based Systems}, publisher = {ACM}, abstract = {I used to be enthusiastic about software. I liked clever, modular architectures; design patterns made for extensibility; virtualized, multi-application runtimes; seamless software updates; reusability in the harsh hardware-accelerated environments. And then, I was summoned to the automotive arena, which was in a desperate need for a centralized processing, artificial intelligence algorithms, service-oriented architectures and a fat software stack for the next-generation vehicles. It seemed like a dream job… at first. Only until I realized that to keep a promise I now need to adhere to the harsh world of reliability, safety and processes. This is a story of my software stack and me travelling, unscathed, following the challenging functional safety and reliability trail. In the keynote, I would give an initial proposal of a reliability estimation method for a Central Vehicle Computer which is dominated by software. The method would first address hardware reliability through the definition of key components, component failure rates and reliability block diagrams, which are based on current proposals of Central Vehicle Computer architectures with dual and triple redundancy, available in industry and research. Then, key software components are identified and positioned, with appropriate classification. Where appropriate, reliability of such components is estimated by means of test statistics obtained from field-trials and laboratory experiments, and also by applying software reliability growth models. Through a combined, flexible approach, inability of identifying systematic faults in modern software algorithms which are based on big data and artificial intelligence (AI) would be addressed, emphasizing the software upgrades as mandatory routine which shall be regularly performed. Finally, I would attempt to propose a common formula for easy reliability calculation in early safety case setup phases.}, howpublished = {M32}, note = {Keynote}, keywords = {automotive, functional safety, software framework}, pubstate = {published}, tppubtype = {conference} } I used to be enthusiastic about software. I liked clever, modular architectures; design patterns made for extensibility; virtualized, multi-application runtimes; seamless software updates; reusability in the harsh hardware-accelerated environments. And then, I was summoned to the automotive arena, which was in a desperate need for a centralized processing, artificial intelligence algorithms, service-oriented architectures and a fat software stack for the next-generation vehicles. It seemed like a dream job… at first. Only until I realized that to keep a promise I now need to adhere to the harsh world of reliability, safety and processes. This is a story of my software stack and me travelling, unscathed, following the challenging functional safety and reliability trail. In the keynote, I would give an initial proposal of a reliability estimation method for a Central Vehicle Computer which is dominated by software. The method would first address hardware reliability through the definition of key components, component failure rates and reliability block diagrams, which are based on current proposals of Central Vehicle Computer architectures with dual and triple redundancy, available in industry and research. Then, key software components are identified and positioned, with appropriate classification. Where appropriate, reliability of such components is estimated by means of test statistics obtained from field-trials and laboratory experiments, and also by applying software reliability growth models. Through a combined, flexible approach, inability of identifying systematic faults in modern software algorithms which are based on big data and artificial intelligence (AI) would be addressed, emphasizing the software upgrades as mandatory routine which shall be regularly performed. Finally, I would attempt to propose a common formula for easy reliability calculation in early safety case setup phases. |
Bodiroga, Nikolina; Antić, Marija; Zečević, Petar; Bjelica, Milan Z Evaluation of fleet management data collection backend using Cassandra database ConferenceM33 2021 Zooming Innovation in Consumer Technologies Conference (ZINC), IEEE, 2021, ISBN: 978-1-6654-0417-4. Abstract | Links | BibTeX | Tags: automotive, ieeexplore, internet of things, networks @conference{2021z1, title = {Evaluation of fleet management data collection backend using Cassandra database}, author = {Nikolina Bodiroga and Marija Antić and Petar Zečević and Milan Z. Bjelica}, doi = {10.1109/ZINC52049.2021.9499260}, isbn = {978-1-6654-0417-4}, year = {2021}, date = {2021-05-26}, booktitle = {2021 Zooming Innovation in Consumer Technologies Conference (ZINC)}, publisher = {IEEE}, abstract = {As the automotive industry development is shifting towards the digitalization and automation of various driving, entertainment and passenger comfort features of the vehicle, numerous IoT sensors are installed and used within the modern cars. These sensors generate data that can be used in fleet management, maintenance, insurance, and different consumer scenarios In this paper, we evaluate one approach towards the implementation of a data collection and storage component of the fleet management system, which supports the real-time gathering and storage of information on a large number of vehicles in motion. Modules have been implemented in the fleet management cloud, which enable data transfer and storage without losing data. The fleet management system tracks the vehicle's location and collects sensory data from within the vehicle at all times, as well as data on the current condition of the vehicle components.}, howpublished = {M33}, keywords = {automotive, ieeexplore, internet of things, networks}, pubstate = {published}, tppubtype = {conference} } As the automotive industry development is shifting towards the digitalization and automation of various driving, entertainment and passenger comfort features of the vehicle, numerous IoT sensors are installed and used within the modern cars. These sensors generate data that can be used in fleet management, maintenance, insurance, and different consumer scenarios In this paper, we evaluate one approach towards the implementation of a data collection and storage component of the fleet management system, which supports the real-time gathering and storage of information on a large number of vehicles in motion. Modules have been implemented in the fleet management cloud, which enable data transfer and storage without losing data. The fleet management system tracks the vehicle's location and collects sensory data from within the vehicle at all times, as well as data on the current condition of the vehicle components. |
Kenjić, Dušan; Antić, Marija; Bjelica, Milan Z Evaluation of Ethernet Subsystem for Domain Controller in Autonomous Vehicles ConferenceM33 2021 Zooming Innovation in Consumer Technologies Conference (ZINC), IEEE, 2021, ISBN: 978-1-6654-0417-4. Abstract | Links | BibTeX | Tags: automotive, ieeexplore, networks @conference{2021zb, title = {Evaluation of Ethernet Subsystem for Domain Controller in Autonomous Vehicles}, author = {Dušan Kenjić and Marija Antić and Milan Z. Bjelica}, doi = {10.1109/ZINC52049.2021.9499282}, isbn = {978-1-6654-0417-4}, year = {2021}, date = {2021-05-26}, booktitle = {2021 Zooming Innovation in Consumer Technologies Conference (ZINC)}, publisher = {IEEE}, abstract = {The expansion of the automotive industry is reflected in the expansion of functionalities and services offered by a modern vehicle. In order for all of them to be executed, it is also necessary to increase the number of physical components within the vehicle. As the entire system grows, so does the problem of connecting the entities within it. The efficient simplification of the system is achieved by introducing domain controllers, and separating the physical components based on the functionality they perform, while creating the backbone communication network between domain controllers. Time-critical and other performance requirements, which are driven by the development of autonomous driving, demand the utilization of new standards and solutions for this communication network backbone. One of those solutions is Automotive Ethernet. In this paper, an implementation of the Ethernet subsystem of the domain controller for autonomous vehicles will be presented and evaluated.}, howpublished = {M33}, keywords = {automotive, ieeexplore, networks}, pubstate = {published}, tppubtype = {conference} } The expansion of the automotive industry is reflected in the expansion of functionalities and services offered by a modern vehicle. In order for all of them to be executed, it is also necessary to increase the number of physical components within the vehicle. As the entire system grows, so does the problem of connecting the entities within it. The efficient simplification of the system is achieved by introducing domain controllers, and separating the physical components based on the functionality they perform, while creating the backbone communication network between domain controllers. Time-critical and other performance requirements, which are driven by the development of autonomous driving, demand the utilization of new standards and solutions for this communication network backbone. One of those solutions is Automotive Ethernet. In this paper, an implementation of the Ethernet subsystem of the domain controller for autonomous vehicles will be presented and evaluated. |
Kostić, Slobodan; Bjelica, Milan Z; Tošić, Nikola; Kovačević, Branimir Prediction of mobile network QoS on the go for in-vehicle infotainment usage ConferenceM33 2021 Zooming Innovation in Consumer Technologies Conference (ZINC), IEEE, 2021, ISBN: 978-1-6654-0417-4. Abstract | Links | BibTeX | Tags: automotive, consumer electronics, digital TV, ieeexplore, networks, user experience @conference{2021zc, title = {Prediction of mobile network QoS on the go for in-vehicle infotainment usage}, author = {Slobodan Kostić and Milan Z. Bjelica and Nikola Tošić and Branimir Kovačević}, doi = {10.1109/ZINC52049.2021.9499249}, isbn = {978-1-6654-0417-4}, year = {2021}, date = {2021-05-26}, booktitle = {2021 Zooming Innovation in Consumer Technologies Conference (ZINC)}, publisher = {IEEE}, abstract = {The rise of autonomous car control leads to more accent on infotainment systems. In a few years, a lot of infotainment features, which rely on the mobile network, will be offered to users. The majority of them are dependent on the mobile network Quality of Service (QoS). While in motion, one can expect different QoS levels which can impact the functionality of infotainment systems and the overall user experience. In this paper, we provide a proposal for a context-aware mobile network QoS prediction module that is ready for in-vehicle application. The main goal of this module is to use the predicted parameters to influence the operation of the in-vehicle infotainment to ensure a better user experience.}, howpublished = {M33}, keywords = {automotive, consumer electronics, digital TV, ieeexplore, networks, user experience}, pubstate = {published}, tppubtype = {conference} } The rise of autonomous car control leads to more accent on infotainment systems. In a few years, a lot of infotainment features, which rely on the mobile network, will be offered to users. The majority of them are dependent on the mobile network Quality of Service (QoS). While in motion, one can expect different QoS levels which can impact the functionality of infotainment systems and the overall user experience. In this paper, we provide a proposal for a context-aware mobile network QoS prediction module that is ready for in-vehicle application. The main goal of this module is to use the predicted parameters to influence the operation of the in-vehicle infotainment to ensure a better user experience. |
Kaprocki, Andrej; Bjelica, Milan Z; Kaprocki, Zvonimir; Milošević, Milena Improvement of the diagnostic tool for visual representation of vehicle signals ConferenceM33 2021 Zooming Innovation in Consumer Technologies Conference (ZINC), 2021, ISBN: 978-1-6654-0417-4. Abstract | Links | BibTeX | Tags: automotive, ieeexplore, networks @conference{2021zd, title = {Improvement of the diagnostic tool for visual representation of vehicle signals}, author = {Andrej Kaprocki and Milan Z. Bjelica and Zvonimir Kaprocki and Milena Milošević}, doi = {10.1109/ZINC52049.2021.9499285}, isbn = {978-1-6654-0417-4}, year = {2021}, date = {2021-05-26}, booktitle = {2021 Zooming Innovation in Consumer Technologies Conference (ZINC)}, abstract = {Because of the constant improvement of automotive technology and the introduction of many new advanced driver assistance systems, vehicle communication is getting more complicated every day, with more data being transferred. A big part of the automotive technology development process is testing. Autonomous driving testing is a complex process, which is important both during the development and with the finished product. The focus of this paper are diagnostic tools used during this testing, specifically, diagnostic tools for live visual representation of vehicle signals. The result of the research shows what a modern visualization diagnostic tool in the automotive industry needs to contain. After a thorough analysis of existing applications of this type, the issues regarding application scaling and signal lag and synchronization were described. Also, a lack of controls and unclear visual representation were noticed. Based on these issues, the proposed solution suggests how this type of application can be improved, by both fixing the mentioned issues, and also expanding the application so that the improved application meets all the needs. The evaluation showed that the improved application offers a more precise representation of the signals, in addition to being more user-friendly. Furthermore, with additional controls, the solution improves the process of automotive real-time testing.}, howpublished = {M33}, keywords = {automotive, ieeexplore, networks}, pubstate = {published}, tppubtype = {conference} } Because of the constant improvement of automotive technology and the introduction of many new advanced driver assistance systems, vehicle communication is getting more complicated every day, with more data being transferred. A big part of the automotive technology development process is testing. Autonomous driving testing is a complex process, which is important both during the development and with the finished product. The focus of this paper are diagnostic tools used during this testing, specifically, diagnostic tools for live visual representation of vehicle signals. The result of the research shows what a modern visualization diagnostic tool in the automotive industry needs to contain. After a thorough analysis of existing applications of this type, the issues regarding application scaling and signal lag and synchronization were described. Also, a lack of controls and unclear visual representation were noticed. Based on these issues, the proposed solution suggests how this type of application can be improved, by both fixing the mentioned issues, and also expanding the application so that the improved application meets all the needs. The evaluation showed that the improved application offers a more precise representation of the signals, in addition to being more user-friendly. Furthermore, with additional controls, the solution improves the process of automotive real-time testing. |
Stepanović, Mia; Bjelica, Milan Z; Kovačević, Branimir; Živkov, Dušan Smart Delay Module For In-Vehicle Live IPTV Streaming ConferenceM33 2021 IEEE International Conference on Consumer Electronics (ICCE), IEEE, 2021, ISBN: 978-1-7281-9766-1. Abstract | Links | BibTeX | Tags: automotive, consumer electronics, digital TV, ieeexplore, user experience @conference{2021veg1, title = {Smart Delay Module For In-Vehicle Live IPTV Streaming}, author = {Mia Stepanović and Milan Z. Bjelica and Branimir Kovačević and Dušan Živkov}, doi = {10.1109/ICCE50685.2021.9427741}, isbn = {978-1-7281-9766-1}, year = {2021}, date = {2021-01-10}, booktitle = {2021 IEEE International Conference on Consumer Electronics (ICCE)}, publisher = {IEEE}, abstract = {Due to the emergence of new trends in the automotive industry, such as autonomous vehicles, there is an increasing emphasis on the driver and passengers' activities as well as on their user experience in such vehicles. One of the main forms of in-vehicle passenger entertainment is infotainment devices that allow them to stream media. Since on-the-go clients do not have a consistent Internet connection quality, streaming live media in such conditions becomes challenging. In this paper, we give an overview of the challenges regarding live media streaming in the no-signal area. We propose a solution for these challenges in the form of extension of the existing architecture of the media subsystem for clients on the move with a smart delay module that provides improvements to Quality of Experience (QoE) and Quality of Service (QoS) for the live media stream while driving.}, howpublished = {M33}, keywords = {automotive, consumer electronics, digital TV, ieeexplore, user experience}, pubstate = {published}, tppubtype = {conference} } Due to the emergence of new trends in the automotive industry, such as autonomous vehicles, there is an increasing emphasis on the driver and passengers' activities as well as on their user experience in such vehicles. One of the main forms of in-vehicle passenger entertainment is infotainment devices that allow them to stream media. Since on-the-go clients do not have a consistent Internet connection quality, streaming live media in such conditions becomes challenging. In this paper, we give an overview of the challenges regarding live media streaming in the no-signal area. We propose a solution for these challenges in the form of extension of the existing architecture of the media subsystem for clients on the move with a smart delay module that provides improvements to Quality of Experience (QoE) and Quality of Service (QoS) for the live media stream while driving. |
2020 |
Manić, Milan; Bjelica, Milan Z; Pešić, Jasmina Proposal for in-car driver alerting system of obstacles and surrounding vehicles ConferenceM33 2020 28th Telecommunications Forum (TELFOR), IEEE, 2020, ISBN: 978-1-6654-0499-0. Abstract | Links | BibTeX | Tags: ADAS, automotive, HMI @conference{2020tfa, title = {Proposal for in-car driver alerting system of obstacles and surrounding vehicles}, author = {Milan Manić and Milan Z. Bjelica and Jasmina Pešić}, doi = {10.1109/TELFOR51502.2020.9306515}, isbn = {978-1-6654-0499-0}, year = {2020}, date = {2020-11-24}, booktitle = {2020 28th Telecommunications Forum (TELFOR)}, publisher = {IEEE}, abstract = {In the automotive industry, safety is a very big issue and there are various driver assistance systems and driver warning systems. Many of these solutions are based on a software system to alert you with audio or visual warning messages. The problem with these solutions is when the driver cannot see or hear these warnings and therefore cannot react promptly. This paper presents a solution on how to warn the driver of the presence of obstacles or other cars in the immediate vicinity by using vibrations as a medium for transmitting messages between the car and the driver. Objects in the immediate vicinity are detected by various sensors and cameras, and then this information is used to make decisions about the nature of the alerts to be activated. In this paper, the hardware and software for the realization of this solution are presented. The system consists of a vibrating seat, a sensor (camera), a controller and a software solution. The principle of operation is as follows: when there is an obstacle on the right side of the vehicle, such as a passing car or some other obstacle, the seat will vibrate on the right side to inform the driver about the existence of an obstacle. The intensity of the vibrations corresponds to the distance from the obstacle, the stronger vibrations correspond to the object that is closer to the car. Thus, vibrations will alert the driver to the presence and distance of an obstacle or a passing car.}, howpublished = {M33}, keywords = {ADAS, automotive, HMI}, pubstate = {published}, tppubtype = {conference} } In the automotive industry, safety is a very big issue and there are various driver assistance systems and driver warning systems. Many of these solutions are based on a software system to alert you with audio or visual warning messages. The problem with these solutions is when the driver cannot see or hear these warnings and therefore cannot react promptly. This paper presents a solution on how to warn the driver of the presence of obstacles or other cars in the immediate vicinity by using vibrations as a medium for transmitting messages between the car and the driver. Objects in the immediate vicinity are detected by various sensors and cameras, and then this information is used to make decisions about the nature of the alerts to be activated. In this paper, the hardware and software for the realization of this solution are presented. The system consists of a vibrating seat, a sensor (camera), a controller and a software solution. The principle of operation is as follows: when there is an obstacle on the right side of the vehicle, such as a passing car or some other obstacle, the seat will vibrate on the right side to inform the driver about the existence of an obstacle. The intensity of the vibrations corresponds to the distance from the obstacle, the stronger vibrations correspond to the object that is closer to the car. Thus, vibrations will alert the driver to the presence and distance of an obstacle or a passing car. |
Manić, Milan; Bjelica, Milan Z Proposal for visual warnings system in the automotive digital cockpit using graphics sharing ConferenceM33 2020 28th Telecommunications Forum (TELFOR), IEEE, 2020. Abstract | Links | BibTeX | Tags: ADAS, automotive, HMI, ieeexplore, infotainment @conference{2020tfb, title = {Proposal for visual warnings system in the automotive digital cockpit using graphics sharing}, author = {Milan Manić and Milan Z. Bjelica}, doi = {10.1109/TELFOR51502.2020.9306638}, year = {2020}, date = {2020-11-24}, booktitle = {2020 28th Telecommunications Forum (TELFOR)}, publisher = {IEEE}, abstract = {In this paper is presented the concept of using shared graphics to display visual warnings in the automotive digital cockpit. Given that cars today have over 100 ECUs (ECU - control unit), communication and management of all these ECUs become a challenging task. This paper focuses on the control units used to display the content and process the data of each screen in the car. The number of control units for data processing and display of content can be reduced by using SoC (SoC - System on a chip) with a hypervisor. A hypervisor is a concept that allows us to run two operating systems on one SoC in real-time. The proposed system consists of one SoC with two operating systems running on a hypervisor and having the ability to display content on three different screens. The proposed solution covers the simultaneous display of content from both operating systems on one screen as well as the display of visual warnings on all screens in the digital cockpit, regardless of the operating system that hosts that screen. Alerts are displayed from a higher security operating system regardless of the content currently displayed from a lower security operating system. This approach has led to the certification of operating systems in terms of security.}, howpublished = {M33}, keywords = {ADAS, automotive, HMI, ieeexplore, infotainment}, pubstate = {published}, tppubtype = {conference} } In this paper is presented the concept of using shared graphics to display visual warnings in the automotive digital cockpit. Given that cars today have over 100 ECUs (ECU - control unit), communication and management of all these ECUs become a challenging task. This paper focuses on the control units used to display the content and process the data of each screen in the car. The number of control units for data processing and display of content can be reduced by using SoC (SoC - System on a chip) with a hypervisor. A hypervisor is a concept that allows us to run two operating systems on one SoC in real-time. The proposed system consists of one SoC with two operating systems running on a hypervisor and having the ability to display content on three different screens. The proposed solution covers the simultaneous display of content from both operating systems on one screen as well as the display of visual warnings on all screens in the digital cockpit, regardless of the operating system that hosts that screen. Alerts are displayed from a higher security operating system regardless of the content currently displayed from a lower security operating system. This approach has led to the certification of operating systems in terms of security. |
Jelić, Borna; Grbić, Ratko; Vranješ, Mario; Bjelica, Milan Z UrTra2D – Urban Traffic 2D Object Detection Dataset ConferenceM33 2020 IEEE 10th International Conference on Consumer Electronics (ICCE-Berlin), 2020, ISBN: 978-1-7281-5885-3. Abstract | Links | BibTeX | Tags: ADAS, automotive, deep learning, ieeexplore @conference{2020berlin1, title = {UrTra2D – Urban Traffic 2D Object Detection Dataset}, author = {Borna Jelić and Ratko Grbić and Mario Vranješ and Milan Z. Bjelica}, doi = {10.1109/ICCE-Berlin50680.2020.9352154}, isbn = {978-1-7281-5885-3}, year = {2020}, date = {2020-11-09}, booktitle = {2020 IEEE 10th International Conference on Consumer Electronics (ICCE-Berlin)}, abstract = {With progress being made in the field of artificial intelligence and especially machine learning, tech and vehicle companies acquired a powerful tool and made a large step towards realisation of a fully autonomous vehicle. Along with the exploding development of more and more powerful hardware, deep learning has become one of the most dominant fields of research in the automotive domain, succeeding the classical computer vision methods. However, to be able to apply deep learning methods to solve a problem, large and appropriate datasets are required in developing a solution, as there is never enough data for deep learning. In this paper, Urban Traffic 2D Object Detection (UrTra2D) dataset is presented, which is intended for training 2D detectors of specific objects common for urban traffic scenes. The data was recorded with an affordable camera mounted inside the vehicle. The dataset contains video sequences and labelled frames of the traffic in the city of Osijek in different weather conditions during both day and night. There are 5 770 labelled frames, totalling in 22 764 labelled objects throughout 11 categories. The UrTra2D dataset is freely available to the research community upon request.}, howpublished = {M33}, keywords = {ADAS, automotive, deep learning, ieeexplore}, pubstate = {published}, tppubtype = {conference} } With progress being made in the field of artificial intelligence and especially machine learning, tech and vehicle companies acquired a powerful tool and made a large step towards realisation of a fully autonomous vehicle. Along with the exploding development of more and more powerful hardware, deep learning has become one of the most dominant fields of research in the automotive domain, succeeding the classical computer vision methods. However, to be able to apply deep learning methods to solve a problem, large and appropriate datasets are required in developing a solution, as there is never enough data for deep learning. In this paper, Urban Traffic 2D Object Detection (UrTra2D) dataset is presented, which is intended for training 2D detectors of specific objects common for urban traffic scenes. The data was recorded with an affordable camera mounted inside the vehicle. The dataset contains video sequences and labelled frames of the traffic in the city of Osijek in different weather conditions during both day and night. There are 5 770 labelled frames, totalling in 22 764 labelled objects throughout 11 categories. The UrTra2D dataset is freely available to the research community upon request. |
Bjelica, Milan Z; Lazić, Krsto; Teslić, Nikola; Živkov, Dušan Multimodal method for selecting a content reproduction mode based on the quality of video signal data flow for mobile receivers PatentPendingM87 P-2020/0406, 2020, (Pending). BibTeX | Tags: automotive, consumer electronics, digital TV, networks, user experience @patent{2020b, title = {Multimodal method for selecting a content reproduction mode based on the quality of video signal data flow for mobile receivers}, author = {Milan Z. Bjelica and Krsto Lazić and Nikola Teslić and Dušan Živkov}, year = {2020}, date = {2020-03-27}, number = {P-2020/0406}, howpublished = {M87}, note = {Pending}, keywords = {automotive, consumer electronics, digital TV, networks, user experience}, pubstate = {published}, tppubtype = {patent} } |
Baba, Filip; Kenjić, Dušan; Bjelica, Milan Z; Kaštelan, Ivan The optimization method of deep learning based on semantic video segmentation on GPUs PatentPendingM87 P-2020/0197, 2020, (Pending). BibTeX | Tags: automotive, consumer electronics, deep learning @patent{2020a, title = {The optimization method of deep learning based on semantic video segmentation on GPUs}, author = {Filip Baba and Dušan Kenjić and Milan Z. Bjelica and Ivan Kaštelan}, year = {2020}, date = {2020-02-19}, number = {P-2020/0197}, howpublished = {M87}, note = {Pending}, keywords = {automotive, consumer electronics, deep learning}, pubstate = {published}, tppubtype = {patent} } |
Bjelica, Milan Z; Stepanović, Mia; Kovačević, Branimir; Teslić, Nikola Trajectory-aware playback to overcome user experience challenges for streaming media in the vehicle ConferenceM33 2020 IEEE International Conference on Consumer Electronics (ICCE), IEEE, 2020, ISBN: 978-1-7281-5186-1. Abstract | Links | BibTeX | Tags: automotive, consumer electronics, digital TV, ieeexplore, user experience @conference{icce20201, title = {Trajectory-aware playback to overcome user experience challenges for streaming media in the vehicle}, author = {Milan Z. Bjelica and Mia Stepanović and Branimir Kovačević and Nikola Teslić}, doi = {10.1109/ICCE46568.2020.9212311}, isbn = {978-1-7281-5186-1}, year = {2020}, date = {2020-01-04}, booktitle = {2020 IEEE International Conference on Consumer Electronics (ICCE)}, publisher = {IEEE}, abstract = {New trends in the automotive industry, such as e-mobility and autonomous driving, give birth to challenges of engaging passengers in a vehicle. Once relieved from driving tasks, passengers may take up productive and entertainment-related activities, such as media consumption. It is assumed that by 2030 in-car cabin would mostly resemble a living room, whereas internet connectivity would become one of the most important enablers for new content delivery. Streaming media in such an environment poses a challenge, given that reliability and adequate coverage in 4G and coming 5G networks are mandatory. In this paper, we give a brief analysis of challenges which streaming media would bring to the user experience. We give a proposal of a software stack for a trajectory-aware playback, capable of predicting streaming quality drops and proposing appropriate fallbacks.}, howpublished = {M33}, keywords = {automotive, consumer electronics, digital TV, ieeexplore, user experience}, pubstate = {published}, tppubtype = {conference} } New trends in the automotive industry, such as e-mobility and autonomous driving, give birth to challenges of engaging passengers in a vehicle. Once relieved from driving tasks, passengers may take up productive and entertainment-related activities, such as media consumption. It is assumed that by 2030 in-car cabin would mostly resemble a living room, whereas internet connectivity would become one of the most important enablers for new content delivery. Streaming media in such an environment poses a challenge, given that reliability and adequate coverage in 4G and coming 5G networks are mandatory. In this paper, we give a brief analysis of challenges which streaming media would bring to the user experience. We give a proposal of a software stack for a trajectory-aware playback, capable of predicting streaming quality drops and proposing appropriate fallbacks. |
Manić, Milan Z; Ponoš, Milica Z; Bjelica, Milan Z; Samardžija, Dragan Proposal for graphics sharing in a mixed criticality automotive digital cockpit ConferenceM33 2020 IEEE International Conference on Consumer Electronics (ICCE), IEEE, 2020, ISBN: 978-1-7281-5186-1. Abstract | Links | BibTeX | Tags: automotive, functional safety, ieeexplore, infotainment, software framework @conference{icce20202, title = {Proposal for graphics sharing in a mixed criticality automotive digital cockpit}, author = {Milan Z. Manić and Milica Z. Ponoš and Milan Z. Bjelica and Dragan Samardžija}, doi = {10.1109/ICCE46568.2020.9212310}, isbn = {978-1-7281-5186-1}, year = {2020}, date = {2020-01-04}, booktitle = {2020 IEEE International Conference on Consumer Electronics (ICCE)}, publisher = {IEEE}, abstract = {In this paper, we present the concept of multilayer cross-platform graphics sharing in the automotive digital cockpit. Considering that automobiles today have around 150 ECUs (engine control units), managing all these ECUs is becoming a challenging task. For example, there is a controller (System on Chip - SoC) for every display in an automobile. This SoC is used for content rendering and data processing. The number of ECUs can be lowered by using SoCs with a hypervisor. A hypervisor is a concept that enables us to run two operating systems on one SoC in real-time. The content from both operating systems can be rendered and presented in the same display output. The proposed system consists of one SoC with two operating systems running on a hypervisor. With this proposed solution, we were able to simultaneously render content from both operating systems on one display output. The proposed solution also covers the rendering of media content on display that is hosted on a different operating system and therefore enables mixed criticality where safety-critical information, such as those presented in the cluster, are presented with no interference with the non-critical operations, such as media rendering. We also evaluate safety concerns and system performance when content is rendered simultaneously on both operating systems.}, howpublished = {M33}, keywords = {automotive, functional safety, ieeexplore, infotainment, software framework}, pubstate = {published}, tppubtype = {conference} } In this paper, we present the concept of multilayer cross-platform graphics sharing in the automotive digital cockpit. Considering that automobiles today have around 150 ECUs (engine control units), managing all these ECUs is becoming a challenging task. For example, there is a controller (System on Chip - SoC) for every display in an automobile. This SoC is used for content rendering and data processing. The number of ECUs can be lowered by using SoCs with a hypervisor. A hypervisor is a concept that enables us to run two operating systems on one SoC in real-time. The content from both operating systems can be rendered and presented in the same display output. The proposed system consists of one SoC with two operating systems running on a hypervisor. With this proposed solution, we were able to simultaneously render content from both operating systems on one display output. The proposed solution also covers the rendering of media content on display that is hosted on a different operating system and therefore enables mixed criticality where safety-critical information, such as those presented in the cluster, are presented with no interference with the non-critical operations, such as media rendering. We also evaluate safety concerns and system performance when content is rendered simultaneously on both operating systems. |
Stepanović, Mia; Bjelica, Milan Z; Kaštelan, Ivan; Velikić, Gordana Scalable approach to extending automotive software using AUTOSAR adaptive stack ConferenceM33 2020 IEEE International Conference on Consumer Electronics (ICCE), IEEE, 2020, ISBN: 978-1-7281-5186-1. Abstract | Links | BibTeX | Tags: automotive, ieeexplore, software framework @conference{icce20203, title = {Scalable approach to extending automotive software using AUTOSAR adaptive stack}, author = {Mia Stepanović and Milan Z. Bjelica and Ivan Kaštelan and Gordana Velikić}, doi = {10.1109/ICCE46568.2020.9212328}, isbn = {978-1-7281-5186-1}, year = {2020}, date = {2020-01-04}, booktitle = {2020 IEEE International Conference on Consumer Electronics (ICCE)}, publisher = {IEEE}, abstract = {The constant expansion of automotive industry has led to a lack of technology and standards in the field that are needed to keep up the pace with automotive requirements. In order to support these new requirements, it is necessary to find a way to integrate new functionalities into existing systems without disruption of the system. The leading automotive industry standard, AUTOSAR, has been expanded with an Adaptive Platform (AA) that offers support for realizing new automotive features. In this paper scalable extension of the software within existing architecture with modules that provide communication with security-critical parts of the system is implemented within AA environment. The scalability in solution provides the flexibility in the development of the future systems. The AUTOSAR foundation ensures preservation of the automotive grade quality within the components.}, howpublished = {M33}, keywords = {automotive, ieeexplore, software framework}, pubstate = {published}, tppubtype = {conference} } The constant expansion of automotive industry has led to a lack of technology and standards in the field that are needed to keep up the pace with automotive requirements. In order to support these new requirements, it is necessary to find a way to integrate new functionalities into existing systems without disruption of the system. The leading automotive industry standard, AUTOSAR, has been expanded with an Adaptive Platform (AA) that offers support for realizing new automotive features. In this paper scalable extension of the software within existing architecture with modules that provide communication with security-critical parts of the system is implemented within AA environment. The scalability in solution provides the flexibility in the development of the future systems. The AUTOSAR foundation ensures preservation of the automotive grade quality within the components. |
2019 |
Nikolić, Mihajlo; Krunić, Momčilo; Bjelica, Milan Z; Četić, Nenad Utilization of pattern generators in Adaptive AUTOSAR Platform ConferenceM33 2019 27th Telecommunications Forum (TELFOR), IEEE IEEE, 2019, ISBN: 978-1-7281-4790-1. Abstract | Links | BibTeX | Tags: automotive, ieeexplore, software framework @conference{telfor2019uc, title = {Utilization of pattern generators in Adaptive AUTOSAR Platform}, author = {Mihajlo Nikolić and Momčilo Krunić and Milan Z. Bjelica and Nenad Četić}, doi = {10.1109/TELFOR48224.2019.8971306}, isbn = {978-1-7281-4790-1}, year = {2019}, date = {2019-11-26}, booktitle = {2019 27th Telecommunications Forum (TELFOR)}, publisher = {IEEE}, organization = {IEEE}, abstract = {This paper will provide an overview of the most used patterns in the implementation process of autonomous driving software and their generators. The emphasis will be on the creation process and use cases of software patterns in the autonomous driving industry. The description of generators and the explanations of their outputs are given through a series of examples. An overview of Test-driven development concepts will be given, as well as a look at the tests used for validation of the generated patterns. The purpose of the paper is to clarify the importance of patterns in autonomous vehicle software and what benefits they provide to the developer. Overall, this paper should provide a wider picture of code generation in AUTOSAR Adaptive Platform.}, howpublished = {M33}, keywords = {automotive, ieeexplore, software framework}, pubstate = {published}, tppubtype = {conference} } This paper will provide an overview of the most used patterns in the implementation process of autonomous driving software and their generators. The emphasis will be on the creation process and use cases of software patterns in the autonomous driving industry. The description of generators and the explanations of their outputs are given through a series of examples. An overview of Test-driven development concepts will be given, as well as a look at the tests used for validation of the generated patterns. The purpose of the paper is to clarify the importance of patterns in autonomous vehicle software and what benefits they provide to the developer. Overall, this paper should provide a wider picture of code generation in AUTOSAR Adaptive Platform. |
Bjelica, Milan Z; Lukač, Željko Central vehicle computer design: Software taking over Journal ArticleM22 IEEE Consumer Electronics Magazine, 8 (6), 2019, ISSN: 2162-2248. Abstract | Links | BibTeX | Tags: ADAS, automotive, ieeexplore, infotainment, market research, software framework @article{cemag_2019, title = {Central vehicle computer design: Software taking over}, author = {Milan Z. Bjelica and Željko Lukač}, doi = {10.1109/MCE.2019.2929813}, issn = {2162-2248}, year = {2019}, date = {2019-11-01}, journal = {IEEE Consumer Electronics Magazine}, volume = {8}, number = {6}, abstract = {To prevent each vehicle manufacturer from “reinventing the wheel” and spending vast amounts of time and engineering, a paradigm shift is needed. Transferring the vehicle design to standardized hardware would enable software to take the key role and allow the horizontal approach in design, where each feature may be added as a module. This sets the stage for a central vehicle computer-a brain for next generation vehicles which is everything but easy to design. This article discusses one such design and identifies the required building blocks for this rising market.}, howpublished = {M22}, keywords = {ADAS, automotive, ieeexplore, infotainment, market research, software framework}, pubstate = {published}, tppubtype = {article} } To prevent each vehicle manufacturer from “reinventing the wheel” and spending vast amounts of time and engineering, a paradigm shift is needed. Transferring the vehicle design to standardized hardware would enable software to take the key role and allow the horizontal approach in design, where each feature may be added as a module. This sets the stage for a central vehicle computer-a brain for next generation vehicles which is everything but easy to design. This article discusses one such design and identifies the required building blocks for this rising market. |
Bjelica, Milan Z; Marinković, Vladimir; Đukić, Miodrag; Lukač, Željko The system and method for real-time decision-making during autonomous driving PatentPendingM87 P-2019/0838, 2019, (Pending). BibTeX | Tags: ADAS, automotive @patent{2019p1, title = {The system and method for real-time decision-making during autonomous driving}, author = {Milan Z. Bjelica and Vladimir Marinković and Miodrag Đukić and Željko Lukač}, year = {2019}, date = {2019-11-01}, number = {P-2019/0838}, howpublished = {M87}, note = {Pending}, keywords = {ADAS, automotive}, pubstate = {published}, tppubtype = {patent} } |
Bjelica, Milan Z; Marinković, Vladimir; Đukić, Miodrag; Kaštelan, Ivan A system of software components for isolated execution of an artificial intelligence algorithm for vehicle PatentPendingM87 P-2019/1098, 2019, (Pending). BibTeX | Tags: ADAS, automotive, deep learning, software framework @patent{2019p2, title = {A system of software components for isolated execution of an artificial intelligence algorithm for vehicle}, author = {Milan Z. Bjelica and Vladimir Marinković and Miodrag Đukić and Ivan Kaštelan}, year = {2019}, date = {2019-10-01}, number = {P-2019/1098}, howpublished = {M87}, note = {Pending}, keywords = {ADAS, automotive, deep learning, software framework}, pubstate = {published}, tppubtype = {patent} } |
Milošević, Marko; Isić, Vesna; Bjelica, Milan Z; Anđelić, Tihomir Efficient Implementation of Camera Mirror System Algorithm on Heterogeneous Chip Architectures ConferenceM33 Consumer Electronics - Berlin (ICCE-Berlin), 2019 IEEE 9th International Conference on, IEEE Consumer Electronics Society, 2019, ISBN: 978-1-7281-2745-3. Abstract | Links | BibTeX | Tags: ADAS, automotive, ieeexplore @conference{icceberlin2019_1, title = {Efficient Implementation of Camera Mirror System Algorithm on Heterogeneous Chip Architectures}, author = {Marko Milošević and Vesna Isić and Milan Z. Bjelica and Tihomir Anđelić}, doi = {10.1109/ICCE-Berlin47944.2019.8966193}, isbn = {978-1-7281-2745-3}, year = {2019}, date = {2019-09-08}, booktitle = {Consumer Electronics - Berlin (ICCE-Berlin), 2019 IEEE 9th International Conference on}, publisher = {IEEE Consumer Electronics Society}, abstract = {Advanced Driving Assistance Systems (ADAS) are vehicle-based intelligent safety systems which help the drivers to improve safety driving. One important building block of ADAS is a Camera Mirror System (CMS). CMS provides means to enhance rearview mirrors by digital information, such as detected obstacles, collision avoidance alerts and more. Efficient implementation of CMS requires the utilization of dedicated processing in hardware, to ensure minimal latency and coexistence with other algorithms in heterogeneous hardware environments. In this paper we analyze CMS algorithm data pipeline and provide insights on how each phase can be efficiently accelerated using dedicated hardware blocks on present-day high-performance microcontrollers. We give early evaluation of the presented approach on top of two architectures: TI TDA2x and NVIDIA Xavier.}, howpublished = {M33}, keywords = {ADAS, automotive, ieeexplore}, pubstate = {published}, tppubtype = {conference} } Advanced Driving Assistance Systems (ADAS) are vehicle-based intelligent safety systems which help the drivers to improve safety driving. One important building block of ADAS is a Camera Mirror System (CMS). CMS provides means to enhance rearview mirrors by digital information, such as detected obstacles, collision avoidance alerts and more. Efficient implementation of CMS requires the utilization of dedicated processing in hardware, to ensure minimal latency and coexistence with other algorithms in heterogeneous hardware environments. In this paper we analyze CMS algorithm data pipeline and provide insights on how each phase can be efficiently accelerated using dedicated hardware blocks on present-day high-performance microcontrollers. We give early evaluation of the presented approach on top of two architectures: TI TDA2x and NVIDIA Xavier. |
Baba, Filip; Kenjić, Dušan; Bjelica, Milan Z; Kaštelan, Ivan Optimizing Deep Learning Based Semantic Video Segmentation on Embedded GPUs ConferenceM33 Consumer Electronics - Berlin (ICCE-Berlin), 2019 IEEE 9th International Conference on, IEEE, 2019, ISBN: 978-1-7281-2745-3. Abstract | Links | BibTeX | Tags: ADAS, automotive, deep learning, ieeexplore @conference{icceberlin2019_2, title = {Optimizing Deep Learning Based Semantic Video Segmentation on Embedded GPUs}, author = {Filip Baba and Dušan Kenjić and Milan Z. Bjelica and Ivan Kaštelan}, doi = {10.1109/ICCE-Berlin47944.2019.8966156}, isbn = {978-1-7281-2745-3}, year = {2019}, date = {2019-09-08}, booktitle = {Consumer Electronics - Berlin (ICCE-Berlin), 2019 IEEE 9th International Conference on}, publisher = {IEEE}, abstract = {Decision making in many industries today is being improved drastically thanks to artificial intelligence and deep learning. New algorithms address challenges such as genome mapping, medical diagnostics, self-driving cars, autonomous robots and more. Deep learning in embedded systems requires high optimization due to the high computational demand, given that power, heat dissipation, size and price constraints are numerous. In this paper we analyze several acceleration methods which include utilization of GPUs for most complex variants of deep learning, such as semantic video segmentation operating in real time. Specifically, we propose mapping of acceleration routines commonly present within deep learning SDKs to different network layers in semantic segmentation. Finally, we evaluate one implementation utilizing the enumerated techniques for semantic segmentation of front camera in autonomous driving front view.}, howpublished = {M33}, keywords = {ADAS, automotive, deep learning, ieeexplore}, pubstate = {published}, tppubtype = {conference} } Decision making in many industries today is being improved drastically thanks to artificial intelligence and deep learning. New algorithms address challenges such as genome mapping, medical diagnostics, self-driving cars, autonomous robots and more. Deep learning in embedded systems requires high optimization due to the high computational demand, given that power, heat dissipation, size and price constraints are numerous. In this paper we analyze several acceleration methods which include utilization of GPUs for most complex variants of deep learning, such as semantic video segmentation operating in real time. Specifically, we propose mapping of acceleration routines commonly present within deep learning SDKs to different network layers in semantic segmentation. Finally, we evaluate one implementation utilizing the enumerated techniques for semantic segmentation of front camera in autonomous driving front view. |
Gamf, Branislav; Usorac, Srđan; Bjelica, Milan Z; Lukač, Željko Video delivery subsystem for multi-SoC automotive machine vision platforms ConferenceM33 Consumer Electronics - Berlin (ICCE-Berlin), 2019 IEEE 9th International Conference on, IEEE, 2019, ISBN: 978-1-7281-2745-3. Abstract | Links | BibTeX | Tags: ADAS, automotive, ieeexplore @conference{Gamf2019, title = {Video delivery subsystem for multi-SoC automotive machine vision platforms}, author = {Branislav Gamf and Srđan Usorac and Milan Z. Bjelica and Željko Lukač}, doi = {10.1109/ICCE-Berlin47944.2019.8966206}, isbn = {978-1-7281-2745-3}, year = {2019}, date = {2019-09-08}, booktitle = {Consumer Electronics - Berlin (ICCE-Berlin), 2019 IEEE 9th International Conference on}, publisher = {IEEE}, abstract = {Automotive microcontrollers in a form of System-on-Chip (SoC) are getting more powerful due to the abundance of algorithms catering to the Advanced Driver-Assistance System (ADAS) applications. Apart from traditional LIDAR and RADAR-based approaches, many new algorithms heavily depend on cameras and video. Delivering video within a heterogeneous hardware environment such as within a single SoC or across SoCs is a daunting task. In this paper, we give a proposal of a video delivery subsystem to be applied to next generation hardware and software architectures for autonomous vehicles. Proposed subsystem considers all major video exchange routes, including DMA, PCI-E and Ethernet, with appropriate software interfaces which can be integrated to future horizontal automotive middleware. Within an early evaluation we demonstrate the utilization of the subsystem in an automotive hardware encompassing three TI TDA2X and two NVIDIA Xavier SoCs.}, howpublished = {M33}, keywords = {ADAS, automotive, ieeexplore}, pubstate = {published}, tppubtype = {conference} } Automotive microcontrollers in a form of System-on-Chip (SoC) are getting more powerful due to the abundance of algorithms catering to the Advanced Driver-Assistance System (ADAS) applications. Apart from traditional LIDAR and RADAR-based approaches, many new algorithms heavily depend on cameras and video. Delivering video within a heterogeneous hardware environment such as within a single SoC or across SoCs is a daunting task. In this paper, we give a proposal of a video delivery subsystem to be applied to next generation hardware and software architectures for autonomous vehicles. Proposed subsystem considers all major video exchange routes, including DMA, PCI-E and Ethernet, with appropriate software interfaces which can be integrated to future horizontal automotive middleware. Within an early evaluation we demonstrate the utilization of the subsystem in an automotive hardware encompassing three TI TDA2X and two NVIDIA Xavier SoCs. |
Bjelica, Milan Z; Đukić, Miodrag; Subotić, Miloš; Lukić, Nemanja The method and system for inserting a notification into a multimedia content stream in a vehicle PatentPendingM87 P-2019/1345, 2019, (Pending). BibTeX | Tags: automotive, consumer electronics, digital TV, HMI, user experience @patent{2019p3, title = {The method and system for inserting a notification into a multimedia content stream in a vehicle }, author = {Milan Z. Bjelica and Miodrag Đukić and Miloš Subotić and Nemanja Lukić}, year = {2019}, date = {2019-09-01}, number = {P-2019/1345}, howpublished = {M87}, note = {Pending}, keywords = {automotive, consumer electronics, digital TV, HMI, user experience}, pubstate = {published}, tppubtype = {patent} } |
Bjelica, Milan Z Deep Learning vs. Safety - Practical Approach and Platform Design Perspective ConferenceKeynoteM32 Proceedings of 2019 International Conference on Systems, Signals and Image Processing (IWSSIP), EURASIP, Osijek, Croatia, 2019, (Keynote). Abstract | Links | BibTeX | Tags: ADAS, automotive, deep learning, keynote, market research @conference{2019_iwssip, title = {Deep Learning vs. Safety - Practical Approach and Platform Design Perspective}, author = {Milan Z. Bjelica}, url = {http://www.milanbjelica.info/wp-content/uploads/2019/06/program-web.pdf https://www.youtube.com/watch?v=tJrDJsBiDqg}, year = {2019}, date = {2019-06-06}, booktitle = {Proceedings of 2019 International Conference on Systems, Signals and Image Processing (IWSSIP)}, publisher = {EURASIP}, address = {Osijek, Croatia}, abstract = {Deep Learning is a promising field, allowing an increase in artificial intelligence applications across many fields, ranging from data science, medical, weather, and aerospace to automotive. Applications of computer vision-based deep learning are vastly assisted by modern System-on-Chip architectures, which provide the required parallelism, heterogeneity and interfacing. However, the application of deep learning to safety-critical contexts where human lives might be at stake, such as in self-driving cars, still has many pitfalls. Ongoing academic research tackles transparent AI, in which the correctness of AI is attempted to be reached by design; however, the outcome of this research is still far-fetched. In this talk, we will discuss a practical approach when integrating deep learning vision-based solutions into a safety-critical context, which can be achieved today. We outline an approach which introduces a software/hardware platform design which fosters diversity, with the goal of minimizing risk of critical failures which are induced by AI in decision making.}, howpublished = {M32}, note = {Keynote}, keywords = {ADAS, automotive, deep learning, keynote, market research}, pubstate = {published}, tppubtype = {conference} } Deep Learning is a promising field, allowing an increase in artificial intelligence applications across many fields, ranging from data science, medical, weather, and aerospace to automotive. Applications of computer vision-based deep learning are vastly assisted by modern System-on-Chip architectures, which provide the required parallelism, heterogeneity and interfacing. However, the application of deep learning to safety-critical contexts where human lives might be at stake, such as in self-driving cars, still has many pitfalls. Ongoing academic research tackles transparent AI, in which the correctness of AI is attempted to be reached by design; however, the outcome of this research is still far-fetched. In this talk, we will discuss a practical approach when integrating deep learning vision-based solutions into a safety-critical context, which can be achieved today. We outline an approach which introduces a software/hardware platform design which fosters diversity, with the goal of minimizing risk of critical failures which are induced by AI in decision making. |
Lazić, Aleksandar; Bjelica, Milan Z; Nađ, Dejan Use of Google Assistant technology in the interactive digital television ConferenceM63 Proceedings of ETRAN 2019, Srebrno Jezero, Serbia, 2019. Abstract | Links | BibTeX | Tags: digital TV, HMI, user interface @conference{etran2019_1, title = {Use of Google Assistant technology in the interactive digital television}, author = {Aleksandar Lazić and Milan Z. Bjelica and Dejan Nađ}, url = {https://www.etran.rs/2019/program2019.pdf}, year = {2019}, date = {2019-06-03}, booktitle = {Proceedings of ETRAN 2019}, address = {Srebrno Jezero, Serbia}, institution = {ETRAN Society}, abstract = {Nowadays, more and more people are using virtual assistant services on various platforms (Android, Windows, iOS). They are becoming present in everyday life such as buying food in market, driving to the job, or for the purpose of an entertainment. This paper presents a software architecture that supports Google Assistant integration in TV application, designed for Android operating system. The aim is to enhance user experience, so previously added intents such as “channel up/down”, “volume up/down” are extended with some more complex commands such as finding TV channel by name and zapping to it or choosing some VOD and schedule it for recording or watching later, by using only a voice command. The majority of existing speech recognition tools provide the result of the speech processing in a free form textual output or structured form textual output. In order to use obtained outputs in an existing TV applications, it is necessary to detect patterns that correspond to mentioned commands. }, howpublished = {M63}, keywords = {digital TV, HMI, user interface}, pubstate = {published}, tppubtype = {conference} } Nowadays, more and more people are using virtual assistant services on various platforms (Android, Windows, iOS). They are becoming present in everyday life such as buying food in market, driving to the job, or for the purpose of an entertainment. This paper presents a software architecture that supports Google Assistant integration in TV application, designed for Android operating system. The aim is to enhance user experience, so previously added intents such as “channel up/down”, “volume up/down” are extended with some more complex commands such as finding TV channel by name and zapping to it or choosing some VOD and schedule it for recording or watching later, by using only a voice command. The majority of existing speech recognition tools provide the result of the speech processing in a free form textual output or structured form textual output. In order to use obtained outputs in an existing TV applications, it is necessary to detect patterns that correspond to mentioned commands. |
Banović, Radenko; Bjelica, Milan Z; Dejanović, Darko; Gvero, Milan Extension of TV Input framework with Google Assistant functionalities in Android environment ConferenceM63 Proceedings of ETRAN 2019, ETRAN Society, 2019. Abstract | Links | BibTeX | Tags: digital TV @conference{etran2019_2, title = {Extension of TV Input framework with Google Assistant functionalities in Android environment}, author = {Radenko Banović and Milan Z. Bjelica and Darko Dejanović and Milan Gvero}, url = {https://www.etran.rs/2019/program2019.pdf}, year = {2019}, date = {2019-06-03}, booktitle = {Proceedings of ETRAN 2019}, publisher = {ETRAN Society}, abstract = {This paper presents one solution of extending the TV Input Framework with functionalities of the Google Assistant package, which enables the storage of EPG data in the TV Provider database, and the search of EPG data stored in the TV Provider database.}, howpublished = {M63}, keywords = {digital TV}, pubstate = {published}, tppubtype = {conference} } This paper presents one solution of extending the TV Input Framework with functionalities of the Google Assistant package, which enables the storage of EPG data in the TV Provider database, and the search of EPG data stored in the TV Provider database. |
Vidaković, Milan; Bjelica, Milan Z; Ciabattoni, Lucio; Vranješ, Mario (Ed.) 2019 Zooming Innovation in Consumer Technologies Conference (ZINC) ProceedingM36 M36, IEEE, Novi Sad, Serbia, 2019, ISBN: 978-1-7281-2901-3. Links | BibTeX | Tags: consumer electronics, ieeexplore @proceedings{Vidakovic2019, title = {2019 Zooming Innovation in Consumer Technologies Conference (ZINC)}, editor = {Milan Vidaković and Milan Z. Bjelica and Lucio Ciabattoni and Mario Vranješ}, url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8769415}, isbn = {978-1-7281-2901-3}, year = {2019}, date = {2019-05-29}, publisher = {IEEE}, address = {Novi Sad, Serbia}, howpublished = {M36}, keywords = {consumer electronics, ieeexplore}, pubstate = {published}, tppubtype = {proceedings} } |
Bjelica, Milan Z; Pavković, Bogdan; Bašičević, Ilija; Marinković, Vladimir The system and procedure for inserting advertisements into the video stream of a vehicle multimedia PatentPendingM87 P-2019/1297, 2019, (Pending). BibTeX | Tags: automotive, consumer electronics, digital TV, infotainment @patent{2019p4, title = {The system and procedure for inserting advertisements into the video stream of a vehicle multimedia}, author = {Milan Z. Bjelica and Bogdan Pavković and Ilija Bašičević and Vladimir Marinković}, year = {2019}, date = {2019-05-01}, number = {P-2019/1297}, howpublished = {M87}, note = {Pending}, keywords = {automotive, consumer electronics, digital TV, infotainment}, pubstate = {published}, tppubtype = {patent} } |
Bjelica, Milan Z; Popović, Miroslav; Antić, Marija; Bašičević, Ilija Method of selecting the optimal parameters for playing video signals on a multimedia device in the vehicle PatentPendingM87 P-2019/1370, 2019, (Pending). BibTeX | Tags: automotive, consumer electronics, digital TV, infotainment, user experience @patent{2019p4b, title = {Method of selecting the optimal parameters for playing video signals on a multimedia device in the vehicle}, author = {Milan Z. Bjelica and Miroslav Popović and Marija Antić and Ilija Bašičević}, year = {2019}, date = {2019-04-03}, number = {P-2019/1370}, howpublished = {M87}, note = {Pending}, keywords = {automotive, consumer electronics, digital TV, infotainment, user experience}, pubstate = {published}, tppubtype = {patent} } |
2018 |
Bjelica, Milan Z; Đukić, Miodrag; Pjevalica, Nebojša; Ačanski, Milan System and procedure for highlighting parts of the instrument cluster display PatentPendingM87 P-2018/1600, 2018, (Pending). BibTeX | Tags: automotive, infotainment @patent{2018Bjelica8, title = {System and procedure for highlighting parts of the instrument cluster display}, author = {Milan Z. Bjelica and Miodrag Đukić and Nebojša Pjevalica and Milan Ačanski}, year = {2018}, date = {2018-12-27}, urldate = {2019-01-23}, number = {P-2018/1600}, howpublished = {M87}, note = {Pending}, keywords = {automotive, infotainment}, pubstate = {published}, tppubtype = {patent} } |
Bjelica, Milan Z; Teslić, Nikola; Velikić, Gordana; Kovačević, Branimir System and procedure with multifunctional camera for driver monitoring and video communication PatentPendingM87 P-2018/1065, 2018, (Pending). BibTeX | Tags: automotive, infotainment, user experience @patent{2018Bjelica7, title = {System and procedure with multifunctional camera for driver monitoring and video communication}, author = {Milan Z. Bjelica and Nikola Teslić and Gordana Velikić and Branimir Kovačević}, year = {2018}, date = {2018-12-10}, number = {P-2018/1065}, howpublished = {M87}, note = {Pending}, keywords = {automotive, infotainment, user experience}, pubstate = {published}, tppubtype = {patent} } |
Vukota, Nataša; Velikić, Gordana; Bjelica, Milan Z; Fimić, Nemanja; Ilić, Mladen [Serbian] Razvoj novog korisničkog interfejsa podsistema za TV prijemnike na bazi Android operativnog sistema - Stage Technical ReportM85 RT-RK Institute for Computer-Based Systems Narodnog Fronta 23a, TR32041, 2018. BibTeX | Tags: digital TV, HMI, user interface @techreport{Stage2018, title = {[Serbian] Razvoj novog korisničkog interfejsa podsistema za TV prijemnike na bazi Android operativnog sistema - Stage}, author = {Nataša Vukota and Gordana Velikić and Milan Z. Bjelica and Nemanja Fimić and Mladen Ilić}, year = {2018}, date = {2018-12-01}, address = {Narodnog Fronta 23a}, institution = {RT-RK Institute for Computer-Based Systems}, howpublished = {M85}, type = {TR32041}, keywords = {digital TV, HMI, user interface}, pubstate = {published}, tppubtype = {techreport} } |
Kaprocki, Nives; Kovačević, Jelena; Bjelica, Milan Z Evaluation of immersive audio technologies on in-vehicle infotainment platforms ConferenceM33 TELFOR 2018, IEEE, Belgrade, Serbia, 2018. Abstract | Links | BibTeX | Tags: audio, automotive, ieeexplore, infotainment @conference{Nives2018, title = {Evaluation of immersive audio technologies on in-vehicle infotainment platforms}, author = {Nives Kaprocki and Jelena Kovačević and Milan Z. Bjelica}, doi = {10.1109/TELFOR.2018.8611863}, year = {2018}, date = {2018-11-21}, booktitle = {TELFOR 2018}, publisher = {IEEE}, address = {Belgrade, Serbia}, abstract = {In-vehicle infotainment systems are being increasingly influenced by consumer electronics trends due to the customer”s demand for high quality video and audio experience. Availability of high-performing low-power heterogeneous automotive platforms with multiple SoCs enabled complex solutions which increase both passenger's safety and comfort. Although the video and ADAS technologies in cars have improved drastically in the recent years, the automotive audio technologies are still far behind their counterparts in consumer devices. This paper evaluates a standard automotive platform in respect to the resource requirements of current immersive audio technologies. The results show that the chosen automotive platforms has the required MIPS budget and memory space to execute complex audio applications.}, howpublished = {M33}, keywords = {audio, automotive, ieeexplore, infotainment}, pubstate = {published}, tppubtype = {conference} } In-vehicle infotainment systems are being increasingly influenced by consumer electronics trends due to the customer”s demand for high quality video and audio experience. Availability of high-performing low-power heterogeneous automotive platforms with multiple SoCs enabled complex solutions which increase both passenger's safety and comfort. Although the video and ADAS technologies in cars have improved drastically in the recent years, the automotive audio technologies are still far behind their counterparts in consumer devices. This paper evaluates a standard automotive platform in respect to the resource requirements of current immersive audio technologies. The results show that the chosen automotive platforms has the required MIPS budget and memory space to execute complex audio applications. |
Lazić, Aleksandar; Bjelica, Milan Z; Nađ, Dejan; Todorović, Branislav M Google Assistant integration in TV application for Android OS ConferenceM33 TELFOR 2018, IEEE, Belgrade, Serbia, 2018. Abstract | Links | BibTeX | Tags: digital TV, ieeexplore @conference{Lazic2018, title = {Google Assistant integration in TV application for Android OS }, author = {Aleksandar Lazić and Milan Z. Bjelica and Dejan Nađ and Branislav M. Todorović}, doi = {10.1109/TELFOR.2018.8612143}, year = {2018}, date = {2018-11-21}, booktitle = {TELFOR 2018}, publisher = {IEEE}, address = {Belgrade, Serbia}, abstract = {This paper presents a software architecture that supports Google Assistant integration in TV application, designed for Android operating system. Nowadays, Google Assistant is becoming more and more popular personal assistant and people freaquently use it's features in the applications on their, smart' devices such as smartphones, smart digital television receivers, smartwatches, etc. The majority of existing speech recognition tools provides the result of the speech processing in a free form textual output or structured form textual output. In order to use obtained outputs in an existing TV applications, it is necessary to detect patterns that correspond to commands such as channel up/down, volume up/down, mute/unmute, etc. The aim is to improve user's quality of experience, so he/she does not have to use a remote contoller, but to say a voice command.}, howpublished = {M33}, keywords = {digital TV, ieeexplore}, pubstate = {published}, tppubtype = {conference} } This paper presents a software architecture that supports Google Assistant integration in TV application, designed for Android operating system. Nowadays, Google Assistant is becoming more and more popular personal assistant and people freaquently use it's features in the applications on their, smart' devices such as smartphones, smart digital television receivers, smartwatches, etc. The majority of existing speech recognition tools provides the result of the speech processing in a free form textual output or structured form textual output. In order to use obtained outputs in an existing TV applications, it is necessary to detect patterns that correspond to commands such as channel up/down, volume up/down, mute/unmute, etc. The aim is to improve user's quality of experience, so he/she does not have to use a remote contoller, but to say a voice command. |
Bjelica, Milan Z How Much Smart is Too Much? Exploring the slow adoption of new consumer technology Journal ArticleM22 IEEE Consumer Electronics Magazine, 7 (6), pp. 23-28, 2018, ISBN: 2162-2248. Abstract | Links | BibTeX | Download | Tags: business, consumer electronics, digital TV, HMI, ieeexplore, internet of things, smart homes, user experience, user interface @article{BjelicaCE, title = {How Much Smart is Too Much? Exploring the slow adoption of new consumer technology}, author = {Milan Z. Bjelica }, doi = {10.1109/MCE.2018.2816179}, isbn = {2162-2248}, year = {2018}, date = {2018-10-05}, journal = {IEEE Consumer Electronics Magazine}, volume = {7}, number = {6}, pages = {23-28}, abstract = {Today's proliferation of smart systems, devices, and things causes some severe side effects. The use cases of "smart" anything, although numerous, are often made very complex due to the abundance of devices required to enable those use cases. This causes a variety of human-machine interfaces (HMIs), which are by no means standardized, making the public adoption of consumer technology much harder than we might anticipate. Smart phones, tablets, and TVs introduce little commonality in user interfaces (UIs) regarding their openness and the variety of applications available. Our vehicles are offering us disconnected, proprietary infotainment systems and awkward input devices, including numerous buttons and touch, jog shuttle, and steering wheel controls. Smart gadgets and homes are among the most complicated both to install and use, as they still require considerable do-it-yourself (DIY) skills or the help of a trained professional. Furthermore, various new wearables now require users to attach electronics to their person-as if the stress of locating the smartphone before leaving the house is not enough on its own. Learning how to use all of these devices, making use of them, and weaving them into everyday life can be so cumbersome that we may stop adopting new solutions altogether. This has already started to happen. Let me attempt to qualify some reasons for the caveat. These come from two trouble-causing dilemmas. The first is integration versus differentiation (Figure 1).}, howpublished = {M22}, keywords = {business, consumer electronics, digital TV, HMI, ieeexplore, internet of things, smart homes, user experience, user interface}, pubstate = {published}, tppubtype = {article} } Today's proliferation of smart systems, devices, and things causes some severe side effects. The use cases of "smart" anything, although numerous, are often made very complex due to the abundance of devices required to enable those use cases. This causes a variety of human-machine interfaces (HMIs), which are by no means standardized, making the public adoption of consumer technology much harder than we might anticipate. Smart phones, tablets, and TVs introduce little commonality in user interfaces (UIs) regarding their openness and the variety of applications available. Our vehicles are offering us disconnected, proprietary infotainment systems and awkward input devices, including numerous buttons and touch, jog shuttle, and steering wheel controls. Smart gadgets and homes are among the most complicated both to install and use, as they still require considerable do-it-yourself (DIY) skills or the help of a trained professional. Furthermore, various new wearables now require users to attach electronics to their person-as if the stress of locating the smartphone before leaving the house is not enough on its own. Learning how to use all of these devices, making use of them, and weaving them into everyday life can be so cumbersome that we may stop adopting new solutions altogether. This has already started to happen. Let me attempt to qualify some reasons for the caveat. These come from two trouble-causing dilemmas. The first is integration versus differentiation (Figure 1). |
Bjelica, Milan Z; Kovačević, Jelena; Lukač, Željko; Četić, Nenad The in-vehicle sound management procedure based on the driver's accompaniment to sound changes PatentPendingM87 P-2018/0855, 2018, (Pending). BibTeX | Tags: audio, automotive, HMI, infotainment @patent{2018_0855, title = {The in-vehicle sound management procedure based on the driver's accompaniment to sound changes}, author = {Milan Z. Bjelica and Jelena Kovačević and Željko Lukač and Nenad Četić}, year = {2018}, date = {2018-10-01}, number = {P-2018/0855}, howpublished = {M87}, note = {Pending}, keywords = {audio, automotive, HMI, infotainment}, pubstate = {published}, tppubtype = {patent} } |
Jovičić, Jelena; Kotur, Mila; Bjelica, Milan Z; Papp, Ištvan Visualizing Functional Verification in Adaptive AUTOSAR ConferenceM33 Consumer Electronics - Berlin (ICCE-Berlin), 2018 IEEE 8th International Conference on, IEEE Consumer Electronics Society, 2018. Abstract | Links | BibTeX | Tags: automotive, ieeexplore @conference{BjelicaICCE2018, title = {Visualizing Functional Verification in Adaptive AUTOSAR}, author = {Jelena Jovičić and Mila Kotur and Milan Z. Bjelica and Ištvan Papp}, doi = {10.1109/ICCE-Berlin.2018.8576232}, year = {2018}, date = {2018-09-03}, booktitle = {Consumer Electronics - Berlin (ICCE-Berlin), 2018 IEEE 8th International Conference on}, publisher = {IEEE Consumer Electronics Society}, abstract = {The automotive industry is developing more and more these days. New features and functions like autonomous driving, digital cockpit, communication between vehicle and cloud, software updates over the air and many other requiring an increasing amount of software. Such a complex software environment is difficult to verify. There are many solutions in this regard in the industry, however, the problem of software testing and verification is still huge. It can also be challenging to demonstrate feature set and assist functional verification procedures, which are very relevant in agile development practices which require sprint-based demonstrations. In this paper, we present an approach to functionally verify software through visualization, in the scope of Adaptive AUTOSAR stack.}, howpublished = {M33}, keywords = {automotive, ieeexplore}, pubstate = {published}, tppubtype = {conference} } The automotive industry is developing more and more these days. New features and functions like autonomous driving, digital cockpit, communication between vehicle and cloud, software updates over the air and many other requiring an increasing amount of software. Such a complex software environment is difficult to verify. There are many solutions in this regard in the industry, however, the problem of software testing and verification is still huge. It can also be challenging to demonstrate feature set and assist functional verification procedures, which are very relevant in agile development practices which require sprint-based demonstrations. In this paper, we present an approach to functionally verify software through visualization, in the scope of Adaptive AUTOSAR stack. |
Šandor, Robert; Stepanović, Mia; Bjelica, Milan Z; Samardžija, Dragan Vehicle2X communication proposal for Adaptive AUTOSAR ConferenceM33 Consumer Electronics - Berlin (ICCE-Berlin), 2018 IEEE 8th International Conference on, IEEE IEEE Consumer Electronics Society, 2018. Abstract | Links | BibTeX | Tags: automotive, ieeexplore, networks @conference{BjelicaICCE2018b, title = {Vehicle2X communication proposal for Adaptive AUTOSAR}, author = {Robert Šandor and Mia Stepanović and Milan Z. Bjelica and Dragan Samardžija}, doi = {10.1109/ICCE-Berlin.2018.8576234}, year = {2018}, date = {2018-09-03}, booktitle = {Consumer Electronics - Berlin (ICCE-Berlin), 2018 IEEE 8th International Conference on}, publisher = {IEEE Consumer Electronics Society}, organization = {IEEE}, abstract = {Expansion of Internet of Things (IoT) technologies through the years was swift. Interconnected devices have found their way to the automotive industry. This paper covers a brief analysis of available solutions and evaluates the usage of MQTT protocol for heterogeneous device communication in a realistic software environment within AUTOSAR Adaptive stack.}, howpublished = {M33}, keywords = {automotive, ieeexplore, networks}, pubstate = {published}, tppubtype = {conference} } Expansion of Internet of Things (IoT) technologies through the years was swift. Interconnected devices have found their way to the automotive industry. This paper covers a brief analysis of available solutions and evaluates the usage of MQTT protocol for heterogeneous device communication in a realistic software environment within AUTOSAR Adaptive stack. |