The P6 project within i-CAVE is responsible for the functional architecture and safety of autonomous and cooperative driving vehicles.
Existing prototype demonstrators of autonomous and cooperative driving vehicles are built on top of current car systems, adding various functional systems (e.g. sensing, localization, perception, and high intelligence systems), mostly by considering the underlying vehicular system as a black box. This enabled fast prototyping and demonstration, at the cost of risking a lack of perceivable overall architecture, which is undesirable from a software engineering viewpoint; it can make the software ineffective and hard to reuse.
Definition and analysis of software architecture enables early prediction of system’s qualities, which can decrease development cost and help avoid software defects that can be costly or even endanger lives. Ensuring software quality is thus critical and a real-time fault detection mechanism unavoidable, especially in the context of autonomous and cooperative driving vehicles.
Software systems are checked against quality attributes in a quality assessment stage of the software development life cycle. This checking is based on quality models, which traditionally do not scale up to autonomous and cooperative driving vehicles with their complex systems and intertwined interactions between systems and environments. Although the quality issues, especially safety, will be tackled in each i-CAVE project in isolation, the integrated quality aspects e.g. safety cases of the systems of each project need to be formulated and evaluated. Therefore, this project investigates automotive architecture, a safety-driven quality model, and means to monitor and ensure safety for autonomous and cooperative driving vehicles.
We are currently focusing on architectural models and quality standards, and on ensuring functional safety at runtime. Current quality standards for automotive software are governed by the mandatory adherence to ISO 26262. However, new developments in co-operative and autonomous driving outreach the boundaries of ISO 26262 and require new paradigms. In this project we also study new safety and quality concerns that can extend current models to include robustness of intelligent algorithms, verification of probabilistic systems and secure communication between vehicles. In order to ensure safety of autonomous and cooperative driving vehicles at runtime, we are currently investigating ways to derive online, real-time, safety mechanisms out of historical data automatically, i.e. to learn behaviors. The learned models can be used to provide context-aware runtime monitoring as a means to ensure functional safety at runtime.
Staff:
Publications
- Klaasse, Functional System Architecture for vehicles with Cooperative Dual Mode Transport System, MSc internship report, Eindhoven University of Technology, December 2016.
- Luo, A. Khabbaz Saberi, T. Bijlsma, J.J. Lukkien and M.G.J. van den Brand, An architecture pattern for safety critical automated driving applications : design and analysis. In: Proc. 11th Annual IEEE International Systems Conference (SysCon), pp. 261-267, April 2017
- Luo, M.J.G. van den Brand, S. Li, and A. Khabbaz Saberi, A systematic approach and tool support for GSN-based safety case assessment. Journal of Systems Architecture : Embedded Software Design : the EUROMICRO journal, 76, 1-16, 2017.
- Kannan Soundarapandian, K. Suri, J. Cadavid, I. Barosan, M. van den Brand, M. Alferez, S. Gerard, Towards Industry 4.0: Gap Analysis between Current Automotive MES and Industry Standards using Model-Based Requirement Engineering, In: Proc. 3rd Workshop on Automotive System/Software Architecture (WASA), In conjunction with IEEE International Conference on Software Architecture (ICSA), April 2017.
- Schlie, D. Wille, L. Cleophas, I. Schaefer, Clustering Variation Points in MATLAB/Simulink Models Using Reverse Signal Propagation Analysis. ICSR 2017: 77-94, May 2017.
- Schlie, D. Wille, S. Schulze, L. Cleophas, I. Schaefer, Detecting Variability in MATLAB/Simulink Models: An Industry-Inspired Technique and its Evaluation. SPLC (A) 2017: 215-224, September 2017.
- Dajsuren, L. Cleophas, S. Kochanthara, S. Klaasse, M.G.J van den Brand, Functional Architecture and Functional Safety for Autonomous and Cooperative Driving Vehicles, research paper, 14th International Symposium on Advanced Vehicle Control, July 2018
- C. Serban, E. Poll, J. Visser – A standard driven functional architectures for fully autonomous vehicles – WASA 2018
- C. Serban, E. Poll, J. Visser – Tactical Safety Reasoning. A Case for Autonomous Vehicles – CA2V 2018
- C. Serban, E. Poll, J. Visser – A Security Analysis of the ETSI ITS Protocol – SAFECOMP 2018
- C. Serban, E. Poll, J. Visser – Adversarial Examples: A Complete Characterization of the Phenomena – preprint
- K. Saberi, E. Barbier, F. Benders, M. van den Brand, On functional safety methods: A system of systems approach. SysCon 2018
- C. Serban, Designing safety critical software systems to manage inherent uncertainty, ICSA 2019
- Loupias, Y. Dajsuren, Safety Analysis Method for Cooperative Driving Systems, IEEE International Conference on Software Architecture, 2019
Visits, detachments, and training
- Dajsuren presented a talk titled “Safety analysis for a cooperative driving system” at Automotive Software Engineering workshop co-located with SOFSEM 2017, January 16–20, 2017, Lero – Limerick, Ireland.
- Kochanthara presented a poster titled “Intelligent Runtime Monitors for Cyber-Physical Systems” at Summer School: Verification Technology, Systems & Applications, August 2017, Saarbrucken, Germany.
- Kochanthara delivered a presentation at SIG on “Architectural and Functional Safety of Automotive Systems”, July 2017, Amsterdam, The Netherlands.
- Kochanthara delivered a talk on “Monitor Synthesis for Automotive systems” at IPA Fall days, November 2017, Nunspeet, The Netherlands.
- Kochanthara delivered an invited talk on Runtime Monitor Synthesis for automotive systems at National Institute of Technology Calicut, India, December 2017.
- Kochanthara attended Winter School on Software Engineering at Pune, India, December 2017.
- Dajsuren co-organized the fourth international Workshop on Automotive Software/System Architectures (WASA) co-located with International Conference on Software Architecture, Seattle, USA, May 2018.
- Kochanthara attended ACM SIGSOFT International Symposium on Software Testing and Analysis and co-located events at Amsterdam, The Netherlands, July 2018.
- Dajsuren presented a paper titled “Functional Architecture and Functional Safety for Autonomous and Cooperative Driving Vehicles” at 14th International Symposium on Advanced Vehicle Control, July 2018, Beijing, China.
- C. Serban presented a work at WASA 2018 (Part of ICSA 2018).
- C. Serban presented a work at CA2V 2019.
- C. Serban will present a work at SAFECOMP 2018.
- Kochanthara supervised two internship students from National Institute of Technology Calicut, India, on Behavioural learning in 2018.
- Dajsuren co-organized the fifth international Workshop on Automotive Software/System Architectures (WASA) co-located with International Conference on Software Architecture, Hamburg, Germany, March 2019.
- C. Serban will present a work at ICSA 2019.
- Dajsuren will present a work at ICSA 2019.
- Kochanthara is supervising 5 Honors track bachelors students and one masters student from Eindhoven university of technology 2018-2019.
- Dajsuren, The future of automotive architecture description and quality mechanisms, Invited talk. Software-Defined Vehicles Congres, 28 November 2018, Berlin
Knowledge transfer moments (KTM; in Dutch KOM)
- C. Serban extended an open source library for adversarial examples in the deep learning context – https://github.com/NullConvergence/dnnmodels
- C. Serban developed an open source library for meta-learning: a ML technique in which the problem of algorithm design is formulated as a learning problem – https://github.com/NullConvergence/Learning2Learn