Validating SuperHuman Automated Driving Performance

التفاصيل البيبلوغرافية
العنوان: Validating SuperHuman Automated Driving Performance
المؤلفون: Paolo Pretto, Barys Shyrokau, Bakir Lacevic, Martin Horn, Matthijs Klomp, Georg Stettinger, Hassaan Islam, Zlatan Ajanovic
المصدر: SMC
Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
سنة النشر: 2020
مصطلحات موضوعية: validation, 0209 industrial biotechnology, business.industry, Computer science, multi-lane driving, traffic lights, Driving simulator, 020207 software engineering, 02 engineering and technology, Track (rail transport), Automation, urban driving, 020901 industrial engineering & automation, Brake, automated driving, 0202 electrical engineering, electronic engineering, information engineering, Benchmark (computing), lane change, planning, SuperHuman, business, Simulation
الوصف: Closed-loop validation of autonomous vehicles is an open problem, significantly influencing development and adoption of this technology. The main contribution of this paper is a novel approach to reproducible, scenario-based validation that decouples the problem into several sub-problems, while avoiding to brake the crucial couplings. First, a realistic scenario is generated from the real urban traffic. Second, human participants, drive in a virtual scenario (in a driving simulator), based on the real traffic. Third, human and automated driving trajectories are reproduced and compared in the real vehicle on an empty track without traffic. Thus, benefits of automation with respect to safety, efficiency and comfort can be clearly benchmarked in a reproducible manner. Presented approach is used to benchmark performance of SBOMP planner in one scenario and validate SuperHuman driving performance.
وصف الملف: application/pdf
اللغة: English
تدمد: 1062-922X
DOI: 10.1109/smc42975.2020.9282822
URL الوصول: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a4a67330445723a7d6d6eb6333e0875f
https://doi.org/10.1109/smc42975.2020.9282822
Rights: OPEN
رقم الانضمام: edsair.doi.dedup.....a4a67330445723a7d6d6eb6333e0875f
قاعدة البيانات: OpenAIRE
الوصف
تدمد:1062922X
DOI:10.1109/smc42975.2020.9282822