Autonomous Vehicles (AV) operate in a safety-critical dynamic environment. Frequently occurring environmental uncertainties and random component failures might result into hazardous events, sometimes even into an accident, if left undetected. Moreover, in the event of random errors, highly integrated automotive systems might suffer from the butterfly effect, where a small failure in a component can lead to an unexpected unsafe behavior within the entire system. While an AV operates in a dynamic environment, traditional safety assurance mechanisms like Fault Tree Analysis (FTA), Failure Mode Effect and Criticality Analysis (FMECA), etc. are plays a vital role, but not sufficient enough to ensure safety (at runtime) as they are based on static worst-case assumptions. One possible way to overcome this is through runtime monitoring, where the AV and its behavior can be monitored during operation. In case of an unplanned behavior or safety-critical deviation appear, the monitor can manage the system to assume a safe state via reconfiguration process. We present our work where we exploit the adaptation behavior of AV, to ensure its safe operation at runtime. At this end, we investigate the adaptation behavior of an Adaptive Cruise Control (ACC) of an AV, followed by implementing different possible adaptation techniques.
Exploiting Adaptation Behavior of an Autonomous Vehicle to Achieve Fail-Safe Reconfiguration
Proceedings
2021-04-18
14 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Deutsch
Fail-safe handling system for autonomous driving vehicle
Europäisches Patentamt | 2023
|FAIL-SAFE HANDLING SYSTEM FOR AUTONOMOUS DRIVING VEHICLE
Europäisches Patentamt | 2021
|Fail-safe motion planning of autonomous vehicles
IEEE | 2016
|METHOD AND APPARATUS FOR PERFOMING FAIL-SAFE FUNCTION OF AUTONOMOUS VEHICLE
Europäisches Patentamt | 2022
|