Ensuring Motion Safety of Autonomous Vehicles through Online Fail-safe Verification

Safety is undoubtedly the most important factor for the success of autonomous vehicles [13]. However, ensuring their safety is a challenging task since they operate in highly uncertain environments with multiple dynamic obstacles whose future motions are unknown [25, 24]. Even when trying to accurately predict and consider the most likely trajectory of obstacles, planned motions might become unsafe when obstacles deviate from the prediction, which regularly happens in real traffic. As a result of the arising uncertainties, most motion planning methods cannot exclude the possibility that the autonomous vehicle causes a collision. For instance, a residual risk of 0.1% per journey can imply one collision in 1,000 journeys. In order to solve safe motion planning, novel approaches need to be developed which 1) provably guarantee safety even if obstacles suddenly deviate from the predicted behavior and 2) are able to cope with any new occurring traffic situation and measurement uncertainties on the fly.

[1]  Ernst-Rüdiger Olderog,et al.  Proving Safety of Traffic Manoeuvres on Country Roads , 2013, Theories of Programming and Formal Methods.

[2]  André Platzer,et al.  Adaptive Cruise Control: Hybrid, Distributed, and Now Formally Verified , 2011, FM.

[3]  E. Feron,et al.  Real-time motion planning for agile autonomous vehicles , 2000, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[4]  Matthias Althoff,et al.  Online Verification of Automated Road Vehicles Using Reachability Analysis , 2014, IEEE Transactions on Robotics.

[5]  Amnon Shashua,et al.  On a Formal Model of Safe and Scalable Self-driving Cars , 2017, ArXiv.

[6]  Matthias Althoff,et al.  An Online Verification Framework for Motion Planning of Self-driving Vehicles with Safety Guarantees , 2019 .

[7]  Philip Koopman,et al.  Autonomous Vehicle Safety: An Interdisciplinary Challenge , 2017, IEEE Intelligent Transportation Systems Magazine.

[8]  Matthias Althoff,et al.  CommonRoad: Composable benchmarks for motion planning on roads , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[9]  Julius Ziegler,et al.  Trajectory planning for Bertha — A local, continuous method , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[10]  Matthias Althoff,et al.  Enhancing motion safety by identifying safety-critical passageways , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

[11]  Thierry Fraichard,et al.  Safe motion planning in dynamic environments , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Sterling J. Anderson,et al.  An optimal-control-based framework for trajectory planning, threat assessment, and semi-autonomous control of passenger vehicles in hazard avoidance scenarios , 2010 .

[13]  Mo Chen,et al.  FaSTrack: A modular framework for fast and guaranteed safe motion planning , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

[14]  Matthias Althoff,et al.  Set-Based Prediction of Pedestrians in Urban Environments Considering Formalized Traffic Rules , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[15]  Ian M. Mitchell.  Comparing Forward and Backward Reachability as Tools for Safety Analysis , 2007, HSCC.

[16]  Matthias Althoff,et al.  SPOT: A tool for set-based prediction of traffic participants , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[17]  Rolf Isermann,et al.  Collision avoidance with combined braking and steering , 2015 .

[18]  Thierry Fraichard,et al.  An efficient and generic 2D Inevitable Collision State-checker , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[19]  Jonas Sjöberg,et al.  Predictive Threat Assessment via Reachability Analysis and Set Invariance Theory , 2011, IEEE Transactions on Intelligent Transportation Systems.

[20]  Martin Buss,et al.  On-line Trajectory Generation for Safe and Optimal Vehicle Motion Planning , 2012, AMS.

[21]  Julius Ziegler,et al.  Optimal trajectory generation for dynamic street scenarios in a Frenét Frame , 2010, 2010 IEEE International Conference on Robotics and Automation.

[22]  Javier Alonso-Mora,et al.  Planning and Decision-Making for Autonomous Vehicles , 2018, Annu. Rev. Control. Robotics Auton. Syst..

[23]  Bernd Westphal,et al.  Can we build it: formal synthesis of control strategies for cooperative driver assistance systems† , 2013, Mathematical Structures in Computer Science.

[24]  Matthias Althoff,et al.  Efficient Computation of Invariably Safe States for Motion Planning of Self-Driving Vehicles , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[25]  Matthias Althoff,et al.  Reachability analysis of nonlinear systems using conservative polynomialization and non-convex sets , 2013, HSCC '13.

[26]  Matthias Althoff,et al.  Computationally Efficient Fail-safe Trajectory Planning for Self-driving Vehicles Using Convex Optimization , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[27]  Hassen Salhi,et al.  Provably safe navigation for mobile robots with limited field-of-views in dynamic environments , 2012, Auton. Robots.