Design of Driver-Assist Systems Under Probabilistic Safety Specifications Near Stop Signs

In this paper, we consider the problem of designing in-vehicle driver-assist systems that warn or override the driver to prevent collisions with a guaranteed probability. The probabilistic nature of the problem naturally arises from many sources of uncertainty, among which the behavior of the surrounding vehicles and the response of the driver to on-board warnings. We formulate this problem as a control problem for uncertain systems under probabilistic safety specifications and leverage the structure of the application domain to reach computationally efficient implementations. Simulations using a naturalistic data set show that the empirical probability of safety is always within 5% of the theoretical value in the case of direct driver override. In the case of on-board warnings, the empirical value is more conservative due primarily to drivers decelerating more strongly than requested. However, the empirical value is greater than or equal to the theoretical value, demonstrating a clear safety benefit.

[1]  Domitilla Del Vecchio,et al.  Computational Tools for the Safety Control of a Class of Piecewise Continuous Systems with Imperfect Information on a Partial Order , 2011, SIAM J. Control. Optim..

[2]  R. Verma,et al.  Semiautonomous Multivehicle Safety , 2011, IEEE Robotics & Automation Magazine.

[3]  Andrew Snyder,et al.  NHTSA’s 2014 Automatic Emergency Braking Test Track Evaluations , 2015 .

[4]  D. Leblanc,et al.  DEVELOPMENT AND VALIDATION OF FUNCTIONAL DEFINITIONS AND EVALUATION PROCEDURES FOR COLLISION WARNING/AVOIDANCE SYSTEMS , 1999 .

[5]  Mattias Bengtsson,et al.  Collision Warning with Full Auto Brake and Pedestrian Detection - a practical example of Automatic Emergency Braking , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[6]  Domitilla Del Vecchio,et al.  Cooperative Collision Avoidance at Intersections: Algorithms and Experiments , 2013, IEEE Transactions on Intelligent Transportation Systems.

[7]  Alexandre M. Bayen,et al.  Computational techniques for the verification of hybrid systems , 2003, Proc. IEEE.

[8]  Peter Kafka,et al.  The automotive standard ISO 26262, the innovative driver for enhanced safety assessment & technology for motor cars , 2012 .

[9]  Alex Pentland,et al.  Modeling and Prediction of Human Behavior , 1999, Neural Computation.

[10]  Domitilla Del Vecchio,et al.  Formal design of a provably safe robotic roundabout system , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Richard M. Murray,et al.  Identification of decision rules in a human-controlled system: vehicles at a traffic intersection , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

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

[14]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[15]  Jianghai Hu,et al.  Application of Reachability Analysis for Stochastic Hybrid Systems to Aircraft Conflict Prediction , 2008, IEEE Transactions on Automatic Control.

[16]  Michael A. Shulman,et al.  DEVELOPMENT AND VALIDATION OF FUNCTIONAL DEFINITIONS AND EVALUATION PROCEDURES FOR COLLISION WARNING/AVOIDANCE SYSTEMS , 1999 .

[17]  Domitilla Del Vecchio,et al.  Partial order techniques for vehicle collision avoidance: Application to an autonomous roundabout test-bed , 2009, 2009 IEEE International Conference on Robotics and Automation.

[18]  Domitilla Del Vecchio,et al.  Safety Control of Hidden Mode Hybrid Systems , 2012, IEEE Transactions on Automatic Control.

[19]  Suzanne E. Lee,et al.  Normal and Hard Braking Behavior at Stop Signs and Traffic Signals , 2005 .

[20]  Mohan M. Trivedi,et al.  Driver Behavior and Situation Aware Brake Assistance for Intelligent Vehicles , 2007, Proceedings of the IEEE.

[21]  Manuela L. Bujorianu,et al.  Extended Stochastic Hybrid Systems and Their Reachability Problem , 2004, HSCC.

[22]  Lotta Jakobsson,et al.  Collision Warning with Auto Brake - A Real-Life Safety Perspective , 2007 .

[23]  Domitilla Del Vecchio,et al.  Stochastic hybrid models for predicting the behavior of drivers facing the yellow-light-dilemma , 2015, 2015 American Control Conference (ACC).

[24]  John Lygeros,et al.  On a problem of stochastic reach-avoid set characterization , 2011, IEEE Conference on Decision and Control and European Control Conference.

[25]  George J. Pappas,et al.  A Framework for Worst-Case and Stochastic Safety Verification Using Barrier Certificates , 2007, IEEE Transactions on Automatic Control.

[26]  Domitilla Del Vecchio,et al.  Efficient algorithms for collision avoidance at intersections , 2012, HSCC '12.

[27]  Vijay Gadepally,et al.  Driver/vehicle state estimation and detection , 2011, 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[28]  Rajesh Rajamani,et al.  Vehicle dynamics and control , 2005 .

[29]  Ruzena Bajcsy,et al.  Semiautonomous Vehicular Control Using Driver Modeling , 2014, IEEE Transactions on Intelligent Transportation Systems.

[30]  J. Lygeros,et al.  A game theoretic approach to controller design for hybrid systems , 2000, Proceedings of the IEEE.

[31]  Daniel V. McGehee,et al.  DRIVER DISTRACTION, WARNING ALGORITHM PARAMETERS, AND DRIVER RESPONSE TO IMMINENT REAR-END COLLISIONS IN A HIGH-FIDELITY DRIVING SIMULATOR , 2002 .