Generation of Scenes in Intersections for the Validation of Highly Automated Driving Functions

The simulation of traffic scenes in the environment of an automated vehicle promises to make significant contribution to the validation of automated driving. The construction of models which describe traffic scenes in a generic manner is complicated, since the parameter space of the scenes is infinite. This paper introduces a statistical approach to generate traffic scenes in intersections. A generic model which allows us to represent the scenes is proposed. The concept of Bayesian networks is used to fit the model onto a publicly accessible dataset and to infer traffic scenes from the model. A quantitative evaluation of the results is achieved by the calculation of the total variation distance (TVD) between the distributions of several physical properties.

[1]  Mykel J. Kochenderfer,et al.  Adaptive Stress Testing for Autonomous Vehicles , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[2]  Wenshuo Wang,et al.  Evaluation of Lane Departure Correction Systems Using a Regenerative Stochastic Driver Model , 2017, IEEE Transactions on Intelligent Vehicles.

[3]  A Wheeler Tim,et al.  Factor graph scene distributions for automotive safety analysis , 2016 .

[4]  Mykel J. Kochenderfer,et al.  Analysis of microscopic behavior models for probabilistic modeling of driver behavior , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[5]  Ding Zhao,et al.  Accelerated Evaluation of Automated Vehicles. , 2016 .

[6]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[7]  Michael Stolz,et al.  Testing of autonomous vehicles using surrogate models and stochastic optimization , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[8]  Philip Koopman,et al.  Toward a Framework for Highly Automated Vehicle Safety Validation , 2018 .

[9]  Luigi del Re,et al.  Reduced Complexity Safety Testing for ADAS & ADF , 2017 .

[10]  Richard E. Neapolitan,et al.  Learning Bayesian networks , 2007, KDD '07.

[11]  P. G. Gipps,et al.  A behavioural car-following model for computer simulation , 1981 .

[12]  Erwin de Gelder,et al.  Assessment of Automated Driving Systems using real-life scenarios , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[13]  Ding Zhao,et al.  Accelerated Evaluation of Automated Vehicles in Car-Following Maneuvers , 2016, IEEE Transactions on Intelligent Transportation Systems.

[14]  Luigi del Re,et al.  Identification of critical cases of ADAS safety by FOT based parameterization of a catalogue , 2017, 2017 11th Asian Control Conference (ASCC).

[15]  Mykel J. Kochenderfer,et al.  Imitating driver behavior with generative adversarial networks , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[16]  Klaus C. J. Dietmayer,et al.  The Ko-PER intersection laserscanner and video dataset , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[17]  Jörg Seewig,et al.  Automated scenario generation for regression testing of autonomous vehicles , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[18]  B. De Schutter,et al.  Traffic Modelling Validation of Advanced Driver Assistance Systems , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[19]  J. Kearney,et al.  Robust and Efficient Computation of the Closest Point on a Spline Curve , 2002 .

[20]  Helbing,et al.  Congested traffic states in empirical observations and microscopic simulations , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[21]  Mykel J. Kochenderfer,et al.  Initial Scene Configurations for Highway Traffic Propagation , 2015, 2015 IEEE 18th International Conference on Intelligent Transportation Systems.