Testing Scenario Library Generation for Connected and Automated Vehicles, Part II: Case Studies

Testing scenario library generation (TSLG) is a critical step for the development and deployment of connected and automated vehicles (CAVs). In Part I of this study, a general method for TSLG is proposed, and theoretical properties are investigated regarding the accuracy and efficiency of CAV evaluation. This paper aims to provide implementation examples and guidelines, and to enhance the proposed methodology under high-dimensional scenarios. Three typical cases, including cut-in, highway-exit, and car-following, are designed and studied in this paper. For each case, the process of library generation and CAV evaluation is elaborated. To address the challenges brought by high dimensionality, the proposed method is further enhanced by reinforcement learning technique. For all three cases, results show that the proposed method can accelerate the CAV evaluation process by multiple magnitudes with same evaluation accuracy, if compared with the on-road test method.

[1]  Huei Peng,et al.  Worst Case Scenarios Generation and Its Application on Driving , 2007 .

[2]  Nidhi Kalra,et al.  Measuring Automated Vehicle Safety: Forging a Framework , 2018 .

[3]  Dirk Helbing,et al.  General Lane-Changing Model MOBIL for Car-Following Models , 2007 .

[4]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[5]  Hampton C. Gabler,et al.  Comparison of Time to Collision and Enhanced Time to Collision at Brake Application during Normal Driving , 2016 .

[6]  Partha S. Roop,et al.  A Formal Approach for Modeling and Simulation of Human Car-Following Behavior , 2018, IEEE Transactions on Intelligent Transportation Systems.

[7]  Kyunghyun Cho,et al.  Query-Efficient Imitation Learning for End-to-End Autonomous Driving , 2016, ArXiv.

[8]  Stephen A. McGuire,et al.  Introductory Statistics , 2007, Technometrics.

[9]  Nanning Zheng,et al.  Artificial intelligence test: a case study of intelligent vehicles , 2018, Artificial Intelligence Review.

[10]  James R. Sayer,et al.  Integrated vehicle-based safety systems: light vehicle field operational test, key findings report. , 2011, Annals of emergency medicine.

[11]  Jonas Fredriksson,et al.  If, When, and How to Perform Lane Change Maneuvers on Highways , 2016, IEEE Intelligent Transportation Systems Magazine.

[12]  T A Ranney,et al.  Models of driving behavior: a review of their evolution. , 1994, Accident; analysis and prevention.

[13]  Khadir Mohamed,et al.  Model Predictive Control: Theory and Design , 2014 .

[14]  Hani S. Mahmassani,et al.  From Existing Accident-Free Car-Following Models to Colliding Vehicles , 2008 .

[15]  Larry Wasserman,et al.  All of Statistics: A Concise Course in Statistical Inference , 2004 .

[16]  Chang Liu,et al.  How Much Data Are Enough? A Statistical Approach With Case Study on Longitudinal Driving Behavior , 2017, IEEE Transactions on Intelligent Vehicles.

[17]  Xun Gong,et al.  Evaluation of the Energy Efficiency in a Mixed Traffic with Automated Vehicles and Human Controlled Vehicles , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

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

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

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

[21]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[22]  Hardi Hungar,et al.  Test Specifications for Highly Automated Driving Functions: Highway Pilot , 2017 .

[23]  Fred Feng,et al.  Can vehicle longitudinal jerk be used to identify aggressive drivers? An examination using naturalistic driving data. , 2017, Accident; analysis and prevention.

[24]  Katja Vogel,et al.  A comparison of headway and time to collision as safety indicators. , 2003, Accident; analysis and prevention.

[25]  Yi Zhang,et al.  Testing Scenario Library Generation for Connected and Automated Vehicles, Part I: Methodology , 2019, IEEE Transactions on Intelligent Transportation Systems.