Automatic Virtual Test Technology for Intelligent Driving Systems Considering Both Coverage and Efficiency
- 26 October 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 69 (12) , 14365-14376
Abstract
The test of intelligent driving systems is faced with the challenges of efficiency because real traffic scenarios are infinite, uncontrollable and difficult to be precisely defined. Based on the complexity index of scenario designed to measure the test effect indirectly, a new combinational generation algorithm of test cases is proposed to make a balance between multiple objects including coverage, case number and test effect. Then a joint simulation platform based on Matlab, PreScan and Carsim is set up to realize the automatic construction of 3D test environment from the generated scenarios, conduction of test and evaluation of test results seamlessly. The proposed strategy has been validated by application to a traffic jam pilot system and the results show that it is beneficial to improve the complexity of scenario and the designed scenarios can find system faults effectively, and the required time to conduct tests is reduced obviously by automation.Keywords
Funding Information
- Natural Science Foundation of Chongqing Municipality (cstc2019jcyj-zdxmX0018)
- Sichuan Science and Technology Program (2020YFSY0070)
This publication has 32 references indexed in Scilit:
- Multiple-Model Switching Control of Vehicle Longitudinal Dynamics for Platoon-Level AutomationIEEE Transactions on Vehicular Technology, 2016
- Taking the Human Out of the Loop: A Review of Bayesian OptimizationProceedings of the IEEE, 2015
- Bayesian optimization for learning gaits under uncertaintyAnnals of Mathematics and Artificial Intelligence, 2015
- Driver Steering Override for Lane-Keeping Aid Using Computer-Aided EngineeringIEEE/ASME Transactions on Mechatronics, 2015
- A Discrete Particle Swarm Optimization for Covering Array GenerationIEEE Transactions on Evolutionary Computation, 2014
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Ford Campus vision and lidar data setThe International Journal of Robotics Research, 2011
- Development and evaluation of collision warning/collision avoidance algorithms using an errable driver modelVehicle System Dynamics, 2010
- FAILURE MODES IN MEDICAL DEVICE SOFTWARE: AN ANALYSIS OF 15 YEARS OF RECALL DATAInternational Journal of Reliability, Quality and Safety Engineering, 2001
- The AETG system: an approach to testing based on combinatorial designIEEE Transactions on Software Engineering, 1997