Autonomous driving systems have been applied to many tasks, such as driving assistance, agriculture automation, logistics robots, and so on. Due to its potential impact on security, transportation, and energy, many countries have invested a lot of resources in their research and development. However, as one kind of typical cyber-physical system, autonomous driving systems need to integrate multiple sources of information to complete various complex driving tasks. These characteristics bring new opportunities and challenges to the testing of autonomous driving systems. This report starts from the analysis of the characteristics of software defects in the autonomous driving system, summarizes the difficulties of test technology research and development, and reports the data-driven testing techniques and methods for the autonomous driving system.
Professor, Department of Computer Science and Technology
Nanjing University
Yang Feng is an assistant research professor in the Department of Computer Science and Technology at Nanjing University. He obtained his Ph.D from the University of California, Irvine. His research interests lay in the quality assurance of complex software systems and the implementation of reliable software infrastructure. He has published more than 40 research papers on the topics of software quality assurance. He also regularly serves on the program committee in top software engineering research venues.
