| |
 Toward Automatic Testing and Safeguarding for Autonomous Driving Systems |  | CHENG Mingfei PhD Candidate
School of Computing and Information Systems
Singapore Management University
| Research Area Dissertation Committee Research Advisor Committee Members |
| | Date 30 July 2025 (Wednesday) | Time 9:00am - 10:00am | Venue Meeting room 5.1, Level 5
School of Computing and Information Systems 1,
Singapore Management University,
80 Stamford Road
Singapore 178902 | Please register by 29 July 2025. We look forward to seeing you at this research seminar. 
|
|
|
| | ABOUT THE TALK Autonomous Driving Systems (ADSs) represent one of the most complex and promising classes of intelligent systems, with the potential to bring profound societal impact. Due to their safety-critical nature and close interaction with the public, rigorous evaluation is essential to ensure the safety and reliability of ADSs before deployment. Although recent advances in ADS testing have shown promise in identifying corner cases, the vast diversity of driving scenarios and the inherent complexity of ADSs continue to pose major challenges for comprehensive testing and effective safeguarding. This dissertation proposal presents a series of automated techniques designed to address these challenges. Specifically, it introduces: (1) behavior-guided safety testing to explore diverse critical scenarios, (2) evaluation of the robustness of ADSs in making optimal decisions, (3) deadlock avoidance testing for multi-vehicle interactions, and (4) a safeguarding approach for runtime decision repair in ADSs. | | | SPEAKER BIOGRAPHY CHENG Mingfei is a Ph.D. candidate in Computer Science at the SMU School of Computing and Information Systems, supervised by Assistant Professor XIE Xiaofei. His research primarily focuses on software engineering for AI-enabled systems, specifically the testing and improvement of autonomous driving systems. |
|
