Prunario: Testing Autonomous Driving Systems by Pruning Likely Redundant Scenarios
This program is tentative and subject to change.
We present Prunario, a novel technique for effectively testing autonomous driving systems (ADS). Ensuring the safety of ADS is critical, as their failures can lead to severe casualties. While ADS testing methods have advanced in recent years, they remain unsatisfactory in generating diverse test scenarios that induce distinct driving behaviors-a key requirement for thoroughly evaluating ADS across different situations. To address this, Prunario employs a novel simulation prediction technique to estimate ADS runtime behavior and prune redundant test scenarios that yield similar driving records. Experimental results demonstrate Prunario's effectiveness: it uncovered 23 previously undetected bugs in an industrial-strength ADS and outperformed three state-of-the-art testing techniques.
This program is tentative and subject to change.
Tue 6 OctDisplayed time zone: Pacific Time (US & Canada) change
10:30 - 12:00 | Fuzzing and Test GenerationOOPSLA at East Hall 1 Chair(s): Michael Pradel CISPA Helmholtz Center for Information Security | ||
10:30 18mTalk | Hunting CUDA Bugs at Scale with cuFuzz OOPSLA Link to publication DOI Pre-print Media Attached | ||
10:48 18mTalk | RandSet: Randomized Corpus Reduction for Fuzzing Seed Scheduling OOPSLA Yuchong Xie Fudan University; Hong Kong University of Science and Technology, Kaikai Zhang Hong Kong University of Science and Technology, Yu Liu Fudan University, Rundong Yang Fudan University, Ping Chen Fudan University, Shuai Wang Hong Kong University of Science and Technology, Dongdong She Hong Kong University of Science and Technology DOI | ||
11:06 18mTalk | Metamorphic Testing for Infrastructure-as-Code Engines OOPSLA David Spielmann University of St. Gallen, George Zakhour University of St. Gallen, Dominik Arnold University of Zurich, Matteo Biagiola USI Lugano; University of St. Gallen, Roland Meier armasuisse, Guido Salvaneschi University of St. Gallen Link to publication DOI Pre-print | ||
11:24 18mTalk | Prunario: Testing Autonomous Driving Systems by Pruning Likely Redundant Scenarios OOPSLA DOI | ||
11:42 18mTalk | OBsmith: LLM-Powered JavaScript Obfuscator Testing OOPSLA Shan Jiang University of Texas at Austin, Chenguang Zhu University of Texas at Austin, Sarfraz Khurshid University of Texas at Austin DOI | ||