Investigation into the state-of-the-practice autonomous driving testing

Guannan Lou, Yao Deng, Xi Zheng*, Mengshi Zhang, Tianyi Zhang

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

Autonomous driving shows great potential to reform modern transportation. However, its reliability and safety have drawn a lot of attention and concerns. Compared with traditional software systems, autonomous driving systems (ADSs) often use deep neural networks in tandem with logic-based modules. This new paradigm poses unique challenges for software testing. Recently, the software engineering (SE) community has devoted significant effort to developing new testing techniques for autonomous driving systems. However, it is not clear to what extent those techniques have addressed the needs of industrial practitioners. To fill this gap, we present the first comprehensive study to identify the current practices and needs of testing autonomous driving systems in industry. We conducted semi-structured interviews with developers from 10 autonomous driving companies and surveyed 100 developers who have worked on autonomous driving systems. Through systematic analysis of interview and questionnaire data, we identified eight common practices and four common needs of testing autonomous driving systems from industry. We further surveyed 98 highly relevant papers from 28 SE conferences, journals, and workshops to find solutions to address those needs. Finally, we analyzed the limitations of existing testing techniques and proposed several future directions for SE researchers.
Original languageEnglish
JournalarXiv
DOIs
Publication statusSubmitted - 23 Jun 2021

Fingerprint

Dive into the research topics of 'Investigation into the state-of-the-practice autonomous driving testing'. Together they form a unique fingerprint.

Cite this