[Paper Review] Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review

Xinhai Zhang, Jianbo Tao+10 more|arXiv (Cornell University)|Oct 16, 2021

Autonomous Vehicle Technology and Safety152 references25 citations

TL;DR

This paper presents a taxonomy for critical scenario identification (CSI) methods in ADS/ADAS, surveys 86 papers from 2017–2020, and highlights open issues and future research directions.

ABSTRACT

Scenario-based approaches have been receiving a huge amount of attention in research and engineering of automated driving systems. Due to the complexity and uncertainty of the driving environment, and the complexity of the driving task itself, the number of possible driving scenarios that an ADS or ADAS may encounter is virtually infinite. Therefore it is essential to be able to reason about the identification of scenarios and in particular critical ones that may impose unacceptable risk if not considered. Critical scenarios are particularly important to support design, verification and validation efforts, and as a basis for a safety case. In this paper, we present the results of a systematic literature review in the context of autonomous driving. The main contributions are: (i) introducing a comprehensive taxonomy for critical scenario identification methods; (ii) giving an overview of the state-of-the-art research based on the taxonomy encompassing 86 papers between 2017 and 2020; and (iii) identifying open issues and directions for further research. The provided taxonomy comprises three main perspectives encompassing the problem definition (the why), the solution (the methods to derive scenarios), and the assessment of the established scenarios. In addition, we discuss open research issues considering the perspectives of coverage, practicability, and scenario space explosion.

Motivation & Objective

• Define a comprehensive taxonomy to categorize CSI methods for ADS/ADAS.
• Provide an overview of state-of-the-art CSI methods through the taxonomy.
• Identify open issues and directions for future CSI research in safety assurance of ADS/ADAS.

Proposed method

• Develop a taxonomy with three main perspectives: problem definition (why), solution (how to derive scenarios), and assessment (evaluation of scenarios).
• Conduct a systematic literature review of CSI methods focusing on ADS/ADAS from 2017–2020.
• Classify and map 86 primary studies to the taxonomy to reveal state of the art.
• Ground the taxonomy in key standards (SAE J3016, ISO 26262, ISO/PAS 21448, etc.) and scenario concepts (scenario, scene, ODD).
• Discuss open issues related to coverage, practicability, and scenario space explosion.

Experimental results

Research questions

• RQ1 RQ1: What taxonomy can systematically categorize and compare state-of-the-art CSI methods for ADS/ADAS?
• RQ2 RQ2: What is the current status of CSI methods research with respect to this taxonomy?
• RQ3 RQ3: What are the remaining problems and challenges for further investigation?

Key findings

• A comprehensive taxonomy for CSI methods is developed.
• An overview of CSI methods is provided by mapping 86 papers (2017–2020) to the taxonomy.
• The study identifies open issues and future research directions, including coverage, practicability, and scenario space explosion.