Scholarlink

<p>Rare safety-critical events remain a major challenge in autonomous vehicle testing. This paper proposes to use game theory to build a novel testing environment for autonomous vehicles. In this environment, a virtual agent based on counterfactual minimization (CFR) is used to accelerate testing and validate the safety performance of autonomous vehicles. The virtual agent updates the adversarial policies to be enforced by continuously accumulating regret values, thus increasing the probability of security-critical events occurring during the testing process. Finally, recognized metrics such as Time-to-Collision (TTC) and Minimum Safe Distance Factor (MSDF) are introduced to assess the quality of the scenario. Experimental results show that the virtual agent based on counterfactual minimization explicitly generates more safety-critical scenarios and accelerates the evaluation process by multiple orders of magnitude (<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="10489_2024_6194_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="23" /> </InlineMediaObject> <EquationSource Format="TEX">\(10^{3}\)</EquationSource> <EquationSource Format="MATHML"><math> <msup> <mn>10</mn> <mn>3</mn> </msup> </math></EquationSource> </InlineEquation> times faster).</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Counterfactual regret minimization for the safety verification of autonomous driving

  • 期刊论文

  • 发表日期：

    2025年1月14日

查看全文
  • Yong Wang,
  • Pengchao Sun,
  • Daifeng Zhang,
  • Yanqiang Li

摘要

Rare safety-critical events remain a major challenge in autonomous vehicle testing. This paper proposes to use game theory to build a novel testing environment for autonomous vehicles. In this environment, a virtual agent based on counterfactual minimization (CFR) is used to accelerate testing and validate the safety performance of autonomous vehicles. The virtual agent updates the adversarial policies to be enforced by continuously accumulating regret values, thus increasing the probability of security-critical events occurring during the testing process. Finally, recognized metrics such as Time-to-Collision (TTC) and Minimum Safe Distance Factor (MSDF) are introduced to assess the quality of the scenario. Experimental results show that the virtual agent based on counterfactual minimization explicitly generates more safety-critical scenarios and accelerates the evaluation process by multiple orders of magnitude ( \(10^{3}\) 10 3 times faster).