ROMAN:基于奖励协调的多头注意力网络用于自动驾驶系统测试
ROMAN: Reward-Orchestrated Multi-Head Attention Network for Autonomous Driving System Testing
AI总结:
ROMAN通过结合多头注意力网络与交通法规加权机制,生成高风险违规场景,提升自动驾驶系统测试的全面性与针对性。
摘要:
自动化驾驶系统(ADS)作为自动驾驶车辆的中枢,负责其安全性和效率。安全部署需要在多样化的现实场景中进行彻底测试,并遵守如限速、信号遵守和让行规则等交通法规。违规行为如闯红灯或超速会带来严重安全风险。然而,当前的测试方法面临重大挑战:生成复杂且高风险的违规场景能力有限,且未能考虑多辆车和关键情况之间的复杂交互。为此,我们提出ROMAN,一种新的ADS测试场景生成方法,结合多头注意力网络与交通法规加权机制。ROMAN旨在生成高风险违规场景以实现更彻底和针对性的ADS评估。多头注意力机制建模车辆、交通信号及其他因素之间的交互。交通法规加权机制实施一种工作流程,利用基于LLM的风险加权模块,根据严重性和发生性两个维度评估违规行为。我们通过在CARLA模拟平台上测试百度Apollo ADS并进行广泛实验来评估ROMAN。实验结果表明,ROMAN在平均违规数量上比最先进的工具ABLE高出7.91%,比LawBreaker高出55.96%,同时保持了更高的场景多样性。此外,只有ROMAN成功为输入的交通法规每一条款生成违规场景,使其能够识别比现有方法更多的高风险违规行为。
英文摘要:
Automated Driving System (ADS) acts as the brain of autonomous vehicles, responsible for their safety and efficiency. Safe deployment requires thorough testing in diverse real-world scenarios and compliance with traffic laws like speed limits, signal obedience, and right-of-way rules. Violations like running red lights or speeding pose severe safety risks. However, current testing approaches face significant challenges: limited ability to generate complex and high-risk law-breaking scenarios, and failing to account for complex interactions involving multiple vehicles and critical situations. To address these challenges, we propose ROMAN, a novel scenario generation approach for ADS testing that combines a multi-head attention network with a traffic law weighting mechanism. ROMAN is designed to generate high-risk violation scenarios to enable more thorough and targeted ADS evaluation. The multi-head attention mechanism models interactions among vehicles, traffic signals, and other factors. The traffic law weighting mechanism implements a workflow that leverages an LLM-based risk weighting module to evaluate violations based on the two dimensions of severity and occurrence. We have evaluated ROMAN by testing the Baidu Apollo ADS within the CARLA simulation platform and conducting extensive experiments to measure its performance. Experimental results demonstrate that ROMAN surpassed state-of-the-art tools ABLE and LawBreaker by achieving 7.91% higher average violation count than ABLE and 55.96% higher than LawBreaker, while also maintaining greater scenario diversity. In addition, only ROMAN successfully generated violation scenarios for every clause of the input traffic laws, enabling it to identify more high-risk violations than existing approaches.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。