论文

多智能体自 play 生成可控自动驾驶关键场景

Learning to Interact in Multi-Agent Self-Play for Controllable Autonomous Driving Scenario Generation

精选理由

搞自动驾驶仿真的同行可以看:它把自 play 从“随机演化”变成“点名要什么交互就生成什么”,攻击性跟车、别车这些难造的边缘场景都能定向合成,比静态地图目标的老框架实用。

一篇 arXiv 论文针对自动驾驶仿真测试中的场景生成难题:现有目标条件自 play 框架依赖静态地图位置目标,无法可靠生成攻击性跟车、对抗性别车等复杂交互行为。

正文

作者提出扩展的多智能体自 play 框架,引入智能体相对动态目标,将策略条件化在这个扩展目标表示上,实现可控、有针对性的场景合成。实验显示该方法能生成静态目标基线无法模拟的交互式驾驶行为。

这类工具面向自动驾驶测试中的长尾场景生成需求,让安全关键边缘用例的构造从手工设计转向可指定的策略控制。

原文 · arXiv cs.LG

Learning to Interact in Multi-Agent Self-Play for Controllable Autonomous Driving Scenario Generation

Large-scale, multi-agent self-play trains robust driving policies effectively in simulation, but controlling these models to generate specific, safety-critical edge cases remains a key challenge. Existing goal-conditioned self-play frameworks rely primarily on static map-location goals and fail to reliably produce complex agent interactions such as aggressive tailgating or adversarial cut-offs. These agent interactions are necessary for rigorous autonomous vehicle (AV) testing. To address this, we present an extended multi-agent self-play framework that introduces agent-relative dynamic goals. By conditioning policies on this extended goal representation, our framework enables targeted, controllable scenario synthesis. We demonstrate that our approach successfully generates interactive driving behaviors that static-goal baselines cannot simulate, providing a flexible tool for long-tail scenario generation in AV testing.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:自动驾驶、多智能体、自博弈、场景生成,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Beyazit Yalcinkaya, Ethan Pronovost, Maximilian Naumann, Marcell Vazquez-Chanlatte),经 AITOP 多维评分管线结构化提炼。