Papers

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

Why we picked it

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。

Body

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。

Original · 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.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include autonomous driving, multi-agent systems, self-play, scene generation.

Source attribution: curated from arXiv cs.LG (@Beyazit Yalcinkaya, Ethan Pronovost, Maximilian Naumann, Marcell Vazquez-Chanlatte).