发表机构
Ben-Gurion University of the Negev（内盖夫本古里安大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对无信号交叉口自动驾驶车辆协调难题提出MAPS分层DRL架构，主智能体生成编码全局策略的原型计划，工作智能体结合局部观测执行控制。实验表明MAPS能实现无碰撞导航、减少行驶时间，且原型计划泛化能力强。
AI 中文摘要
在无信号交叉口协调自动驾驶车辆对多智能体强化学习（MARL）系统来说仍然是一项关键挑战，这类系统通常在组合动作空间、对特权信息的依赖或僵化的智能体设计方面存在困难。我们提出了主智能体原型计划系统（MAPS），这是一种分层深度强化学习（DRL）架构，其中一个集中式主智能体生成一个紧凑的连续嵌入，即原型计划，它编码了全局协调策略。分散的工作智能体将此嵌入与局部观测相结合以执行特定车辆的控制，将战略意图与战术执行解耦，并实现每个模块的独立优化。作为这种协调机制的概念验证评估，我们在HighwayEnv中对72种交叉口配置测试了MAPS。MAPS实现了无碰撞导航，同时显著减少了平均行驶时间，优于现有最先进的基线。学习到的原型计划还表现出强大的泛化能力：一个用三个智能体训练的系统在零样本部署到五个智能体场景时成功率达到94%，证实了基于原型计划的分层学习为多车辆协调提供了一个有前景的框架。
英文摘要
Coordinating autonomous vehicles at unsignalized intersections remains a critical challenge for multi-agent reinforcement learning (MARL) systems, which typically struggle with combinatorial action spaces, reliance on privileged information, or rigid agent designs. We propose Master-Agent Proto-plan System (MAPS), a hierarchical deep reinforcement learning (DRL) architecture in which a centralized Master agent generates a compact, continuous embedding, denoted as proto-plan, that encodes a global coordination strategy. Decentralized Worker agents integrate this embedding with local observations to execute vehicle-specific control, decoupling strategic intent from tactical execution and enabling independent optimization of each module. As a proof-of-concept evaluation of this coordination mechanism, we test MAPS across 72 intersection configurations in HighwayEnv. MAPS achieves collision-free navigation while significantly reducing average travel time, outperforming state-of-the-art baselines. The learned proto-plans further exhibit robust generalization: a system trained with three agents achieves a 94% success rate when deployed zero-shot to five-agent scenarios, confirming that proto-plan-based hierarchical learning provides a promising framework for multi-vehicle coordination.
