CoLMDriver：基于大语言模型的协商机制助力协同自动驾驶

CoLMDriver: LLM-based Negotiation Benefits Cooperative Autonomous Driving

March 11, 2025

作者: Changxing Liu, Genjia Liu, Zijun Wang, Jinchang Yang, Siheng Chen

cs.AI

摘要

车对车（V2V）协同自动驾驶在提升安全性方面展现出巨大潜力，它能够有效应对单智能体系统中固有的感知与预测不确定性。然而，传统协同方法受限于僵化的协作协议，在面对未见过的交互场景时泛化能力不足。尽管基于大语言模型（LLM）的方法提供了泛化的推理能力，但其在空间规划上的挑战及不稳定的推理延迟阻碍了其在协同驾驶中的直接应用。为克服这些局限，我们提出了CoLMDriver，首个基于LLM的全流程协同驾驶系统，实现了基于语言的有效协商与实时驾驶控制。CoLMDriver采用并行驾驶流程，包含两大核心组件：(i) 基于LLM的协商模块，采用演员-评论家范式，通过所有车辆先前决策的反馈持续优化协作策略；(ii) 意图引导的路径点生成器，将协商结果转化为可执行的路径点。此外，我们引入了InterDrive，一个基于CARLA的仿真基准，包含10个具有挑战性的交互驾驶场景，用于评估V2V协同性能。实验结果表明，CoLMDriver在多种高交互性的V2V驾驶场景中显著优于现有方法，成功率提升了11%。代码将在https://github.com/cxliu0314/CoLMDriver 上发布。

English

Vehicle-to-vehicle (V2V) cooperative autonomous driving holds great promise for improving safety by addressing the perception and prediction uncertainties inherent in single-agent systems. However, traditional cooperative methods are constrained by rigid collaboration protocols and limited generalization to unseen interactive scenarios. While LLM-based approaches offer generalized reasoning capabilities, their challenges in spatial planning and unstable inference latency hinder their direct application in cooperative driving. To address these limitations, we propose CoLMDriver, the first full-pipeline LLM-based cooperative driving system, enabling effective language-based negotiation and real-time driving control. CoLMDriver features a parallel driving pipeline with two key components: (i) an LLM-based negotiation module under an actor-critic paradigm, which continuously refines cooperation policies through feedback from previous decisions of all vehicles; and (ii) an intention-guided waypoint generator, which translates negotiation outcomes into executable waypoints. Additionally, we introduce InterDrive, a CARLA-based simulation benchmark comprising 10 challenging interactive driving scenarios for evaluating V2V cooperation. Experimental results demonstrate that CoLMDriver significantly outperforms existing approaches, achieving an 11% higher success rate across diverse highly interactive V2V driving scenarios. Code will be released on https://github.com/cxliu0314/CoLMDriver.