发表机构
School of future Transportation, Chang’an University; Hangzhou International Innovation Institute, Beihang University; School of information, Renmin University of China; School of Artificial Intelligence and Robotics, Hunan University（长安大学未来交通学院; 北京航空航天大学杭州国际创新研究院; 中国人民大学信息学院; 湖南大学人工智能与机器人学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对现有协同自动驾驶协商方法易收敛到次优解的问题，提出基于LLM的多决策路径协商框架CoLMIN，通过三个关键组件实现稳定高质量共识，在CARLA仿真中性能优于现有方法。
AI 中文摘要
多车协同自动驾驶通过网联车辆间的信息共享提升自动驾驶系统的安全性与可靠性，在改善交通安全方面展现出巨大潜力。基于大语言模型（LLM）的方法利用LLM强大的推理能力实现有效的车际协商，提升协同驾驶性能。然而，复杂交通场景中的驾驶决策本质上存在多解性，导致现有基于协商的方法常过早收敛到次优解，阻碍共识形成，限制了协同自动驾驶系统的实际部署。为解决这一挑战，本文提出CoLMIN，一种面向协同自动驾驶的基于LLM的多决策路径协商框架，通过多决策路径协商与反思推理实现稳定的决策共识。CoLMIN包含三个关键组件：（i）基于LLM的多意图协商模块（LMin），采用协商者-评估者范式，生成多个候选驾驶意图供联合评估；（ii）基于评估的浅层反思模块（ESRM），分析协商结果并提供反馈以指导后续协商，从而加速共识形成；（iii）基于LLM的深层反思模块（LDRM），对协商历史进行长期反思，以缓解认知固化，防止系统收敛到次优解。在CARLA仿真环境中的实验结果表明，CoLMIN在具有挑战性的交互驾驶场景中显著优于现有方法。
英文摘要
Multi-vehicle cooperative autonomous driving enhances the safety and reliability of autonomous driving systems through information sharing among connected vehicles, demonstrating significant potential for improving traffic safety. LLM-based approaches leverage strong reasoning capabilities of LLMs to enable effective inter-vehicle negotiation and improve cooperative driving performance. However, driving decisions in complex traffic scenarios are inherently multi-solution in nature. As a result, existing negotiation-based methods often converge prematurely to suboptimal solutions, hindering consensus formation and limiting the practical deployment of cooperative autonomous driving systems. To address this challenge, we propose CoLMIN, the LLM-based multi-decision path negotiation framework for cooperative autonomous driving, achieving stable decision consensus through multi-decision path negotiation and reflective reasoning. To achieve stable and high-quality consensus in cooperative autonomous driving, CoLMIN consists of three key components: (i) an LLM-based Multi-Intent Negotiation module (LMin), which adopts a Negotiator-Evaluator paradigm and generates multiple candidate driving intentions for joint evaluation; (ii) an Evaluation-based Shallow Reflection Module (ESRM), which analyzes negotiation outcomes and provides feedback to guide subsequent negotiations, thereby accelerating consensus formation; and (iii) an LLM-based Deep Reflection Module (LDRM), which performs long-term reflection over negotiation histories to mitigate cognitive fixation and prevent the system from converging to suboptimal solutions. Experimental results in the CARLA simulation environment demonstrate that CoLMIN significantly outperforms existing methods in challenging interactive driving scenarios.
