Skip to content
Open access

CoLMIN: LLM-based Multi-Decision Path Negotiation for Cooperative Autonomous Driving

Sep 2026 · IEEE transactions on multimedia · pp. 1-13 · 0 citations · 57 references
Computer Science

TL;DR

CoLMIN, the LLM-based multi-decision path negotiation framework for cooperative autonomous driving, achieves stable decision consensus through multi-decision path negotiation and reflective reasoning, and significantly outperforms existing methods in challenging interactive driving scenarios.

Abstract

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.

Read PDF

Similar papers

Nov 2026

Learning enhanced game theoretic decision-making for interaction-aware autonomous driving in urban traffic scenarios.

Autonomous vehicles (AVs) are expected to significantly improve road safety and traffic efficiency. However, ensuring safe decision-making in complex urban traffic scenarios remains a critical challenge due to complex interactions between AVs and surrounding vehicles. In this context, the behaviors of nearby vehicles i...

Shen Li, Hao-Jie Gui, Kai Yang et al. · 0 citations
Sep 2026

A Multi-UAV Cooperative Navigation Method Based on Policy Decomposition Structure

Simulation results demonstrate that, compared to traditional methods, GS-MADDPG improves the navigation success rate, robustness, and generalization performance, and verifies its effectiveness in multi-UAV cooperative navigation for search and rescue tasks.

Li Tan, Hai-Xia Zhao, Jia-Qin Chai et al. · 0 citations
Open access Sep 2026

Infrastructure-Assisted Cooperative Decision Model With Priority Awareness at Unsignalized Intersections

Unsignalized intersections pose a significant challenge for multi-vehicle cooperative decision-making, where safety and efficiency must be ensured simultaneously under dynamic traffic conditions. To address this challenge, this study proposes a Vehicle-to-Infrastructure Integrated Distributed Agent Decision-Making...

Si-Fan Wu, Xu-Ting Duan, Hao Zhang et al. · 0 citations
Open access 2026

Risk-Aware Mixed Prioritized Experience Replay for Cooperative Path Planning of UAV Swarms in Complex Dynamic Airspace

Training results show that MPER-MASAC maintains the highest mean reward in the later stage among Multi-Agent Deep Deterministic Policy Gradient, MASAC, and MPER-MASAC, and the effectiveness of the proposed risk-aware mixed prioritized experience replay mechanism in improving task execution performance in the evaluated...

Feng Wang, Shuai-Tong Wu, Fang-Chao Tian · 0 citations
Nov 2026

Hierarchical Cloud-Edge Cooperative Control Framework for Multi-Vehicle Autonomous Driving Using Reinforcement Learning and Model Predictive Control

This study presents a hierarchical cooperative control framework for hybrid electric vehicles in intelligent transportation systems, termed “cloud-coordinated cooperative driving with deep reinforcement learning.” The framework integrates reinforcement learning with model predictive control (MPC) to balance adaptabil...

Ning Tong, Shi-Fan Luo, Hao Li et al. · 0 citations
Open access 2026

A Self-Organizing Federated Reinforcement Learning Framework for Cross-Scenario Collaborative AVP Trajectory Planning

A Self-Organizing Federated Reinforcement Learning (SO-FRL) framework for cloud-edge-vehicle collaboration that combines a self-organizing network with federated node-level knowledge transfer, enabling continual policy evolution without directly sharing raw trajectories or sensor streams.

Xin-Hao Liu, Xian-Sheng Guo, Gordon Owusu Boateng et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.