LLM-Assisted Coalition Formation for Cooperative Perception in Autonomous Driving

2026-08-01

AI Summary

This work addresses the suboptimal participant selection in cooperative perception caused by bandwidth constraints, unreliable communication links, and information redundancy. To tackle this challenge, we propose a large language model (LLM)-assisted coalition formation framework that jointly models perceptual diversity and communication reliability for the first time. The framework leverages determinantal point processes (DPPs) to capture information complementarity and integrates network constraints to co-optimize coalition selection and power allocation. An efficient solution is achieved through convex relaxation and the alternating direction method of multipliers (ADMM). Furthermore, an LLM module facilitates collaborative decision-making among multiple vehicles. Experimental results on the OPV2V and V2V4Real datasets demonstrate that the proposed approach significantly enhances overall coalition utility, achieving a favorable trade-off among task performance, safety, and communication efficiency.

Abstract

Cooperative perception (CP) enables connected autonomous vehicles (CAVs) to share complementary observations for safer navigation, but practical deployment is limited by bandwidth constraints, unreliable links, and redundant information exchange. Existing CP methods often assume predefined participants and merely focus on collective perception. Likewise, recent LLM-based cooperative driving frameworks facilitate multi-vehicle reasoning but do not regulate participation criteria to select more beneficial vehicles. To bridge this gap, we propose an LLM-assisted coalition formation framework that selects the most informative helper vehicles before LLM reasoning. The approach jointly optimizes perceptual diversity using a determinantal point process (DPP) over multimodal vehicle embeddings and communication-aware reliability. This leads to a joint coalition selection and power allocation problem, which we solve efficiently via a relaxed convex reformulation and an ADMM-based optimization strategy that decouples diversity-aware selection from network-aware resource allocation. The selected coalition is then summarized and provided with an LLM reasoning module for efficient and less redundant multi-vehicle decision support. Experimental results show that our approach outperforms other baselines in overall coalition value, while maintaining high diversity and improved networking efficiency. The framework achieves a better balance between task performance and safety across OPV2V and V2V4Real datasets, demonstrating its effectiveness for cooperative autonomous driving with communication constraints.

Problem

• cooperative perception
• coalition formation
• autonomous driving
• communication constraints
• vehicle selection

Innovation

• LLM-assisted coalition formation
• cooperative perception
• determinantal point process (DPP)
• communication-aware optimization
• multi-vehicle reasoning