AI 中文总结
该研究针对现有协同感知方法未优化车辆选择的问题，提出LLM辅助的联盟形成框架，结合DPP与ADMM优化，在OPV2V等数据集上实现更优性能与网络效率。
AI 中文摘要
协同感知（CP）使联网自动驾驶车辆（CAV）能够共享互补观测以实现更安全的导航，但其实际部署受限于带宽约束、不可靠链路及冗余信息交换。现有CP方法常假设参与者预先定义，仅聚焦于集体感知；近期基于大语言模型（LLM）的协同驾驶框架虽支持多车辆推理，但未制定参与标准以选择更有益的车辆。为填补这一空白，我们提出一种LLM辅助的联盟形成框架，在LLM推理前先选择信息最丰富的辅助车辆。该方法通过多模态车辆嵌入上的确定性点过程（DPP）联合优化感知多样性，并考虑通信感知的可靠性，由此得到一个联盟选择与功率分配的联合问题，我们通过松弛凸重构和基于交替方向乘子法（ADMM）的优化策略高效求解，该策略将感知多样性驱动的选择与网络感知的资源分配解耦。选定的联盟随后被汇总，并与LLM推理模块结合，以实现高效且冗余度更低的多车辆决策支持。实验结果表明，我们的方法在整体联盟价值上优于其他基线方法，同时保持高多样性并提升网络效率；该框架在OPV2V和V2V4Real数据集上实现了任务性能与安全性的更好平衡，证明了其在通信约束下协同自动驾驶中的有效性。
英文摘要
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.
CommentsAccepted for presentation at IEEE Global Communications Conference (GLOBECOM 2026), Cognitive Radio and AI-Enabled Networks Symposium
