Multi-Agent Orchestration with the Common-Sense Reasoning Capabilities of LLMs for Autonomous Driving

2026-08-20

AI Summary

论文提出一种混合框架，通过协调强化学习与PID控制，并利用大语言模型的常识推理能力来改进自主驾驶车辆在多样化和未知场景中的决策和感知能力。

Abstract

Autonomous vehicles require robust perception and decision-making capabilities to operate in diverse and unseen scenarios. While reinforcement learning and rule-based methods can provide effective control and safety mechanisms, their performance may degrade in situations requiring contextual reasoning. Large Language Models (LLMs) have demonstrated strong capabilities in understanding multimodal information and generating contextual reasoning, however, their use for direct vehicle control can introduce latency and hallucination risks. To address these limitations, a hybrid framework is proposed. This system uses an orchestrator to coordinate PPO-trained reinforcement learning and PID control, with LLM common-sense reasoning applied throughout the framework. LLM reasoning is further employed iteratively to refine the RL reward function for dynamic driving environments. The proposed framework is evaluated in highly randomized CARLA scenarios under diverse environmental and traffic conditions. The results demonstrate the potential of integrating LLM-based reasoning with conventional autonomous driving methods while retaining structured control and safety mechanism.

Problem

• Autonomous Driving
• Contextual Reasoning
• Reinforcement Learning

Innovation

• Hybrid Framework
• Common-Sense Reasoning
• LLMs
• PPO Reinforcement Learning
• Dynamic Driving Environments