Enhancing Autonomous Vehicle Training with Language Model Integration and Critical Scenario Generation

TL;DR

CRITICAL is a closed-loop framework that enhances autonomous vehicle training by generating critical scenarios using traffic dynamics, behavior analysis, safety measures, and LLMs, leading to improved learning, performance, and safety.

Contribution

The paper introduces CRITICAL, a novel framework integrating LLMs and critical scenario generation into AV training, improving learning efficiency and safety validation.

Findings

Performance improvements with LLM integration and critical scenario generation.

Enhanced safety resilience and robustness of AV systems.

Faster development and validation of autonomous vehicle agents.

Abstract

This paper introduces CRITICAL, a novel closed-loop framework for autonomous vehicle (AV) training and testing. CRITICAL stands out for its ability to generate diverse scenarios, focusing on critical driving situations that target specific learning and performance gaps identified in the Reinforcement Learning (RL) agent. The framework achieves this by integrating real-world traffic dynamics, driving behavior analysis, surrogate safety measures, and an optional Large Language Model (LLM) component. It is proven that the establishment of a closed feedback loop between the data generation pipeline and the training process can enhance the learning rate during training, elevate overall system performance, and augment safety resilience. Our evaluations, conducted using the Proximal Policy Optimization (PPO) and the HighwayEnv simulation environment, demonstrate noticeable performance improvements with the integration of critical case generation and LLM analysis, indicating CRITICAL's potential to improve the robustness of AV systems and streamline the generation of critical scenarios. This ultimately serves to hasten the development of AV agents, expand the general scope of RL training, and ameliorate validation efforts for AV safety.