Case-based Reasoning Augmented Large Language Model Framework for Decision Making in Realistic Safety-Critical Driving Scenarios

TL;DR

This paper introduces a novel framework combining case-based reasoning with large language models to improve decision-making in safety-critical autonomous driving scenarios, enhancing accuracy, interpretability, and robustness.

Contribution

The paper proposes a CBR-augmented LLM framework that integrates scene understanding and case retrieval for better decision-making in complex driving environments.

Findings

Improved decision accuracy in risky scenarios

Enhanced justification quality and human alignment

Robust performance in real-world conditions

Abstract

Driving in safety-critical scenarios requires quick, context-aware decision-making grounded in both situational understanding and experiential reasoning. Large Language Models (LLMs), with their powerful general-purpose reasoning capabilities, offer a promising foundation for such decision-making. However, their direct application to autonomous driving remains limited due to challenges in domain adaptation, contextual grounding, and the lack of experiential knowledge needed to make reliable and interpretable decisions in dynamic, high-risk environments. To address this gap, this paper presents a Case-Based Reasoning Augmented Large Language Model (CBR-LLM) framework for evasive maneuver decision-making in complex risk scenarios. Our approach integrates semantic scene understanding from dashcam video inputs with the retrieval of relevant past driving cases, enabling LLMs to generate maneuver recommendations that are both context-sensitive and human-aligned. Experiments across multiple open-source LLMs show that our framework improves decision accuracy, justification quality, and alignment with human expert behavior. Risk-aware prompting strategies further enhance performance across diverse risk types, while similarity-based case retrieval consistently outperforms random sampling in guiding in-context learning. Case studies further demonstrate the framework's robustness in challenging real-world conditions, underscoring its potential as an adaptive and trustworthy decision-support tool for intelligent driving systems.