A Large-Language-Model Supported Personalized Driving Framework for Lane Change in Highway Scenarios

2026-06-30

AI Summary

This work addresses the challenge of effectively translating users’ implicit driving preferences—expressed in natural language—into executable and distinguishable personalized lane-changing behaviors. To this end, the authors propose a novel personalized driving framework that integrates large language models (LLMs) with retrieval-augmented generation (RAG), marking the first application of RAG in autonomous driving. The framework accurately interprets implicit natural language instructions and maps them to stylized parameters within the Apollo planning module, supporting aggressive, normal, and conservative driving styles. Distinct lane-changing parameter sets are constructed through behavioral clustering and style-intensity ranking. Experimental results demonstrate that the approach significantly improves the accuracy of interpreting natural language preferences and generates clearly differentiated personalized lane-changing maneuvers on the Apollo platform, thereby validating the feasibility of deeply integrating LLMs with autonomous driving systems.

Abstract

Personalized driving can improve the user acceptance of automated driving systems. However, existing methods still provide limited support for translating natural-language driving preferences, especially when such preferences are expressed implicitly, into executable and distinguishable driving behaviors. This paper proposes a large language model (LLM)-supported personalized driving framework for highway lane-change scenarios. The framework maps natural-language driving commands to executable planning parameters in the open-source Apollo automated driving stack according to three driving styles: aggressive, normal, and conservative. To establish this mapping, candidate planning parameters are evaluated based on the resulting lane-change behaviors, and style-specific parameter sets are constructed through clustering and style-intensity ranking. For command interpretation, a retrieval dataset is constructed to support retrieval-augmented generation (RAG), enabling LLM-based interpretation of implicit user commands. Experimental results show that the derived parameter sets generate distinguishable personalized lane-change behaviors, while RAG consistently improves preference interpretation, particularly for implicit commands. These results indicate the potential of integrating LLM-based natural-language interaction with Apollo to support personalized lane-change behavior generation. The source code and the relevant datasets are available at: https://github.com/ftgTUGraz/LLM-Personalized-Driving.

Problem

• personalized driving
• natural-language preferences
• lane change
• implicit commands
• automated driving

Innovation

• Large Language Model
• Personalized Driving
• Retrieval-Augmented Generation
• Lane Change Behavior
• Apollo Autonomous Driving