Saved in:
Bibliographic Details
Main Authors: Shu, Yiming, Xu, Jiahui, Tang, Jiwei, Gao, Ruiyang, Sun, Chen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.05686
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911304369831936
author Shu, Yiming
Xu, Jiahui
Tang, Jiwei
Gao, Ruiyang
Sun, Chen
author_facet Shu, Yiming
Xu, Jiahui
Tang, Jiwei
Gao, Ruiyang
Sun, Chen
contents Autonomous highway driving demands a critical balance between proactive, efficiency-seeking behavior and robust safety guarantees. This paper proposes Language Action-guided Reinforcement Learning (LA-RL) with Safety Guarantees, a novel framework that integrates the semantic reasoning of large language models (LLMs) into the actor-critic architecture with an improved safety layer. Within this framework, task-specific reward shaping harmonizes the dual objectives of maximizing driving efficiency and ensuring safety, guiding decision-making based on both environmental insights and clearly defined goals. To enhance safety, LA-RL incorporates a safety-critical planner that combines model predictive control (MPC) with discrete control barrier functions (DCBFs). This layer formally constrains the LLM-informed policy to a safe action set, employs a slack mechanism that enhances solution feasibility, prevents overly conservative behavior and allows for greater policy exploration without compromising safety. Extensive experiments demonstrate that it significantly outperforms several current state-of-the-art methods, offering a more adaptive, reliable, and robust solution for autonomous highway driving. Compared to existing SOTA, it achieves approximately 20$\%$ higher success rate than the knowledge graph (KG) based baseline and about 30$\%$ higher than the retrieval augmented generation (RAG) based baseline. In low-density environments, LA-RL achieves a 100$\%$ success rate. These results confirm its enhanced exploration of the state-action space and its ability to autonomously adopt more efficient, proactive strategies in complex, mixed-traffic highway environments.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05686
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LA-RL: Language Action-guided Reinforcement Learning with Safety Guarantees for Autonomous Highway Driving
Shu, Yiming
Xu, Jiahui
Tang, Jiwei
Gao, Ruiyang
Sun, Chen
Systems and Control
Autonomous highway driving demands a critical balance between proactive, efficiency-seeking behavior and robust safety guarantees. This paper proposes Language Action-guided Reinforcement Learning (LA-RL) with Safety Guarantees, a novel framework that integrates the semantic reasoning of large language models (LLMs) into the actor-critic architecture with an improved safety layer. Within this framework, task-specific reward shaping harmonizes the dual objectives of maximizing driving efficiency and ensuring safety, guiding decision-making based on both environmental insights and clearly defined goals. To enhance safety, LA-RL incorporates a safety-critical planner that combines model predictive control (MPC) with discrete control barrier functions (DCBFs). This layer formally constrains the LLM-informed policy to a safe action set, employs a slack mechanism that enhances solution feasibility, prevents overly conservative behavior and allows for greater policy exploration without compromising safety. Extensive experiments demonstrate that it significantly outperforms several current state-of-the-art methods, offering a more adaptive, reliable, and robust solution for autonomous highway driving. Compared to existing SOTA, it achieves approximately 20$\%$ higher success rate than the knowledge graph (KG) based baseline and about 30$\%$ higher than the retrieval augmented generation (RAG) based baseline. In low-density environments, LA-RL achieves a 100$\%$ success rate. These results confirm its enhanced exploration of the state-action space and its ability to autonomously adopt more efficient, proactive strategies in complex, mixed-traffic highway environments.
title LA-RL: Language Action-guided Reinforcement Learning with Safety Guarantees for Autonomous Highway Driving
topic Systems and Control
url https://arxiv.org/abs/2512.05686