Safe Reinforcement Learning of Autonomous Highway Driving: A Unified Framework for Safety and Efficiency

2026-06-12 · Chufei Yan, Zhihao Cui, Yiyan Lv, Taojie Chen, Ning Bian, Yulei Wang arxiv

Deep reinforcement learning (DRL) offers a compelling route to decision-making for advanced autonomous vehicles (AVs), yet its trial-and-error nature makes it difficult to guarantee safety during training and to achieve both safety and efficiency at deployment. We propose a unified safe reinforcement learning (SRL) framework that integrates safe distance (SD), reward machines (RM), and mixture-of-experts (MoE), termed MoE-RM-SRL. For deployment, SD and RM jointly shape a rule-aware reward that encodes highway traffic regulations and stage-wise objectives, enabling safe and reliable behavior without sacrificing efficiency. For training, we introduce a sparsely gated MoE layer comprising up to 11 deep Q-networks (DQNs); an SD-based gating rule activates a minimal set of experts for lane-keeping and lane-changing, mitigating the instability, discontinuities, and impulsive transients commonly induced by switching between heterogeneous controllers (e.g., MPC/rule-based modules and learned policies). We implement the proposed architecture in CARLA and integrate it with a 6-DoF driver-in-the-loop virtual-reality (DiL-VR) platform. Experiments in stochastic two-lane traffic show that MoE-RM-SRL substantially improves safety and efficiency over state-of-the-art baselines, and the framework naturally extends to multi-lane driving as well as on-ramp merging and exiting scenarios.

📄 PDF Abstract BibTeX arXiv:2606.14609

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning Autonomous Vehicles

Decision-making Strategy on Highway for Autonomous Vehicles using Deep Reinforcement Learning

2020-07-16 · Jiangdong Liao, Teng Liu, Xiaolin Tang, Xingyu Mu 외

Autonomous driving is a promising technology to reduce traffic accidents and improve driving efficiency. In this work, a deep reinforcement learning (DRL)-enabled decision-making policy is constructed for autonomous vehi…

Autonomous Driving Autonomous Vehicles Decision Making Deep Reinforcement Learning+2

HighwayLLM: Decision-Making and Navigation in Highway Driving with RL-Informed Language Model

2024-05-22 · Mustafa Yıldırım, Barkin Dagda, Saber Fallah

Autonomous driving is a complex task which requires advanced decision making and control algorithms. Understanding the rationale behind the autonomous vehicles' decision is crucial to ensure their safe and effective oper…

Autonomous Driving Autonomous Vehicles Decision Making Language Modeling+2

Dueling Deep Q Network for Highway Decision Making in Autonomous Vehicles: A Case Study

2020-07-16 · Teng Liu, Xingyu Mu, Xiaolin Tang, Bing Huang 외

This work optimizes the highway decision making strategy of autonomous vehicles by using deep reinforcement learning (DRL). First, the highway driving environment is built, wherein the ego vehicle, surrounding vehicles, …

Autonomous Vehicles Decision Making Deep Reinforcement Learning reinforcement-learning+1

Safe Reinforcement Learning with Probabilistic Control Barrier Functions for Ramp Merging

2022-12-01 · Soumith Udatha, Yiwei Lyu, John Dolan

Prior work has looked at applying reinforcement learning and imitation learning approaches to autonomous driving scenarios, but either the safety or the efficiency of the algorithm is compromised. With the use of control…

Autonomous Driving Imitation Learning reinforcement-learning Reinforcement Learning+2

Autonomous Highway Driving using Deep Reinforcement Learning

2019-03-29 · Subramanya Nageshrao, Eric Tseng, Dimitar Filev

The operational space of an autonomous vehicle (AV) can be diverse and vary significantly. This may lead to a scenario that was not postulated in the design phase. Due to this, formulating a rule based decision maker for…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)