Safe Reinforcement Learning with Mixture Density Network: A Case Study in Autonomous Highway Driving

2020/07/02 by Ali Baheri, Baheri, Ali
Computer Science · Engineering · #Autonomous Vehicle Technology and Safety #FOS: Electrical engineering #Reinforcement Learning in Robotics #Systems and Control (eess.SY) #Traffic control and management #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2007.01698

openalex publication_date 2020/07/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents a safe reinforcement learning system for automated driving that benefits from multimodal future trajectory predictions. We propose a safety system that consists of two safety components: a heuristic safety and a learning-based safety. The heuristic safety module is based on common driving rules. On the other hand, the learning-based safety module is a data-driven safety rule that learns safety patterns from driving data. Specifically, it utilizes mixture density recurrent neural networks (MD-RNN) for multimodal future trajectory predictions to accelerate the learning progress. Our simulation results demonstrate that the proposed safety system outperforms previously reported results in terms of average reward and number of collisions.

Citations

• Recurrent World Models Facilitate Policy Evolution

Related

• Deep Reinforcement Learning with Enhanced Safety for Autonomous Highway\n Driving
• Autonomous Driving using Safe Reinforcement Learning by Incorporating a Regret-based Human Lane-Changing Decision Model
• Autonomous Highway Driving using Deep Reinforcement Learning
• Autonomous Highway Merging in Mixed Traffic Using Reinforcement Learning and Motion Predictive Safety Controller
• Adversarial Mixture Density Networks: Learning to Drive Safely from\n Collision Data