论文标题
使用混合密度网络的安全加固学习：自动高速公路驾驶中的案例研究
Safe Reinforcement Learning with Mixture Density Network: A Case Study in Autonomous Highway Driving
论文作者
论文摘要
本文提出了一种安全的加固学习系统，用于自动驾驶，从多模式的未来轨迹预测中受益。我们提出了一个由两个安全组成组成的安全系统：一种启发式安全性和基于学习的安全性。启发式安全模块基于常见的驾驶规则。另一方面，基于学习的安全模块是数据驱动的安全规则，该规则可以从驱动数据中学习安全模式。具体而言，它利用混合物密度复发性神经网络（MD-RNN）进行多模式的未来轨迹预测来加速学习进度。我们的仿真结果表明，根据平均奖励和碰撞数量，该提议的安全系统先前胜过先前报告的结果。
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.
