期刊
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
卷 5, 期 2, 页码 294-305出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIV.2019.2955905
关键词
Autonomous driving; tactical decision making; reinforcement learning; Monte Carlo tree search
类别
资金
- Wallenberg Artificial Intelligence, Autonomous Systems, and Software Program (WASP) - Knut and Alice Wallenberg Foundation
- Vinnova Strategic Vehicle Research and Innovation programme (FFI)
Tactical decision making for autonomous driving is challenging due to the diversity of environments, the uncertainty in the sensor information, and the complex interaction with other road users. This article introduces a general framework for tactical decision making, which combines the concepts of planning and learning, in the form of Monte Carlo tree search and deep reinforcement learning. The method is based on the AlphaGo Zero algorithm, which is extended to a domain with a continuous state space where self-play cannot be used. The framework is applied to two different highway driving cases in a simulated environment and it is shown to perform better than a commonly used baseline method. The strength of combining planning and learning is also illustrated by a comparison to using the Monte Carlo tree search or the neural network policy separately.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据