期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 32, 期 12, 页码 5526-5538出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2020.3042981
关键词
Decision making; Erbium; Adaptation models; Acceleration; Automotive engineering; Space vehicles; Reinforcement learning; Decision-making; direct search; parameterization; reinforcement learning (RL)
类别
资金
- National Nature Science Foundation of China [61790564, U19A2069]
- Research Team of Optimization and Control of Automotive Powertrain, Jilin Provincial Science and Technology Department [20200301011RQ]
- China Automobile Industry Innovation and Development Joint Fund [U1664257]
The proposed method utilizes optimization embedded reinforcement learning to achieve adaptive decision-making under roundabouts. With a modified actor of the Actor-Critic framework, the algorithm efficiently determines macro-scale and medium-scale behaviors. The method demonstrates high algorithm efficiency and better system performance in simulations of different roundabout scenarios.
The roundabout is a typical changeable, interactive scenario in which automated vehicles should make adaptive and safe decisions. In this article, an optimization embedded reinforcement learning (OERL) is proposed to achieve adaptive decision-making under the roundabout. The promotion is the modified actor of the Actor-Critic framework, which embeds the model-based optimization method in reinforcement learning to explore continuous behaviors in action space directly. Therefore, the proposed method can determine the macroscale behavior (change lane or not) and medium-scale behaviors of desired acceleration and action time simultaneously with high sample efficiency. When scenarios change, medium-scale behaviors can be adjusted timely by the embedded direct search method, promoting the adaptability of decision-making. More notably, the modified actor matches human drivers' behaviors, macroscale behavior captures the human mind's jump, and medium-scale behaviors are preferentially adjusted through driving skills. To enable the agent adapts to different types of the roundabout, task representation is designed to restructure the policy network. In experiments, the algorithm efficiency and the learned driving strategy are compared with decision-making containing macroscale behavior and constant medium-scale behaviors of the desired acceleration and action time. To investigate the adaptability, the performance under an untrained type of roundabout and two more dangerous situations are simulated to verify that the proposed method changes the decisions with changeable scenarios accordingly. The results show that the proposed method has high algorithm efficiency and better system performance.
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