期刊
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
卷 23, 期 5, 页码 4642-4650出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITS.2020.3047129
关键词
Reinforcement learning; Vehicle-to-everything; Space vehicles; Sensors; Roads; Mathematical model; Delays; Lane changing; reinforcement learning; deep learning
资金
- National Key Research and Development Program of China [2018AAA0101402]
- National Natural Science Foundation of China [61790565]
- Shenzhen Municipal Science and Technology Innovation Committee [JCYJ20170412172030008]
This paper studies a harmonious lane-changing strategy for autonomous vehicles without V2X communication support through multi-agent reinforcement learning, which is more effective in improving traffic efficiency compared to competitive strategy.
In this paper, we study how to learn a harmonious deep reinforcement learning (DRL) based lane-changing strategy for autonomous vehicles without Vehicle-to-Everything (V2X) communication support. The basic framework of this paper can be viewed as a multi-agent reinforcement learning in which different agents will exchange their strategies after each round of learning to reach a zero-sum game state. Unlike cooperation driving, harmonious driving only relies on individual vehicles' limited sensing results to balance overall and individual efficiency. Specifically, we propose a well-designed reward that combines individual efficiency with overall efficiency for harmony, instead of only emphasizing individual interests like competitive strategy. Testing results show that competitive strategy often leads to selfish lane change behaviors, anarchy of crowd, and thus the degeneration of traffic efficiency. In contrast, the proposed harmonious strategy can promote traffic efficiency in both free flow and traffic jam than the competitive strategy. This interesting finding indicates that we should take care of the reward setting for reinforcement learning-based AI robots (e.g., automated vehicles) design, when the utilities of these robots are not strictly in alignment.
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