上海交通大学学报 ›› 2021, Vol. 55 ›› Issue (8): 1027-1034.doi: 10.16183/j.cnki.jsjtu.2020.319

所属专题: 《上海交通大学学报》2021年12期专题汇总专辑 《上海交通大学学报》2021年“自动化技术、计算机技术”专题

• • 上一篇    下一篇

基于主从博弈的智能车汇流场景决策方法

胡益恺a,c, 庄瀚洋b,c(), 王春香a,c, 杨明a,b,c   

  1. 上海交通大学 a.自动化系, 上海 200240
    b.密西根学院, 上海 200240
    c.系统控制与信息处理教育部重点实验室, 上海 200240
  • 收稿日期:2020-10-09 出版日期:2021-08-28 发布日期:2021-08-31
  • 通讯作者: 庄瀚洋 E-mail:zhuanghany11@sjtu.edu.cn
  • 作者简介:胡益恺(1996-),男,安徽省合肥市人,硕士生,主要研究方向为机器人
  • 基金资助:
    国家自然科学基金(61873165);国家自然科学基金(U1764264);上海汽车工业科技发展基金(1807)

Stackelberg-Game-Based Intelligent Vehicle Decision Method for Merging Scenarios

HU Yikaia,c, ZHUANG Hanyangb,c(), WANG Chunxianga,c, YANG Minga,b,c   

  1. a. Department of Automation, Shanghai 200240, China
    b. University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai 200240, China
    c. Key Laboratory of System Control and Information Processing of the Ministry of Education, Shanghai Jiao Tong University, Shanghai 200240, China
  • Received:2020-10-09 Online:2021-08-28 Published:2021-08-31
  • Contact: ZHUANG Hanyang E-mail:zhuanghany11@sjtu.edu.cn

摘要:

现有智能车决策方法未考虑路权信息、车辆礼貌驾驶以及车辆有限感知范围等因素,容易导致汇流时的安全隐患.针对该类问题,提出一种基于主从博弈的智能车辆决策方法.该方法通过构建结合路权的博弈模型,对汇流场景进行参数化建模,再引入合作因子等目标项设计相应的收益函数,最终设计汇流场景中的车辆决策求解框架,以达到该场景下决策收益的最大值.实验结果表明,所提方法能够提高在数据集上的车辆决策行为预测准确率,并能提高车辆在高车流密度环境中的决策稳健性.

关键词: 智能车决策方法, 主从博弈, 汇流, 路权, 合作收益

Abstract:

Existing decision-making methods for intelligent vehicles do not consider factors such as the right of way information, polite driving of the vehicle, and limited perception range of the vehicle, which may easily lead to safety hazards in merging scenarios. Aimed at these problems, a Stackelberg-game-based decision-making method is proposed. This method constructs a game model combining the right of way and conducts parametric modeling of the merging scenarios. Then, the cooperation factor is introduced to design the corresponding profit function. Finally, the vehicle decision-making solution framework is designed to achieve the maximum value of decision-making benefits in this scenario. The experimental results illustrate that the proposed method can effectively improve the accuracy of vehicle decision-making behavior prediction on the datasets and the decision-making robustness in a high traffic density environment.

Key words: intelligent vehicle decision-making methods, Stackelberg-game, merging scenario, right of way, cooperation reward

中图分类号: