欢迎访问《兵工学报》官方网站,今天是

兵工学报 ›› 2025, Vol. 46 ›› Issue (7): 240575-.doi: 10.12382/bgxb.2024.0575

• • 上一篇    下一篇

融合行为基元优化与博弈的轨迹跟踪控制方法

王博洋1,2,*(), 李欣萍1, 宋俊杰3, 关海杰1, 刘海鸥1, 陈慧岩1   

  1. 1 北京理工大学 机械与车辆学院, 北京 100081
    2 北京理工大学 郑州智能科技研究院, 河南 郑州 450046
    3 中国北方车辆研究所, 北京 100072
  • 收稿日期:2024-07-15 上线日期:2025-08-12
  • 通讯作者:
  • 基金资助:
    国家自然科学基金项目(52302489)

A Trajectory Tracking Control Method Incorporating Behavior Primitive Optimization and Game Coordination

WANG Boyang1,2,*(), LI Xinping1, SONG Junjie3, GUAN Haijie1, LIU Hai’ou1, CHEN Huiyan1   

  1. 1 School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China
    2 Zhengzhou Research Institute, Beijing Institute of Technology, Zhengzhou 450046, Henan, China
    3 China North Vehicle Research Institute, Beijing 100072, China
  • Received:2024-07-15 Online:2025-08-12

摘要:

为解决以拟人化行为基元序列为期望轨迹的无人车轨迹跟踪控制问题,提出了一种行为基元离线优化与在线博弈协调相结合的轨迹跟踪控制方法。以从真实驾驶数据中直接提取出的行为基元库为根基,通过基于模型的非线性优化方法,生成满足车辆运动学特性约束的行为基元库;通过粒子群算法离线寻优得到行为基元库中各类别基元的最优控制参量,并采用多层感知机建立控制器最优参量与行为基元类别之间的映射关系;在对基元内控制参量进行优化的基础上,以在线博弈协调控制方法为核心,实现行为基元间的最优控制参量生成。试验结果表明,所提出的融合行为基元优化与博弈的控制方法,能够显著提升对行为基元序列的跟踪控制精度,并有效解决各独立行为基元间的稳定平滑过渡问题。

关键词: 行为基元, 轨迹跟踪控制, 粒子群优化, 微分博弈理论

Abstract:

The trajectory tracking control of unmanned vehicle with a sequence of human-like behavior primitives as the desired trajectory is studied.A trajectory tracking control method combining the offline optimization of behavior primitives and the online coordination of game is proposed.Based on the behavior primitive library extracted directly from real driving data,a model-based nonlinear optimization method is applied to generate a behavior primitive library that satisfies the constraints of vehicle kinematic properties.The optimal control parameters for each category of primitives in the behavior primitive library are obtained by offline optimization using the particle swarm algorithm,and a multilayer perceptual machine is applied to establish the mapping relationship between the optimal parameters of controller and the categories of behavioral primitives.Based on the optimization of the control parameters within the primitives,the online game coordinated control method is used as the core to generate the optimal control parameter between the behavior primitives.The experimental results show that the proposed trajectory tracking control method can significantly improve the tracking accuracy of the behavior primitive sequences and effectively solve the problem of stable and smooth transition between independent behavior primitives.

Key words: behavior primitive, trajectory tracking control, particle swarm optimization, differential game theory