引用本文:张浪文,王中旭,魏海翔,谢巍.移动机器人轨迹跟踪的参数估计与原对偶神经网络预测控制[J].控制理论与应用,2026,43(2):278~286.[点击复制]
ZHANG Lang-wen,WANG Zhong-xu,WEI Hai-xiang,XIE Wei.Trajectory tracking of mobile robots based on parameter estimation and primal-dual neural network predictive control[J].Control Theory & Applications,2026,43(2):278~286.[点击复制]
移动机器人轨迹跟踪的参数估计与原对偶神经网络预测控制
Trajectory tracking of mobile robots based on parameter estimation and primal-dual neural network predictive control
摘要点击 164  全文点击 24  投稿时间:2023-12-06  修订日期:2025-03-11
查看全文  查看/发表评论  下载PDF阅读器   HTML
DOI编号  10.7641/CTA.2024.30790
  2026,43(2):278-286
中文关键词  轮式移动机器人  轨迹跟踪  模型预测控制  原对偶神经网络  卷积神经网络
英文关键词  mobile robots  trajectory tracking  model predictive control  primal-dual neural network  convolutional neural network
基金项目  国家自然科学基金项目(62473160), 广东省基础与应用基础研究基金项目(2023A1515030119, 2023A1515240070), 清远市科技计划项目(2023 DZX006)资助.
作者单位E-mail
张浪文* 华南理工大学 自动化科学与工程学院 aulwzhang@scut.edu.cn 
王中旭 华南理工大学自动化科学与工程学院  
魏海翔 华南理工大学自动化科学与工程学院  
谢巍 华南理工大学自动化科学与工程学院  
中文摘要
      本文针对轮式移动机器人的不确定参数估计与轨迹跟踪问题, 研究了基于卷积神经网络(CNN)的移动机器 人不确定模型参数估计方法, 提出了移动机器人的原对偶神经网络(PDNN)模型预测控制(MPC)轨迹跟踪控制算法. 对于轮式移动机器人而言, 轮胎侧偏刚度受到负载扰动、未建模动态和路况变化等不确定因素影响, 在实际行驶过 程中难以实时测量. 论文研究侧偏刚度的CNN回归模型, 以估计机器人运行过程中的不确定性. 考虑前轮偏角与加 速度等状态的约束条件, 研究基于CNN参数估计的移动机器人预测控制设计方法, 提出基于PDNN的移动机器人预 测控制问题求解算法, 并证明了所提出基于CNN参数估计的PDNN-MPC算法稳定性. 最后, 为了验证控制器的有效 性, 对所提出的PDNN-MPC算法进行验证.
英文摘要
      This work focuses on the problem of uncertain parameter estimation and trajectory tracking for wheeled mobile robots. A method for estimating uncertain model parameters of mobile robots based on the convolutional neural network (CNN) is studied, and a primal-dual neural network (PDNN) model predictive control (MPC) tracking control algorithm for mobile robots is proposed. For wheeled mobile robots, tire lateral stiffness is affected by load disturbance, unmodelled dynamics and load changes, which is difficult to measure in real time during actual driving. CNN estimator of lateral stiffness is designed to eliminate uncertainty during robot operation considering the constraint conditions of front wheel deviation and acceleration. This work studies the design of predictive control for mobile robots based on CNN parameter estimation and proposes a PDNN based algorithm with CNN parameter estimation for solving the predictive control problem of mobile robots. The stability of the proposed PDNN-MPC algorithm is proved. Finally, to verify the effectiveness of the controller, the proposed PDNN-MPC algorithm is validated.