基于机器学习的移动机器人路径跟踪MPC控制器参数自整定

doi:10.1007/s12204-022-2545-z

J Shanghai Jiaotong Univ Sci ›› 2024, Vol. 29 ›› Issue (6): 1028-1036.doi: 10.1007/s12204-022-2545-z

基于机器学习的移动机器人路径跟踪MPC控制器参数自整定

刘月笙, 贺宁, 贺利乐, 张译文, 习坤, 张梦芮

（西安建筑科技大学机电工程学院，西安710055）

接受日期:2021-12-23 出版日期:2024-11-28 发布日期:2024-11-28

Self-Tuning of MPC Controller for Mobile Robot Path Tracking Based on Machine Learning

LIU Yuesheng (刘月笙), HE Ning^∗(贺宁), HE Lile (贺利乐),ZHANG Yiwen (张译文), XI Kun (习坤), ZHANG Mengrui (张梦芮)

(School of Mechatronic Engineering, Xi’an University of Architecture and Technology, Xi’an 710055, China)

Accepted:2021-12-23 Online:2024-11-28 Published:2024-11-28

摘要/Abstract

摘要： 模型预测控制（MPC）是一种广泛应用于机器人系统的基于模型的最优控制策略。研究了轮式移动机器人路径跟踪MPC控制器参数整定问题，提出了一种新的参数自整定方法。首先，提出了两个新的路径跟踪性能指标，即稳态时间比值和稳态距离比值，以更准确地反映MPC控制性能。其次，基于机器学习方法构建所提出的指标与MPC参数之间的映射关系，进一步设计了一种能够在线自动整定控制参数的新型控制器结构。最后，利用一台真实的轮式移动机器人进行实验验证。实验结果表明：与现有方法比较，所提出方法在机器人路径跟踪的快速性、准确性和自适应性方面都有显著提高。

关键词: 模型预测控制, 路径跟踪, 移动机器人, 机器学习, 参数整定

Abstract: Model predictive control (MPC) is a model-based optimal control strategy widely used in robot systems.In this work, the MPC controller tuning problem for the path tracking of the wheeled mobile robot is studied and a novel self-tuning approach is developed. First, two novel path tracking performance indices, i.e., steadystate time ratio and steady-state distance ratio are proposed to more accurately reflect the control performance.Second, the mapping relationship between the proposed indices and the MPC parameters is established based on machine learning technique, and then a novel controller structure which can automatically tune the control parameters online is further designed. Finally, experimental verification with an actual wheeled mobile robot is conducted, which shows that the proposed method could outperform the existing method via achieving significant improvement in the rapidity, accuracy and adaptability of the robot path tracking.

中图分类号:

TP181
TP242

刘月笙, 贺宁, 贺利乐, 张译文, 习坤, 张梦芮. 基于机器学习的移动机器人路径跟踪MPC控制器参数自整定[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(6): 1028-1036.

LIU Yuesheng (刘月笙), HE Ning^∗(贺宁), HE Lile (贺利乐), ZHANG Yiwen (张译文), XI Kun (习坤), ZHANG Mengrui (张梦芮). Self-Tuning of MPC Controller for Mobile Robot Path Tracking Based on Machine Learning[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(6): 1028-1036.

参考文献

[1] XI Y G, LI D W, LIN S. Model predictive control—status and challenges [J]. Acta Automatica Sinica,2013, 39(3): 222-236.
[2] ZHANG R D, XUE A K, GAO F R. Model predictive control : Approaches based on the extended state space model and extended non-minimal state space model [M]. Singapore: Springer, 2018.
[3] CHEN Y, JIANG W L, SHI X H, et al. Tuning parameters for model predictive controller based on CSA-SQP[J]. Journal of Ningbo University (Natural Science & Engineering Edition), 2017, 30(4): 51-57 (in Chinese).
[4] IRA A S, MANZIE C, SHAMES I, et al. Tuning of multivariable model predictive controllers through expert bandit feedback [J]. International Journal of Control,2021, 94(10): 2650-2658.
[5] MOUMOUH H, LANGLOIS N, HADDAD M. A novel tuning approach for MPC parameters based on artificial neural network [C]//2019 IEEE 15th International Conference on Control and Automation. Edinburgh:IEEE, 2019: 1638-1643.
[6] JARDINE P T, GIVIGI S, YOUSEFI S. Parameter tuning for prediction-based quadcopter trajectory planning using learning automata [J]. IFACPapersOnLine, 2017, 50(1): 2341-2346.
[7] LIU C, WANG D Y, ZHANG Y X, et al. Model predictive control for path following and roll stabilization of marine vessels based on neurodynamic optimization[J]. Ocean Engineering, 2020, 217: 107524.
[8] HE N, QI L P, LI R X, et al. Design of a model predictive trajectory tracking controller for mobile robot based on the event-triggering mechanism [J]. Mathematical Problems in Engineering, 2021, 2021:5573467.
[9] LUO L H. Steering control for lane keeping system based on MPC [J]. Journal of Shanghai Jiao Tong University, 2014, 48(7): 1015-1020 (in Chinese).
[10] CAO Y, HE D B, YU F, et al. Generalized predictive control based on vehicle path following strategy by using active steering system [J]. Journal of Shanghai Jiao Tong University, 2016, 50(3): 401-406 (in Chinese).
[11] ZHAO Y Q, WANG J, ZANG L G, et al. Path tracking for different wheelbase vehicles [J]. Journal of Shanghai Jiao Tong University, 2015, 49(4): 481-486 (inbChinese).

[1]	吴振龙, 刘艳红, 薛亚丽, 李东海, CHEN Yangquan. 基于预期动态方程的含高比例可再生能源孤岛运行微电网负荷频率控制[J]. 上海交通大学学报, 2024, 58(6): 954-964.
[2]	邱革非, 冯泽华, 沈赋, 何超, 何虹辉, 刘铠铭. 考虑车网互动的园区电网动态双层能量管理策略[J]. 上海交通大学学报, 2024, 58(6): 916-925.
[3]	张啸天1，何德峰1，廖飞2. 复杂环境及约束下舰载机自动着舰迭代模型预测控制[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(4): 712-724.
[4]	穆建彬，杨海丽，何德峰. 基于控制屏障函数的自主移动机器人安全编队分布式模型预测控制[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(4): 678-688.
[5]	孙乾洋, 周利, 丁仕风, 刘仁伟, 丁一. 基于人工神经网络的极地船舶冰阻力预报方法[J]. 上海交通大学学报, 2024, 58(2): 156-165.
[6]	鲍朱杰, 李祯, 王斐亮, 庞博, 杨健. 基于机器学习的直角扣件滑移和扭转性能预测方法[J]. 上海交通大学学报, 2024, 58(2): 242-252.
[7]	何文, 高斌, 王强强, 冯少孔, 叶冠林. 基于高斯混合聚类的综合物探方法及其在岩溶勘探中的应用[J]. 上海交通大学学报, 2024, 58(11): 1724-1734.
[8]	徐长节, 李欣雨. 基于人工神经网络的深基坑支护结构侧移预测[J]. 上海交通大学学报, 2024, 58(11): 1735-1744.
[9]	何宇, 欧阳子路, 邹璐, 陈伟民, 邹早建. 基于矢量场制导法和模型预测控制的船舶路径跟踪与避碰[J]. 上海交通大学学报, 2024, 58(11): 1644-1653.
[10]	刘传斌, 矫文书, 吴秋伟, 陈健, 周前. 基于模型预测控制的风储联合电场参与电网二次调频策略[J]. 上海交通大学学报, 2024, 58(1): 91-101.
[11]	李明爱1,2,3，许冬芹1. 综述：运动想像脑机接口中的迁移学习[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(1): 37-59.
[12]	姜恩宇, 陈宇, 施峥靖, 吴哲城, 林顺富, 李东东. 考虑碳配额引导需求响应的微电网能量管理策略[J]. 上海交通大学学报, 2023, 57(9): 1126-1136.
[13]	奚鑫泽, 邢超, 覃日升, 何廷一, 和鹏, 孟贤, 程春辉. 含双馈风力发电系统的配电网短路电流特性[J]. 上海交通大学学报, 2023, 57(7): 921-927.
[14]	苏泓嘉, 罗宇成, 刘飞. 装备体系效能评估及支撑技术综述[J]. 空天防御, 2023, 6(3): 29-38.
[15]	张晨宇, 孟帅. 基于模型预测控制的深海钻井立管再入井仿真分析[J]. 上海交通大学学报, 2023, 57(11): 1389-1399.

基于机器学习的移动机器人路径跟踪MPC控制器参数自整定

Self-Tuning of MPC Controller for Mobile Robot Path Tracking Based on Machine Learning

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价