Trajectory Control of Crawler Robot Based on LSTM and SMC

doi:10.16182/j.issn1004731x.joss.21-1248

Abstract

Abstract:

Trajectory tracking is an important part of mobile robot control technology and possesses prospect. Highly nonlinear dynamic characteristics are the main obstacles of controller design. A SMC method based on LSTM and quasi-sliding mode is proposed. The kinematics model and dynamics model of the tracked vehicle are given, and the sliding mode control system is established based on the dynamics model. LSTM network based on deep learning method is designed to control and compensate the unknown interference items, reduce the influence of external interference, and reduce the tremor phenomenon by combining the advantages of LSTM network and quasi-sliding mode. The stability analysis of the control system is given. MATLAB/Simulink simulation experiments are carried out on different trajectories. Compared with the existing methods, the superiority is proven.

Key words: LSTM, SMC, kinematic model, dynamic model, trajectory tracking

CLC Number:

TP183

Dongyang Liu, Wenwen Zha, Liang Tao, Cheng Zhu, Lichuan Gu, Jun Jiao. Trajectory Control of Crawler Robot Based on LSTM and SMC[J]. Journal of System Simulation, 2023, 35(4): 747-759.

Figures/Tables 19

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Table 1

Table 2

Fig. 8

Fig. 9

Table 3

Fig. 10

Fig. 11

Table 4

Table 5

Fig. 12

Fig. 13

Table 6

References 20

1	卞永明, 杨濛, 刘宇超, 等. 履带式移动机器人轨迹跟踪控制技术研究[J]. 中国工程机械学报, 2018, 16(3): 189-193, 206.
	Bian Yongming, Yang Meng, Liu Yuchao, et al. Research on Tracking Control Technology of Crawler Mobile Robot[J]. Chinese Journal of Construction Machinery, 2018, 16(3): 189-193, 206.
2	张华强, 王国栋, 吕云飞, 等. 基于改进纯追踪模型的农机路径跟踪算法研究[J]. 农业机械学报, 2020, 51(9): 18-25.
	Zhang Huaqiang, Wang Guodong, Yunfei Lü, et al. Research on Agricultural Machinery Path Tracking Algorithm Based on Improved Pure Tracking Model[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(9): 18-25.
3	张朝宇, 董万静, 熊子庆, 等. 履带式油菜播种机模糊自适应纯追踪控制器设计与试验[J]. 农业机械学报, 2021, 52(12): 105-114.
	Zhang Chaoyu, Dong Wanjing, Xiong Ziqing, et al. Design and Experiment of Fuzzy Adaptive Pure Pursuit Control of Crawler-type Rape Seeder[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(12): 105-114.
4	杨福威, 孟红, 朱强. 基于模型预测控制的履带式无人平台轨迹跟踪控制算法研究[J]. 舰船电子工程, 2018, 38(3): 44-50.
	Yang Fuwei, Meng Hong, Zhu Qiang. Research on Tracking Control Algorithm of Tracked Unmanned Platform Based on Model Predictive Control[J]. Ship Electronic Engineering, 2018, 38(3): 44-50.
5	张志达, 郑玲, 张紫薇, 等. 基于自适应模型预测的智能汽车横向轨迹跟踪控制[J]. 中国公路学报, 2022, 35(7): 305-316.
	Zhang Zhida, Zheng Ling, Zhang Ziwei, et al. Lateral Trajectory Tracking Control of Intelligent Vehicles Based on Adaptive Model Prediction[J]. China Journal of Highway and Transport, 2022, 35(7): 305-316.
6	冯浩, 殷晨波, 曹东辉, 等. 挖掘机器人伺服系统神经网络滑模控制[J]. 液压与气动, 2021, 45(10): 104-110.
	Feng Hao, Yin Chenbo, Cao Donghui, et al. Neural Network Sliding Mode Control of Excavating Robot Servo System[J]. Chinese Hydraulics & Pneumatics, 2021, 45(10): 104-110.
7	范其明, 吕书豪. 移动机器人的自适应神经网络滑模控制[J]. 控制工程, 2017, 24(7): 1409-1414.
	Fan Qiming, Shuhao Lü. Adaptive Neural Network Sliding Mode Control of Mobile Robot[J]. Control Engineering of China, 2017, 24(7): 1409-1414.
8	许洋洋, 王莹, 薛东彬. 采用改进模糊神经网络PID控制的移动机器人运动误差研究[J]. 中国工程机械学报, 2019, 17(6): 510-514.
	Xu Yangyang, Wang Ying, Xue Dongbin. Research on Motion Error of Mobile Robot Using Improved Fuzzy Neural Network PID Control[J]. Chinese Journal of Engineering Machinery, 2019, 17(6): 510-514.
9	匡文龙, 沈文龙, 姬长英, 等. 农用履带机器人轨迹跟踪控制系统设计与试验[J]. 东北农业大学学报, 2020, 51(4): 78-87.
	Kuang Wenlong, Shen Wenlong, Ji Changying, et al. Design and Experiment of Track Tracking Control System for Agricultural Crawler Robot[J]. Journal of Northeast Agricultural University, 2020, 51(4): 78-87.
10	焦俊, 孔文, 王强, 等. 基于输入模糊化的农用履带机器人自适应滑模控制[J]. 农业机械学报, 2015, 46(6): 14-19, 13.
	Jiao Jun, Kong Wen, Wang Qiang, et al. Self-adaptive Sliding Mode Control Based on Input Fuzzy for Agricultural Tracked Robot[J]. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(6): 14-19, 13.
11	焦俊, 陈靖, 乔焰, 等. 直流电机驱动农用履带机器人轨迹跟踪自适应滑模控制[J]. 农业工程学报, 2018, 34(4): 64-70.
	Jiao Jun, Chen Jing, Qiao Yan, et al. Adaptive Sliding Mode Control of Trajectory Tracking Based on DC Motor Drive for Agricultural Tracked Robot[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(4): 64-70.
12	Zheng Kunming, Hu Youmin, Wu Bo. Intelligent Fuzzy Sliding Mode Control for Complex Robot System with Disturbances[J]. European Journal of Control(S0947-3580), 2020, 51: 95-109.
13	Yao Xuan, Chen Zhaobo. Sliding Mode Control with Deep Learning Method for Rotor Trajectory Control of Active Magnetic Bearing System[J]. Transactions of the Institute of Measurement and Control(S0142-3312), 2019, 41(5): 1383-1394.
14	Zhou Minghao, Feng Yong, Xue Chen, et al. Deep Convolutional Neural Network Based Fractional-Order Terminal Sliding-Mode Control for Robotic Manipulators[J]. Neurocomputing(S0925-2312), 2020, 416(27): 143-151.
15	Hassrizal H B, Rossiter J, Othman S M, et al. Particle Swarm Algorithm Sliding Mode Control on Spacecraft's Attitude with Switching Function Method Thorough Error Feedback[C]//IOP Conference Series: Materials Science and Engineering. IOP Publishing, 2019, 705(1): 012039.
16	Nguyen C T, Duong T L, Duong M Q, et al. Chattering-Free Single-Phase Robustness Sliding Mode Controller for Mismatched Uncertain Interconnected Systems with Unknown Time-Varying Delays[J]. Energies(S1996-1073), 2020, 13(1): 282.
17	于广宇, 董学平, 王祥民, 等. 弹性网下基于LSTM的分解炉出口温度预测[J]. 系统仿真学报, 2021, 33(5): 1078-1085. DOI:10.16182/j.issn1004731x.joss.20-0012 .
	Yu Guangyu, Dong Xueping, Wang Xiangmin, et al. Decomposition Furnace Outlet Temperature Prediction Based on ElasticNet and LSTM[J]. Journal of System Simulation, 2021, 33(5): 1078-1085. DOI:10.16182/j.issn1004731x.joss.20-0012 .
18	魏腾飞, 潘庭龙. 基于改进PSO优化LSTM网络的短期电力负荷预测[J]. 系统仿真学报, 2021, 33(8): 1866-1874. DOI:10.16182/j.issn1004731x.joss.20-0297 .
	Wei Tengfei, Pan Tinglong. Short-term Power Load Forecasting Based on LSTM Neural Network Optimized by Improved PSO[J]. Journal of System Simulation, 2021, 33(8): 1866-1874. DOI:10.16182/j.issn1004731x.joss.20-0297 .
19	孟小凡, 宋华. 基于神经网络的卫星姿控系统故障预测 [J].系统仿真学报, 2019, 31(11): 2499-2508. DOI:10.16182/j.issn1004731x.joss.19-FZ0351E .
	Meng Xiaofan, Song Hua. Satellite Attitude Control System Failure Prediction Based on Neural Network[J]. Journal of System Simulation, 2019, 31(11): 2499-2508. DOI:10.16182/j.issn1004731x.joss.19-FZ0351E .
20	Iossaqui J G, Camino J F, Zampieri D E. A Nonlinear Control Design for Tracked Robots with Longitudinal Slip-ScienceDirect[J]. IFAC Proceedings Volumes(S2405-8963), 2011, 44(1): 5932-5937.

主要参数	量值
质量/kg	200
转动惯量/( kg·m²)	0.5
参考速度/(m/s)	0.5
参考角速度/(rad/s)	0
起始速度/(m/s)	0
起始角速度/(rad/s)	0

控制方法	最大跟踪偏差	平均绝对偏差
SMC	0.104	0.025
SMC-LSTM	0.069	0.018

主要参数	量值
质量/kg	200
转动惯量/(kg·m²)	0.5
参考速度/(m/s)	1
参考角速度/(rad/s)	0.25
起始速度/(m/s)	0
起始角速度/(rad/s)	0

控制方法	最大跟踪偏差	平均绝对偏差
SMC	0.112	0.034
SMC-LSTM	0.074	0.026

主要参数	量值
质量/kg	200
转动惯量/( kg·m²)	0.5
参考速度/(m/s)	0.5
参考角速度(折点处)/(rad/s)	0.33π
起始速度/(m/s)	0
起始角速度/(rad/s)	0