具有外部扰动双臂空间机器人的神经网络在线自学习补偿控制  

On-line Self-learning Compensation Control for Dual-arm Space Robot with External Disturbances via Neural Network

作　　者：陈志勇[1] 陈力[1] 

机构地区：[1]福州大学,福州350108

出　　处：《中国机械工程》2010年第17期2114-2118,共5页China Mechanical Engineering

基　　金：国家自然科学基金资助项目(10672040)

摘　　要：探讨了在未知外部扰动影响下,漂浮基双臂空间机器人载体姿态与两机械臂末端爪手协调运动的补偿控制问题。利用系统动量守恒关系对漂浮基双臂空间机器人的运动学、动力学进行分析,导出了系统的工作空间动力学方程。以此为基础,针对系统存在未知外部扰动的复杂情况,设计了漂浮基双臂空间机器人协调运动的神经网络在线自学习补偿控制方案。该控制方案可以有效地避免对载体位置相关量进行实时测量与反馈,并由于神经网络良好的在线自学习补偿作用,有效地补偿了外部扰动对控制精度的影响,大大提高了整个系统的鲁棒性及自适应能力。仿真运算验证了控制方法的可行性。The compensation control problems of coordinated motion between the base＇s attitude and two end-effector of a free-floating dual-arm space robot with unknown external disturbances to track the desired trajectories were discussed.With the linear momentum conservation of the system,the kinematics and dynamics of the system were analyzed,and then the dynamics equations of the system described in workspace were derived.Based on the results,a neural network on-line self-learning compensation control scheme for coordinated motion of the free-floating dual-arm space robot with unknown external disturbances was designed.The control scheme proposed can avoid the measurements of the position-related variables of the base,and effcetively enhance the robustness and adaptive ability of the system bacause of the good on-line self-learning compensation of the neural network for external disturbances.Simulation results validate the feasibility of the presented control scheme.

关 键 词：双臂空间机器人 外部扰动 协调运动 神经网络 自学习补偿控制 

分 类 号：TP241[自动化与计算机技术—检测技术与自动化装置]