Abstract：Based on an artificial neural network inverse dynamic model of robot manipulators,a nonlinear model-based control scheme is presented in this paper.The implementation of the whole scheme assumes no anyknowledge of the system.The simulation tests for the two-link hydraulic robot manipulators indicate that theposition control system under consideration has acceptable good tracking performance,and demostrate thatartificial neural networks have potential of solying identification and control problems of nonlinear systems.
[1] 陆佑方,王彬.多柔体系统动力学,高等教育出版社(将于1994年出版) [2] 蒋新松.机器人及机器人学中的控制问题.机器人,1990112(5),1-13 [3] 彭商贤,赵臣,张启先.试论国内外机器人机械学的发展趋向.机器人,1991i13(3)}48-53 [4] 冯冠民,王彬,陆估方.转动规范理论及其在柔体系统动力学中的应用,多体系统动力学—理论、计算方法和应用.上海交大出版社,1992,1-7. [5] 张策等.弹性连杆机构的分析与设计.机械工业出版社,1989 I [6] Pfeiffer F.Geber B.A multistage-approach to the dynamics and control of elastic robots.IEEE Int' I Con( on Roboticsand Automation,1:2-8 [7] Koppens W P&others.The dynamics of a deformable body experiencing large displacements.J of Applied Mechanics,1988,55,676-680 [8] 郭吉丰,童忠舫.挠性机器人逆动力学建模.机器人,1991113(2),1-9 [9] 王照林等.关于柔性结构动力系统稳定性与控制.中国科学,1992i(11),1219-1227 [10] 马正东·フレキツブルロボツトァームの逆动力学·博士论文旧本京都大学,1988, [11] 费从宇.柔性机械臂动力学、逆动力学和主动控制中若干问题的研究.博士论文,哈尔滨工业大学,1992 [12] 潘振宽.柔性多体系统动力学建模理论与数值仿真研究.博士论文,上海交大,1992
