研究了机械臂的位置跟踪问题，提出了基于神经网络的自适应输出反馈控制方法. 该方法无需系统精确的数学模型，适用于具有非线性不确定性和外界干扰的机械臂控制系统. 设计的控制器由三部分组成：基于动态补偿器的输出反馈控制项、神经网络自适应控制项和鲁棒控制项. 神经网络的权值自适应学习率由Lyapunov稳定性理论得出. 仿真结果表明设计的控制器能驱动机械臂精确跟踪期望的位置，验证了该控制方法的有效性.
The position tracking control problem for manipulators is addressed, and an adaptive output feedback controller based on neural network is proposed. The controller does not need an exact model, and is applicable to manipulators control systems with nonlinear uncertain dynamics and environmental disturbances.The controller is composed of three parts: output feedback control based on dynamic compensator, a neural network, and an item of robust control. The adaptive learning law of neural network can be obtained based on the Lyapunov stability theory. Numerical simulations show excellent performance of position control for picking manipulators.
[1] SPONG M, VIDYASAGAR M. Robot dynamics and control [M]. New York: John Wiley and Sons, 1989: 50-52.
[2] CANUDAS C, SICILIANO B, BASIN G. Theory of robot control [M]. New York: Springer, 1996: 35-38.
[3] SCIAVICCO L, SICILIANO B. Modeling and control of robot manipulators [M]. London: Springer-Verlag, 2000: 15-16.
[4] LEWIS F L, DAWSON D M, ABDALLAH C T. Robot manipulators control: theory and practice[M]. New York: JohnMarcel Dekker, 2004: 75-77.
[5] 贾鹤鸣，宋文龙，郭婧. 基于神经网络滑模的采摘机械臂控制设计 [J]. 吉林大学学报：工学版，2012, 42(3)：709-713.
JIA Heming, SONG Wenlong, GUO Jing. Sliding mode control for picking manipulators based on neural-network [J]. Jounal of Jilin University: Engineering and Technology Edition, 2012, 42(3): 709-713. (in Chinese)
[6] SU Y X, PETER C, ZHENG C H. Global asymptotic saturated PID control for robot manipulators [J]. IEEE Transactions on Control Systems Technology, 2010, 18(6): 1280-1288.
[7] SHAFIQUL I, LIU X P. Robust sliding mode control for robot manipulators [J]. IEEE Transactions on Industrial Electronics, 2011, 58(6): 2444-2453.
[8] SHAFIQUL I, PETER X. P D output feedback control design for industrial robotic manipulators [J]. IEEE/ASME Transactions on Mechatronics, 2011, 16(1): 187-197.
[9] 吴玉香，周东霞，胡跃明. 一类不确定非线性系统的鲁棒自适应控制[J]. 控制理论与应用，2008, 25(6)：1053-1058.
WU Yuxiang, ZHOU Dongxia, HU Yueming. Robust adaptive control of a class of uncertain nonlinear system [J]. Control Theory and Applications, 2008, 25(6): 1053-1058. (in Chinese)
[10] LORINC M, BELA L. Control of robotic systems with unknown friction and payload [J]. IEEE Transactions on Control Systems Technology, 2011, 19(6): 1534-1539.
[11] 于志刚，沈永良，宋申民. 机械臂鲁棒自适应运动控制 [J] .控制理论与应用，2011, 28(7): 1021-1024.
YU Zhigang, SHEN Yongliang, SONG Shenmin. Robust adaptive motion control for manipulator[J]. Control Theory and Applications, 2011, 28(7): 1021-1024. (in Chinese)
[12] 熊根良，刘伊威，黄剑斌，刘宏，蒋再南，孙奎. 基于DSP/ FPGA的反步法阻抗控制柔性关节机械臂[J]. 控制与决策，2009, 24(8): 1137-1142.
XIONG Genliang, LIU Yiwei, HUANG Jianbin, LIU Hong, JIANG Zainan, SUN Kui. Backstepping impedance control flexible joint manipulators using DSP/FPGA structure [J]. Control and Decision, 2009, 24(8): 1137-1142. (in Chinese)
[13] 林雷，王洪瑞，任华彬. 基于模糊变结构的机械臂控制 [J]. 控制理论与应用，2007, 24(4): 643-650.
LIN Lei, WANG Hongrui, REN Huabin. Fuzzy-based variable structure control for robotic manipulators [J]. Control Theory and Application, 2007, 24(4): 643-650. (in Chinese)
[14] 党进，倪风雷，刘业超，刘宏.一种前馈补偿和模糊滑模相结合的柔性机械臂控制 [J]. 西安交通大学学报，2011, 45(3): 75-80.
DANG Jin, NI Fenglei, LIU Yechao, LIU Hong. Control strategy for flexible manipulator based on feedforward compensation and fuzzy-sliding mode control [J]. Journal of Xi’an Jiaotong University, 2011, 45(3): 75-80. (in Chinese)
[15] JAGANNATHAN S, LEWIS F L, LIU K. Motion control and obstacle avoidance of mobile robot with an onboard manipulator [J]. Journal of Intelligent Manufacturing Systems, 1994, 5(5): 287-302.
[16] WAI R J. Tracking control based on neural network strategy for robot manipulator [J]. Neurocomputing, 2003, 51(10): 425-445.
