作者: Kazuo Kiguchi , Toshio Fukuda
关键词:
摘要: _This paper presents an effective adaptive neural network feedback controller for force control of robot manipulators in unknown environment by applying damping neurons which possess elastic-viscous properties. The unexpected overshooting and oscillation caused the and/or unmodeled dynamics a manipulator can be decreased efficiently effect proposed neurons. Furthermore, fuzzy controlled evaluation function is applied learning controller, so that able to adapt more effectively. effectiveness evaluated experiment with 3 d.o.f. direct-drive planar manipulator.