Constructing Fast Hydraulic Robot Models for Optimal Motion Planning
作者： John Bares , Murali Krishna
DOI:
关键词: Excavator 、 Robot 、 Actuator 、 Simulated annealing 、 Artificial neural network 、 Simulation 、 Hydraulic machinery 、 Computer science 、 Motion planning 、 Control theory 、 Testbed
摘要: Computing optimal motions for any robot requires a good model, and method to compute the using that model. As research is conducted into automating operations in construction, excavation etc. there arises need hydraulic machines used these areas. Hydraulic disallow simple extension of work done previously on motion planning electric drive robots. We have constructed fast model excavator(HEX) can capture non-linear actuator interactions. This simulate 75 secs machine 1 sec. real time Sun Sparc 20. use set neural networks approximate response functions. HEX with simulated annealing optimization time-optimal HEX, defined start end states. demonstrate efficacy show results from it computation. Real testbed are shown both cases. first such result has been reported literature machines.
参考文章(5)
John J. Craig, Introduction to Robotics Mechanics and Control ,(1986)
M. Krishna, J. Bares, Hydraulic system modeling through memory-based learning intelligent robots and systems. ,vol. 3, pp. 1733- 1738 ,(1998) , 10.1109/IROS.1998.724848
K.S. Narendra, K. Parthasarathy, Identification and control of dynamical systems using neural networks IEEE Transactions on Neural Networks. ,vol. 1, pp. 4- 27 ,(1990) , 10.1109/72.80202
P. Rowe, A. Stentz, Parameterized scripts for motion planning intelligent robots and systems. ,vol. 2, pp. 1119- 1124 ,(1997) , 10.1109/IROS.1997.655149
Z. Shiller, S. Dubowsky, On computing the global time-optimal motions of robotic manipulators in the presence of obstacles international conference on robotics and automation. ,vol. 7, pp. 785- 797 ,(1991) , 10.1109/70.105387