Title :
Hopfield network application to optimal edge selection
Author :
Chung, C.H. ; Lee, K.S.
Author_Institution :
Dept. of Control & Instrum. Eng., Kwangwoon Univ., Seoul, South Korea
Abstract :
The goal of the present work is to plan the shortest collision-free path in 3-D, when a robot is navigated to pick up some tools or to repair some parts from various locations. To accomplish this goal, the path coordinator should have the capabilities of an obstacle avoidance strategy and a traveling salesman problem strategy (TSP). The obstacle avoidance strategy is to plan the shortest collision-free path between each pair of n locations in 2-D or in 3-D. The TSP strategy is to compute a minimal system cost of a tour that is defined as a closed path navigating each location exactly once. The TSP strategy can be implemented by a neural network. The obstacle avoidance strategy in 2-D can be implemented by the V-graph algorithm. However, the V-graph algorithm is not useful in 3-D, because it cannot compute the global optimality n 3-D. Thus, the path coordinator is proposed to solve this problem, having the capabilities of selecting the optimal edges by the modified genetic algorithm and computing the optimal nodes along the optimal edges by the recursive compensation algorithm
Keywords :
computerised navigation; genetic algorithms; neural nets; planning (artificial intelligence); robots; Hopfield network; genetic algorithm; neural network; obstacle avoidance; optimal edge selection; path coordinator; recursive compensation algorithm; robot; shortest collision-free path; traveling salesman problem; Cost function; Euclidean distance; Genetic algorithms; Instruments; Navigation; Orbital robotics; Path planning; Robot kinematics; Robustness; Space stations;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170621