Title :
Competition of Multi Biomimetic Robots Bases on Accumulating Competition Neural Network
Author :
Wang, Kun ; Bao, Hong ; Wang, Cong Si
Author_Institution :
Minist. of Edu Key Lab. of Electron. Equip. Struct., XiDian Univ., Xi´´an, China
Abstract :
Competition is a basic characteristic of organisms. In this paper, competition is adopted in the control of multi biomimetic robots in order to make robots achieve tasks well. Basing on the theory of accumulating competition neural network, competition of paths and multi biomimetic robots is presented. By this method, optimal path can be found by the competition of partial paths. Collisions between robots are solved effectively and biomimetic robots can get destination in the least time. Phenomenon of congestion is avoided. The simulative results show the feasibility and effectiveness of this approach.
Keywords :
biomimetics; collision avoidance; multi-robot systems; neural nets; unsupervised learning; multibiomimetic robots competition; neural network; partial paths competition; robots collision avoidance; Biological control systems; Biomimetics; Collision avoidance; Electronic equipment; Marine animals; Motion planning; Neural networks; Organisms; Robot kinematics; Robustness;
Conference_Titel :
Computational Intelligence and Software Engineering, 2009. CiSE 2009. International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-4507-3
Electronic_ISBN :
978-1-4244-4507-3
DOI :
10.1109/CISE.2009.5363637