DocumentCode :
1871717
Title :
Hybrid evolutionary motion planning via visibility-based repair
Author :
Dozier, Gerry ; Esterline, Albert ; Homaifar, Abdollah ; Bikdash, Marwan
Author_Institution :
NASA Center for Autonomous Control Eng., North Carolina A&T State Univ., Greensboro, NC, USA
fYear :
1997
fDate :
13-16 Apr 1997
Firstpage :
507
Lastpage :
511
Abstract :
Introduces a hybrid evolutionary system for global motion planning within unstructured environments. This hybrid system combines a novel obstacle representation scheme, the concept of evolutionary searching and a new concept that we refer to as `visibility-based repair´ to form a hybrid which quickly transforms infeasible motions into feasible ones. Our hybrid evolutionary system differs from other evolutionary motion planners in that (1) more emphasis is placed on repairing infeasible motions to develop feasible ones rather than using simulated evolution exclusively as a means of discovering feasible motions, (2) a continuous map of the environment is used rather than a discretized map, and (3) it develops motion plans for moving or mobile destinations. In this paper, we demonstrate the effectiveness of this new hybrid by using two challenging motion planning problems where the target tries to move away from our point robot
Keywords :
genetic algorithms; maintenance engineering; mobile robots; optimal control; path planning; search problems; visibility; GEPOA; continuous environment map; evolutionary search; feasible motions; global motion planning; hybrid evolutionary motion planning; infeasible motion repair; mobile destinations; moving target; obstacle representation scheme; unstructured environments; visibility graphs; visibility-based repair; Constraint optimization; Control engineering; Design optimization; Machine learning; Machine learning algorithms; Motion planning; NASA; Navigation; Path planning; Robot kinematics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Evolutionary Computation, 1997., IEEE International Conference on
Conference_Location :
Indianapolis, IN
Print_ISBN :
0-7803-3949-5
Type :
conf
DOI :
10.1109/ICEC.1997.592363
Filename :
592363
Link To Document :
بازگشت