DocumentCode
2375323
Title
Punctuated anytime learning for hexapod gait generation
Author
Parker, Gary B.
Author_Institution
Connecticut Coll., New London, CT, USA
Volume
3
fYear
2002
fDate
2002
Firstpage
2664
Abstract
Punctuated anytime learning is presented as the solution for two problems: the use of anytime learning with an off-line learning module and the linking of the actual robot to its simulation during evolutionary robotics. Two methods of punctuated anytime learning, fitness biasing and the co-evolution of model parameters, are described and compared using the common task of gait generation for a hexapod robot with changing capabilities.
Keywords
evolutionary computation; gait analysis; legged locomotion; evolutionary robotics; fitness biasing; hexapod gait generation; hexapod robot; offline learning module; punctuated anytime learning; simulation; Control systems; Educational institutions; Evolutionary computation; Feedback; Learning systems; Mobile agents; Robot sensing systems; Sensor systems; Target tracking; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Robots and Systems, 2002. IEEE/RSJ International Conference on
Print_ISBN
0-7803-7398-7
Type
conf
DOI
10.1109/IRDS.2002.1041672
Filename
1041672
Link To Document