DocumentCode :
295888
Title :
An architecture for behaviour coordination learning
Author :
Hoff, Joel ; Bekey, George
Author_Institution :
Center for Neural Eng., Univ. of Southern California, Los Angeles, CA, USA
Volume :
5
fYear :
1995
fDate :
Nov/Dec 1995
Firstpage :
2375
Abstract :
This paper describes a neural architecture for learning coordination of different behaviours in a situated agent. Behaviour-oriented approaches define the control of an agent directly in terms of its tasks. A key challenge is how to manage the agent´s ongoing tasks so that action conflict is minimized and the desired levels of compliance with overall goals are achieved. We present mechanisms for adapting the coordination strategy through short- and long-term adaptive inhibition and time-varying performance feedback. Finally, we present preliminary experimental results for a simulated robot which demonstrate the effectiveness of this method
Keywords :
adaptive systems; cooperative systems; intelligent control; learning (artificial intelligence); mobile robots; navigation; neural nets; neurocontrollers; path planning; adaptive inhibition; behaviour coordination learning; compliance control; decentralised architecture; intelligent agents; intelligent robots; navigation; neural architecture; performance feedback; Computer architecture; Computer science; Intelligent agent; Intelligent robots; Navigation; Neural engineering; Robot kinematics; Robustness; Statistical analysis; Voting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
Type :
conf
DOI :
10.1109/ICNN.1995.487733
Filename :
487733
Link To Document :
بازگشت