Accession Number : ADA325516
Title : Learning Controllers for Complex Behavioral Systems.
Descriptive Note : Technical rept.,
Corporate Author : CALIFORNIA UNIV BERKELEY
Personal Author(s) : Crawford, Lara S. ; Sastry, S. S.
PDF Url : ADA325516
Report Date : 03 DEC 1996
Pagination or Media Count : 18
Abstract : Biological control systems routinely guide complex dynamical systems through complicated tasks such as running or diving. Conventional control techniques, however, stumble with these problems, which have complex dynamics, many degrees of freedom, and a task which is often only partially specified. To address problems like these, we are using a biologically inspired, hierarchical control structure, in which controllers composed of radial basis function networks learn the controls required at each level of the hierarchy. Through learning and proper encoding of behaviors and controls, some of these difficulties in controlling complex systems can be overcome.
Descriptors : *ROBOTICS, *ARTIFICIAL INTELLIGENCE, ALGORITHMS, COMPUTERIZED SIMULATION, NEURAL NETS, AUTOMATION, COMPUTER LOGIC, DEGREES OF FREEDOM, DYNAMIC PROGRAMMING, HYBRID COMPUTERS, CONTROL SEQUENCES.
Subject Categories : Cybernetics
Distribution Statement : APPROVED FOR PUBLIC RELEASE