Robot Learning and Error Correction

We descr ibe a l ea rn ing paradigm designed to improve the performance of a robot in a p a r t i a l l y unpred ic tab le environment. The paradigm was suggested by phenomena observed in animal behavior and it models aspects of t ha t behavior. (See Fl f o r d e t a i l s . ) An implementation as a working program is under way, intended f o r i nco rpo ra t i on in the now ope ra t i ona l JPL robo t . R ieger 's CSA system is the implementat ion language and inc ludes a p lan synthes i z e r ( R l ) . A b r i e f overview o f the r o b o t ' s e x i s t i ng system o rgan iza t ion is g iven in Thompson's paper on robot nav iga t ion in these proceedings ( T l ) •