Robust Neural Force Control with Robot Dynamic Uncertainties under Totally Unknown Environm.pdfVIP

Robust Neural Force Control with Rob ot Dynamic Uncertainties under Totally Unknown Environment Seul Jung and T C Hsia Rob otics Research Lab oratory Department of Electrical and Computer Engineering University of California Davis Davis CA emailhsiaeceucdavisedu and jungeceucda visedu Abstract Within this framework many control algorithms have b een prop osed to tackle these problems In this p aper a new robust robot for ce tracking Lasky and Hsia have prop osed the innerouter impedance control scheme that uses neural network as lo op control scheme that uses the integral control of a compensator is proposed The proposed neural com the force error b etween desired force and actual force p ensator has the capability of making the robot to track to mo dify the reference tra jectory Sera ji and Col a specied desired force as wel l as of compensating for baugh have prop osed the adaptive techniques of uncertainties in environment location and stiness using force tracking errors to deal with uncertainties and the uncertainties in robot dynamics The neural of environment stiness and lo cation The authors compensator is trained separately for fr ee space mo