A fuzzy-logic concept for highly fast and accurate position control of industrial robots

Different approaches of a learnable fuzzy-logic (FL) concept for highly fast and accurate position control of industrial robots are presented which provide both time-optimality for large position errors as well as well damped response (no overshoot) near the target. For automatic optimization of the control parameters an additional neural-network component is introduced. Based on simulation and experiments the performance and robustness of the presented FL concept are discussed.