FUZZY-LOGIC-BASED REINFORCEMENT LEARNING OF ADMITTANCE CONTROL FOR AUTOMATED ROBOTIC MANUFACTURING

An approach to admittance control using fuzzy-logic-based reinforcemen t learning is proposed for the robotic automation of typical manufactu ring operations. The proposed approach provides the necessary nonlinea r control actions required in a typical automated robotic manufacturin g task. Simultaneously, it reduces the controller development time due to the incorporation of pre-existing process knowledge in a neural-ne twork form. The pre-existing knowledge is further refined using reinfo rcement learning via a CMAC (Cerebellar Model Articulation Controller) based critic network. Automated robotic deburring offers an attractiv e alternative to manual deburring in terms of reduced costs and improv ed quality of the finished parts. Hence. robotic deburring is used as an example of a typical manufacturing task to verify the performance o f the proposed approach. However, the approach is general enough to be easily extended to similar manufacturing tasks. Simulation results ar e presented, which demonstrate the effectiveness of the proposed strat egy in controlling the automated robotic deburring task. (C) 1998 Else vier Science Ltd. All rights reserved.