A fuzzy behavior-based control system for manipulation

Behavior-based approaches to robot control are extremely popular in mobile robotics, but still rarely used for manipulation. We propose a behavior-based system that performs manipulation tasks using visual feedback. The distinctive points of our proposal are: (i) visual behaviors are implemented using a new camera-based approach; (ii) reactive fuzzy rules an used to arbitrate behaviors; and (iii) the outputs of concurrent behaviors are fused using fuzzy logic. We show experiments on a real arm performing a pick-and-place task that illustrate our approach and demonstrate its advantages over current approaches.