Situation based task selection mechanism for interactive robot system

This paper presents a situation-based task selection mechanism which enables a life supporting robot system to perform tasks-based on the user´s situation. Stimulated by interactions between robot and user, this mechanism constructs and updates the association between the user´s situation and tasks so that the robot could adapt to user´s behaviors related to the robot´s tasks effectively. For the user adaptation, radial basis function networks (RBFN) and associative learning algorithms are used. The proposed mechanism is applied to CRF3 (character robot face 3) system to prove its feasibility and effectiveness.