Motion sensing based framework for robot manipulation

Abstract

To data, outside of controlled environments, robots have normally performed manipulation tasks when operated with human. This pattern requires operators with high technical skills training and targeted knowledge acquiring for varied teach-pendant operating system. Motion sensing technology, enabling human-machine interaction in a novel and natural user interface using gestures, crucial inspires us to adopt a user-friendly and straight-forward interaction mode on robot manipulation. Thus, in this paper, we presented a motion sensing based framework for robot manipulation, which recognizes gesture commands captured by motion sensing input device and drives the action of robots. For compatibility, a general hardware interface layer was also developed in the framework. Simulation and physical experiments have been conducted for preliminary validation. The results have shown that the proposed framework is an effective approach for general robot manipulation with motion sensing control.