Machine-mediated Motor Skill Training Method in Haptic-enabled Chinese Handwriting Simulation System

Training of motor skill through machine-mediated method is a promising way to improve complex dexterous manipulation skill. New method of fusion between human motor skill and machine capability is studied to transfer skill from expert to novice. Haptic-enabled Chinese handwriting training system is established as a benchmark platform for studying learning and transfer of motor skill. Perceptible element of haptic skill is proposed to model human motor skill. Four rules of machine-mediated training system are identified according to human´s skill learning characteristics. Architecture of a hierarchical hybrid control training system is proposed based on the learning rules. Phantom desktop is used as the haptic interface and haptic-visual feedback is developed for three training modes, which includes facsimile mode, transcribe mode and reciting mode. Human subject experiments validate the proposed training rules. Fusion of human skill and machine capability by haptic-enable multiple signal feedback system is proved effective to train novice to get familiar with Chinese character handwriting skill