Abstract: In the immersive transformer training simulator, using MEMS inertial motion capture system, the operator’s motion data was captured and analyzed. According to the typical operation in the substation virtual environment, the semantics of interaction were studied. SVM classification algorithm based on grid search and cross validation was used to recognize operator’s gestures. The identified gestures were used to actuate the virtual human’s action in the substation virtual environment. A priority classified character animation method with deformation weight control was proposed to render different priority level actions at the same time. Two modes of virtual operation performance, character animation sequences and real time data-driven, were supported. An immersive transformer training simulator was realized and it worked fine.

Key words: virtual environment, motion capture, gesture recognition, transformer training simulator