Visual Perception of Humanoid Movement

Abstract

We examined similarity judgements of arm movements generated by different control strategies with the goal of producing natural looking movements on humanoid robots and virtual humans. We examined a variety of movements generated by human motion capture data as well as fourteen differenct synthetic motion generation algorithms that were developed based on human motor production theories and computational considerations. In experiments we displayed motion clips generated by these 15 different methods on both a humanoid robot and a computer graphic character and obtained judgements of similarity between pairs of movements. Experimental results reveal that for movements with obviously different paths as occurred with two production techniques then, as expected, hand paths dominated in the perception of similarity. However, for roughly similar paths as occurred for the other techniques then judgements about fast movements appeared to be based on their velocity profile while judgements to slow movements were based on more detailed representation of the movement.