A vision-based framework for the discovery-driven manipulation of non-rigid objects

Since the analytical expressions for the representation of non-rigid object structure and motion are severely underconstrained, current techniques for non-rigid object manipulation employ physical object models known prior to sensing. Recently, however, psychophysical studies have revealed that humans are able to discover proper motor coordination skills through sensory input without the use of previously known physical models. In this paper, a robust, discovery-driven, vision-based framework for the robotic manipulation of non-rigid objects is developed and experimentally verified using Various flexible linear objects. Employing the novel concept of relative elasticity, the algorithms derived using this framework are completely sensor-based, requiring the use of no a priori explicit, physics-based models.