| In the past, automatic handling in robotics has been mostly limited to rigid objects. This investigation introduces the use of vision and force feedback for the manipulation of highly deformable objects. Deformable active contours, or snake, based on an approach proposed by Trevelyan are developed to visually observe changes in object shape over time. Finite-element models of object deformations are used with force feedback to predict expected visually observed deformations. Our approach has improved the performance of deformable contour tracking over traditional computer vision tracking techniques. This approach also allows the use of a vision sensor as a force sensor. This is because visually observed material deflections can be transformed into applied stress estimates through a FEM. Therefore, internal object stresses due to object manipulation can be visually observed and controlled, thus, creating a framework within which deformable object manipulation can occur. A pinhole camera model is used to accomplish vision and force sensor feedback assimilation from these two sensing modalities during manipulation. |
