Learning visually guided grasping: a test case in sensorimotor learning

Abstract—We present a general scheme for learning sensorimotor tasks which allows rapid on-line learning and generalization of the learned knowledge to unfamiliar objects. The scheme consists of two modules, the first generating candidate actions and the second estimating their quality. Both modules work in an alternating fashion until an action which is expected to provide satisfactory performance is generated, at which point the system executes the action. This design decomposes the learning problem and thus simplifies it and allows direct generalization among objects for the quality estimation. Since the proposed scheme requires some initial knowledge about the task, we developed a method for off-line selection of heuristic strategies and quality predicting features, based on statistical analysis. The usefulness of the scheme was demonstrated in the context of learning visually guided grasping. We consider a system that coordinates a parallel-jaw gripper and a fixed camera. The...

• Type: Journal
• Year: 1998
• Where: TSMC
• Authors: Ishay Kamon, Tamar Flash, Shimon Edelman
• Keywords: General Scheme, Rapid On-line Learning, TSMC 1998, first Generating Candidate