Grasp Learning by Sampling from Demonstration
This addresses the challenge of grasp learning for robots in uncertain, cluttered settings where traditional object models are unavailable, though it appears incremental as it builds on existing stochastic optimization approaches.
The paper tackles the problem of robotic grasping in cluttered environments with high uncertainty by proposing a model-free stochastic optimization method that requires only a few user demonstrations and an initial grasp affordance sketch, without relying on object geometric knowledge. The experiments show promising applicability of the method.
Robotic grasping traditionally relies on object features or shape information for learning new or applying already learned grasps. We argue however that such a strong reliance on object geometric information renders grasping and grasp learning a difficult task in the event of cluttered environments with high uncertainty where reasonable object models are not available. This being so, in this paper we thus investigate the application of model-free stochastic optimization for grasp learning. For this, our proposed learning method requires just a handful of user-demonstrated grasps and an initial prior by a rough sketch of an object's grasp affordance density, yet no object geometric knowledge except for its pose. Our experiments show promising applicability of our proposed learning method.