Active and Transfer Learning of Grasps by Sampling from Demonstration
This work addresses robotic grasping, potentially improving efficiency in manipulation tasks, but it appears incremental as it builds on existing learning paradigms.
The paper tackles the problem of learning grasping skills for known and novel objects by proposing active and transfer learning methods based on kernel adaptive, mode-hopping Markov Chain Monte Carlo, with experiments showing promising applicability.
We guess humans start acquiring grasping skills as early as at the infant stage by virtue of two key processes. First, infants attempt to learn grasps for known objects by imitating humans. Secondly, knowledge acquired during this process is reused in learning to grasp novel objects. We argue that these processes of active and transfer learning boil down to a random search of grasps on an object, suitably biased by prior experience. In this paper we introduce active learning of grasps for known objects as well as transfer learning of grasps for novel objects grounded on kernel adaptive, mode-hopping Markov Chain Monte Carlo. Our experiments show promising applicability of our proposed learning methods.