Learning Grasp Configurations for Novel Objects from Prior Examples
share
We present a new approach to learning grasp configurations for a novel object from known example objects. We assume the novel object and the example object belong to the same category in which objects share the same topology and have a similar shape. Both the novel and the example objects are segmented into the same semantic parts. We learn a grasp space for each part of the example object using a combination of optimization and learning algorithm. We perform shape warping between the corresponding parts of the example object and the novel object, and use them to compute the corresponding grasps. Finally, we assemble the individual parts and the associated grasps of the novel object, and use local replanning to adjust grasp configurations to satisfy the stability and physical constraints (e.g., that they are penetration-free). Our algorithm can automatically handle a wide range of object categories and a variety of robotic hand grasps.
READ FULL TEXT