Certified Grasping
This work addresses the problem of reliable robotic grasping for planar objects, offering a geometric certification approach that is incremental in improving grasp planning algorithms.
The paper tackles the problem of ensuring robustness in planar grasping by defining geometric certificates for grasp success and developing convex-combinatorial models to synthesize these certificates, resulting in validated certifiable grasps for arbitrary planar objects using point-finger manipulators in simulations and real robot experiments.
This paper studies robustness in planar grasping from a geometric perspective. By treating grasping as a process that shapes the free-space of an object over time, we can define three types of certificates to guarantee success of a grasp: (a) invariance under an initial set, (b) convergence towards a goal grasp, and (c) observability over the final object pose. We develop convex-combinatorial models for each of these certificates, which can be expressed as simple semi-algebraic relations under mild-modeling assumptions. By leveraging these models to synthesize certificates, we optimize certifiable grasps of arbitrary planar objects composed as a union of convex polygons, using manipulators described as point-fingers. We validate this approach with simulations and real robot experiments, by grasping random polygons, comparing against other standard grasp planning algorithms, and performing sensorless grasps over different objects.