Transferring functional grasps through contact warping and local replanning

Abstract

We present a method for transferring grasps between objects of the same functional category. This transfer is intended to preserve the functionality of a grasp constructed for one of the objects, thus enabling the analogous action to be performed on a novel object for which no grasp has been specified. Manipulation knowledge is hence generalized from a single example to a class of objects with a significant amount of shape variability. The transfer is achieved through warping the surface geometry of the source object onto the target object, and along with it the contact points of a grasp. The warped contacts are locally replanned, if necessary, to ensure grasp stability, and a suitable grasp pose is computed. We present extensive results of experiments with a database of four-finger grasps, designed to systematically cover variations on grasping the mugs of the Princeton Shape Benchmark.

One-shot learning and generation of dexterous grasps for novel objects

“…Methods close in spirit to our own include the work of Hillenbrand & Roa (2012), who addressed the problem of transferring a multi-finger grasp between two objects of known 3D shape. A known object's geometry is warped until it matches that of a novel object, thereby also warping grasp points on the surface of the known object onto candidate grasp points on the novel object.…”

Probabilistic consolidation of grasp experience

“…In [10] the authors proposed to correct grasps by adapting to local geometry using the force-closure criterion. Contact positions were transferred between objects of the same functional class by surface geometry warping.…”

“…Compared to our work, this system did not integrate experience from training data or feedback from grasp execution. Differently from [10], [11] and [8] included an off-line training phase based on examples demonstrated by a teacher. In our work, training also relies on human demonstration.…”

Dexterous reaching, grasp transfer and planning using electrostatic representations

“…The mapping between hands with different number of fingers is, however, not well defined, and these methods do not generalise over different shapes of objects. A recent extension of this approach that maps contact positions of a grasp to similar objects is presented in [9]. This technique warps the surface geometry of a source object to a target object along with the contact points of a grasp, but does not deal with the non-contact relationships between the hand and the object, nor does it consider the approach for the grasp.…”