Finding all valid hand configurations for a given precision grasp

Abstract

Abstract-Planning a precision grasp for a robot hand is usually decomposed into two main steps. First, a set of contact points over the object surface must be determined, ensuring they allow a stable grasp. Second, the inverse kinematics of the robot hand must be solved to verify whether the contact points can actually be reached. Whereas the first problem has been largely solved in a general posing, the second one has only been tackled with local convergence methods. These methods only provide one solution to the problem, even if many are possible, and depending on the initial estimation they use, they may fail to converge, which results in grasp re-planning in situations where it could be avoided. This paper overcomes both issues by providing a complete method to solve the kinematics of human-like hands. The method is able to find all possible configurations that reach the specified contact points, even when positive-dimensional sets of such configurations are possible.

Hierarchical Fingertip Space: A Unified Framework for Grasp Planning and In-Hand Grasp Adaptation

“…Classical works formulate contact-level grasp synthesis as an optimization problem [8], [12], [23]- [27] for which the objective -grasp stability -is commonly measured using force analysis in the contact wrench space [28]. The problem of calculating feasible hand configurations has also been addressed in this context [2], [29]. To account for uncertainties in physical properties of objects, grasp friction sensitivity [30] and independent contact regions [31] have been investigated.…”

Grasping bulky objects with two anthropomorphic hands

“…Many of this approaches use optimization methods to find valid hand configurations [12], [13], [14], [15], [16], or discretize the workspace of the hands in order to simplify the search of suitable poses of the fingers on the object surface [17], [18], [19], or select the best grasp using a set of grasp quality metrics [20], [21].…”

“…• In the main loop three points are randomly selected, one from S t and two from S f , an ID is assigned to the candidate triplet in order to verify if this combination has not been formed before (line [13][14][15][16][17][18]. Then, the distances between the fingers are computed and the condition in eq.…”

On the evolution of fingertip grasping manifolds

“…For fingertip grasping, localizing contacts on the object that provide a stable grasp [4]- [6] and finding a hand configuration for realizing these contacts [7]- [9] have been addressed as separate problems. As a result, in these approaches it is not guaranteed that the planned contacts are kinematically feasible for a specific hand [1], [2].…”