Toward Grasping Against the Environment: Locking Polygonal Objects Against a Wall Using Two-Finger Robot Hands

摘要

Caging offers a robust strategy for grasping objects with robot hands. This letter utilizes caging for locking polygonal objects against a wall using minimalistic two-finger robot hands. From the object's perspective, the wall and two-finger hand form an equivalent three-finger hand. The object is first caged by trapezoidal finger formations of the equivalent three-finger hand, and the hand is then closed until the object is locked against the wall in the desired grasp. The object can then be safely grasped and moved away from the wall, or it can be held fixed against it to be worked on by tools. This letter presents a novel and efficient caging-to-locking algorithm. While the equivalent hand's <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">configuration space</i> is four-dimensional, the algorithm uses the hand's two-dimensional contact space, which represents all contacts by two and three of the equivalent hand's fingers along the object boundary. The problem of computing the critical cage formation that allows the object to escape the equivalent hand is reduced to a search along a <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">caging graph</i> constructed incrementally in the equivalent hand's contact space. Starting from the desired locking grasp, the graph is searched for an escape path which passes through the critical cage formation. The technique is demonstrated with a detailed example.