Gravity-Based Robotic Cloth Folding Jur van den Berg, Stephen Miller, Ken Goldberg, Pieter Abbeel Abstract We consider how the tedious chore of folding clothes can be performed by a robot. At the core of our approach is the definition of a cloth model that allows us to reason about the geometry rather than the physics of the cloth in significant parts of the state space. We present an algorithm that, given the geometry of the cloth, computes how many grippers are needed and what the motion of these grippers are to achieve a final configuration specified as a sequence of g-folds—folds that can be achieved while staying in the subset of the state space to which the geometric model applies. G-folds are easy to specify and are sufficiently rich to capture most common cloth folding procedures. We consider folds involving single and stacked layers of material and describe experiments folding towels, shirts, sweaters, and slacks with a Willow Garage PR2 robot. 1 Introduction An English patent for a clothes washing machine was issued in 1691. Since then, there have been many innovations in washing and drying, but folding of clothes remains a manual (and notoriously tedious) activity. In this paper, we present a geometric model and algorithms that are steps toward autonomous robot folding of clothes. Cloth is highly non-rigid, flexible, and deformable with an infinite- dimensional configuration space. We consider articles of clothing that can be de- scribed by a simple polygonal boundary when lying flat on a horizontal surface. We introduce a deterministic geometric model of cloth motion based on gravity and assumptions about material properties. We constrain robot motion such that at all times, one part of the cloth is lying horizontally on the table and one part (pos- sibly empty) hangs vertically from the grippers parallel to the gravity vector. This allows a configuration of the cloth to be fully determined by the line that separates University of California, Berkeley. E-mail: {berg, sdavidmiller, goldberg, pabbeel}@berkeley.edu 1