Developing and Comparing Single-arm and Dual-arm Regrasp

TL;DR

This paper develops and compares algorithms for single-arm and dual-arm regrasp, analyzing their performance through extensive simulations to guide practical robot grasping strategies based on object shape and grasping conditions.

Contribution

The paper introduces efficient algorithms for both single-arm and dual-arm regrasp, addressing the combinatorial complexity and providing insights into their comparative performance.

Findings

Dual-arm regrasp is more effective with good grasp clearance.

Overlapping grasps reduce dual-arm regrasp success.

Algorithms enable practical dual-arm regrasp with reduced overlap.

Abstract

The goal of this paper is to develop efficient regrasp algorithms for single-arm and dual-arm regrasp and compares the performance of single-arm and dual-arm regrasp by running the two algorithms thousands of times. We focus on pick-and-place regrasp which reorients an object from one placement to another by using a sequence of pick-ups and place-downs. After analyzing the simulation results, we find dual-arm regrasp is not necessarily better than single-arm regrasp: Dual-arm regrasp is flexible. When the two hands can grasp the object with good clearance, dual-arm regrasp is better and has higher successful rate than single-arm regrasp. However, dual-arm regrasp suffers from geometric constraints caused by the two arms. When the grasps overlap, dual-arm regrasp is bad. Developers need to sample grasps with high density to reduce overlapping. This leads to exploded combinatorics in previous methods, but is possible with the algorithms presented in this paper. Following the results, practitioners may choose single-arm or dual-arm robots by considering the object shapes and grasps. Meanwhile, they can reduce overlapping and implement practical dual-arm regrasp by using the presented algorithms.