ScissorBot: Learning Generalizable Scissor Skill for Paper Cutting via Simulation, Imitation, and Sim2Real

TL;DR

This paper presents ScissorBot, a robotic system capable of generalizable paper cutting by combining simulation, imitation learning, and sim-to-real transfer, achieving human-level performance.

Contribution

The work introduces a novel action primitive sequence for imitation learning and a sim-to-real transfer method tailored for complex paper deformation tasks.

Findings

Outperforms baseline methods in simulation and real-world tests

Achieves performance comparable to human operators

Successfully handles continual paper deformation during cutting

Abstract

This paper tackles the challenging robotic task of generalizable paper cutting using scissors. In this task, scissors attached to a robot arm are driven to accurately cut curves drawn on the paper, which is hung with the top edge fixed. Due to the frequent paper-scissor contact and consequent fracture, the paper features continual deformation and changing topology, which is diffult for accurate modeling. To ensure effective execution, we customize an action primitive sequence for imitation learning to constrain its action space, thus alleviating potential compounding errors. Finally, by integrating sim-to-real techniques to bridge the gap between simulation and reality, our policy can be effectively deployed on the real robot. Experimental results demonstrate that our method surpasses all baselines in both simulation and real-world benchmarks and achieves performance comparable to human operation with a single hand under the same conditions.