DeRi-IGP: Learning to Manipulate Rigid Objects Using Deformable Objects via Iterative Grasp-Pull

TL;DR

This paper introduces a novel vision-based neural policy and a primitive called Iterative Grasp-Pull for manipulating rigid objects via deformable linear objects, enabling effective, generalizable, and collaborative transportation in both simulated and real-world settings.

Contribution

The paper presents a universal, learning-based primitive and decentralized algorithm for manipulating rigid objects with deformable objects, improving over existing methods in generalization and operational space.

Findings

Outperforms baseline methods significantly.

Effective in both simulated and real-world environments.

Enables human-robot collaboration for object transportation.

Abstract

Robotic manipulation of rigid objects via deformable linear objects (DLO) such as ropes is an emerging field of research with applications in various rigid object transportation tasks. A few methods that exist in this field suffer from limited robot action and operational space, poor generalization ability, and expensive model-based development. To address these challenges, we propose a universally applicable moving primitive called Iterative Grasp-Pull (IGP). We also introduce a novel vision-based neural policy that learns to parameterize the IGP primitive to manipulate DLO and transport their attached rigid objects to the desired goal locations. Additionally, our decentralized algorithm design allows collaboration among multiple agents to manipulate rigid objects using DLO. We evaluated the effectiveness of our approach in both simulated and real-world environments for a variety of soft-rigid body manipulation tasks. In the real world, we also demonstrate the effectiveness of our decentralized approach through human-robot collaborative transportation of rigid objects to given goal locations. We also showcase the large operational space of IGP primitive by solving distant object acquisition tasks. Lastly, we compared our approach with several model-based and learning-based baseline methods. The results indicate that our method surpasses other approaches by a significant margin.