hrc-dom

Reactive Human-Robot Collaborative Manipualtion

of Deformable Linear Object

Using a New Topological Latent Control Model

Peng Zhou, Pai Zheng, Jiaming Qi, Chengxi Li, Hoi-Yin Lee, Anqing Duan, Liang Lu, Zhongxuan Li, Luyin Hu,

and David Navarro-Alarcon

Abstract: Real-time reactive manipulation of deformable objects is a challenging task that requires robots to quickly and adaptively respond to changes in the object's shape and external force. In this paper, a novel approach is proposed for real-time reactive deformable linear object manipulation in the context of human-robot collaboration. The proposed approach, namely, a topological latent control model, combines a topological latent representation and a fixed-time sliding controller to enable seamless interaction between humans and robots. The topological latent control model provides a framework for controlling the shape and motion of deformable objects, while the topological latent representation allows for efficient representation of the object's shape and topology. The fixed-time sliding controller ensures that the object is manipulated in real-time, while also ensuring that it remains accurate and stable during the manipulation process. The proposed approach is tested on a variety of different deformable object manipulation tasks, including motor-robot experiments and human-robot experiments, and is found to be highly effective and efficient.

We would like to thank all the reviewers and editors for your time and effort in moving this manuscript to the public.

To address the issues raised by the reviewers from RCIM in 2nd revision,

We have executed an exhaustive series of experiments to compare the performance of GMM-based spline and PCD-based B-spline in representing deformable linear objects.
Corrections were made to the figure references associated with the validation of the generalization capabilities of our TopoLSC using Deformable Linear Objects (DLOs) of varying lengths and diameters.
Additional experiments involving human-robot collaborative peg-in-hole tasks (see the right setup) were conducted to substantiate the concepts of human-robot collaboration emphasized in the paper's title and central themes. Please refer to the experimental details as below: