Learning to Estimate 3-D States of Deformable Linear Objects from Single-Frame Occluded Point Clouds

TL;DR

This paper introduces a data-driven two-branch neural network architecture that robustly estimates the 3-D states of deformable linear objects from single-frame occluded point clouds, enhancing robotic manipulation capabilities.

Contribution

A novel two-branch network with a fusion module for accurate DLO state estimation from occluded point clouds, improving robustness and precision.

Findings

Effective in both simulation and real-world scenarios

Handles heavy occlusions with smooth and precise estimations

Applicable to robotic manipulation of DLOs in 3-D space

Abstract

Accurately and robustly estimating the state of deformable linear objects (DLOs), such as ropes and wires, is crucial for DLO manipulation and other applications. However, it remains a challenging open issue due to the high dimensionality of the state space, frequent occlusions, and noises. This paper focuses on learning to robustly estimate the states of DLOs from single-frame point clouds in the presence of occlusions using a data-driven method. We propose a novel two-branch network architecture to exploit global and local information of input point cloud respectively and design a fusion module to effectively leverage the advantages of both methods. Simulation and real-world experimental results demonstrate that our method can generate globally smooth and locally precise DLO state estimation results even with heavily occluded point clouds, which can be directly applied to real-world robotic manipulation of DLOs in 3-D space.