Learning to Estimate 3-D States of Deformable Linear Objects from Single-Frame Occluded Point Clouds
Authors:
- 29 May 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7119-7125
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.Keywords
All Related Versions
Funding Information
- National Key R&D Program of China (2020AAA0105200)
- Institute for Guo Qiang, Tsinghua University
- National Natural Science Foundation of China (U21A20517,52075290)
This publication has 19 references indexed in Scilit:
- Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data2020
- Self-Supervised Learning of State Estimation for Manipulating Deformable Linear ObjectsIEEE Robotics and Automation Letters, 2020
- Robust Deformation Model Approximation for Robotic Cable Manipulation2019
- Occlusion-robust Deformable Object Tracking without Physics Simulation2019
- A Framework for Manipulating Deformable Linear Objects by Coherent Point DriftIEEE Robotics and Automation Letters, 2018
- Dense 3D Regression for Hand Pose Estimation2018
- Fourier-Based Shape Servoing: A New Feedback Method to Actively Deform Soft Objects into Desired 2-D Image ContoursIEEE Transactions on Robotics, 2017
- State estimation for deformable objects by point registration and dynamic simulation2017
- Tracking deformable objects with point clouds2013
- Point Set Registration: Coherent Point DriftIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010