Model-Free 3-D Shape Control of Deformable Objects Using Novel Features Based on Modal Analysis

Bohan Yang, Bo Lu, Wei Chen, Fangxun Zhong, Yun-Hui Liu

IEEE Transactions on Robotics, 2023

Model-Free 3-D Shape Control of Deformable Objects Using Novel Features Based on Modal Analysis — Model-free 3-D shape control of deformable objects using modal-analysis-based features.

Abstract

This paper presents a model-free framework for three-dimensional shape control of deformable objects using novel features derived from modal analysis. By exploiting intrinsic deformation modes, the proposed approach enables effective visual servoing without requiring explicit physical models of the deformable object. Experimental results on deformable object manipulation tasks demonstrate accurate shape regulation, robustness to modeling uncertainties, and improved control performance compared to conventional model-based methods.

Main Contributions

Model-free 3-D shape control framework for deformable objects
Novel modal-analysis-based features for visual servoing
Extensive experimental validation on deformable object manipulation

Citation

@ARTICLE{10122176,
  author  = {Yang, Bohan and Lu, Bo and Chen, Wei and
             Zhong, Fangxun and Liu, Yun-Hui},
  title   = {Model-Free 3-D Shape Control of Deformable Objects Using Novel Features Based on Modal Analysis},
  journal = {IEEE Transactions on Robotics},
  volume  = {39},
  number  = {4},
  pages   = {3134--3153},
  year    = {2023},
  doi     = {10.1109/TRO.2023.3269347}
}