# Learning Bimanual Cloth Manipulation with Vision-based Tactile Sensing via Single Robotic Arm

Source: [Learning Bimanual Cloth Manipulation with Vision-based Tactile Sensing via Single Robotic Arm](<https://www.sota2.com/research/paper/69b248aed030084c22e2fa69>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-13T05:00:04.336Z

Authors: Dongmyoung Lee, Wei Chen, Xiaoshuai Chen, Rui Zong, Petar Kormushev

Published: 2026-03-11T10:15:42.000Z

## Abstract

Robotic cloth manipulation remains challenging due to the high-dimensional state space of fabrics, their deformable nature, and frequent occlusions that limit vision-based sensing. Although dual-arm systems can mitigate some of these issues, they increase hardware and control complexity. This paper presents Touch G.O.G., a compact vision-based tactile gripper and perception/control framework for single-arm bimanual cloth manipulation. The proposed framework combines three key components: (1) a novel gripper design and control strategy for in-gripper cloth sliding with a single robot arm, (2) a Vision Foundation Model-backboned Vision Transformer pipeline for cloth part classification (PC-Net) and edge pose estimation (PE-Net) using real and synthetic tactile images, and (3) an encoder-decoder synthetic data generator (SD-Net) that reduces manual annotation by producing high-fidelity tactile images. Experiments show 96% accuracy in distinguishing edges, corners, interior regions, and grasp failures, together with sub-millimeter edge localization and 4.5{\\deg} orientation error. Real-world results demonstrate reliable cloth unfolding, even for crumpled fabrics, using only a single robotic arm. These results highlight Touch G.O.G. as a compact and cost-effective solution for deformable object manipulation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Edge Pose Estimation on Real Tactile dataset](<https://www.sota2.com/research/sota/edge-pose-estimation-on-real-tactile-dataset.md>): Edge Pose Estimation; Real Tactile dataset; Position X Error (mm): 0.25.

- [Cloth-part classification on Tactile Cloth Dataset](<https://www.sota2.com/research/sota/cloth-part-classification-on-tactile-cloth-dataset.md>): Cloth-part classification; Tactile Cloth Dataset; Precision (Edge): 97.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.10609>)

[PDF](<https://arxiv.org/pdf/2603.10609.pdf>)
