aiqbench analysis
This research presents CeDiRNet-6DoF, a deep learning framework that solves the complex problem of robot cloth unfolding by jointly predicting 6-degree-of-freedom grasp poses from visual inputs. By integrating dense 3D regression with specific encoding techniques for Euler angles, the method achieves state-of-the-art performance in bimanual robotic setups, addressing perceptual ambiguities caused by occlusions and folds. The work establishes a robust foundation for manipulating deformable objects in unstructured environments, advancing the practical capabilities of vision-based robotics.
Vision-Based 6-DoF Grasp Pose Estimation for Robot Cloth Unfolding
arXiv:2609.31452v1 Announce Type: new Abstract: Cloth manipulation is a challenging task due to the deformable and high-dimensional nature of cloth, which leads to complex interaction dynamics and perceptual ambiguity arising from frequent occlusions of critical visual cues such as folds, edges, and grasp points. In this work, we tackle cloth unfolding using a regrasping-in-the-air strategy, where one manipulator holds the cloth while the other grasps it at an optimally selected point to unfold it. To this end, we propose CeDiRNet-6DoF, a deep learning framework that jointly predicts effective grasp points and the complete 6-DoF grasp pose from the observed cloth configuration. By integrating dense 3D grasp regression with segmentation and sine-cosine-encoded Euler angles, the proposed method reliably estimates the grasp configuration that maximizes the unfolded cloth area. We extensively evaluated CeDiRNet-6DoF on a bimanual robotic setup within the ICRA 2024 Cloth Competition framework, achieving state-of-the-art performance. An ablation study further validates the benefits of key design components, including joint segmentation, background randomization, and image cropping. These results establish CeDiRNet-6DoF as a robust and versatile foundation for reliable robotic cloth manipulation in unstructured environments.
Abstract:Cloth manipulation is a challenging task due to the deformable and high-dimensional nature of cloth, which leads to complex interaction dynamics and perceptual ambiguity arising from frequent occlusions of critical visual cues such as folds, edges, and grasp points. In this work, we tackle cloth unfolding using a regrasping-in-the-air strategy, where one manipulator holds the cloth while the other grasps it at an optimally selected point to unfold it. To this end, we propose CeDiRNet-6DoF, a deep learning framework that jointly predicts effective grasp points and the complete 6-DoF grasp pose from the observed cloth configuration. By integrating dense 3D grasp regression with segmentation and sine-cosine-encoded Euler angles, the proposed method reliably estimates the grasp configuration that maximizes the unfolded cloth area. We extensively evaluated CeDiRNet-6DoF on a bimanual robotic setup within the ICRA 2024 Cloth Competition framework, achieving state-of-the-art performance. An ablation study further validates the benefits of key design components, including joint segmentation, background randomization, and image cropping. These results establish CeDiRNet-6DoF as a robust and versatile foundation for reliable robotic cloth manipulation in unstructured environments.
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2609.31452 [cs.RO]
(or arXiv:2609.31452v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.31452 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1109/TCYB.2026.3732543 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 287 words
Related coverage
The Machines that Make the Machines
NVIDIA · Oct 7, 2026
Unlocking Sim2Real for a Robotic Arm with RL Accelerated by AMD Instinct GPUs
AMD · Sep 29, 2026
BRAVE-6D: Benchmark for Robotic Active Vision in 6DOF Pose Estimation
arXiv · Sep 16, 2026
xperception -- Making Robotic Grasping Easier
arXiv · Jul 21, 2026