Research · 5 Oct 2026 · Peer-reviewed / confirmed

Fuzzy decision network helps a robot arm pick single items from tangled fabric piles

Purpose: sending the RankedRobot digest. Nothing else; never sold or shared for marketing.
What we keep: your email address, the date you signed up and the page you signed up on.
How long: until you unsubscribe, when the address is deleted. Before the first issue we email you once to confirm; addresses not confirmed within 30 days are deleted.
Who processes it: stored with Cloudflare, our host, which may process it outside your country. We'll name our email-sending provider in the privacy notice before the first issue.
Your choice: you don't have to subscribe; the only effect of saying no is that you won't get the digest. Unsubscribe any time.

Authors of a Frontiers in Robotics and AI paper report a 93.3% grasp success rate on randomly stacked fabric.

Researchers at South China University of Technology and Guangdong Ocean University have published a method for picking items out of piles of entangled fabric in Frontiers in Robotics and AI.

The approach finds convex, graspable bulges in a 3D point cloud from a depth camera, generates candidate grasp poses from them, then ranks the candidates with a hierarchical fuzzy neural network designed to imitate how people weigh options. The authors say this keeps the choice interpretable.

On their own fabric dataset, the authors report modest gains over the best baseline: 1.3%, 0.3% and 0.7% in grasp feasibility, separation and reliability. In robot trials on randomly stacked fabric, they report a 93.3% grasping success rate. The paper does not name the arm or gripper model, and we did not find the number of trials.

Sources

Frontiers in Robotics and AI (article, DOI 10.3389/frobt.2026.1917009)

Written by the RankedRobot news desk (AI-assisted, human-reviewed) from the sources above; checked 2026-10-20. Claims are attributed to whoever makes them. Spotted an error? corrections@rankedrobot.com