Using depth and appearance features for informed robot grasping of highly wrinkled clothes

By Arnau Ramisa, Guillem Alenyà, Francesc Moreno-Noguer, Carme Torras. 2012

132 citations recorded by the source corpus.

Detecting grasping points is a key problem in cloth manipulation. Most current approaches follow a multiple re-grasp strategy for this purpose, in which clothes are sequentially grasped from different points until one of them yields to a desired configuration. In this paper, by contrast, we circumvent the need for multiple re-graspings by building a robust detector that identifies the grasping points, generally in one single step, even when clothes are highly wrinkled. In order to handle the large variability a deformed cloth may have, we build a Bag of Features based detector that combines appearance and 3D geometry features. An image is scanned using a sliding window with a linear classifier, and the candidate windows are refined using a non-linear SVM and a “grasp goodness” criterion to select the best grasping point. We demonstrate our approach detecting collars in deformed polo shirts, using a Kinect camera. Experimental results show a good performance of the proposed method not only in identifying the same trained textile object part under severe deformations and occlusions, but also the corresponding part in other clothes, exhibiting a degree of generalization.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours (2015, background): “Grasped objects, on being dropped, at times bounce/roll off the robot workspace, however using cluttered environments also ensures that the robot always has an object to grasp.”
Data-Driven Grasp Synthesis—A Survey (2013, methodology): “The following approaches use labeled training examples: [87, 88, 89, 67, 91, 92, 93, 94, 30, 28, 29, 31, 97, 98, 32, 99, 100, 101, 102, 105, 20, 106]”
Robotic manipulation and sensing of deformable objects in domestic and industrial applications: a survey (2018, methodology): “The following works focused on manipulation tasks that consider different starting conﬁgurations for the articles (e.g. crumpled or lying ﬂat).”
Deep Imitation Learning of Sequential Fabric Smoothing Policies (2019, background): “They measure wrinkledness as the average absolute deviation in a local pixel region for each point in a depth map of the fabric [37] and apply a force perpendicular to the largest wrinkle.”