Publication
Learning algorithms for robot manipulation of clothing and plant leaves
Conference Article
Conference
ICRA Workshop on Advances in Robot Manipulation of Clothes and Flexible Objects (W-CloPeMa)
Edition
2014
Doc link
http://clopemaweb.felk.cvut.cz/2014/02/04/icra2014/
File
Authors
Projects associated
Abstract
Manipulator robots are widening their range of activities in factories, as well as finding increased application in human-centered domains such as healthcare, education, entertainment and services. For robots to become handy co-workers and helpful assistants, quick and user-friendly ways to endow them with flexible manipulation skills are needed. At the Perception and Manipulation Lab of IRI (CSIC-UPC), we are addressing several of the learning challenges arising in this context, especially in handling deformable objects such as clothing, vegetables, and cables. Five types of learning algorithms are being developed and applied: visual object recognition/classification and pose estimation using appearance and depth data, kinematic and dynamic robot model learning, learning manipulation tasks from demonstrations, reinforcement learning of skills, and learning to plan and act. The most representative of these works will be showcased along the presentation.
Categories
intelligent robots, learning (artificial intelligence), planning (artificial intelligence), service robots.
Author keywords
cloth manipulation, robot learning, deformable objects
Scientific reference
C. Torras. Learning algorithms for robot manipulation of clothing and plant leaves, 2014 ICRA Workshop on Advances in Robot Manipulation of Clothes and Flexible Objects, 2014, Hong-Kong.
Follow us!