Cooperative grasping through topological object representation
2015 (English)In: IEEE-RAS International Conference on Humanoid Robots, IEEE Computer Society, 2015, 685-692 p.Conference paper (Refereed)Text
We present a cooperative grasping approach based on a topological representation of objects. Using point cloud data we extract loops on objects suitable for generating entanglement. We use the Gauss Linking Integral to derive controllers for multi-agent systems that generate hooking grasps on such loops while minimizing the entanglement between robots. The approach copes well with noisy point cloud data, it is computationally simple and robust. We demonstrate the method for performing object grasping and transportation, through a hooking maneuver, with two coordinated NAO robots.
Place, publisher, year, edition, pages
IEEE Computer Society, 2015. 685-692 p.
Anthropomorphic robots, Robots, Topology, Noisy point, Object grasping, Point cloud data, Topological objects, Topological representation, Multi agent systems
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-181529DOI: 10.1109/HUMANOIDS.2014.7041437ScopusID: 2-s2.0-84945179216ISBN: 9781479971749OAI: oai:DiVA.org:kth-181529DiVA: diva2:913006
2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014, 18 November 2014 through 20 November 2014
QC 201603182016-03-182016-02-022016-03-18Bibliographically approved