Enabling grasping of unknown objects through a synergistic use of edge and surface information
2012 (English)In: The international journal of robotics research, ISSN 0278-3649, E-ISSN 1741-3176, Vol. 31, no 10, 1190-1213 p.Article in journal (Refereed) Published
Grasping unknown objects based on visual input, where no a priori knowledge about the objects is used, is a challenging problem. In this paper, we present an Early Cognitive Vision system that builds a hierarchical representation based on edge and texture information which provides a sparse but powerful description of the scene. Based on this representation, we generate contour-based and surface-based grasps. We test our method in two real-world scenarios, as well as on a vision-based grasping benchmark providing a hybrid scenario using real-world stereo images as input and a simulator for extensive and repetitive evaluation of the grasps. The results show that the proposed method is able to generate successful grasps, and in particular that the contour and surface information are complementary for the task of grasping unknown objects. This allows for dealing with rather complex scenes.
Place, publisher, year, edition, pages
2012. Vol. 31, no 10, 1190-1213 p.
vision-based grasping, grasping unknown objects, visual scene representation, dexterous hands
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-103144DOI: 10.1177/0278364912452621ISI: 000307838700005ScopusID: 2-s2.0-84865526912OAI: oai:DiVA.org:kth-103144DiVA: diva2:559394
FunderEU, European Research Council, FP7-ICT-270273 FP7-IST-270212ICT - The Next Generation
QC 201210092012-10-092012-10-042013-04-11Bibliographically approved