Title
Extraction of grasp-related features by human dual-hand object exploration
Abstract
We consider the problem of objects exploration for grasping purposes, specifically in cases where vision based methods are not applicable. A novel dual-hand object exploration method is proposed that takes benefits from a human demonstration to enrich knowledge about an object. The user handles an object freely using both hands, without restricting the object pose. A set of grasp-related features obtained during exploration is demonstrated and utilized to generate grasp oriented bounding boxes that are basis for pre-grasp hypothesis. We believe that such exploration done in a natural and user friendly way creates important link between an operator intention and a robot action.
Year
Venue
Keywords
2009
ICAR: 2009 14TH INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS, VOLS 1 AND 2
robots,accuracy,computer science,hardware,shape,machine vision,robustness,tactile sensors,friction,feature extraction,object recognition,meteorology
Field
DocType
Citations 
Object detection,Computer vision,GRASP,Method,Machine vision,Feature extraction,Artificial intelligence,User Friendly,Engineering,Robot,Cognitive neuroscience of visual object recognition
Conference
3
PageRank 
References 
Authors
0.46
12
4
Name
Order
Citations
PageRank
Krzysztof Charusta130.46
Dimitar Dimitrov237649.21
Achim J. Lilienthal31468113.18
Boyko Iliev411111.46