DocumentCode :
3078145
Title :
Grasp recognition and mapping on humanoid robots
Author :
Do, Martin ; Romero, Javier ; Kjellström, Hedvig ; Azad, Pedram ; Asfour, Tamim ; Kragic, Danica ; Dillmann, Rüdiger
Author_Institution :
Univ. of Karlsruhe (TH), Karlsruhe, Germany
fYear :
2009
fDate :
7-10 Dec. 2009
Firstpage :
465
Lastpage :
471
Abstract :
In this paper, we present a system for vision-based grasp recognition, mapping and execution on a humanoid robot to provide an intuitive and natural communication channel between humans and humanoids. This channel enables a human user to teach a robot how to grasp an object. The system comprises three components: human upper body motion capture system which provides the approaching direction towards an object, hand pose estimation and grasp recognition system, which provides the grasp type performed by the human as well as a grasp mapping and execution system for grasp reproduction on a humanoid robot with five-fingered hands. All three components are real-time and markerless. Once an object is reached, the hand posture is estimated, including hand orientation and grasp type. For the execution on a robot, hand posture and approach movement are mapped and optimized according to the kinematic limitations of the robot. Experimental results are performed on the humanoid robot ARMAR-IIIb.
Keywords :
humanoid robots; image motion analysis; pose estimation; robot vision; ARMAR-IIIb humanoid robot; grasp recognition system; hand pose estimation; human upper body motion capture system; natural communication channel; vision-based grasp recognition; Anthropomorphism; Communication channels; Education; Educational robots; Humanoid robots; Humans; Kinematics; Motion estimation; Robot programming; Robot vision systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Humanoid Robots, 2009. Humanoids 2009. 9th IEEE-RAS International Conference on
Conference_Location :
Paris
Print_ISBN :
978-1-4244-4597-4
Electronic_ISBN :
978-1-4244-4588-2
Type :
conf
DOI :
10.1109/ICHR.2009.5379538
Filename :
5379538
Link To Document :
بازگشت