TY - GEN
T1 - Articulated object modeling based on visual and haptic observations
AU - Wang, Wei
AU - Koropouli, Vasiliki
AU - Lee, Dongheui
AU - Kühnlenz, Kolja
PY - 2013
Y1 - 2013
N2 - Manipulation of articulated objects constitutes an important and hard challenge for robots. This paper proposes an approach to model articulated objects by integrating visual and haptic information. Line-shaped skeletonization based on depth image data is realized to extract the skeleton of an object given different configurations. Using observations of the extracted object's skeleton topology, the kinematic joints of the object are characterized and localized. Haptic data in the form of task-space force required to manipulate the object, are collected by kinesthetic teaching and learned by Gaussian Mixture Regression in object joint state space. Following modeling, manipulation of the object is realized by first identifying the current object joint states from visual observations and second generalizing learned force to accomplish the new task.
AB - Manipulation of articulated objects constitutes an important and hard challenge for robots. This paper proposes an approach to model articulated objects by integrating visual and haptic information. Line-shaped skeletonization based on depth image data is realized to extract the skeleton of an object given different configurations. Using observations of the extracted object's skeleton topology, the kinematic joints of the object are characterized and localized. Haptic data in the form of task-space force required to manipulate the object, are collected by kinesthetic teaching and learned by Gaussian Mixture Regression in object joint state space. Following modeling, manipulation of the object is realized by first identifying the current object joint states from visual observations and second generalizing learned force to accomplish the new task.
KW - Articulated object modeling
KW - Object skeletonization
KW - Vision-based articulated object manipulation
UR - http://www.scopus.com/inward/record.url?scp=84878246393&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84878246393
SN - 9789898565471
T3 - VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications
SP - 253
EP - 259
BT - VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications
T2 - 8th International Conference on Computer Vision Theory and Applications, VISAPP 2013
Y2 - 21 February 2013 through 24 February 2013
ER -