Title :
Data fusion for compliant motion tasks based on human skills
Author :
Cortesão, Rui ; Koeppe, Ralf ; Nunes, Urbano ; Hirzinger, Gerd
Author_Institution :
Electr. & Comput. Eng. Dept., Coimbra Univ., Portugal
Abstract :
The paper discusses new developments of the data fusion paradigm due to Cortesao and Koeppe (1999, 2000). A bank of Kalman filters is analyzed in the fusion process. Experiments for a robotic compliant motion task (peg-in-hole) emerged from human skills are reported. Stereo vision and pose sense are fused to execute the task. Feedforward artificial neural networks (ANNs) are trained to transfer human skills to robotic manipulators.
Keywords :
Kalman filters; assembling; compliance control; feedforward neural nets; filtering theory; manipulators; robot vision; sensor fusion; stereo image processing; Kalman filters; data fusion; feedforward ANN; feedforward artificial neural networks; human skills; peg-in-hole insertion; pose sensing; robotic compliant motion task; stereo vision; Aerospace engineering; Humans; Information filtering; Information filters; Mechatronics; Robot sensing systems; Sensor phenomena and characterization; State estimation; Stereo vision; Stochastic resonance;
Conference_Titel :
Intelligent Robots and Systems, 2002. IEEE/RSJ International Conference on
Print_ISBN :
0-7803-7398-7
DOI :
10.1109/IRDS.2002.1043972
