Abstract | ||
---|---|---|
Acquisition of new sensorimotor knowledge by imitation is a promising paradigm for robot learning. To be effective, action learning should not be limited to direct replication of movements obtained during training but must also enable the generation of actions in situations a robot has never encountered before. This paper describes a methodology that enables the generalization of the available sensorimotor knowledge. New actions are synthesized by the application of statistical methods, where the goal and other characteristics of an action are utilized as queries to create a suitable control policy, taking into account the current state of the world. Nonlinear dynamic systems are employed as a motor representation. The proposed approach enables the generation of a wide range of policies without requiring an expert to modify the underlying representations to account for different task-specific features and perceptual feedback. The paper also demonstrates that the proposed methodology can be integrated with an active vision system of a humanoid robot. 3-D vision data are used to provide query points for statistical generalization. While 3-D vision on humanoid robots with complex oculomotor systems is often difficult due to the modeling uncertainties, we show that these uncertainties can be accounted for by the proposed approach. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/TRO.2010.2065430 | IEEE Transactions on Robotics |
Keywords | Field | DocType |
humanoid robots,knowledge representation,motion estimation,nonlinear dynamical systems,robot vision,statistical analysis,3-D vision data,action learning,discrete dynamic movement primitive,humanoid robot,motor representation,nonlinear dynamic system,oculomotor system,perceptual feedback,periodic dynamic movement primitive,robot learning,sensorimotor knowledge,statistical generalization,statistical method,task specific feature,task specific generalization,vision system,Active vision on humanoid robots,humanoid robots,imitation learning,learning and adaptive systems | Robot learning,Active vision,Knowledge representation and reasoning,Machine vision,Computer science,Artificial intelligence,Robot,Knowledge acquisition,Robotics,Humanoid robot | Journal |
Volume | Issue | ISSN |
26 | 5 | 1552-3098 |
Citations | PageRank | References |
121 | 4.16 | 41 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ales Ude | 1 | 898 | 85.11 |
Andrej Gams | 2 | 385 | 29.54 |
tamim asfour | 3 | 1889 | 151.86 |
Jun Morimoto | 4 | 296 | 24.17 |