Goal-directed imitation for robots: A bio-inspired approach to action understanding and skill learning
| Autor: | Wolfram Erlhagen, Albert Mukovskiy, Giorgio Panin, H.T. van Schie, Estela Bicho, Alois Knoll, Harold Bekkering, C. Kiss |
|---|---|
| Přispěvatelé: | Universidade do Minho |
| Rok vydání: | 2006 |
| Předmět: |
0209 industrial biotechnology
Computer science General Mathematics media_common.quotation_subject Control (management) action sequence 02 engineering and technology Goal inference 03 medical and health sciences 020901 industrial engineering & automation 0302 clinical medicine Robustness (computer science) Control theory Mirror neuron dynamic field mirror neurons media_common Science & Technology business.industry Action intention and motor control Imitation learning Computer Science Applications ddc Action (philosophy) Control and Systems Engineering Robot Action understanding Artificial intelligence Cognitive imitation Imitation business 030217 neurology & neurosurgery Software |
| Zdroj: | Robotics and Autonomous Systems, 54, 353-360 Robotics and Autonomous Systems, 54, 5, pp. 353-360 Repositório Científico de Acesso Aberto de Portugal Repositório Científico de Acesso Aberto de Portugal (RCAAP) instacron:RCAAP |
| ISSN: | 0921-8890 |
| Popis: | In this paper we present a robot control architecture for learning by imitation which takes inspiration from recent discoveries in action observation/execution experiments with humans and other primates. The architecture implements two basic processing principles: 1) imitation is primarily directed toward reproducing the goal/end state of an observed action sequence, and 2) the required capacity to understand the motor intention of another agent is based on motor simulation. The control architecture is validated in a robot system imitating in a goal-directed manner a grasping and placing sequence displayed by a human model. During imitation, skill transfer occurs by learning and representing ppropriate goal-directed sequences of motor primitives. After having established computational links between the representations of goal and means, further knowledge about the meaning of objects is transferred (“where to place specific objects”). The robustness of the goal-directed organization of the controller is tested in the presence of incomplete visual information and changes in environmental constraints. European grant ArteSImit (IST-2000-29686) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect