Loading...
Please wait, while we are loading the content...
Similar Documents
Hierarchies of Coupled Inverse and Forward Models for Abstraction in Robot Action Planning, Recognition and Imitation
| Content Provider | Semantic Scholar |
|---|---|
| Author | Johnson, Matthew Demiris, Yiannis |
| Copyright Year | 2005 |
| Abstract | Coupling internal inverse and forward models gives rise to on-line simulation processes that may be used as a common computational substrate for action execution, planning, recognition, imitation and learning. In this paper, multiple coupled internal inverse and forward models are arranged in a hierarchical fashion, with each level of the hierarchy interacting with other levels through top-down and bottom-up processes. Through experiments involving imitation of a human demonstrator performing object manipulation tasks, this architecture is shown to equip a robot with a multi-level motor abstraction capability. This is then used to solve the correspondence problem in action recognition. The architecture is inspired by biological evidence. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://core.ac.uk/download/pdf/19456309.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
