@inproceedings{Johnson:2005,
author = {Johnson, M and Demiris, Y},
pages = {69--76},
publisher = {AISB},
title = {Hierarchies of Coupled Inverse and Forward Models for Abstraction in Robot Action Planning, Recognition and Imitation},
url = {http://www.aisb.org.uk/publications/proceedings/aisb2005/3_Imitation_Final.pdf},
year = {2005}
}

Download

TY  - CPAPER
AB  - 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.
AU  - Johnson,M
AU  - Demiris,Y
EP  - 76
PB  - AISB
PY  - 2005///
SP  - 69
TI  - Hierarchies of Coupled Inverse and Forward Models for Abstraction in Robot Action Planning, Recognition and Imitation
UR  - http://www.aisb.org.uk/publications/proceedings/aisb2005/3_Imitation_Final.pdf
UR  - http://hdl.handle.net/10044/1/12622
ER  - 

Download