Imperial College London
Alternate

Professor Yiannis Demiris

Faculty of Engineering, Department of Electrical and Electronic Engineering

Professor of Human-Centred Robotics, Head of ISN
 
 
 
//

Contact

 

+44 (0)20 7594 6300y.demiris Website

 
 
//

Location

 

1011Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inbook{Ognibene:2013:10.1007/978-3-642-39875-9_5,
author = {Ognibene, D and Wu, Y and Lee, K and Demiris, Y},
booktitle = {Computational and Robotic Models of the Hierarchical Organization of Behavior},
doi = {10.1007/978-3-642-39875-9_5},
editor = {Baldassarre and Mirolli},
pages = {81--98},
publisher = {Springer},
title = {Hierarchies for embodied action perception},
url = {http://dx.doi.org/10.1007/978-3-642-39875-9_5},
year = {2013}
}
Download

RIS format (EndNote, RefMan)

TY  - CHAP
AB  - During social interactions, humans are capable of initiating and responding to rich and complex social actions despite having incomplete world knowledge, and physical, perceptual and computational constraints. This capability relies on action perception mechanisms that exploit regularities in observed goal-oriented behaviours to generate robust predictions and reduce the workload of sensing systems. To achieve this essential capability, we argue that the following three factors are fundamental. First, human knowledge is frequently hierarchically structured, both in the perceptual and execution domains. Second, human perception is an active process driven by current task requirements and context; this is particularly important when the perceptual input is complex (e.g. human motion) and the agent has to operate under embodiment constraints. Third, learning is at the heart of action perception mechanisms, underlying the agent’s ability to add new behaviours to its repertoire. Based on these factors, we review multiple instantiations of a hierarchically-organised biologically-inspired framework for embodied action perception, demonstrating its flexibility in addressing the rich computational contexts of action perception and learning in robotic platforms.
AU  - Ognibene,D
AU  - Wu,Y
AU  - Lee,K
AU  - Demiris,Y
DO  - 10.1007/978-3-642-39875-9_5
EP  - 98
PB  - Springer
PY  - 2013///
SP  - 81
TI  - Hierarchies for embodied action perception
T1  - Computational and Robotic Models of the Hierarchical Organization of Behavior
UR  - http://dx.doi.org/10.1007/978-3-642-39875-9_5
ER  -
Download