Paper Info
Title
Belief modelling for situation awareness in human-robot interaction
Abstract
To interact naturally with humans, robots need to be aware of their own surroundings. This awareness is usually encoded in some implicit or explicit representation of the situated context. In this paper, we present a new framework for constructing rich belief models of the robot's environment. Key to our approach is the use of Markov Logic as a unified framework for inference over these beliefs. Markov Logic is a combination of first-order logic and probabilistic graphical models. Its expressive power allows us to capture both the rich relational structure of the environment and the uncertainty arising from the noise and incompleteness of low-level sensory data. The constructed belief models evolve dynamically over time and incorporate various contextual information such as spatio-temporal framing, multi-agent epistemic status, and saliency measures. Beliefs can also be referenced and extended “top-down” via linguistic communication. The approach is being integrated into a cognitive architecture for mobile robots interacting with humans using spoken dialogue.
Year
DOI
Venue
2010
10.1109/ROMAN.2010.5598723
Viareggio
Keywords
Field
DocType
Markov processes,belief networks,cognitive systems,formal logic,human-robot interaction,mobile robots,multi-agent systems,speech-based user interfaces,Markov Logic,belief model,belief modelling,cognitive architecture,first order logic,human robot interaction,low level sensory data,mobile robots,multi-agent epistemic status,probabilistic graphical model,situation awareness,spatio temporal framing,spoken dialogue
Situated,Inference,Computer science,Multi-agent system,First-order logic,Artificial intelligence,Graphical model,Probabilistic logic,Cognitive architecture,Mobile robot
Conference
ISSN
ISBN
Citations 
1944-9445
978-1-4244-7991-7
12
PageRank 
References 
Authors
0.87
18
3
Name
Order
Citations
PageRank
Pierre Lison114612.35
Carsten Ehrler2120.87
Geert-Jan M. Kruijff347146.51