Exploiting probabilistic knowledge under uncertain sensing for efficient robot behaviour

Hanheide, Marc and Gretton, Charles and Dearden, Richard W. and Hawes, Nick A. and Wyatt, Jeremy L. and Goedelbecker, Moritz and Pronobis, Andrzej and Aydemir, Alper and Zender, Hendrik (2011) Exploiting probabilistic knowledge under uncertain sensing for efficient robot behaviour. In: Twenty-Second International Joint Conference on Artificial Intelligence, 16-22 July 2011, Barcelona, Catalonia, Spain.

Documents
Hanheide2011-Exploiting_Probabilistic_Knowledge_under_Uncertain_Sensing_for_Efficient_Robot_Behaviour.pdf
[img]
[Download]
Request a copy
[img] PDF
Hanheide2011-Exploiting_Probabilistic_Knowledge_under_Uncertain_Sensing_for_Efficient_Robot_Behaviour.pdf - Whole Document
Restricted to Repository staff only

1MB

Full text URL: http://dx.doi.org/10.5591/978-1-57735-516-8/IJCAI1...

Abstract

Robots must perform tasks efficiently and reli- ably while acting under uncertainty. One way to achieve efficiency is to give the robot common- sense knowledge about the structure of the world. Reliable robot behaviour can be achieved by mod- elling the uncertainty in the world probabilistically. We present a robot system that combines these two approaches and demonstrate the improvements in efficiency and reliability that result. Our first con- tribution is a probabilistic relational model integrat- ing common-sense knowledge about the world in general, with observations of a particular environ- ment. Our second contribution is a continual plan- ning system which is able to plan in the large prob- lems posed by that model, by automatically switch- ing between decision-theoretic and classical proce- dures. We evaluate our system on object search tasks in two different real-world indoor environ- ments. By reasoning about the trade-offs between possible courses of action with different informa- tional effects, and exploiting the cues and general structures of those environments, our robot is able to consistently demonstrate efficient and reliable goal-directed behaviour.

Item Type:Conference or Workshop Item (Paper)
Additional Information:Robots must perform tasks efficiently and reli- ably while acting under uncertainty. One way to achieve efficiency is to give the robot common- sense knowledge about the structure of the world. Reliable robot behaviour can be achieved by mod- elling the uncertainty in the world probabilistically. We present a robot system that combines these two approaches and demonstrate the improvements in efficiency and reliability that result. Our first con- tribution is a probabilistic relational model integrat- ing common-sense knowledge about the world in general, with observations of a particular environ- ment. Our second contribution is a continual plan- ning system which is able to plan in the large prob- lems posed by that model, by automatically switch- ing between decision-theoretic and classical proce- dures. We evaluate our system on object search tasks in two different real-world indoor environ- ments. By reasoning about the trade-offs between possible courses of action with different informa- tional effects, and exploiting the cues and general structures of those environments, our robot is able to consistently demonstrate efficient and reliable goal-directed behaviour.
Keywords:Robotics, Human-robot interaction
Subjects:H Engineering > H670 Robotics and Cybernetics
Divisions:College of Science > School of Computer Science
ID Code:6756
Deposited By: Marc Hanheide
Deposited On:02 Nov 2012 14:12
Last Modified:04 Dec 2013 16:10

Repository Staff Only: item control page