Exploiting Probabilistic Knowledge under Uncertain Sensing for Efficient Robot Behaviour

Hanheide, Marc; Gretton, Charles; Dearden, Richard; Hawes, Nick; Wyatt, Jeremy L.; Pronobis, Andrzej; Aydemir, Alper; Göbelbecker, Moritz; Zender, Hendrik

doi:10.5591/978-1-57735-516-8/IJCAI11-407

Exploiting Probabilistic Knowledge under Uncertain Sensing for Efficient Robot Behaviour

Marc Hanheide, Charles Gretton, Richard Dearden, Nick Hawes, Jeremy L. Wyatt, Andrzej Pronobis, Alper Aydemir, Moritz Göbelbecker, Hendrik Zender

Download BibTeX Cite

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 2442-2448.

https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-407

Abstract

Robots must perform tasks efficiently and reliably while acting underuncertainty. 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 modelling the uncertaintyin 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 contribution is a probabilistic relational model integrating common-sense knowledge about the world in general, with observations of a particular environment. Our second contribution is a continual planning system which is able to plan in the large problems posed by that model, by automatically switching between decision-theoretic and classical procedures. We evaluate our system on object search tasks in two different real-world indoor environments. By reasoning about the trade-offs between possible courses of action with different informational effects, and exploiting the cues and general structures of those environments, our robot is able to consistently demonstrate efficient and reliable goal-directed behaviour.

Marc Hanheide, Charles Gretton, Richard Dearden, Nick Hawes, Jeremy L. Wyatt, Andrzej Pronobis, Alper Aydemir, Moritz Göbelbecker, and Hendrik Zender. 2011. Exploiting Probabilistic Knowledge under Uncertain Sensing for Efficient Robot Behaviour. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11. IJCAI, 2442–2448. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-407

@inproceedings{ijcai2011p407,
  title     = {Exploiting Probabilistic Knowledge under Uncertain Sensing for Efficient Robot Behaviour},
  author    = {Hanheide, Marc and Gretton, Charles and Dearden, Richard and Hawes, Nick and Wyatt, Jeremy L. and Pronobis, Andrzej and Aydemir, Alper and Göbelbecker, Moritz and Zender, Hendrik},
  booktitle = {Proceedings of the Twenty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-11}},
  publisher = {AAAI Press/International Joint Conferences on Artificial Intelligence},
  editor    = {Toby Walsh},
  pages     = {2442--2448},
  year      = {2011},
  month     = {7},
  doi       = {10.5591/978-1-57735-516-8/IJCAI11-407},
  url       = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-407},
}

TY  - CPAPER
TI  - Exploiting Probabilistic Knowledge under Uncertain Sensing for Efficient Robot Behaviour
AU  - Hanheide, Marc
AU  - Gretton, Charles
AU  - Dearden, Richard
AU  - Hawes, Nick
AU  - Wyatt, Jeremy L.
AU  - Pronobis, Andrzej
AU  - Aydemir, Alper
AU  - Göbelbecker, Moritz
AU  - Zender, Hendrik
T2  - Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11
PB  - AAAI Press/International Joint Conferences on Artificial Intelligence
PY  - 2011
SP  - 2442
EP  - 2448
DO  - 10.5591/978-1-57735-516-8/IJCAI11-407
UR  - https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-407
ER  -