Knowledge-driven world modeling

J. Elfring; S. Dries, van den; M.J.G. Molengraft, van de; J.L.M. Bruyninckx

Knowledge-driven world modeling

J. Elfring, S. Dries, van den, M.J.G. Molengraft, van de, J.L.M. Bruyninckx

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

4 Downloads (Pure)

Abstract

In order to allow safe operation and good performance, robots need an accurate model of their environment. Such a world model is constructed from sensor detections and typically contains information about positions and velocities of surrounding objects. This paper proposes how prior knowledge about those objects can be used to improve the performance of a world model, which is implemented by a Multiple Hypothesis Filter (MHF). More specifically, knowledge about object dynamics, expected locations, relations between object classes and detector characteristics is incorporated in the probabilistic models of the MHF. The results of simulations confirmed the potential of incorporating such object knowledge in a world model.

Original language	English
Title of host publication	Proceedings of the Workshop : Knowledge Representation for Autonomous Robots (IROS 2011), 25-30 September 2011, San Francisco, USA
Publication status	Published - 2011
Event	conference; International Conference on Intelligent Robots and Systems; 2011-09-25; 2011-09-30 - Duration: 25 Sept 2011 → 30 Sept 2011

Conference

Conference	conference; International Conference on Intelligent Robots and Systems; 2011-09-25; 2011-09-30
Period	25/09/11 → 30/09/11
Other	International Conference on Intelligent Robots and Systems

Cite this

@inproceedings{f2678683244b43d28d34a87a03b797b2,

title = "Knowledge-driven world modeling",

abstract = "In order to allow safe operation and good performance, robots need an accurate model of their environment. Such a world model is constructed from sensor detections and typically contains information about positions and velocities of surrounding objects. This paper proposes how prior knowledge about those objects can be used to improve the performance of a world model, which is implemented by a Multiple Hypothesis Filter (MHF). More specifically, knowledge about object dynamics, expected locations, relations between object classes and detector characteristics is incorporated in the probabilistic models of the MHF. The results of simulations confirmed the potential of incorporating such object knowledge in a world model.",

author = "J. Elfring and {Dries, van den}, S. and {Molengraft, van de}, M.J.G. and J.L.M. Bruyninckx",

year = "2011",

language = "English",

booktitle = "Proceedings of the Workshop : Knowledge Representation for Autonomous Robots (IROS 2011), 25-30 September 2011, San Francisco, USA",

note = "conference; International Conference on Intelligent Robots and Systems; 2011-09-25; 2011-09-30 ; Conference date: 25-09-2011 Through 30-09-2011",

}

TY - GEN

T1 - Knowledge-driven world modeling

AU - Elfring, J.

AU - Dries, van den, S.

AU - Molengraft, van de, M.J.G.

AU - Bruyninckx, J.L.M.

PY - 2011

Y1 - 2011

N2 - In order to allow safe operation and good performance, robots need an accurate model of their environment. Such a world model is constructed from sensor detections and typically contains information about positions and velocities of surrounding objects. This paper proposes how prior knowledge about those objects can be used to improve the performance of a world model, which is implemented by a Multiple Hypothesis Filter (MHF). More specifically, knowledge about object dynamics, expected locations, relations between object classes and detector characteristics is incorporated in the probabilistic models of the MHF. The results of simulations confirmed the potential of incorporating such object knowledge in a world model.

AB - In order to allow safe operation and good performance, robots need an accurate model of their environment. Such a world model is constructed from sensor detections and typically contains information about positions and velocities of surrounding objects. This paper proposes how prior knowledge about those objects can be used to improve the performance of a world model, which is implemented by a Multiple Hypothesis Filter (MHF). More specifically, knowledge about object dynamics, expected locations, relations between object classes and detector characteristics is incorporated in the probabilistic models of the MHF. The results of simulations confirmed the potential of incorporating such object knowledge in a world model.

M3 - Conference contribution

BT - Proceedings of the Workshop : Knowledge Representation for Autonomous Robots (IROS 2011), 25-30 September 2011, San Francisco, USA

T2 - conference; International Conference on Intelligent Robots and Systems; 2011-09-25; 2011-09-30

Y2 - 25 September 2011 through 30 September 2011

ER -

Knowledge-driven world modeling

Abstract

Conference

Fingerprint

Cite this