Publication: Unified fusion system based on bayesian networks for autonomous mobile robots
Loading...
Full text at PDC
Publication Date
2002-12-31
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Int Soc Information Fusion
Citations
Exportar
Abstract
A multisensor fusion system that is usedfor estimating the location of a robot and the state of the objects around is presented. The whole fusion system has been implemented as a Dynamic Bayesian Networks (DBN) with the purpose of having a homogenous and formalized way of capturing the dependencies that exist between the robot location, the state of the environment, and all the sensorial data. At this stage of the research it consists of two independent DBNs, one for estimating the robot location and another for building an occupancy probabilistic map of the environment, which are the basis of a unified fusion system. The dependencies of the variables and information in the two DBN will be captured by a unique DBN constructed by adding arcs (and nodes if necessary) between the two DBN. The DBN implemented so far can be used in robots with different sets of sensors.
Description
ISF © 2002. International Conference on Information Fusion (Fusion 2002) (5º. 8-11 Jul, 2002. Annapolis, Maryland, EEUU)
UCM subjects
Unesco subjects
Keywords
Citation
[l] RC. Luo & M.G. Kay. Multisensor Integration and Fusion for Intelligent Machines and Systems. Ablex Publishing, 1995.
[2] M.A. Abidi, R.C. Gonzalez. The use of Multisensor Data for Robotic Application IEEE Transactions on Robotics and Automation, Vol. 6, No 2,1992.
[3] W. Burger amd B. Bhanu. Qualitative motion understanding. Kluver Academic Publishers. Massachusetts 1992.
[4] S. Thrun, W. Burgard, D. Fox. A probabilistic approach for concurrent mapping and localization for mobile robots. Machine Learning, 31:29-53, 1998.
[5] Learning in Graphical Models. Ed. by Michael 1. Jordan. The MIT Press, Cambridge MassachW 1999.
[6] Finn V. Jensen. An Introduction to Bayesian Networks. Springer-Verlag New York 1996
[7] P. lbarguengoytia, L.E. Sucar, S. Vadera. A Probabilistic Model for Sensor Validation. Proc. 12th Conference on Uncertainty in Artificial Intelligence, Portland, Morgan-Kaufmann, San Mateo, CA. 1996.
[8] J.M. Regh, K.P. Murphy, P.W. Fieguth. Vision-Based Speaker Detection Using Bayeslan Networks. Computer Vision and Pattern Recognition (CVPR99), Ft Collins, CO, June 1999
[9] J. Sherrah, S. Gong. Tracking Discontinuous Motion using Bayesian Inference. Proc. of the 6th European Conference on Computer Vision. Dublin. 2000
[10] J.A. López-Orozco, J.M de la Cruz, J. Sanz , J. Flores. Multisensor Fusion Environment Measures Using Bayesian Networks. Proc. of the Int. Conf on Multisource-Multisensom Information Fusion. Las Vegas, USA. 1998.
[11] K.P. Murphy. Bayesian Map Learning in Dynamic Environments. NIPS 99. Neural Info. Proc. Systems. 1999
[12] AE. Nicholson, JM. Brady. Qmamic Belief Networks for Discrete Monitoring. IEEE Trans. OIL System, Man and Cybernetics. Vol 24, NO 11, Noviembre 1994.
[13] K.P. Murpy. Filtering and Smoothing in Linear Dynamical System using the Junction Tree Algorithm. Technical Report, CS-Berkeley
[14] J.A. Lopez-Orozco, J.M. de la Cruz, E. Besada, P. Ruiperez. An Asynchronous, Robust and Distibutd Multisensor Fusion System for Mobile Robots. The International Joumal of Robotics Research. Vol 19, No. 10. October 2000.
[15] A.G.O. Mutambara. Decenlralizd Estimation and Control fur Multisensor Systems. CRC Press 1998.
[I6] J.A. López-Orozco, J.M. de la Cruz, E. Domínguez, E. Besada, 0.R Polo. An Open Sensing Architecture to Autonomous Mobile Robots. Proc. of the IEEE Int. Symp. on Computational Intelligence in Robotics and Automation (CIRA). ISCI/CIRA/ISAS Joint Conference. Gaithersburg, MD 1998.