Non-Gaussian State Estimation in an Outdoor Decentralised Sensor Network

This paper presents the development and demonstration of non-Gaussian, decentralized state estimation using an outdoor sensor network consisting of an autonomous air vehicle, a manual ground vehicle, and two human operators. The location and appearance of landmarks were estimated using bearing only observations from monocular cameras. We show that inclusion of visual and identity information aids validation gating for data association when geometric information alone cannot discriminate individual landmarks. The combination of geometric, appearance, and identity information provided a common description (or map) of natural features for each of the nodes in the network. We also show the final map from the live demonstration which includes position estimates and classification labels of the observed features

[1]  A.S. Willsky,et al.  Nonparametric belief propagation for self-calibration in sensor networks , 2004, Third International Symposium on Information Processing in Sensor Networks, 2004. IPSN 2004.

[2]  Sumit Roy,et al.  Decentralized structures for parallel Kalman filtering , 1988 .

[3]  Lawrence D. Stone,et al.  Bayesian Multiple Target Tracking , 1999 .

[4]  Antonio Torralba,et al.  Contextual Models for Object Detection Using Boosted Random Fields , 2004, NIPS.

[5]  Yakov Bar-Shalom,et al.  Multitarget-Multisensor Tracking: Principles and Techniques , 1995 .

[6]  R. Muirhead.  Aspects of Multivariate Statistical Theory , 1982, Wiley Series in Probability and Statistics.

[7]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[8]  Stefan B. Williams,et al.  A decentralized architecture for Active Sensor Networks , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[9]  Alexei Makarenko,et al.  Hierarchical Environment Model for Fusing Information from Human Operators and Robots , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Hugh F. Durrant-Whyte,et al.  Closed form solutions to the multiple-platform simultaneous localization and map building (SLAM) problem , 2000, SPIE Defense + Commercial Sensing.

[11]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[12]  Hugh Durrant-Whyte,et al.  Data Fusion and Sensor Management: A Decentralized Information-Theoretic Approach , 1995 .

[13]  Antonio Torralba,et al.  Context-based vision system for place and object recognition , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[14]  H. Durrant-Whyte,et al.  Rich probabilistic representations for bearing only decentralised data fusion , 2005, 2005 7th International Conference on Information Fusion.

[15]  Geoffrey E. Hinton,et al.  The EM algorithm for mixtures of factor analyzers , 1996 .

[16]  Jeffrey K. Uhlmann,et al.  A non-divergent estimation algorithm in the presence of unknown correlations , 1997, Proceedings of the 1997 American Control Conference (Cat. No.97CH36041).

[17]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[18]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[19]  Carlos Guestrin,et al.  Robust Probabilistic Inference in Distributed Systems , 2004, UAI.

[20]  L. Saul,et al.  Think globally, fit locally: unsupervised l earning of non-linear manifolds , 2002 .

[21]  H. Sorenson,et al.  Recursive bayesian estimation using gaussian sums , 1971 .

[22]  Alan S. Willsky,et al.  Mobile agents in adaptive hierarchical Bayesian networks for global awareness , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[23]  Ben Upcroft,et al.  Representing natural objects in unstructured environments , 2005, NIPS 2005.

[24]  David G. Stork,et al.  Pattern Classification , 1973 .

[25]  Dorin Comaniciu,et al.  Kernel-Based Object Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[27]  Alexei Makarenko,et al.  Operators as information sources in sensor networks , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[28]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[29]  Yaakov Bar-Shalom,et al.  Multitarget-multisensor tracking: Advanced applications , 1989 .

[30]  H. Sorenson,et al.  Nonlinear Bayesian estimation using Gaussian sum approximations , 1972 .

[31]  Mark S. Nixon,et al.  Feature Extraction and Image Processing , 2002 .

[32]  Sebastian Thrun,et al.  Decentralized Sensor Fusion with Distributed Particle Filters , 2002, UAI.

[33]  J. Bather,et al.  Mixture Reduction Algorithms for Uncertain Tracking , 1988 .

[34]  Hugh Durrant-Whyte,et al.  Communication In General Decentralised Filters And The Coordinated Search Strategy , 2004 .

[35]  Miles C. Walton,et al.  Collaborative Tools for Mixed Teams of Humans and Robots , 2003 .

[36]  Alexei Makarenko,et al.  Implementation of an Indoor Active Sensor Network , 2004, ISER.

[37]  D. Alspach.  A gaussian sum approach to the multi-target identification-tracking problem , 1975, Autom..

[38]  Jan Nunnink,et al.  A MAS approach to fusion of heterogeneous information , 2005, The 2005 IEEE/WIC/ACM International Conference on Web Intelligence (WI'05).

[39]  H. Nii.  Blackboard Systems , 1998 .