@inproceedings{UpcroftRidleyOngetal., author = {Upcroft, Ben and Ridley, Matthew and Ong, Lee Ling and Douillard, Bertrand and Kaupp, Tobias and Kumar, Suresh and Bailey, Tim and Ramos, Fabio and Makarenko, Alexei and Brooks, Alex and Sukkarieh, Salah and Durrant-Whyte, Hugh F.}, title = {Multi-level state estimation in an outdoor decentralised sensor network}, series = {Experimental Robotics: The 10th International Symposium on Experimental Robotics ; Springer Tracts in Advanced Robotics (STAR, volume 39)}, booktitle = {Experimental Robotics: The 10th International Symposium on Experimental Robotics ; Springer Tracts in Advanced Robotics (STAR, volume 39)}, editor = {Khatib, Oussama and Kumar, Vijay and Rus, Daniela}, publisher = {Springer}, address = {Berlin, Heidelberg}, isbn = {978-3-540-77456-3}, doi = {10.1007/978-3-540-77457-0_33}, pages = {355 -- 365}, abstract = {Decentralised estimation of heterogeneous sensors is performed on an outdoor network. Attributes such as position, appearance, and identity represented by non-Gaussian distributions are used in in the fusion process. It is shown here that real-time decentralised data fusion of non-Gaussian estimates can be used to build rich environmental maps. Human operators are also used as additional sensors in the network to complement robotic information.}, language = {en} } @inproceedings{WangKumarKauppetal., author = {Wang, X. Rosalind and Kumar, Suresh and Kaupp, Tobias and Upcroft, Ben and Durrant-Whyte, Hugh}, title = {Applying ISOMAP to the learning of hyperspectral image}, series = {Australian Conference on Robotics and Automation (ACRA'05)}, booktitle = {Australian Conference on Robotics and Automation (ACRA'05)}, editor = {Sammut, C.}, pages = {1 -- 8}, abstract = {In this paper, we present the application of a non-linear dimensionality reduction technique for the learning and probabilistic classification of hyperspectral image. Hyperspectral image spectroscopy is an emerging technique for geological investigations from airborne or orbital sensors. It gives much greater information content per pixel on the image than a normal colour image. This should greatly help with the autonomous identification of natural and manmade objects in unfamiliar terrains for robotic vehicles. However, the large information content of such data makes interpretation of hyperspectral images time-consuming and userintensive. We propose the use of Isomap, a non-linear manifold learning technique combined with Expectation Maximisation in graphical probabilistic models for learning and classification. Isomap is used to find the underlying manifold of the training data. This low dimensional representation of the hyperspectral data facilitates the learning of a Gaussian Mixture Model representation, whose joint probability distributions can be calculated offline. The learnt model is then applied to the hyperspectral image at runtime and data classification can be performed.}, language = {en} } @inproceedings{KauppMakarenkoKumaretal., author = {Kaupp, Tobias and Makarenko, Alexei and Kumar, Suresh and Upcroft, Ben and Williams, Stefan}, title = {Operators as information sources in sensor networks}, series = {2005 IEEE/RSJ International Conference on Intelligent Robots and Systems}, booktitle = {2005 IEEE/RSJ International Conference on Intelligent Robots and Systems}, publisher = {IEEE}, doi = {10.1109/IROS.2005.1545015}, pages = {936 -- 941}, abstract = {This paper presents an approach of integrating human operators into a sensor network formed by a heterogeneous team of unmanned air and ground vehicles. Several objectives of human-network interaction are identified. The main focus of this work is on human-to-network information flow, i.e. human operators are regarded as information sources. It is argued that operators should make raw observations which are converted into the sensor network's common representation by a probabilistic model. The concepts are discussed in the context of an outdoor sensor network under development. Human operators contribute geometric feature information in the form of range and bearing observations. Visual feature properties are specified via meaningful class labels. A sensor model, represented as a Bayesian network, translates label observations into the system's representation. The model is also used to classify features as observed by robotic sensors.}, language = {en} } @inproceedings{DurrantWhyteSukkariehRamosetal., author = {Durrant-Whyte, Hugh and Sukkarieh, Salah and Ramos, Fabio and Bailey, Tim and Kumar, Suresh and Ong, Lee-Ling and Ridley, Matthew and Kaupp, Tobias and Douillard, Bertrand and Upcroft, Ben}, title = {Non-gaussian state estimation in an outdoor decentralised sensor network}, series = {Proceedings of the 45th IEEE Conference on Decision and Control}, booktitle = {Proceedings of the 45th IEEE Conference on Decision and Control}, publisher = {IEEE}, address = {Piscataway}, doi = {10.1109/CDC.2006.377533}, pages = {366 -- 372}, abstract = {This paper presents the development and demonstration of non-Gaussian, decentralised 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.}, language = {en} } @inproceedings{WangKumarRamosetal., author = {Wang, X. Rosalind and Kumar, Suresh and Ramos, Fabio and Kaupp, Tobias and Upcroft, Ben and Durrant-Whyte, Hugh}, title = {Probabilistic classification of hyperspectral images by learning nonlinear dimensionality reduction mapping}, series = {2006 9th International Conference on Information Fusion}, booktitle = {2006 9th International Conference on Information Fusion}, pages = {1 -- 8}, language = {en} } @inproceedings{UpcroftRidleyOngetal., author = {Upcroft, Ben and Ridley, Matthew and Ong, Lee Ling and Douillard, Bertrand and Kaupp, Tobias and Kumar, Suresh and Bailey, Tim and Ramos, Fabio and Makarenko, Alexei and Brooks, Alex and Sukkarieh, Salah and Durrant-Whyte, Hugh F.}, title = {Multilevel state estimation in an outdoor decentralised sensor network}, series = {10th International Symposium on Experimental Robotics 2006 (ISER'06), Rio de Janeiro, Brazil}, booktitle = {10th International Symposium on Experimental Robotics 2006 (ISER'06), Rio de Janeiro, Brazil}, language = {en} } @inproceedings{WangKumarRamosetal., author = {Wang, X. Rosalind and Kumar, Suresh and Ramos, Fabio and Kaupp, Tobias and Upcroft, Ben and Durrant-Whyte, Hugh F.}, title = {Learning in hyperspectral images using a nonlinear dimensionality reduction technique}, series = {9th International Conference on Information Fusion (Fusion 2006), Florence, Italy}, booktitle = {9th International Conference on Information Fusion (Fusion 2006), Florence, Italy}, language = {en} }