@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{KauppMakarenkoRamosetal., author = {Kaupp, Tobias and Makarenko, Alexei and Ramos, Fabio and Upcroft, Ben and Williams, Stefan and Durrant-Whyte, Hugh}, title = {Adaptive human sensor model in sensor networks}, series = {2005 7th International Conference on Information Fusion}, volume = {1}, booktitle = {2005 7th International Conference on Information Fusion}, publisher = {IEEE}, doi = {10.1109/ICIF.2005.1591929}, abstract = {This paper presents the design of a probabilistic model of human perception as an integral part of a decentralized data fusion system. The system consists of a team of human operators and robotic platforms, together forming a heterogeneous sensor network. Human operators are regarded as information sources submitting raw observations. The observations are converted into a probabilistic representation suitable for fusion with the system's belief. The conversion is performed by a human sensor model (HSM). The initial HSM is built offline based on an average of multiple human subjects conducting a calibration experiment. Since individual human operators may vary in their performance, an online adaptation of the HSM is required. The network estimate is used for adaptation because the true feature state is unknown at runtime. Results of an outdoor calibration experiment using range and bearing observations are presented. Simulations show the feasibility of efficient online adaptation.}, language = {en} } @article{KauppDouillardRamosetal., author = {Kaupp, Tobias and Douillard, Bertrand and Ramos, Fabio and Makarenko, Alexei and Upcroft, Ben}, title = {Shared environment representation for a human-robot team performing information fusion}, series = {Journal of Field Robotics: Special Issue on Teamwork}, volume = {24}, journal = {Journal of Field Robotics: Special Issue on Teamwork}, number = {11-12}, doi = {10.1002/rob.20201}, pages = {911 -- 942}, abstract = {This paper addresses the problem of building a shared environment representation by a human-robot team. Rich environment models are required in real applications for both autonomous operation of robots and to support human decision-making. Two probabilistic models are used to describe outdoor environment features such as trees: geometric (position in the world) and visual. The visual representation is used to improve data association and to classify features. Both models are able to incorporate observations from robotic platforms and human operators. Physically, humans and robots form a heterogeneous sensor network. In our experiments, the human-robot team consists of an unmanned air vehicle, a ground vehicle, and two human operators. They are deployed for an information gathering task and perform information fusion cooperatively. All aspects of the system including the fusion algorithms are fully decentralized. Experimental results are presented in form of the acquired multi-attribute feature map, information exchange patterns demonstrating human-robot information fusion, and quantitative model evaluation. Learned lessons from deploying the system in the field are also presented. © 2007 Wiley Periodicals, Inc.}, 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{KauppDouillardUpcroftetal., author = {Kaupp, Tobias and Douillard, Bertrand and Upcroft, Ben and Makarenko, Alexei}, title = {Hierarchical environment model for fusing information from human operators and robots}, series = {2006 IEEE/RSJ International Conference on Intelligent Robots and Systems}, booktitle = {2006 IEEE/RSJ International Conference on Intelligent Robots and Systems}, publisher = {IEEE}, doi = {10.1109/IROS.2006.282398}, pages = {5837 -- 5842}, abstract = {This paper considers the problem of building environment models by fusing information gathered by robotic platforms with human perceptual information. Rich environment models are required in real applications for both autonomous operation of robots and to support human decision making. Hierarchical models are well suited to represent complex environments because they: offer multiple abstractions of the available information to support analysis and decision-making, and permit the incorporation of higher-level human observations. The contributions of this paper are two-fold: (1) development of a probabilistic three-level environment model for distributed information gathering, and (2) experimental demonstration of fully decentralized, cooperative human-robot information gathering using an outdoor sensor network comprised of an unmanned air vehicle, a ground vehicle, and two human operators. Several information exchange patterns are presented which qualitatively demonstrate human-robot information fusion}, language = {en} } @inproceedings{DouillardUpcroftKauppetal., author = {Douillard, Bertrand and Upcroft, Ben and Kaupp, Tobias and Ramos, Fabio and Durrant-Whyte, Hugh}, title = {Bayesian filtering over compressed appearance states}, series = {Proceedings of the Australasian Conference on Robotics and Automation (ACRA)}, booktitle = {Proceedings of the Australasian Conference on Robotics and Automation (ACRA)}, abstract = {This paper presents a framework for performing real-time recursive estimation of landmarks' visual appearance. Imaging data in its original high dimensional space is probabilistically mapped to a compressed low dimensional space through the definition of likelihood functions. The likelihoods are subsequently fused with prior information using a Bayesian update. This process produces a probabilistic estimate of the low dimensional representation of the landmark visual appearance. The overall filtering provides information complementary to the conventional position estimates which is used to enhance data association. In addition to robotics observations, the filter integrates human observations in the appearance estimates. The appearance tracks as computed by the filter allow landmark classification. The set of labels involved in the classification task is thought of as an observation space where human observations are made by selecting a label. The low dimensional appearance estimates returned by the filter allow for low cost communication in low bandwidth sensor networks. Deployment of the filter in such a network is demonstrated in an outdoor mapping application involving a human operator, a ground and an air vehicle.}, language = {en} } @inproceedings{KauppBrooksUpcroftetal., author = {Kaupp, Tobias and Brooks, Alex and Upcroft, Ben and Makarenko, Alexei}, title = {Building a software architecture for a human-robot team using the orca framework}, series = {Proceedings 2007 IEEE International Conference on Robotics and Automation}, booktitle = {Proceedings 2007 IEEE International Conference on Robotics and Automation}, publisher = {IEEE}, doi = {10.1109/ROBOT.2007.364051}, pages = {3736 -- 3741}, abstract = {This paper considers the problem of building a software architecture for a human-robot team. The objective of the team is to build a multi-attribute map of the world by performing information fusion. A decentralized approach to information fusion is adopted to achieve the system properties of scalability and survivability. Decentralization imposes constraints on the design of the architecture and its implementation. We show how a component-based software engineering approach can address these constraints. The architecture is implemented using Orca - a component-based software framework for robotic systems. Experimental results from a deployed system comprised of an unmanned air vehicle, a ground vehicle, and two human operators are presented. A section on the lessons learned is included which may be applicable to other distributed systems with complex algorithms. We also compare Orca to the player software framework in the context of distributed systems.}, 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} }