Keynote Lectures
Dieter Fox:
Activity Recognition From Wearable Sensors
Tuesday July 1, 9:00
Abstract
Recent advances in wearable sensing and computing devices and in fast, probabilistic inference techniques make possible the fine-grained estimation of a person's activities over extended periods of time. In this talk I will show how dynamic Bayesian networks and conditional random fields can be used to estimate the location and activity of a person based on information such as GPS readings or WiFi signal strength. Our models use multiple levels of abstraction to bridge the gap between raw sensor measurements and high level information such as a user's mode of transportation, her current goal, and her significant places (e.g. home or work place). I will also present work on using RFID tags or a wearable multi-sensor system to estimate a person's fine-grained activities.
This is joint work with Brian Ferris, Lin Liao, Don Patterson, Alvin Raj, Amarnag Subramanya, Jeff Bilmes, Gaetano Borriello, and Henry Kautz.
Biography
Dieter Fox is Associate Professor and Director of the Robotics and State Estimation Lab in the Computer Science & Engineering Department at the University of Washington, Seattle. He obtained his Ph.D. from the University of Bonn, Germany. Before joining UW, he spent two years as a postdoctoral researcher at the CMU Robot Learning Lab. Dieter's current research focuses on probabilistic state estimation with applications in robotics and activity recognition.
Hugh F. Durrant-Whyte:
Maximal Information Systems
Wednesday, July 2, 9:00
Abstract
Information provides a quantitative metric for describing the value of individual systems components in autonomous systems tasks such as tracking, mapping and navigation, search and exploration; tasks in which the objective is information gain in some form. An information model is an abstraction of system capabilities in an anonymous form which allows a priori reasoning on the system itself. By construction, information measures have properties of composability and additivity and thus provides a natural means of modelling and describing large scale systems of systems.
This talk will begin by describing how information measures arise naturally in autonomous tracking, mapping and navigation, search and exploration tasks. It is then demonstrated that the performance of individual sensors and platforms can be modelled using these information measures and that system-level performance metrics can be computed. These ideas are illustrated in a series of tasks involving mixed air and ground autonomous systems. These include flight-tests of cooperative UAVs engaged in tracking and navigation tasks, mixed UAV, ground vehicles and human operatives, engaged in mapping and picture compilation operations, and operations involving multi-platform search in constrained environments. In each, it is shown how information provides both a performance metric and design objective underpinning large-scale systems of systems operation.
Biography
Hugh Durrant-Whyte received the B.Sc. in Nuclear Engineering from the University of London, U.K., in 1983, and the M.S.E. and Ph.D. degrees, both in Systems Engineering, from the University of Pennsylvania, U.S.A., in 1985 and 1986, respectively. From 1987 to 1995, he was a Lecturer in Engineering Science, at the University of Oxford, U.K. From 1995 to 2002 he was Professor of Mechatronic Engineering at University of Sydney. In 2002 he was awarded an inaugural Australian Research Council (ARC) Federation Fellowship. He also now leads the ARC Centre of Excellence in Autonomous Systems. His research work focuses on autonomous vehicle navigation and decentralised data fusion methods. His work in applications includes automation in cargo handling, mining, defence, and marine systems. He has published over 300 technical papers and has won numerous awards and prizes for his work. He is a Fellow of the Academy of Technical Sciences, a Fellow of the IEEE and an IEEE Robotics Society Distinguished Lecturer.
Henk A. P. Blom:
Air Traffic Collision Risk Modelling, Analysis and Rare Event Simulation
Thursday, July 3, 9:00
Abstract
Fault and event trees are the dominantly used safety risk models in air traffic. However, the combination of concurrent, dynamic and random effects cannot properly be captured by these classical techniques. In this lecture it will be explained how safety risk modeling and analysis can be formulated as a problem of estimation rare event probability of a large scale stochastic hybrid system. This formulation allows using stochastic hybrid modeling, analysis and particle system tools that have proven their power in multi-sensor multi-target data fusion. In addition to exploiting this similarity, the complementary challenge is to estimate rare events. The modelling and analysis approaches in handling this will be explained and illustrated for air traffic examples, and includes a benchmark versus fault/event trees.
Biography
Henk Blom is principal scientist at National Aerospace Laboratory NLR in Amsterdam, The Netherlands. He holds a PhD from Delft University of Technology on the thesis “Bayesian estimation for decision-directed stochastic control”, and has over twenty five years experience in stochastic modeling and analysis with application towards data fusion and safety risk in air traffic management. He is (co-)author of over 100 articles in scientific journals, books and conference proceedings, and of the volume “Stochastic Hybrid Systems, Theory and Safety Critical Systems”, Springer, 2006. Dr. Blom is Fellow of the IEEE.