Speaker name:

Hugh Durrant-Whyte

Affiliation:

University of Sydney

Title:

Autonomous Mobile Sensor Networks

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.

Biodata:

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, 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.

Speaker name:

Mohan Trivedi

Affiliation:

Laboratory for Intelligent and Safe Automobiles
University of California at San Diego

Title:

Holistic Perception and Dynamic Displays for Active Safety

Abstract:

The primary goal of intelligent driver support systems should be to provide effective warnings and alarms to the drivers to enhance safe driving. We will discuss multidisciplinary research activities focused on the design and evaluation of new types of Intelligent Driver Support Systems and their components. Systematic efforts to understand and characterize driver behavior and ethnography surrounding the task of driving are essential in the development of human-centric driver assistance systems. Novel instrumented vehicles are used for conducting experiments, where the rich contextual information about vehicle dynamics, surround and driver state are captured for careful, detailed ethnographic studies, as well as realistic data for developing algorithms to analyze multi sensory signals for active safety. In this presentation, we will provide a systems-oriented framework for developing multimodal sensing, inferencing algorithms and human-vehicle interfaces for safer automobiles. We will consider three main components of the system, driver, vehicle, and vehicle surround. We will discuss various issues and ideas for developing models for these main components as well as activities associated with the complex task of safe driving. The presentation will include discussion of novel sensory systems and algorithms for capturing not only the dynamic surround information of the vehicle but also the state, intent and activity patterns of drivers. We will also introduce a new type of visual display called "dynamic active display". These displays present visual information to the driver where driving view and safety-critical visual icons are presented to the driver in a manner that minimizes deviation of her gaze direction without adding to unnecessary visual clutter. These contributions indicate the basic promise the "human-centric active safety" (HCAS) systems in enhancing the safety and comfort of automobile based travel.

Biodata:

Mohan Manubhai Trivedi is a Professor of Electrical and Computer Engineering and the founding Director of the Computer Vision and Robotics Research Laboratory at the University of California in San Diego. Trivedi has a broad range of research interests in the intelligent systems, computer vision, intelligent ("smart") environments, intelligent vehicles and transportation systems and human-machine interfaces areas. In partnership with several automobile companies, he established the Laboratory for Intelligent and Safe Automobiles ("LISA") at UCSD to pursue a multidisciplinary research agenda. Mohan served on the Executive Committee of the California Inst. for Telecommunication and Information Technologies [Cal-IT2] as the leader of the Intelligent Transportation and Telematics Layer at UCSD and he is elected Vice-Chair of the University of California System Wide UC Discovery Digital Media Program. Trivedi was the Editor-in-Chief of the Machine Vision and Applications (1996-2004) and is an Editor of the IEEE Transactions on Intelligent Transportation Systems. He served as the Chairman of the Robotics Technical Committee of the IEEE Computer Society and Program Co-Chair of the 2006 IEEE Intelligent Vehicles Symposium. Trivedi has received the Distinguished Alumnus Award from the Utah State University, Pioneer Award (Technical Activities) and Meritorious Service Award from the IEEE Computer Society. Mohan serves regularly as a consultant to industry and government agencies in the USA and abroad.

Speaker name:

Ronald Mahler

Affiliation:

Lockheed Martin

Title:

Random set information fusion: State of the art

Abstract:

The emergence of unconventional defense and security challenges has greatly increased the need for fusing and exploiting unconventional and highly disparate forms of information, ranging from radar to attributes, features, natural-language statements, and inference rules. Finite-set statistics (FISST) is the result of a decade-long effort to address such challenges. It is a seamless, systematic, and novel extension of formal Bayes modeling and the recursive Bayes filter to multitarget and non-traditional information. This seamless unification includes: (1) a unified theory of measurements; (2) unified mathematical representation of uncertainty, including randomness, imprecision, vagueness, ambiguity, contingency, etc.; (3) a unified single- and multi-target modeling methodology based on generalized likelihood functions; (4) a unification of much of expert systems theory, including fuzzy, Bayes, Dempster-Shafer, and rule-based techniques; (5) unified and optimal multitarget detection and estimation; (6) unified and optimal fusion of disparate information; and (7) a systematic multitarget calculus for devising principled new approximation strategies such as the so-called PHD and CPHD filters. FISST has attracted much international interest in a relatively short time. FISST-based research efforts are in progress in at least a dozen nations. FISST-based algorithms are being or have been investigated under more than a dozen basic and applied R&D contracts from U.S. Department of Defense agencies such as the Army Research Office (ARO), the Air Force Office of Scientific Research (AFOSR), the Navy SPAWAR Systems Center, the Missile Defense Agency (MDA), the Defense Advanced Research Projects Administration (DARPA), and four different sites of the Air Force Research Laboratory (AFRL). Typical applications to which FISST is being applied include passive-acoustic target identification, multitarget detection and tracking, group and cluster tracking, distributed multitarget tracking, multistatic tracking, bearing-only tracking, multi-user detection in communications networks, sensor management, management of dispersed mobile sensors, robust automatic target recognition, and scientific performance evaluation. In this presentation I briefly summarize the current state of art, practice, and application of random set information fusion techniques.

Biodata:

Since 1991 Dr. Mahler's research has been focused on data fusion, expert systems, multitarget tracking, sensor management, nonlinear filtering, random set theory, and conditional event algebra. Since 1994 his primary work has been based on "finite-set statistics," a mathematically rigorous random set-based extension of ordinary statistics to multitarget, multisensor problems. He has applied this theory to develop a unified, probabilistic approach to data fusion, and has transitioned this work into a number of DoD applied R&D projects. This work includes a unified expert-systems theory, and a fundamentally new paradigm for multitarget detection and tracking called the "PHD/CPHD filter." His research is being pursued by other research teams in several nations, including Australia, Britain, Canada, Finland, Germany, Italy, Spain, and the U.S. The Swedish Defence Research Agency (FOI) has mounted a serious effort.

Since 1995 he has authored five dozen papers, two books, and one monograph in such subjects, including ten journal papers. His latest book is Statistical Multisource-Mulititarget Information Fusion, published by Artech House Publishers in March 2007. He was principal organizer, co-chair, and proceedings co-editor (Springer-Verlag 1997) for an Aug. 1996 scientific workshop on random sets, jointly sponsored by ONR, USARO, and LMTS. He has been invited to serve on technology planning workshops for AFRL/IF, BMDO/POET, SPAWAR SSC, and for the Electronics Division of the Army Research Office, and as a reviewer of the DARPA Dynamic Data Base (DDB) project.

He has been invited to speak at many conferences, universities, and DoD labs, including Harvard, Johns Hopkins, the University of Massachusetts (Amherst), the USAF Institute of Technology, SPAWAR Systems Center, the USAF Correlation and Tracking Symposium, the IEEE Conference on Decision and Control, the SPIE AeroSense Conference, and the National Symposium on Sensor and Data Fusion.

In particular, he has given an invited two-day tutorial in February 2002 at the International Conference on Information, Decision, and Control (Adelaide, Australia); a half-day invited tutorial at the 2002 International Conference on Information Fusion (Annapolis); a one-hour invited tutorial at the IEEE Workshop on Multitarget Tracking (Madison WI); an invited tutorial in the Jan. 2004 IEEE Aerospace and Electronic Systems Magazine; and a plenary keynote presentation at the 2004 International Conference on Information Fusion (Stockholm).

Speaker name:

Alex Zelinsky

Affiliation:

Director of the CSIRO ICT Centre

Title:

Real World Problems Driving a Multi-Disciplinary Approach to Sensor Network Solutions

Abstract:

Australia like many countries around the world is facing major challenges associated with the environment particularly around the sustainable use of natural resources - water and energy. Industries such as agriculture which account for a significant portion of the GDP in most developed countries must adapt to the new circumstances. However, managing farms, particularly large-scale extensive farming systems, is hindered by lack of data and increasing shortage of labour. Wireless sensor networks is a key technology for the next generation of environmental monitoring and management systems that for the farms of tomorrow.

CSIRO has developed Sensor Networks technology with high reliability. Our technology has shown two years of continuous outdoor operations in an ad-hoc network that has faced diverse weather conditions. Building such systems helped solve the problem of how to program and deploy much larger wireless sensor networks. Systems are now being deployed that do real work in agricultural applications. One example includes monitoring salinity in irrigation. The sensor network advises local sugar cane farmers of the point at which water becomes too saline to use for irrigation, thus saving water, time, money and crops. Another major area of applications for sensor networks is the monitoring and management of water resources. Knowing how much water is available is important to determine appropriate usage patterns for irrigation while maintaining environment flows. To support a broad range of monitoring tasks reliability is essential. Our sensor networks can measures environmental variables such as temperature, soil moisture, water quality, humidity and solar energy levels. Charged by miniature solar panels, these sensor nodes can exchange data to deliver it back to a central database for analysis.

We have recently deployed a large heterogeneous sensor network on a working farm to explore sensor network applications. The current deployment consists of over 40 moisture sensors that provide soil moisture profiles at varying depths, weight sensors to compute the amount of food and water consumed by animals, electronic tag readers, up to 40 sensors that can be used to track movement of cattle (consisting of GPS, compass and accelerometers), and 20 sensor/actuators that can be used to apply different stimuli (audio, vibration and mild electric shock) to the animals. The static part of the network is designed for 24/7 operation and is linked to the Internet via a dedicated high-gain radio link, also solar powered. The initial goals of the deployment are to provide a test bed for sensor network research in programmability and data handling while also being a vital tool for scientists to study animal behaviour. Our longer term aim is to create a management system that completely transforms the way farms are managed.

This talk will discuss the sensor network platforms that have developed at CSIRO and how the challenges posed by real world application problems are driving the technology solutions.

Biodata:

Dr Alex Zelinsky is Director of the CSIRO ICT Centre. With 250 research professionals, the Centre is responsible for developing Information and Communication Technologies that deliver the benefits of innovation to industry and position Australia to compete globally. The centre has developed a world class technology platform for sensor networks. The platform is being applied to underpin cross-disciplinary research across the CSIRO - particularly in distributed energy, health, agriculture and environment applications.

Prior to joining CSIRO in July 2004, Dr Zelinsky was Chief Executive Officer and Founder of Seeing Machines Pty Limited and a Professor at the Australian National University in the Research School of Information Sciences and Engineering. He is extensively published and is internationally recognised as a leader in the fields of Robotics and Computer Vision. Dr Zelinsky is well known for the commercialisation of his ground-breaking research into computer vision systems.

Dr Zelinsky has worked in the computer industry and has had extensive experience developing leading edge technologies for global markets. He has received numerous national and international awards for his work including:

• Australian Engineering Excellence Awards (1999, 2001)
• Australian Eureka Science Prize (2002)
• US R&D magazine Top 100 Award (2002).

In 2002-2004 Dr. Zelinsky was selected as a Technology Pioneer by the World Economic Forum. He is a Fellow of the Academy of Technological Sciences and Engineering. In 2005 Dr Zelinsky was awarded a Clunies Ross Award for Science and Technology Innovation.

Dr Zelinsky serves as a Director on the Board of Funnelback Pty Limited and Epicorp Limited - a leading incubator of ICT technology. He is also a contributor to Australian ICT industry and government advisory boards, and a member of the AEEMA - ICT Australia Board of Management, and a member of the ICT Advisory Board to the Federal Minister for Communications, Information Technology and the Arts, Senator Helen Coonan.