Professor G. M. T. D'Eleuterio
University of Toronto
Institute for Aerospace Studies
4925 Dufferin St., Ontario, Canada M3H 5T6
Phone: 1-416-667-7707
Fax: 1-416-667-7799
Email: gabriele.deleuterio (at) utoronto.ca
Web: http://sr.utias.utoronto.ca/
Education
- Ph.D. - University of Toronto
- M.A.Sc - University of Toronto
- B.A.Sc. - University of Toronto
Research Overview
The Moon has not been disturbed by human footprints since 1972. But as we gain a purchase on the new century, we are preparing a return to Earth’s closest celestial neighbor. This time, however, we plan on staying.
Preparation for a permanent lunar habitat will require robotic missions in advance of humans. Robotics have played a key role in space exploration, from the success of Canadarm on the Space Shuttle to Sojourner which made the first tracks on Mars. They will precede us to the planets and planetoids and will, in a very literal sense, pave the way for our return to the Moon. Robots are currently our surrogate explorers but they will eventually become our companions as we begin to take steps farther into the Solar System. To this end, the UTIAS Space Robotics Group has been working on the concept of network robotics (or collective robotics or group robotics as it is also known); that is, a “swarm” of robots working cooperatively to accomplish a common goal or a form of consensus. Such an approach is necessitated by planetary network science where multiple and distributed measurements have to be made simultaneously as in conducting atmospheric or seismology studies. Even geological exploration and the search for extraterrestrial life will benefit from the network approach. Moreover, robot colonies will be required for resource utilization in situ and to construct habitats on alien soil. But the robots must be robust, autonomous and “intelligent.” Herein lies the great challenge not just for space robotics but robotics in general. It is our Group's mission to foster robotic life.
The Space Robotics Group, led by Professor Gabriele D’Eleuterio, has a long history in robotics research for the Canadian space program. Our work dates back to developing general simulation dynamics techniques that were used in the design and development of Canadarm2 for the International Space Station. At present, our Group is participating in the development of a multirobot system for autonomous lunar excavation in support of the planned return to the Moon.
In keeping with its mission, the Group’s research is motivated by biology. The notion of “intelligent robotics” is very much in vogue these days. However, our interpretation of “intelligence” in fact derives from observations and knowledge of the natural world. Our robotic control strategies are founded on neural network architectures that mimic the brain. But, ultimately, what has led to the emergence of intelligent creatures in our world has been the natural process of evolution. Accordingly, we are also working with and developing new algorithms of artificial evolution. Our Group is also seeking to understand better the dynamics of evolution and, in this way, not only do we hope these techniques to have a greater impact on the artificial world of robotics but perhaps we can also give back to the field of biology.
As one of our main interests is multiagent systems, we are also turning our attention to flying robots. We have recently begun an effort to build flying robotic “insects.” But these too are not without potential space application as small flying robots have been proposed for the exploration of Mars. In the end, we are constantly turning to the natural world for inspiration.