Space & Terrestrial Autonomous Robotic Systems

Assistant Professor J. Kelly

University of Toronto
Institute for Aerospace Studies
4925 Dufferin St., Ontario, Canada M3H 5T6

Phone: +1-416-667-7708
Fax: +1-416-667-7799
Email: jkelly (at) utias.utoronto.ca
Web: http://starslab.ca/

Education

  • Ph.D. – University of Southern California
  • M.S.  – University of Southern California
  • M.Sc. – University of Alberta
  • B.Sc. – University of Alberta

Awards and Honours

Dean’s Catalyst Professor (2018)
Connaught New Researcher Award (2017)
Science Leadership Program Fellow (2016)

Research Summary

Professor Kelly’s research is focussed on developing robust autonomous systems that are able to operate independently over long durations in challenging environments, for example, in space and on remote planetary surfaces. His team carries out research at the nexus of sensing, planning, and control, with an emphasis on the study of fundamental problems related to perception, representation, and understanding of the world. Prof. Kelly is also interested in ‘bringing space robotics down to Earth,’ by leveraging opportunities for technology transfer from space systems to terrestrial robots.

Prof. Kelly is currently Dean’s Catalyst Professor at UTIAS; this early-career award is designed to promote and accelerate the contributions of the Faculty of Applied Science & Engineering’s most promising junior academic staff. He received his Ph.D. from the University of Southern California, where he was an Annenberg Fellow and was supported in part by a PGS-D award from NSERC Canada. Before moving to UTIAS, he held a postdoctoral appointment in the Robust Robotics Group at the Massachusetts Institute of Technology. Prior to graduate school, he was a Software Engineer in the Space Technologies division of the Canadian Space Agency.

The work in Kelly’s group is motivated by the desire to implement effective autonomy solutions across a broad spectrum of application domains. Specifically, the group seeks to build robots that are:

  • pervasive — widely deployed in assistive roles across the spectrum of human activity (robots everywhere!),
  • persistent — able to operate reliably and independently for long durations, on the order of days, weeks, or more, and
  • perceptive — aware of their environment, and capable of acting intelligently when confronted with new situations and experiences.

Towards these goals, Kelly’s group designs algorithms for an array of sensing devices and robotic platforms. Examples of current research topics include: power-on-and-go sensor systems, energy-aware path planning for planetary rovers, and deep learning methods for reliable navigation under challenging conditions (e.g., extreme lighting and appearance change). The group has recently launched a major initiative in the area of collaborative mobile manipulation for dynamic, shared environments. Theoretical results are verified through rigorous experimental trials, to ensure that the group’s research can be successfully applied in the field.

Applications from talented and enthusiastic students are always welcome. Please visit the STARS Laboratory web site  (http://starslab.ca/) for more information and consider joining us (http://www.starslab.ca/join-us/)!