Author Archives: Jonathan Kelly

Prof. Kelly joins Schwartz Reisman Institute as Faculty Affiliate

Robotics and AI hold tremendous potential to transform society for the better. But, with great power comes great responsibility, to ensure that these technologies are used for societal good. Prof. Kelly is now a Faculty Affiliate at the Schwartz Reisman Institute for Technology and Society (starting in September 2021), and is excited to further the mission of the SRI: “To deepen our knowledge of technologies, societies, and what it means to be human by integrating research across traditional boundaries and building human-centred solutions that really make a difference. We want to make sure powerful technologies truly make the world a better place – for everyone.”

Prof. Kelly to serve on IEEE Transactions on Robotics Editorial Board

Starting August 1, 2021, Prof. Kelly will serve as an Associate Editor for the IEEE Robotics and Automation Society’s Transactions on Robotics. The IEEE T-RO publishes research papers that represent major advances in the state-of-the-art in all areas of robotics and welcomes original papers that report on any combination of theory, design, experimental studies, analysis, algorithms, and integration and application case studies involving all aspects of robotics. T-RO citation statistics from Clarivate analytics, released June 2020, list an impact factor of 6.123 (#2 in robotics).

How do rovers drive safely on Mars? Online livestream talk May 12, 2021 as part of NSERC Science Odyssey

We’re delighted to announce that STARS Laboratory student Olivier Lamarre will present a public talk on May 12, 2021 as part of the NSERC Science Odyssey Festival! Olivier will describe how rovers navigate safely on Mars – the talk is for all ages, no technical background required! Olivier is a NASA JPL veteran who has spent time there as a visiting researcher and internship student, working on rover path planning. You can watch the free livestream via this link:

Two papers on learning and calibration for navigation to appear at ICRA 2021

We’re excited to be present two new papers at ICRA 2021 in Xi’an, China! Our first paper describes a learning-based technique to adjust camera gain and exposure parameters to maximize the number of inlier feature matches for visual motion estimation under challenging lighting conditions. We demonstrate successful navigation through road tunnels – a situation where competing algorithms, and built-in auto-exposure and automatic gain adjustment, fail. Grab the preprint here:; this work will appear in RA-L and at ICRA.

Our second paper presents a continuous-time approach for extrinsic calibration of cameras and 3D millimetre-wave radar sensors. This research, carried out in partnership with the LAMOR group at the University of Zagreb, enables accurate in-field calibration without the need for radar retroreflectors or specialized visual targets. Grab the preprint here:

Please join us for the presentation sessions at ICRA to learn more!

Traversability Uncertainty poster wins 1st Prize at IROS 2020 Workshop on Planetary Exploration Robots!

Congratulations to Ph.D. student Olivier Lamarre and postdoc Ahmad Bilal Asghar on winning 1st prize at the IROS 2020 Workshop on Planetary Exploration Robots! The associated short abstract describes considerations related to traversability uncertainty for long-duration rover navigation planning on remote planetary surfaces. Great work! Thanks to Moog for sponsoring the award!

Prof. Kelly to serve on IEEE Robotics & Automation Magazine Editorial Board

Starting January 1, 2021, Prof. Kelly will serve as an Associate Editor for the IEEE Robotics and Automation Society’s Robotics & Automation Magazine (RAM). The magazine has over 12,000 readers and is consistently listed by Thomson’s Journal Citation Reports (JCR) as one of the most highly ranked publication in both the Robotics (#7) and Automation & Control (#15) categories, with an impact factor of 4.250 in 2018 (5-years IF:4.816). The magazine publishes four issues per year: March, June, September and December.

Pixels to pixels – RA-L and IROS 2020 paper on learning latent dynamics for control from pixels!

New RA-L and IROS 2020 work with the RLAI Lab at the University of Alberta on learning robust latent dynamics from images only. We demonstrate how latent dynamics can be made more robust for real-world robotic applications by composing a Kalman filter with a learned, heteroskedastic uncertainty model. Watch the YouTube video to find out more!