Welcome new students!

Welcome to our new STARS Laboratory M.A.Sc. students!

Olivier Lamarre has joined us from McGill University to work on projects related to planetary rovers navigation and scientific exploration. Emmett Wise hails from Queen’s University, and will be exploring an exciting project involving vehicle localization using ground-penetrating radar!

We’re excited to have the new team members!

Prof. Kelly receives Connaught New Researcher Award

Our laboratory received a Connaught New Researcher Award (at the maximum funding level) for the proposal entitled “Seeing the Light: Advancing Visual Sensing for Robust and Reliable Robot Navigation and Manipulation.”

The award will assist in our efforts to use vision data for navigation and manipulation in very challenging environments, under large lighting and appearance changes.

Welcome 2017 summer students!

We’re happy to welcome new students for summer 2017: Filip Marić has joined us as an exchange student from the University of Zagreb, working on mobile manipulation as part of his MSc project, Yilun Wu from UofT Engineering Science will be conducting some exciting UAV research, and Luke Volpatti, also from Engineering Science, will extend our calibration tools. Looking forward to a great summer!

Paper accepted at ICRA 2017

Congratulations to Valentin and Lee, whose paper, “Reducing Drift in Visual Odometry by Inferring Sun Direction using a Bayesian Convolutional Neural Network”, was accepted to ICRA 2017 in Singapore! Hope to see you there for the presentation!

STARS at ISER 2016

Jonathan and Lee traveled to Japan this week for the 2016 International Symposium on Experimental Robotics (ISER) in Tokyo, where Lee presented his paper, “Improving Stereo Visual Odometry Using Visual Illumination Estimation”, to an enthusiastic crowd of robotics researchers from around the world. We had some great conversations over Japanese beer and fresh sushi, and took in the sights and sounds of Tokyo, narrowly avoiding a typhoon in the process. The next ISER is in Buenos Aires in 2018 — see you there!

Lee won one of six competitive travel grants to attend ISER, and has a cool certificate to prove it!

Lee won one of six competitive travel grants to attend ISER, and has a cool certificate to prove it!

Lee presenting his paper with the help of some smooth animations.

Lee presenting his paper with the help of some smooth animations.

Roboticists love silly photos.

Roboticists love silly photos.

Best Student Paper at MFI 2016 & Travel Award to ISER 2016!

Congratulations to Jacob Lambert (along with his co-authors Lee Clement, Matthew Giamou, and Jonathan) for winning the Best Student Paper at the 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems in Baded-Baden, Germany!

Lee Clement was also awarded a travel award to the 2016 International Symposium of Experimental Robotics in Tokyo, Japan where he is presenting a paper on improving visual odometry through sun detection. Congrats Lee and Jacob!

STARS at RSS 2016

This weekend we drove over to the lovely University of Michigan campus to attend the workshops at RSS 2016. During the daytime, we listened to several heated exchanges about the future of hyper-parametric function approximation (i.e. Deep Learning) in robotics. During the night, we spent some time arguing over the best local Michigan brews. A great time all-around!

Lee and Valentin at RSS 2016.

Lee and Valentin at RSS 2016.

The Deep Learning workshop at RSS 2016.

The Deep Learning workshop at RSS 2016.

STARS Research at SVAR 2016

We visited MDA in Brampton, Ontario today for the 2016 Space Vision and Advanced Robotics Workshop. Jacob presented his work on entropy-based extrinsic sensor calibration, while Valentin talked about first responder localization using foot-mounted IMUs. We took home Second Prize (space pens!) in MDA’s Best Demo competition!

803726581_11466720249575892786

“Infrastructure-free First Responder Localization” won Second Prize in the Best Demo competition!

802610765_3263682648483356701

“Extrinsic Calibration of 2D Lidars Through Entropy Minimization”