To get updates from our aUToronto self-driving car team, please visit this page.
Dynamic Systems Lab News
Tuesday February 9th, 2021
Wondering how to improve the performance of an off-the-shelf robot when access to its controller is limited? In this IJRR paper, we propose a neural-network-based approach that learns an add-on module to enhance the performance of a black-box system using only minimal knowledge/data from the system
Paper: journals.sagepub.com/doi/10.1177/0278364920953902
Quadrotor Impromptu Tracking with Neural Network
www.youtube.com
This video shows a deep neural network (DNN)-based approach for enhancing robot performance in tracking arbitrary trajectories impromptu. In this approach, a...Friday February 5th, 2021
In our latest RA-L paper we investigated whether motion distortion and Doppler effects have an impact on radar-based navigation including odometry on the Oxford dataset and metric localization using our own platform, Boreas.
The paper: arxiv.org/abs/2011.03512
Friday January 29th, 2021
The pandemic has been challenging for everyone, but it has taught us lessons in adaptation: from flying drones in the living room to exchanging gifts virtually. Check out the rest of our team photos: www.dynsyslab.org/photos
Friday January 22nd, 2021
We are looking for outstanding UofT undergraduate students interested in funded (e.g. NSERC USRA, ESROP, U of T Excellence Award, etc) summer research opportunities in robotics, machine learning and/or control. Students interested in this exciting opportunity should fill out this form by January 31st. forms.gle/khsnc8PXS9Zhx1iQ8
Friday January 8th, 2021
Prof. Angela Schoellig has been elected to serve on the IEEE Robotics and Automation Society (RAS) Administrative Committee for the next 3 years. Send her your suggestions for the IEEE RAS here: lnkd.in/dfW-XGG
robotics.utoronto.ca
Schoellig is one of only six new members elected to the RAS Administrative Committee this year.Congrats, Angela. I just sent my suggestions and I signed with my name. There is a lot to improve.
Thursday December 17th, 2020
With all the best wishes for a joyful holiday season. Take a break and enjoy the video!
2020 Holiday Greetings from the Dynamic Systems Lab
youtu.be
It has been an unusual year! We are sharing this short video to send best wishes for a healthy and joyful holiday season.Video by Abhishek Goudar, Wenda Zhao...Tuesday December 15th, 2020
Join us LIVE this week **Tue-Fri at 11h15-12h30 (EST)** for four Invited Sessions on Learning-Based Control at CDC2020, covering model and controller learning & safety guarantees. Co-organizers: Matthias Mueller, Melanie Zeilinger, Sebastian Trimpe.
CDC 2020 Program | Program at a Glance
css.paperplaza.net
CDC 2020 Technical Program Monday December 14, 2020 Monday Tuesday Wednesday Thursday Friday Next Top Click on the day's program and use the arrow keys for easy horizonta...Monday December 14th, 2020
Happy Holidays from Skule! Can you find our lab’s robots?
🎄
www.youtube.com
Celebrate the holiday season, and reflect on the past year with the Twelve Days of Skule™, as performed by U of T Engineering student Connor Glossop.Monday November 30th, 2020
ICYMI: Check out our IROS2020 Presentation about playing catch with a mobile manipulator. We proposed a planning and control framework that achieves a success rate of 85%.
Paper: arxiv.org/pdf/2003.07489.pdf
Catch the Ball: Accurate High-Speed Motions for Mobile Manipulators via Inverse Dynamics Learning
www.youtube.com
In this project, we focus on the mobile manipulator ball-catching task. We introduce a framework including two components: a bi-level motion optimization alg...Wednesday November 25th, 2020
ICYMI: The IROS2020 presentation for our RA-L paper. We learn robot parameters for trajectory estimation in a Gaussian variational inference setting. Our method works without ground truth, i.e. with only noisy measurements including outliers
Paper: www.dynsyslab.org/wp-content/papercite-data/pdf/wong-ral20b.pdf
