To get updates from our aUToronto self-driving car team, please visit this page.
Dynamic Systems Lab News
Our latest RA-L paper describes a new method to pack more expressiveness into models used in Stochastic MPC at low computational cost while supporting online adaptation and model selection to adapt to changes in robot dynamics.
Paper: ieeexplore.ieee.org/abstract/document/9369887
Looking for a lightweight, low-cost localization solution for a group of agents?Have a look at our recent work on ultra-wideband (UWB) time-difference-of-arrival (TDOA) positioning systems. With a neural network bias model and an efficient M-estimation based Kalman filter, our proposed localization framework is able to run on-board a 27g quadcopter!
Paper: ieeexplore.ieee.org/document/9372785
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
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
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
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
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.
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
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...
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...
Happy Holidays from Skule! Can you find our lab’s robots?
🎄
