We’re excited to announce the release of our University of Toronto Canadian Planetary Emulation Terrain Energy-Aware Rover Navigation Dataset. The dataset was gathered by a small, four-wheeled rover at a planetary analog test facility in Canada. The rover was equipped with a suite of sensors designed to enable the study of energy-aware navigation and path planning algorithms. Our International Journal of Robotics Research data paper is available here.
The dataset includes more than 14,000 colour omnidirectional stereo panoramas captured from a synchronized 10-camera cluster and 16,000 high-resolution monocular terrain images. IMU, pyranometer (solar irradiance), drive power consumption, wheel encoder, and GPS measurements are also included. All data are presented in human-readable text files and as standard-format images; additional Robot Operating System (ROS) parsing tools and several georeferenced aerial maps of the test environment are also included. The full dataset is accessible from:
Congratulations to Dr. Valentin Peretroukhin for successfully defending his PhD on March 6! His dissertation, “Learned Improvements to the Visual Egomotion Pipeline” described ways to augment classical visual egomotion techniques with learned models. We wish him the best as he moves to Boston to postdoc at MIT!
We’re organizing the second ‘Debates on the Future of Robotics Research’ workshop at ICRA 2020 in Paris! The event will take place on May 31 – we have an outstanding group of speakers and organizers this year and are looking forward to a memorable day of discussions! Submissions for the Lightning Talks session are now open – full details are available at http://roboticsdebates.org/. Hope to see you there!
Congratulations to Dr. Lee Clement for successfully defending his PhD on November 29! His dissertation, “On Learning Models of Appearance for Robust Long-Term Visual Navigation” focussed on enabling successful long-term autonomy (localization, navigation, and mapping) under substantial appearance change (due to lighting variation and other effects). We wish him success in the future!
Cybersecurity is already a critical issue – what will happen when we deploy thousand or millions of (potentially hackable) robots on our roads, in our hospitals, and inside our homes? Prof. Kelly is giving a keynote talk about these issues at this year’s CANARIE Summit in Montreal on October 1!
We’re super-proud of Erin Richardson, our lab alum, who was featured with the awesome aerospace engineer, tireless STEM promoter, and UTIAS graduate Natalie Panek in “Path Among the Stars” – a short segment aired during the CNN Apollo 11 documentary film (June 23, 2019). Congratulations Erin and Natalie – you inspire us to reach for the stars!
Interested in the challenges involved in building robust, reliable, and safe robotics software? Prof. Kelly will give a keynote talk on this topic at the CANARIE Canadian Research Software Conference in Montreal on May 29! More details, including the talk abstract, are available here.
Congratulations to our Ph.D. student Matthew Giamou for being awarded one of just five inaugural RBC Borealis AI Graduate Fellowships! This award will support Matt’s work on certifiably correct algorithms for safe and efficient state estimation. More information is available here: http://entrepreneurs.utoronto.ca/news-events/rbcfellowship/
Interested in where robotics is headed and how we can shape its future? We are organizing a day of head-to-head discussions at the ICRA 2019 “Debates on the Future of Robotics Research” workshop. Join us for a day of interesting debates and deep insights! And consider submitting a short position paper for the lighting talks session! Speaker lineup and position paper submission at http://roboticsdebates.org/
We’re delighted to announce the launch of our Self-Driving Cars Specialization on the Coursera platform, with instructors Prof. Steven Waslander (TRAIL) and Prof. Jonathan Kelly! You can find out more about the Specialization here, and check out the overview video on YouTube.
Huge thanks to Lee Clement, Valentin Peretroukhin, Trevor Ablett, and Filip Marić as well as staff and students at the University of Toronto and to Coursera for making this happen!