...

Robotics and Embodied AI Lab (REAL)

The Robotics and Embodied AI Lab (REAL)s is a research lab affiliated with DIRO and Mila, at Université de Montréal. REAL is dedicated to making robots and other embodied agents more capable, easier to use, and safer with machine learning where appropriate.

In particular, REAL is focussed on building representations of the world (such as for simultaneous localization and mapping), modelling of uncertainty, and building better workflows to teach robotic agents new tasks (such as through simulation or demonstration). We are always looking out for talented students to join us as full-time students / visitors. To know more, click on the link below.

Learn more
News
December 05, 2020
Krishna won an NVIDIA fellowship for 2021-22. Congratulations!

November 30, 2020
We released gradslam - a differentiable dense SLAM framework for deep learning. Check it out!

October 30, 2020
We organized an IROS workshop on Benchmarking progress in autonomous driving

October 15, 2020
Checkout our new Neurips 2020 Oral paper La-MAML: Look-Ahead Meta-Learning for Continual Learning [Code], [Short Video].

October 10, 2020
Two papers accepted to Neurips 2020 (one of them an oral - top 1.1%). Congratulations Gunshi and Ruixiang!

September 10, 2020

June 30, 2020
Gunshi Gupta succesfully completes her M.Sc. and joins Wayve as a deep learning researcher!

June 05, 2020
Our paper [MapLite: Autonomous intersection navigation without detailed prior maps] was adjudged best Robotics and Automation Letters (RAL) paper for 2019! Check it out here. And, here’s a short video abstract.

More news …
Projects

gradslam active

Differentiable dense SLAM for task-driven representation learning

Last updated 3 mins ago


Active Domain Randomization active

Making sim-to-real transfer more efficient

Last updated 3 mins ago


Kimplete inactive

Learning to construct amodal, interactable representations of the world

Last updated 3 mins ago


Deep Active Localization inactive

Learned active localization, implemented on “real” robots.

Last updated 3 mins ago


Efficient Sim-to-real transfer

A major thrust area for the group

Last updated 3 mins ago


Self-supervised visual odometry estimation inactive

A self-supervised deep network for visual odometry estimation from monocular imagery.

Last updated 3 mins ago


All projects…

© Robotics and Embodied AI Lab Team, 2019

Department of Computer Science and Operations Research | Université de Montréal

Powered by jekyll