Join us tomorrow for this week's robot learning seminar, in which Ankit Goyal from NVIDIA will present his talk titled "View Transformers for 3D Manipulation in Robotics". See you there at 11:30AM ET! YouTube.com/@MontrealRobot… #Manipulation #multiViewLearning #transformers

There is still time (Oct 15) to submit your work to our #CoRL2024 workshop on ML that generalizes across robot morphologies. Website: sites.google.com/view/corl-mapo… Submission Link: openreview.net/group?id=corl.… Speakers below.

Creating Generalist robotics policies (GRPs) is tricky. In this video (and code) I share how to create a GRP from scratch from some basic transformer code. This is the first step in my plan to create a course on large models and scaling for RL and Robotics.

Hi all! We are thrilled to have Mandi Zhao from Stanford University giving a talk at the robot learning seminar! The talk is titled "New Perspectives on Harnessing Foundation Models for Robot Learning". See you at 11:30AM ET! YouTube.com/@MontrealRobot… #foundationModels #real2sim2real

Don't Miss the Standing the Test of Time Workshop at IROS 2024! Join us on October 14th from 1:30 PM to 5:30 PM in Room 17 for an afternoon of stimulating discussions on the evolution of world representations in robotics! montrealrobotics.ca/test-of-time-w… Ser you all there!

The workshop is starting now! #IROS2024 montrealrobotics.ca/test-of-time-w…

Mila - Institut québécois d'IA is now open for supervision applications! Those who are interested in joining my lab (REAL - Robotics and Embodied AI Lab) for an MSc or PhD should submit to this system. #ScalingRL #Robotics #reinforcementlearning #acceleratedscience

Hey all! We are thrilled to have Lukas Schmid from MIT for this week's seminar: "Active Perception and Long-term Understanding of Dynamic Human-Centric Scenes". See you at 11:30AM ET! youtube.com/@MontrealRobot… #activePerception #longterm #lifelong #dynamicScenes

Resharing as CtRL-Sim was accepted at #CoRL2024, which we will present this week in Munich! Also, all the code is now available, so you can start training your own controllable and reactive driving agents: github.com/montrealroboti…

Hi! This week in the robot learning seminar, we will have Vincent Leroy from NAVER LABS Europe. His talk is titled "From CroCo to MASt3R: A Paradigm Change in 3D Vision?". See you at 11:30AM ET! YouTube.com/@MontrealRobot… #foundationModels #vision #selfSupervised

Hey all! We are thrilled to have Bryan Chan from University of Alberta for this week's seminar! The talk is titled: "Why can't we use reinforcement learning for image-based robotic manipulation?". See you at 11:30AM ET! youtube.com/@MontrealRobot… #rl #manipulation, #imitationLearning

Hi! This week in the robot learning seminar, we will have Sayantan Auddy from TU Berlin. His talk is titled "Continual Learning for Robotic Manipulation". See you at 11:30AM ET! YouTube.com/@MontrealRobot… #manipulation #continualLearning #domainRandomization

I am teaching a class on #FoundationalModels for #robotics and Scaling #DeepRL algorithms. This class expands on last year's class and my generalist robotics policies tutorial and code. I plan to share the lectures and code assignments. Starting with the first lectures below.

This venture has been exciting and essential. Technology is changing fast these days, and experts can help policymakers make more informed decisions on the challenges of #AI specific policies and prepare for challenges due to evolving technology, including for #robotics.

Shockingly accurate. Waiting for a grant to be approved before starting the research project is #toolittletolate. #fundamentalresearch funding is what makes it easier to act on good research opportunities.

If you're attending The AAMAS Conference 2025 and are interested in general evaluation of AI agents, you should check our tutorial on May 19th! The website is here sites.google.com/view/aamas2025…, including some draft notes! Co-organized with Marc Lanctot, Ian Gemp, and Kate Larson 1/2

A few days ago, most of the REAL - Robotics and Embodied AI Lab lab went out for lunch at one of the local Cabanes à sucres! There was soooo much syrup.

In my next lecture on #robotlearning, I cover generalization across sequences and robots. This generalization across sequences of actions or states is a challenging, data-intensive process that requires experience across various robots and tasks.

How can we make behavioural cloning (BC) achieve better combinatorial generalization on out-of-distribution goals? We propose BYOL-γ: an auxiliary self-predictive loss to improve generalization for goal-conditioned BC. 🧵1/6

My lab with REAL - Robotics and Embodied AI Lab was honoured to present our recent research and explain how machine learning enables robotics that will drive innovation in Canada. It was a pleasure getting into the details!