Can we learn dynamics model features offline for better online adaptation? Check out Adaptive-Control-Oriented Meta-Learning at #RSS2021 (Tues. and Thurs.)! roboticsconference.org/program/papers… w/ Navid Azizan, J.-J. Slotine, and @MarcoPavoneSU Code (w/ #JAX): git.io/JqkQ4

Happening now!

Thank you to everyone who attended my successful PhD defense yesterday on "Uncertainty-Aware Spatiotemporal Perception for Autonomous Vehicles"! The recording is now up on YouTube: youtu.be/Ou3Oi07sc70

New on arXiv: we present a learning control approach capable of safe and efficient online adaptation. Our approach combines elements of classical adaptive control, modern robust MPC, and Bayesian meta-learning to yield guaranteed-safe online adaptation! arxiv.org/abs/2212.01371 🧵

So excited to hold our 5th Robot Learning Workshop NeurIPS Conference this year on Trusworthy Robotics on Dec. 9th!

Excited to present our work with Mykel Kochenderfer on "Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction" Conference on Robot Learning! Come by our poster (paper #54) at Poster Session 4, 4:05-5:20 pm NZDT tomorrow! Paper: arxiv.org/pdf/2211.08701… Code: github.com/sisl/Interpret…

Out-of-distribution inputs derail predictions of ML models. How can we cope with OOD data in robotics? How do we even define what makes data OOD? We provide a perspective paper arguing a system-level view of OOD data in robotics! 🧵 (1/5) Now on Arxiv: arxiv.org/abs/2212.14020

Exciting first day co-teaching Marco Pavone’s AA203: Optimal and Learning-Based Control, with Spencer M. Richards at Stanford Engineering! Interested in the intersections between optimal control and RL? Look no further, all course materials will be available at: stanfordasl.github.io/aa203/

A new machine-learning technique can efficiently learn to control a robot, leading to better performance. Using this method, “we’re able to naturally create controllers that function much more effectively in the real world,” Navid Azizan says. mitsha.re/QK9p50PmHxG

I’ll be at poster 707 in a few minutes, and at Oral C2 later around 4:12pm HST!

Excited to talk about robot generalization on Saturday at 08:20 - 08:45 am at the 6th Robot Learning Workshop. If you are NeurIPS Conference for the next few days, reach out and I am happy to chat/catch up!

Thanks to everyone who came to my talk today and for all the questions! If you want to hear my thoughts on whether scale is enough for robot deployment, come by the debate in room B2 at 4:15 pm CST!