We are finally releasing a new benchmark!! #RSS2023 Main highlights are: * For real-world * Reproducible (3D printing) * 9 furniture assembly long-horizon tasks * 200+ hrs of demonstrations This apparently is my 3rd furniture-related benchmark.🥹 https://t.co/XrlP4cAuYS

Very excited to start sharing some of the work we have been doing at Amazon FAR. In this work we present OmniRetarget, which can generate high-quality interaction-preserving data from human motions for learning complex humanoid skills. High-quality re-targeting really helps

It's almost time for #CoRL 2025! A reminder that we're hosting the Data in Robotics workshop this Saturday Sept 27th. We have a packed schedule and are also attempting to livestream the event for those who can't attend in person.

We have our speakers: @JosephLim_AI @KarlPertsch @mayacakmak , Serena Booth, @JasonMa2020 @shahdhruv_ @MashaItkina We also have a great panel lined up from 3-3:40pm! @svlevine @yukez @MashaItkina @SudeepDasari @ashwinb96 @JasonMa2020 @shahdhruv_

Honored that our @RL_Conference paper won the Outstanding Paper Award on Empirical Reinforcement Learning Research! 📜Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-Functions 📎 https://t.co/owm0hVVsUK Grateful to my advisors @JosephLim_AI and @ebiyik_!

https://t.co/AAuq5Emr37 CoRL 2025 schedule is released now! Please note that the whole schedule is earlier than other times. The submission deadline: 4/28 The conference: 9/27-9/30 @corl_conf #corl2025

Do you work on robotics? Do you like robots? Then, visit Korea next year! We (@ryoo_michael @gupta_abhinav_ @SongShuran Haewon and more) are organizing CoRL 2025 in Seoul, Korea!! #CoRL @corl_conf #robotics

I've been historically bearish on skill-based RL and @Jesse_Y_Zhang consistently shows me I'm probably wrong. Come check out EXTRACT at 1600 at @corl_conf (poster #11) to see him yank semantically meaningful skills out offline data by leveraging PTLMs. https://t.co/BddE1rsvXr

This work was guided by Jesse's co-advisor's @ebiyik_ and @JosephLim_AI, but I think we all agree that Jesse is effectively running his own little lab. If you're thinking about hiring a postdoc in the area of RL for robotics, Jesse comes a ton of insight and mentoring experience!

And this will be my last tweet for the time being!

Well.. we won the best system paper award #RSS2023 @RoboticsSciSys !! @MinhoHeo’s talk can be found at: https://t.co/HyEQQErXOk We (@MinhoHeo @doohyun22 @YoungwoonLee & I) gave quite a bit of effort into this talk. So, we hope you enjoy the talk and, of course, the project :)

My student @MinhoHeo will be giving a talk in 2hrs (11am KST today). #RSS2023 This work is also one of the best system paper finalists too! Come and check it out :)

@MinhoHeo @YoungwoonLee @doohyun22 On Friday, at a workshop, about BOSS — bootstrapping a skill library for unseen environments with LLM Short Talk (Friday 4:30pm) & Poster(2:45pm) Room: 306A By @Jesse_Y_Zhang @JiahuiZhang_32 @KarlPertsch Ziyi Liu @xiangrenNLP @minsuk_chang @shaohua0116 https://t.co/qFkDsAzurw

Then, on Wednesday, we have FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation. Talk (Wednesday 11am) & Poster (Wednesday 3pm) By @MinhoHeo @YoungwoonLee @doohyun22 https://t.co/K1LHgNJF35

Then, on Tuesday, we have PATO: Policy Assisted TeleOperation for Scalable Robot Data Collection. Talk (Tuesday 11am) & Poster (Tuesday 3pm) By Shivin Dass, @KarlPertsch Hejia Zhang, @YoungwoonLee @snikolaidis19 https://t.co/eygwDyvRAs

We have a bunch of presentations this year. Starting with my own talk (Skill-based Robot Learning) at the Interdisciplinary Exploration of Generalizable Manipulation Policy Learning: Paradigms and Debates workshop. Today at 1:30pm Room: 322A https://t.co/3GhCBTtP2I

At #RSS2023 this week w/ some of my (ex-)students from CLVR (@YoungwoonLee @MinhoHeo @doohyun22 @sungj1026 ). Excited to meet about topics on robot learning, RL, physical reasoning, long-horizon manipulation, etc. + Recruiting (int’l & domestic) students. Plz come and say hi!

Having humans annotate data to pre-train robots is expensive and time-consuming! Introducing SPRINT: A pre-training approach using LLMs and offline RL to equip robots w/ many language-annotated skills while minimizing human annotation effort! URL: https://t.co/KuxuUeaXmA 🧵👇

Excited to present PATO: Policy Assisted TeleOperation, our recent work on scaling robot data collection! PATO uses a policy trained on prior data to assist the user during data collection, making teleop easier and even allows to teleop multiple robots simultaneously. 🧵👇

Check out our #CoRL2022 paper on learning skill dynamics for model-based RL! We present a sample efficient RL algorithms by temporal abstraction (skills). @YoungwoonLee @lucy_x_shi (an undergrad who will graduate soon!)