Laura Smith @smithlaura1028
CS PhD Student @berkeley_ai Joined August 2022-
Tweets24
-
Followers1K
-
Following153
-
Likes95
Can we leverage VLMs for robot manipulation in the open world? Checkout our new work MOKA, a simple and effective visual prompting method!
Rapidly adapting a variety of previously learned skills enables robots to handle... unexpected situations. Like when someone puts roller skates on the robot without its knowledge. But also some more realistic situations. Cool new paper by @_anniechen_ et al. building on APRL!
Rapidly adapting a variety of previously learned skills enables robots to handle... unexpected situations. Like when someone puts roller skates on the robot without its knowledge. But also some more realistic situations. Cool new paper by @_anniechen_ et al. building on APRL!
Very excited to introduce ROAM, our new work that allows a robot to *adapt on-the-go* as it faces OOD situations during deployment, drawing on pre-trained behaviors. See as ROAM enables our Go1 to roller skate zero-shot 🤖🐕🛼 (without any lessons!) 🧵(1/9)
How can our robots autonomously practice **new tasks** in **new environments**? Introducing BOSS: A reinforcement learning (RL) framework that trains agents to solve new tasks in new environments with LLM guidance! **CoRL 2023 Oral** 🧵👇
Excited and deeply grateful to share that I've been selected as a recipient of the 2023 Google PhD Fellowship! Thank you @GoogleAI for graciously supporting my research in developing intelligent, self-improving real-world systems 🤖
Excited and deeply grateful to share that I've been selected as a recipient of the 2023 Google PhD Fellowship! Thank you @GoogleAI for graciously supporting my research in developing intelligent, self-improving real-world systems 🤖
🎉Excited to share a fun little hardware project we’ve been working on. GELLO is an intuitive and low cost teleoperation device for robot arms that costs less than $300. We've seen the importance of data quality in imitation learning. Our goal is to make this more accessible 1/n
World models are promising for enabling general-purpose robots. But how do we train them since robot data is limited? Our solution: Shared world models on human videos and robots using affordances as the joint action space. Pre-train on human video, then fine-tune to robot tasks!
Introducing Masked Trajectory Modeling (MTM), a new general-purpose framework for sequential decision making. A single transformer trained with MTM can exhibit multiple capabilities by simply choosing different masking patterns at inference time. Accepted at ICML 2023. 🧵👇
Can we use end-to-end RL to learn to race from images in just 10-20 min? FastRLAP builds on RLPD and offline RL pretraining to learn to race both indoors and outdoors in under an hour, matching a human FPV driver (i.e., the first author...): sites.google.com/view/fastrlap/ Thread:
Introducing 𝗥𝗼𝗯𝗼𝗣𝗶𝗮𝗻𝗶𝘀𝘁 🎹🤖, a new benchmark for high-dimensional robot control! Solving it requires mastering the piano with two anthropomorphic hands. This has been one year in the making, and I couldn’t be happier to release it today! Some highlights below:
Sergey Levine @svlevine
79K Followers 122 Following Associate Professor at UC Berkeley Co-founder, Physical IntelligenceTed Xiao @xiao_ted
11K Followers 680 Following I teach robots to be smarter @GoogleDeepMind. Tweets about robot learning, scaling, and large models. Opinions my own.Danijar Hafner @danijarh
14K Followers 868 Following Building AI that makes autonomous decisions using world models, artificial curiosity, and temporal abstraction @DeepMindAbhishek Gupta @abhishekunique7
5K Followers 639 Following Assistant Professor at University of Washington. I like robots, and reinforcement learning. Previously: post-doc at MIT, PhD at BerkeleyEugene Vinitsky @EugeneVinitsky
13K Followers 2K Following Anti-cynic. Artificial narrow intelligence. Autonomous vehicles, multi-agent learning, and transportation. RS at Apple, Asst. Prof at @nyutandon. He/him.Xiaolong Wang @xiaolonw
11K Followers 948 Following Assistant Professor @UCSDJacobs Postdoc @berkeley_ai PhD @CMU_RoboticsChenhao Li @breadli428
2K Followers 324 Following Doctoral fellow @ETH_AI_Center | Robot learning at RSL & LAS | Prev. @MIT, @ETH_en, @MPI_IS.taylor howell @taylorhowell
769 Followers 313 FollowingEric Jang @ericjang11
69K Followers 3K Following physical AGI at 1X. Author of "AI is Good for You" https://t.co/eFg4WXhg0pRishabh Agarwal @agarwl_
6K Followers 544 Following Senior Research Scientist, @GoogleDeepMind, ex-🧠. Agents that make decisions. NeurIPS Best Paper (RLiable). Mila, IIT Bombay.Fei Xia @xf1280
6K Followers 694 Following Research Scientist at @GoogleDeepMind, Robot Learning, Computer Vision. PhD from @StanfordAILab @StanfordSVL, previously @Tsinghua_Uni. #AGI through EmbodimentYuzhe Qin @QinYuzhe
2K Followers 559 Following Robot Learning @ UC San Diego; prev: @NVIDIA Robotics @GoogleXXingyu Lin @Xingyu2017
1K Followers 335 Following Postdoc at @berkeley_ai. PhD from @SCSatCMU. #Learning #RoboticsRyan Hoque @ryan_hoque
630 Followers 343 Following PhD candidate & roboticist @berkeley_ai • fleet learning, imitation learning • formerly @NVIDIARobotics, @Uber ATG, @Berkeley_EECSLaura Liu @lauraqq
19 Followers 379 FollowingPoorvi @Poorvi_rh
50 Followers 228 Following CV/Robotics @ Stealth Startup | MS Computer Vision @CMU | CSE @IIT BombayLeah Jones @LeahJones579602
136 Followers 3K FollowingAshwin Balakrishna @ashwinb96
230 Followers 142 Following Researcher @ToyotaResearch. Previously PhD at @berkeley_ai. Interested in algorithms for large-scale robot learning.Cookie Quantum @QuantummCookie
0 Followers 26 FollowingZhengyi (Zen) Luo @zhengyiluo
1K Followers 667 Following PhD student in Robotics/CS @CMU_Robotics | Vision, Robotics, AR & VR | Visiting @RealityLabs, ex-intern @NvidiaAI, @apple, co-creator of @CirkitDesignYi Su @YiSu37328759
381 Followers 616 Following Researcher @GoogleDeepmind. Phd from @Cornell. Working on contextual bandits, reinforcement learning and their applications in user interactive systems.ahad @ahadj0
12 Followers 100 FollowingMichael L. @Michael_J_Lutz
250 Followers 243 Following building an army of web agents @bardeenai | @zfellows_ | @berkeleyml | @berkeley_eecsAakanksha Chowdhery @achowdhery
7K Followers 3K Following LLMs @ Google DeepMind :: PaLM, Gemini // Previously @MSFTResearch, @Stanford, @Princeton // views my own and subject to changeDomingo @Domingo_Yue
0 Followers 103 Followingchona grace pormento @ChonaPorme15887
0 Followers 24 FollowingCharles @Charles78135046
0 Followers 17 FollowingKamyar Ghasemipour @coolboi95
864 Followers 2K Following ML grad student at U of T / Vector Institute. I go by Kamyar. Currently affiliated with Google Robotics. He/Him.Rose “Vile” Schlo.. @jewkaiser
179 Followers 3K Following Kaiser Permanente star ships are approaching: Only Bangers from the GabbacannonAlexander Wan @alexwan55
472 Followers 944 Following CS at Berkeley; @BerkeleyML @BerkeleyNLP; NLP researchHyunyoung Jung @HyunyoungJung5
10 Followers 66 FollowingKeiran Paster @keirp1
1K Followers 636 Following Currently PhD at the University of Toronto. Fall 2023 student researcher at Google. Training sequence models. Recent: APE, STEVE-1, OpenWebMath, Llemma.Peter Chen @peterxichen
3K Followers 1K Following Covariant CEO and Co-Founder. Previously @OpenAI, @UCBerkeley PhD.Brian Ichter @brian_ichter
1K Followers 178 Following Research Scientist at Google Brain, interested in robotics and AIAI @hanekeai
18 Followers 634 FollowingTaewan @taewankeem
29 Followers 96 Following Phd student in UW. Interested in math, control theory, and optimization.Quanting Xie @DanielXieee
322 Followers 766 Following Incoming PhD @CMU CLAW_Lab @CMU_RI | Prev @Apple || #Embodied_AI #Robot_Learning #Humanoid #Dexterous_handHanxiao Jiang @jiang_hanxiao
261 Followers 318 Following Ph.D. student @IllinoisCS. Research interest: Robot Learning, Robot Vision, 3D VisionP @pepijn2233
57 Followers 552 FollowingStephenMak @StephenMak7
61 Followers 248 Following PhD in Multi-Agent Reinforcement Learning @Cambridge_UniDavide Tateo @davide_tateo
280 Followers 234 Following Ricercatore italiano in "esilio" in Germania. "Safe and Reliable Robot Learning" Research Group Leader @ias_tudarmstadt. @Mushroom_RLAaditya ; @Aaditya26082004
524 Followers 7K Following CS'26 • Machine Learning • Open-Source • Web Dev. • Algorithms • Jai Shree Krishna 🦚🪈Malin Råman Delin @Malin_RD
239 Followers 2K Following Leading the GenAI revolution in M&A 🤖 | Expert insights on AI tools & trends 📈 | Bridging cutting-edge tech with B2B acquisition success 🚀 | Let's discuss 🌐Minkyung Lee @blossomindy
46 Followers 153 Following Love AI Robotics🤖 PhD student at KHU(@kh_univ) studying on Deep Learning, Reinforcement Learning, Robot Learning.Quazi @_Quazi_
746 Followers 1K Following Dev for TowerClimb, a procedurally generated roguelike-platformer. I also do graphics / animation / robotics R&D.Alexey Krivenkov @AKrivenkov38410
34 Followers 51 FollowingFrank P Seidl @SpaceConscious
40K Followers 43K Following Alchemist Series, A Walk to the Moon, Artist Frank Seidl https://t.co/JCAYEksEjJ MCAD Alumnus 72 https://t.co/g9qjzVRgOD - Model Flo Li, San Diego - https://t.co/oC2TJ77H7IJiange Yang @JiangeYang
20 Followers 229 Following PhD student at Nanjing University, formerly the Research Intern at Microsoft Research Asia @MSFTResearch. https://t.co/8IPVFyItVn Robot LearningFeiyuxiaoAuto @feiyuxiaothu
46 Followers 131 Following Husband and Dad. Decision making/Motion Planning in autonomous systems. Former researcher intern in @ToyotaCRDL and student in SVM in @Tsinghua_Uni.Luke Jackson @LukeJac39568852
26 Followers 52 FollowingJoel Ye @_JoelYe
351 Followers 540 Following NeuroAI PhD student @CarnegieMellon. Being a brain-computer interface.Anna Hakhverdyan @anna_ssi_
101 Followers 245 FollowingChase Bauer @ChaseCBauer
29 Followers 285 FollowingAchint Soni @TrickyInjustice
3 Followers 197 Following MMath student in Computer Science @UWaterloo | Generative modeling | Undergrad from @IITKanpur |Will W @SkoutGuillaume
69 Followers 524 Following Insights - Data Scientist #datascience #dataviz #NLG #data.Homanga Bharadhwaj @mangahomanga
1K Followers 522 Following PhD student @SCSatCMU. Visiting researcher @MetaAI. Hater of hot takes. Lover of analyses.AK @_akhaliq
309K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxSergey Levine @svlevine
79K Followers 122 Following Associate Professor at UC Berkeley Co-founder, Physical IntelligenceYann LeCun @ylecun
710K Followers 718 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.Karol Hausman @hausman_k
22K Followers 141 Following @Physical_int ex: researcher @GoogleAI/@DeepMind, adj. Prof. @Stanford. Into robots, AI, NBA, philosophy, soccer and almond croissants. 🇵🇱🇺🇸Ted Xiao @xiao_ted
11K Followers 680 Following I teach robots to be smarter @GoogleDeepMind. Tweets about robot learning, scaling, and large models. Opinions my own.Danijar Hafner @danijarh
14K Followers 868 Following Building AI that makes autonomous decisions using world models, artificial curiosity, and temporal abstraction @DeepMindAbhishek Gupta @abhishekunique7
5K Followers 639 Following Assistant Professor at University of Washington. I like robots, and reinforcement learning. Previously: post-doc at MIT, PhD at BerkeleyEugene Vinitsky @EugeneVinitsky
13K Followers 2K Following Anti-cynic. Artificial narrow intelligence. Autonomous vehicles, multi-agent learning, and transportation. RS at Apple, Asst. Prof at @nyutandon. He/him.Deepak Pathak @pathak2206
16K Followers 316 Following I study topics in AI (machine learning, robotics & computer vision).Xiaolong Wang @xiaolonw
11K Followers 948 Following Assistant Professor @UCSDJacobs Postdoc @berkeley_ai PhD @CMU_RoboticsShane Gu @shaneguML
28K Followers 1K Following Research Scientist & Manager @GoogleDeepMind Tokyo/MTV. ex: @GoogleAI Brain, @OpenAI. (JP: @shanegJP)Lerrel Pinto @LerrelPinto
5K Followers 181 Following Assistant Professor of CS @nyuniversity. I like robots!Aviral Kumar @aviral_kumar2
2K Followers 338 Following Research Scientist at Google DeepMind. Incoming Assistant Professor of CS & ML at CMU (Fall 2024). PhD from UC Berkeley.Marc G. Bellemare @marcgbellemare
13K Followers 350 Following CSO & co-founder, Reliant AI. Ex RL research lead at Google Brain, DeepMind. Known for Atari 2600 RL benchmark, Distributional RL (MIT Press 2023).taylor howell @taylorhowell
769 Followers 313 FollowingEric Jang @ericjang11
69K Followers 3K Following physical AGI at 1X. Author of "AI is Good for You" https://t.co/eFg4WXhg0pMarkus Wulfmeier @m_wulfmeier
12K Followers 1K Following machine learning & the real world @GoogleDeepMind - european @ELLISforEurope - transfer and generalisation - priors: @oxfordrobots @berkeley_ai @ETH @MITMichael Chang @mmmbchang
2K Followers 2K Following Amplify human creativity Gemini @GoogleDeepMind Prev @LangChainAI, @MetaAI, @SchmidhuberAI PhD @berkeley_ai, w/ @svlevine, @cocosci_lab. BS @MIT @MITCoCoSciFei Xia @xf1280
6K Followers 694 Following Research Scientist at @GoogleDeepMind, Robot Learning, Computer Vision. PhD from @StanfordAILab @StanfordSVL, previously @Tsinghua_Uni. #AGI through EmbodimentAshwin Balakrishna @ashwinb96
230 Followers 142 Following Researcher @ToyotaResearch. Previously PhD at @berkeley_ai. Interested in algorithms for large-scale robot learning.Kamyar Ghasemipour @coolboi95
864 Followers 2K Following ML grad student at U of T / Vector Institute. I go by Kamyar. Currently affiliated with Google Robotics. He/Him.Adi (e/acc) @aditya_baradwaj
18K Followers 2K Following Currently building @Astra_API 🦀. Ex-@AlamedaResearch engineer. Previously at @Google and @UCBerkeley.Vivek Myers @vivek_myers
230 Followers 414 Following PhD student @berkeley_ai | BS in Math+CS @Stanford '22Kevin Frans @kvfrans
2K Followers 420 Following @berkeley_ai prev mit, read my thoughts: https://t.co/7CZsOTsiH8Ruijie Zheng @ruijie_zheng12
228 Followers 220 Following Computer Science PhD student at University of Maryland Ex-Research Intern at @MSFTResearchJianlan Luo @jianlanluo
293 Followers 84 Following Postdoc @BerkeleyAI Previously at Google X @Theteamatx, PhD from @UCBerkeleyBoyi Li @Boyiliee
1K Followers 253 FollowingPierluca D'Oro @proceduralia
1K Followers 356 Following Final-year PhD student at Mila and researcher at Meta, working on the science of AI agents. Made in Sicily.Evgenii Nikishin @nikishin_evg
1K Followers 844 Following PhD student @Mila_Quebec working on AI agents. Past: a research scientist intern @GoogleDeepMind London #StopWar 🇺🇦Victoria Dean @vdean314
2K Followers 2K Following Assistant Professor of Computer Science at @OlinCollege. Robotics, AI ethics, DEI, baking. She/her #BlackLivesMatterAndreea Bobu @andreea7b
1K Followers 402 Following Research Scientist at BDAII and incoming Assistant Professor @MIT, working at the intersection of machine learning, robotics, and human-robot interaction.Antonio Loquercio @antoniloq
2K Followers 689 Following #ComputerVision and #Robotics PostDoc at @Berkeley_EECS (BAIR) with Jitendra Malik in #Berkeley, California.Archit Sharma @archit_sharma97
4K Followers 339 Following Final-year CS PhD student @Stanford. Previously, AI Resident @Google Brain, undergraduate @IITKanpur, research intern @MILAMontreal.Simon Zhai @simon_zhai
140 Followers 125 Following PhD @ Berkeley EECS, sometimes I click likes for trollsWenlong Huang @wenlong_huang
2K Followers 811 Following PhD Student @StanfordSVL @StanfordAILab. Previously @Berkeley_AI @GoogleDeepMind. Robotics, Foundation Models.Ria Doshi @riadoshi21
178 Followers 304 Following research @berkeley_ai | author @codedetectives 👩🏻💻Annie Chen @_anniechen_
651 Followers 408 Following PhD student @StanfordAILab. Prev: research @GoogleAI, Stanford BS/MSTianyu Li EasyPaperSn.. @SniperPaper
55 Followers 114 Following CS Phd @ Gatech exResearch Scientist@FAIRSehoon Ha @sehoonha
664 Followers 304 Following Assistant Professor at Georgia Institute of Technology https://t.co/GWRmzIyQrcOier Mees @oier_mees
1K Followers 224 Following Postdoc at @berkeley_ai. PhD @UniFreiburg. Prev. intern @NVIDIAAI. Research on robotics, language, computer vision, MLXingyu Lin @Xingyu2017
1K Followers 335 Following Postdoc at @berkeley_ai. PhD from @SCSatCMU. #Learning #RoboticsIgor Mordatch @IMordatch
4K Followers 236 Following Research scientist @DeepMind. Interested in AI/education/visual art/nature. Previously @OpenAI and @UCBerkeley.Sean Kirmani @SeanKirmani
354 Followers 486 Following Researcher at @GoogleDeepMind. Technology optimist.Thomas Wolf @Thom_Wolf
68K Followers 4K Following Co-founder and CSO @HuggingFace - open-source and open-scienceDavid Duvenaud @DavidDuvenaud
28K Followers 3K Following Machine learning prof @UofT. Working on generative models, inference, & latent structure.Dorsa Sadigh @DorsaSadigh
8K Followers 390 Following CS Faculty @Stanford, @StanfordAILab 20% Research scientist @GoogleDeepMind PhD and BS from @Berkeley_EECSGe Yang @EpisodeYang
2K Followers 2K Following I am planting acorns one at a time with policy gradient.Glen Berseth @GlenBerseth
2K Followers 262 Following Assistant Prof at @UMontreal @Mila_Quebec @MontrealRobots. Creating generalist problem-solving agents for the real world. he/him/ilGabe Margolis @gabe_mrgl
663 Followers 359 Following Grad Student at @MIT_CSAIL. Robot learning, motor skills for contact-rich tasks.Alexandre L.-Piché @alexpiche_
1K Followers 5K Following Searching for Q* at @ServiceNowRSRCH, PhD candidate at @MilaMontreal. Prev. Research intern at @DeepMind.Yuni Fuchioka 渕岡�.. @yunifuchioka
491 Followers 294 Following PhD student, ETH Zürich Robotic Systems Lab @leggedrobotics | Master's at @UBC with @Mvandepanne | Japanese guy raised in Canada living in SwitzerlandKevin Black @kvablack
370 Followers 73 Following phd @berkeley_ai, deep reinforcement learning + roboticsJan Peters @Jan_R_Peters
4K Followers 422 Following #RobotLearning Professor (#MachineLearning #Robotics) at @ias_tudarmstadt of @TUDarmstadt (Part of @ELLISforEurope, @Hessian_AI and @DFKI)Corey Lynch @coreylynch
10K Followers 1K Following AI at @figure_robot, previously research scientist at @GoogleDeepMind.Mohit Shridhar @mohito1905
1K Followers 1K Following Research Scientist at @Dyson. @uwcse PhD in Robotics.Alfredo Canziani @alfcnz
86K Followers 268 Following Musician, math lover, cook, dancer, 🏳️🌈, and an ass prof of Computer Science at New York UniversityRyan Hoque @ryan_hoque
630 Followers 343 Following PhD candidate & roboticist @berkeley_ai • fleet learning, imitation learning • formerly @NVIDIARobotics, @Uber ATG, @Berkeley_EECSDaniel Zeng @danielzeng_
42 Followers 116 Following ML Research at Genesis Therapeutics Prev at Stanford, Google Research"CAREER has arrived." I am fortunate to have received the NSF CAREER award this year. I really appreciate all of my students, collaborators, and mentors. I hope to produce more interesting results in future years.
Introducing 𝐌𝐨𝐛𝐢𝐥𝐞 𝐀𝐋𝐎𝐇𝐀🏄 -- Hardware! A low-cost, open-source, mobile manipulator. One of the most high-effort projects in my past 5yrs! Not possible without co-lead @zipengfu and @chelseabfinn. At the end, what's better than cooking yourself a meal with the 🤖🧑🍳
Seems like a good time to retweet this ;) Recent results are amazing but let's not conclude that robotics is solved... lots of great research remains to be done!
Check out our recent work (led by @robominyoung ) on customizing robot behaviors based on human feedback!
We only train once: How can we effectively customize a robot for multiple users? We propose 'Promptable Behaviors', a novel personalization framework that deals with diverse preferences without any retraining. website: promptable-behaviors.github.io paper: arxiv.org/abs/2312.09337 🧵👇
HIQL is one of the simplest hierarchical RL methods -- just train a value function as usual, but extract two policies instead of one. This leads to huge improvements in many offline GCRL tasks! Come by our poster today (Wed 5-7pm, #1413)! Project page: seohong.me/projects/hiql/
Goal conditioned RL w/ a surprisingly simple way to do hierarchy ("I can't believe it's hierarchical"): just using a flat (low-level) value function to train a high- and low-level actor turns out to work really well for offline GCRL: seohong.me/projects/hiql/ Hierarchical IQL: 🧵👇
How to tackle complex household tasks like opening doors, and cleaning tables in real? Introducing HarmonicMM: Our latest model seamlessly combines navigation and manipulation, enabling robots to tackle household tasks using only RGB visual observation and robot proprioception.
we have trained a humanoid transformer with large-scale reinforcement learning in simulation and deployed it to the real world zero-shot
The ViperX 6-DoF arm from @trossenrobotics is now available in Menagerie with some initial sysID by the amazing @the_real_btaba! github.com/google-deepmin…
We finally have all the components to continue our research into autonomous robotic surgery using the DaVinci Research Kit!
Check out our new paper on online RL exploration from unlabeled (no reward) prior data! A super fun project with Jason Zhang, @its_dibya @yayitsamyzhang @svlevine
Leveraging prior unlabeled data is a powerful recipe in machine learning. Can it help with exploration in RL? Turns out that very simple ways of including prior data -- just by labeling it with UCB reward estimates and running RLPD -- can work great! A summary of our new paper 👇
Leveraging prior unlabeled data is a powerful recipe in machine learning. Can it help with exploration in RL? Turns out that very simple ways of including prior data -- just by labeling it with UCB reward estimates and running RLPD -- can work great! A summary of our new paper 👇
We have also released the code for GELLO: Please see github.com/wuphilipp/gell…. Please share if you make and use GELLO in your own projects! Contributions are welcome and appreciated!
We have released the hardware files and instructions for GELLO 🦾! See the updated website wuphilipp.github.io/gello_site/. Here's a video of me assembling it start to finish in 30 min! GELLO is also at CoRL this week, see 👇 for details
Introducing LocoMuJoCo, the first imitation learning benchmark tailored towards locomotion! It comes with a diverse set of environments ranging from musculoskeletal models to the brand-new @UnitreeRobotics H1 robot, and also many motion capture datasets! github.com/robfiras/loco-…
Happy to be with my lab members at #CoRL2023! I think I got a new Twitter banner... :)
Looking forward to present RoboPianist in Atlanta for #CoRL23 this week! DMs are open in case you want to talk robotics, MuJoCo or anything else. • Poster session 3 (4:15-5:00 PM) • Updated paper: kzakka.com/robopianist/
Introducing 𝗥𝗼𝗯𝗼𝗣𝗶𝗮𝗻𝗶𝘀𝘁 🎹🤖, a new benchmark for high-dimensional robot control! Solving it requires mastering the piano with two anthropomorphic hands. This has been one year in the making, and I couldn’t be happier to release it today! Some highlights below:
Handing new scenarios is one of the biggest open challenges for machine learning. ROAM enables our robot to adapt *in real time* to large changes -- payloads, crippled legs, and even roller skates. 🤖🛼 Paper & Code: anniesch.github.io/adapt-on-the-g…
Very excited to introduce ROAM, our new work that allows a robot to *adapt on-the-go* as it faces OOD situations during deployment, drawing on pre-trained behaviors. See as ROAM enables our Go1 to roller skate zero-shot 🤖🐕🛼 (without any lessons!) 🧵(1/9)
We can tell our robots what we want them to do, but language can be underspecified. Goal images are worth 1,000 words, but can be overspecified. Hand-drawn sketches are a happy medium for communicating goals to robots! 🤖✏️Introducing RT-Sketch: rt-sketch.github.io 🧵1/11
Very excited to introduce ROAM, our new work that allows a robot to *adapt on-the-go* as it faces OOD situations during deployment, drawing on pre-trained behaviors. See as ROAM enables our Go1 to roller skate zero-shot 🤖🐕🛼 (without any lessons!) 🧵(1/9)
Rapidly adapting a variety of previously learned skills enables robots to handle... unexpected situations. Like when someone puts roller skates on the robot without its knowledge. But also some more realistic situations. Cool new paper by @_anniechen_ et al. building on APRL!
Very excited to introduce ROAM, our new work that allows a robot to *adapt on-the-go* as it faces OOD situations during deployment, drawing on pre-trained behaviors. See as ROAM enables our Go1 to roller skate zero-shot 🤖🐕🛼 (without any lessons!) 🧵(1/9)
How can robot hands learn to do kitchen tasks from safe, continual real-world interaction? In our new CoRL 2023 paper DEFT, we learn policy priors from human videos and use our soft robot hand to safely adapt the policy with real world practice. 1/