🚀Unsupervised RL can learn skills purely from reward-free interactions with an environment. But what form of skills can facilitate efficient downstream hierarchical learning? Introducing DUSDi: Disentangled Unsupervised Skill Discovery (NeurIPS24). jiahenghu.github.io/DUSDi-si… 🧵

Here are two videos of our ICRA demo where @RobobertoMM performed intercontinental teleoperation of our Tiago in Austin, USA, all the way from Japan! 🇯🇵 -> 🇺🇲 Thanks @xf1280 and @albertyu101 for the videos.

This will be on Monday at ICRA, full day. A great set of speakers, panels, and posters. Come to learn and discuss about Mobile Manipulation!

Collecting data for stationary robot arms was easy, but there wasn't a similar tool for mobile manipulators, so we created ours! With TeleMoMa you can use as input an RGB-D camera, VR controllers, keyboard... or combinations of those. Check it out!

This is going to be a great workshop for researchers interested in Mobile Manipulation. If you are attending #ICRA24, don't miss it!

And thanks to all coorganizers: @DHonerkamp, @Ken_Harada, @GeorgiaChal, @SnehalJauhri, Yuqian Yiang, Weiwei Wan, Nick Heppert, Tim Welschehold, Abhinav Valada. An activity of our IEEE-Technical Committee on @MobileManip

🥳 I'm excited to share that my paper "Active Perceptive Motion Generation for Mobile Manipulation" with @SnehalJauhri and @GeorgiaChal got accepted to #ICRA2024! 🥳 (1/6) Go check it out: sites.google.com/view/actper…

Mobile ALOHA's hardware is very capable. We brought it home yesterday and tried more tasks! It can: - do laundry👔👖 - self-charge⚡️ - use a vacuum - water plants🌳 - load and unload a dishwasher - use a coffee machine☕️ - obtain drinks from the fridge and open a beer🍺 - open doors🚪 - play with pets🐱 - throw away trash - turn on/off a lamp💡 Project website: mobile-aloha.github.io/ Co-lead @tonyzzhao, advised by @chelseabfinn (amazing photographing from @qingqing_zhao_ )

Excited to release OK-Robot, an open-vocabulary mobile-manipulator for homes. Simply tell the robot what to pick and where to drop it in natural language, and it will do it. Like: Me: "OK Robot, move the Takis from the desk to the nightstand" Robot: ⬇️

Large Language Models (LLMs) and Vision-Language Models (VLMs) are poised to revolutionize robotics. Join our workshop at #ICRA2024 on VLMs/LLMs for scene understanding, decision making, control, and more: vlmnm-workshop.github.io/ Submissions due March 11, 2024!

Wouldn’t it be nice if you could bring a robot home, give it a video of your room, and immediately start asking it to move objects around? Turns out, now you can! Introducing OK-Robot, a zero-shot language-specified pick & drop system that we built with exactly ZERO training! 🧵

Introducing Open-World Mobile Manipulation 🦾🌍 – A full-stack approach for operating articulated objects in open-ended unstructured environments: Unlocking doors with lever handles/ round knobs/ spring-loaded hinges 🔓🚪 Opening cabinets, drawers, and refrigerators 🗄️ 👇 open-world-mobilemanip.githu… Led by: @HaoyuXiong1 , @mendonca_rl , @kenny__shaw @deepakpathak 1/n

Adaptive Mobile Manipulation project from @CarnegieMellon Based on AgileX Robotics's #RangerMini2 mobile robot, Integrate sensors such as robotic arm and depth camera to complete to be a completed solution, which can realize the functions of intelligent movement and processing.

Excited to share our latest work, Vision-Language Frontier Maps – a SOTA approach for semantic navigation in robotics. VLFM enables robots to navigate and find objects in novel environments using vision-language foundation models, zero-shot! Accepted to #ICRA2024! 🧵

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 🤖🧑‍🍳

Let's make robots that can help out in *any* home environment! Check out our poster on *Open Vocabulary Mobile Manipulation* at #CoRL2023 @corl_conf tomorrow 12pm-12:45pm eastern. Presented by the great @yvsriram - applying for PhD programs this fall! ovmm.github.io/

Very excited about this first work coming out of my lab, @RobInRoboticsUT, for RSS23! CausalMoMa makes RL policy learning for whole-body MoMa easier by stabilizing backpropagation gradients. And the policies transfer 0-shot to the real world! Great work by @JiahengHu1

1/7 Wanna something between reactive motion generation and motion planning? I am happy to share our newest work Hierarchical Policy Blending as Optimal Transport (HIPBOT) accepted at #L4DC2023! Project website: sites.google.com/view/hipobo…

Training sensorimotor Mobile Manipulation policies with RL is hard: many objectives (non-collision, reach…) and high DoF (arm, base, head…) CausalMoMa (shorturl.at/gjIUW, RSS23) makes it possible by leveraging causal dependencies between action dims and rewards.

Oliver Huke, RACE Robotics Test Facilities Manager at UKAEA, makes it look easy as he navigates Spot across different terrain... This course is part of a competition Oliver has helped to organise at ICRA 2023, which sees different robots perform mobile manipulation tasks within the terrains and obstacles. The @ieee_ras_icra Quadruped Robot Challenges (QRC) has great potential to lead the robotics community in technology advancement, inform researchers and developers about the rigors required to reliably deploy into unstructured environments, and foster interactions with industries to create practical robotic systems. To find out more about Remote Applications in Challenging Environments (RACE), visit race.ukaea.uk/ #robotics l #fusionenergy l #ICRA2023