Interesting....same as our upcoming low-cost and open-sourced hand. 😉

LLMs are capable of high-level planning, but they require pre-trained skills! Our #ICLR2024 paper instead uses LLM guidance to train RL agents from scratch to solve 25+ long-horizon robotics tasks across four benchmarks w/ >85% success rates Paper & code: mihdalal.github.io/planseqlearn

Cool work using our open source LEAP Hand on a small robot arm! Excited to see where your project goes!

DeXtremeFGP is our new follow-up work on bringing a Geometric Fabrics based framework with DeXtreme for smooth and safe behaviours on the real robot. All trained in simulation. website: dextreme.org/fgp.html paper: arxiv.org/abs/2405.02250

Great investigative work by Toru and co! Gloves are definitely a great way to collect robot hand teleop data. Our lab has also been also building a big setup which we will demo and open-source at RSS 2024 :)

Reactive vs Planning is a big debate. As a proponent of bottom-up robotics, I am always curious as to how far we can push the reactive paradigm. Presenting SPIN this week at #CVPR2024: end-to-end policy for perception, navigation & manipulation without any mapping or planning.

Exciting new work! Fast, robust, reactive, direct-from-sensor grasp-anything policies. RL really works, and it’s going to transform the entire robotics economy. DextrAH-G: Dexterous Arm-Hand Grasping arxiv.org/abs/2407.02274

Our new exciting work on hand arm grasp-anything is out now. All trained in sim with RL. Direct pixels to action grasping on a 23 DoF system with hand and arm jointly coordinating to pick up objects. Fast, reactive and buttery smooth motion. Some of the coolest results (!)

Using human hand and video data with powerful tools such as HRP is a very important part in building dexterous robot hand policies!

We are demoing our LEAP Hand teleoperation system today (Thursday) at #rss2024 with MANUS™ in van Hasseltzaal (the demo room behind the poster rooms in the 3rd floor). Come try and teleoperate our low-cost easy-to-build dexterous robots hands!

Thank you for organizing the workshop! It was really fun and super informative with a ton of great speakers!

Great new project and results by Austin Patel and co using LEAP Hand. Congrats!

Want to scale RL with your shiny new GPU? 🚀 In our ICML24 Oral we find that RL algorithms hit a barrier when data is scaled up. Our new algorithm, SAPG, proposes a simple fix. It scales to 25k envs and solves hard tasks where PPO makes no progress. sapg-rl.github.io 1/n

We’re pushing the boundaries of what’s possible in #robotics with our cutting-edge gloves. Watch how Tesla, @CloneRobotics, Wonik Robotics, @Kenny__Shaw, and others use gloves to train and operate advanced technology.

Designing good robot hands for robot learning is a VERY VERY hard problem. With our latest work we have made some progress on this but there's still more to do. I encourage more people to get into hand design, it's a very interesting research problem!

"We design and manufacture low-cost and easy-to-use devices for collecting human demonstration data" 🤔 they forgot to mention git clone umi-gripper.github.io

🔗 Thoughts on Research Impact in AI. Grad students often ask: how do I do research that makes a difference in the current, crowded AI space? This is a blogpost that summarizes my perspective in six guidelines for making research impact via open-source artifacts. Link below.

Thank you Kevin for all of the help! Should be very useful for many!

Some CVPR 2025 new policies: 1. Submitters must review 2. Terrible reviewers will have their submissions rejected 3. Authors may not submit over 25 papers Reasonable policies, but the fact that the ML community has gotten to the point where any are required is embarrassing