simulation & RL for humanoids @ UMA + frenetic open-sourcer. Sorbonne mEng '26. Past: PAL Robotics, uTokyo, AIRBUS
nvidia-smi
Joined October 2022
- Tweets932
- Following457
- Followers882
- Likes2.7K
Pinned Tweet
Open-sourcing pal_mjlab -- the RL work I did at PAL Robotics. Velocity tracking, motion imitation, and dual-arm reaching across KANGAROO, TALOS, and TIAGo Pro. Multiple tasks transferred to real hardware, all built on @kevin_zakka's mjlab.
Louis Le Lay ✈️ CoRL retweeted
Excited to announce I just joined @UMA_Robots as Lead Middleware Engineer!
Every robot has a nervous system, and I will help build theirs. 20+ years on one question: the right data, to the right place, at the right time. From DDS to Zenoh, now for humanoid robots.
Let’s build! 🦾
Louis Le Lay ✈️ CoRL retweeted
The @Tesla Roadster stunts, simulated in MuJoCo! Thrusters are site actuators, the ramp suction uses adhesion actuators, and the builtin box QP decides how hard to fire each jet.
I really like these guys, I think it's the best open-sourced hardware out there
🚀RP1 is officially here.
🌍Putting control of robotics back in developers’ hands.
Introducing RP1 (ROBOTO 01) by RoboParty—a high-performance, fully open-source humanoid robotics platform for frontier robotics research and embodied AI model development.
🤖 Open across the full hardware and software stack:
• Robot platform: mechanical CAD, bill of materials, and assembly documentation
• Actuators: in-house ROMOMO joint designs and related technical resources
• Control: electrical systems, firmware, low-level drivers, and motion control implementations
• Development: simulation models, SDKs, data processing tools, and training tools
• Engineering foundations: technical documentation and research materials
Open the black box.
Understand the system.
Make it your own.
A deviation in motion can originate in the model, control policy, actuator response, or mechanical structure.
RP1 opens up the design and implementation of these layers so developers can trace problems, modify the system, and validate changes on real hardware.
Open-source algorithms for advanced motion control
RP1 has demonstrated continuous walking, recovery from disturbances, getting back up after a fall, and human motion tracking.
UFO and MimicLite connect motion learning, control policies, and execution on real hardware.
The open toolchain connects data collection, simulation training, hardware deployment, and experimental validation—supporting joint iteration across models, control, and hardware.
From RPO to RP1, we’re turning one team’s engineering experience into a starting point for many more.
Opening the future of embodied AI to everyone ready to explore it.
🔗RP1 on GitHub:
github.com/Roboparty/RP1
#RoboParty #RP1 #OpenSourceRobotics #EmbodiedAI
back-to-back from octi et al.
(1/6) From @GoogleDeepmind’s AlphaGo to AlphaZero, we saw machines find moves that reached beyond what we’d imagined for them. No one taught them those strategies. They emerged from reinforcement learning: playing, failing, and trying again under a single binary task reward for success or failure. Inspired by them, we couldn’t help but wonder: what might a robot discover if we gave it that same freedom to learn?
That question led us to AlphaNIST. Starting tabula rasa, with that same binary reward plus only a simple control cost, a single policy solves all 20 @NIST assembly tasks at a 98.2% success rate in simulation. More surprising still, AlphaNIST can complete 10 different tasks in a row, receiving that reward only once, after all 10 are done.
Just as AlphaGo’s strategies surprised its creators, AlphaNIST discovered dexterous strategies we couldn’t have come up with ourselves.
Paper: arxiv.org/abs/2610.13354
Website: alpha-nist.github.io
Louis Le Lay ✈️ CoRL retweeted
(1/6) From @GoogleDeepmind’s AlphaGo to AlphaZero, we saw machines find moves that reached beyond what we’d imagined for them. No one taught them those strategies. They emerged from reinforcement learning: playing, failing, and trying again under a single binary task reward for success or failure. Inspired by them, we couldn’t help but wonder: what might a robot discover if we gave it that same freedom to learn?
That question led us to AlphaNIST. Starting tabula rasa, with that same binary reward plus only a simple control cost, a single policy solves all 20 @NIST assembly tasks at a 98.2% success rate in simulation. More surprising still, AlphaNIST can complete 10 different tasks in a row, receiving that reward only once, after all 10 are done.
Just as AlphaGo’s strategies surprised its creators, AlphaNIST discovered dexterous strategies we couldn’t have come up with ourselves.
Paper: arxiv.org/abs/2610.13354
Website: alpha-nist.github.io
Louis Le Lay ✈️ CoRL retweeted
We hosted @Numerama in our lab for their deep dive on the humanoid race between the US and China.
Our CEO @RemiCadene on what real autonomy looks like beyond spectacular demos, and where Europe fits in.
Full video (in French) 👇
Louis Le Lay ✈️ CoRL retweeted
(1/5) Everyone says dexterous manipulation needs real-world data. These policies were trained with none. Our robots mesh gears, thread nuts, and insert pegs zero-shot from RGB, and the same recipe works for locomotion across terrains much harder than before.
The missing piece wasn't a better RL algorithm, but a small tweak to what the robot practices.
Today we're releasing Success-Guided Sampling (SGS), a simple change to the task sampler that unlocks new levels of dexterity and agility with large-scale, end-to-end sim2real RL.
No demonstrations, no per-task reward tuning. Just PPO at scale.
Check out the policies yourself at sgs-rl.github.io! All videos at 1x speed! 🧵 🔈
Louis Le Lay ✈️ CoRL retweeted
First flip of a Booster K1 ever? @boosterobotics
Louis Le Lay ✈️ CoRL retweeted
“Decommissioning” our @boosterobotics robot with a front flip off a table for fun. Made end-to-end in half a day.
Louis Le Lay ✈️ CoRL retweeted
Meet Workhorse 🐴: we study how to learn whole-body loco-manipulation skills from human demos without teleop.
Here is my favourite video: we tried everything to make it fail🏒.
One take, real-time, fully autonomous.
Can a humanoid learn robust whole-body loco-manipulation directly from a human? No robot, no teleop, no retargeting.
Meet Workhorse 🐴: our G1 topples and climbs a suitcase, catches a thrown box, and sorts boxes with hands and a kick. Fully autonomous.
More videos at hybridrobotics.github.io/wor…
Louis Le Lay ✈️ CoRL retweeted
Can a humanoid learn robust whole-body loco-manipulation directly from a human? No robot, no teleop, no retargeting.
Meet Workhorse 🐴: our G1 topples and climbs a suitcase, catches a thrown box, and sorts boxes with hands and a kick. Fully autonomous.
More videos at hybridrobotics.github.io/wor…
oh wow love it
Can a humanoid learn robust whole-body loco-manipulation directly from a human? No robot, no teleop, no retargeting.
Meet Workhorse 🐴: our G1 topples and climbs a suitcase, catches a thrown box, and sorts boxes with hands and a kick. Fully autonomous.
More videos at hybridrobotics.github.io/wor…
Louis Le Lay ✈️ CoRL retweeted
⚡ One policy, millions of embodiments, over 200 robot models. Can we add yours?
We're building γ₀, a generalist RL policy for motion control trained across millions of randomized embodiments derived from a growing collection of more than 200 robot models.
Louis Le Lay ✈️ CoRL retweeted
Really cool hand :)
Boston Dynamics is an inspiration for so many!
Today we give Atlas dexterous hands, with the strength to take on real work, and the simplicity for mass manufacturing. Like the body, the hands are designed with high fidelity simulation in mind, to enable sim-to-real RL. If you give dexterous hands to a robot, make them do dexterous things.
More thoughts here
Blog: bostondynamics.com/blog/robo…
Video: youtube.com/watch?v=4whgw2gL…
Louis Le Lay ✈️ CoRL retweeted
Any online optimization (IK, ID, MPC) for low-level control should be abandoned. A RL policy can fundamentally track more precisely, more robustly, and adaptively to unknown disturbances and uncharacterized noise, especially for low-cost hardware, even on a manipulator.
these days we're blessed with a cool new interaction-aware retargeting method every day
Humanoids can imitate our movements, but can they imitate how we manipulate objects?
OTRetarget uses optimal transport to jointly retarget robot + object motion, preserving contacts across body and object shapes.
🔗simple-robotics.github.io/pu…
#HumanoidRobots #Robotics