Pinned Tweet
🚀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
Built for research. Open for everyone.
Let's push humanoid robotics forward, together!
🔗RP1 on GitHub:
github.com/Roboparty/RP1
Join our Discord community:
discord.gg/DTcW6rR3Xa
For ecosystem partnerships:
[email protected]
Join RoboParty and help build an open-source robotics ecosystem.
Turn one team’s work into a starting point for many more.
We invite research teams, developers, and engineering partners to join the RP1 ecosystem.
Together, we can adapt algorithms, share demos on real robots, and exchange hardware modifications—making proven engineering work easier for others to build on.
Bring a research question, an algorithm, or an idea for a practical application.
Join our Discord community:
discord.gg/DTcW6rR3Xa
For ecosystem partnerships:
[email protected]
Join RoboParty and help build an open-source robotics ecosystem.
🤖 Coming soon. 🚀
RP1 — The fully open-source humanoid robot.
Built for developers. Born for intelligence.
#RoboParty #RP1 #OpenSource
Congratulations to RoboParty’s Ye Lei on this latest work, PredActor! 🎉 Excited to see predictive action diffusion advancing steerable humanoid control.
Can humanoid motion generation and control be unified in a single policy?
PredActor uses a single end-to-end diffusion policy rather than separate motion generation and tracking. With proprioceptive feedback, it predicts internal future states and directly outputs actions at 50 Hz onboard a Unitree G1. Text-conditioned motion, joystick steering, disturbance response, and semantic interpolation are supported in the single policy.
Project Page: masteryip.github.io/predacto…
RoboParty’s RP1 made its first global public dynamic showcase at #IROS2026. Powered by UFO—an unsupervised RL framework for humanoid control—and RoboParty’s full-stack hardware, RP1 points toward an open foundation for humanoid robotics. Open-source coming in October. #RoboParty
RoboParty’s RP1 took the KickMe challenge at IROS 2026.
Pushed and kicked by visitors, RP1 recovered its balance and kept moving.
Powered by UFO, an unsupervised reinforcement learning framework for discovering humanoid skills.
#HumanoidRobotics #EmbodiedAI #OpenSource
Humanoid robotics needs to be open.
At #IROS2026, RoboParty will debut ROBOTO 01 (RP1)—a high-performance, full-stack open-source humanoid robot built for developers and researchers.
📍 Booth A100
📅 Pittsburgh | Sep 27–Oct 1
Come see RP1 in motion.
Want to reach out ahead of time? Join our WhatsApp group: chat.whatsapp.com/HjBeVcWOkZ… or email us: contact@roboparty
恭喜 RoboParty Lab 成员 @DavidSunok47 全新成果 INTACT 正式发布!该成果已开源至 RoboParty 仓库,欢迎访问 github.com/Roboparty/INTACT-…
Congrats to the RoboParty Lab member@DavidSunok47 on the official release of INTACT! This achievement is now open-sourced on github.com/Roboparty/INTACT-…
RoboParty retweeted
LeWM predicts action effects, but searches 9,000 sequences to act.
Introducing INTACT: an end-to-end unified JEPA that completes the other half of LeWM: intent to action.
Only 1 epoch. 0 search.
95.33% Direct macro SR.
2.9-5.5 ms inference.
~300× lower planning latency.
🤖Great robotics ideas get stuck on repetitive groundwork.
Party OS from RoboParty Lab solves this with complete humanoid research toolchains.
RoboParty Lab Launches | Party OS for Physical AI Infra youtu.be/7V1N677rAwI?si=IKHC…
Great robotics ideas get stuck on repetitive groundwork.
Party OS from RoboParty Lab solves this with complete humanoid research toolchains.
Video intro: youtu.be/7V1N677rAwI
lab.roboparty.com |
github.com/Roboparty/Party_O…
🏆 RoboParty's RP_VLA took 2nd place globally at #ICRA2026 Reasoning to Action track
🥇 #1 in 2/4 tasks: Restocking & Organizing Shelves, Sorting Packages Continuous.
VLA is the robot's brain — the hardest problem in embodied AI. This is RoboParty's midterm answer.
🤖 Check out concept clips of our open-source full-stack humanoid ROBOTO Origin!
We’ve received user replication cases and are now calling for more participants.
Our prototype is being iterated continuously — stay tuned for updates 🛠️
youtube.com/watch?v=gxdKXrVl…
🤖🏆We are honored to share that our system secured ⭐Global Top 3 ⭐in the ICRA 2026 Official Online Simulation Competition — a flagship event of IEEE ICRA, the world’s most prestigious conference in robotics and embodied intelligence!
#RoboParty #ICRA2026 #Robotics
1/
Humanoid robotics doesn’t need more demos. It needs more rebuildable baselines.
So we open-sourced RoboParty ROBOTO ORIGIN: hardware + motion control + bring-up + validation.
Built in 120 days — from zero to 3 m/s running.
Let’s make humanoids reproducible.
3/
What we open-sourced is not fragments.
We’re publishing the full engineering loop:
sourcing → assembly → calibration → locomotion control → training → validation
That’s the part everyone keeps reinventing.
4/
Join the co-build program.
What we want most:
Rebuild reports
Calibration + failure modes
Benchmark logs
Documentation PRs
Fork it. Validate it. Improve it.
GitHub: github.com/Roboparty/roboto_…
Docs: roboparty.com/roboto_origin/…
Web: roboparty.com/














