Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Build a humanoid robot yourself! ๐Ÿชš OpenArm is an open-source humanoid robot. It comes with full CAD, control code, firmware, and simulation tools, everything needed to build, modify, and operate it. The arms are designed to be compliant and backdrivable. Teleoperation is supported, with force feedback and real-time gravity...

233,493 Aufrufe โ€ข vor 1 Jahr โ€ขvia X (Twitter)

33 Kommentare

Profilbild von Lukas Ziegler
Lukas Zieglervor 1 Jahr

Start building:

Profilbild von Tom Primoลพiฤ ๐Ÿช๐Ÿฃ๐Ÿฅข๐Ÿค–๐Ÿฆพ๐Ÿฆฟ๐Ÿš€๐Ÿ—ป๐ŸŒ๐Ÿซ๐Ÿ๐Ÿค๐ŸŒฏ/acc
Tom Primoลพiฤ ๐Ÿช๐Ÿฃ๐Ÿฅข๐Ÿค–๐Ÿฆพ๐Ÿฆฟ๐Ÿš€๐Ÿ—ป๐ŸŒ๐Ÿซ๐Ÿ๐Ÿค๐ŸŒฏ/accvor 1 Jahr

who can I throw money at to to get this delivered in a box?

Profilbild von PrismaX
PrismaXvor 1 Jahr

This robot is better at the bottle flip challenge than humans.

Profilbild von Danijar Hafner
Danijar Hafnervor 1 Jahr

Finally robots can welcome people with open arms

Profilbild von 5่ปธใƒž ๏ผ ไบ”ๅๅต ๅ…ฌไฟŠ
5่ปธใƒž ๏ผ ไบ”ๅๅต ๅ…ฌไฟŠvor 1 Jahr

ๅ‹•็”ปใ‚’็ฝฎใ„ใฆใŠใใพใ™ใ€‚

Profilbild von ๐ŸŒธ ellie ๐ŸŒธ
๐ŸŒธ ellie ๐ŸŒธvor 1 Jahr

@jicapal wonder if you could put this in a backpack and use at work to be hands free in some situations like doc ock

Profilbild von Ivan Ilych
Ivan Ilychvor 1 Jahr

Also @enactic_ai

Profilbild von Lukas Ziegler
Lukas Zieglervor 1 Jahr

@enactic_ai shiiii, couldnโ€™t find them somehow, hope the link to GitHub is enough โœŒ๐Ÿผ

Profilbild von alexanderha
alexanderhavor 1 Jahr

6500$ according to the hardware docs

Profilbild von Loosh AI
Loosh AIvor 1 Jahr

OpenArm hits the sweet spot between accessibility and real-world capability โ€” bridging simulation with compliant hardware is exactly what open-source robotics needed. This could accelerate the next wave of embodied AI innovation.

Profilbild von Haven Labs
Haven Labsvor 1 Jahr

Interesting. Weโ€™ve been working on a platform that lets robotics teams run full digital-twin simulations before deploying to hardware, letting real-world robots learn faster and safer. Love seeing open-source projects like this pushing dexterous manipulation into the mainstream

Profilbild von PrismaX
PrismaXvor 1 Jahr

The teleoperation looks nice with almost 0 latency.

Profilbild von Lilith Datura
Lilith Daturavor 1 Jahr

we got robot arms now

Profilbild von deks
deksvor 1 Jahr

okay, I will. and thank you, let's!

Profilbild von Ritwik Pavan
Ritwik Pavanvor 1 Jahr

very cool

Profilbild von YODABEAST
YODABEASTvor 1 Jahr

Excellent idea ๐Ÿ’ก!

Profilbild von Helvio
Helviovor 1 Jahr

Can I deploy on Docker?

Profilbild von Dennis
Dennisvor 1 Jahr

Bookmarked This looks awesome. In this age of AI no maker/robotics enthusiast has an excuse to not create stuff like this, now that AI is eliminating all technical expertise barriers.

Profilbild von The Alloy Mind
The Alloy Mindvor 1 Jahr

looks pretty efficient ! nicely done

Profilbild von Marlon
Marlonvor 1 Jahr

brb setting this up in my home office

Profilbild von truth.phd
truth.phdvor 1 Jahr

Compliant, backdrivable arms are not just safe; they are a cheat code for learning and teleop data. Switch on gravity compensation, then the arm feels weightless; you can guide it by hand and record trajectories, torques, and contact events to replay or train policies later. Add a simple wrist force torque estimate from motor current and joint velocity; now you can do ad hoc haptics, bump detection, and soft grasping. Bonus: use sim to autotune impedance modes: soft for exploration, stiff for precision, medium for everyday tasks. Cheap tactile works too: foam pads with conductive film become touch sensors; great for learning where the robot contacts the world. Build; demo; record; refine; repeat; that is the loop that turns open hardware into capable behavior.

Profilbild von WhiskeyJack
WhiskeyJackvor 1 Jahr

Is it going to be compatible with cameras and automation? I need arms that can be mounted and fully automated. This is the first example I have seen that looks to be fast enough.

Profilbild von Henri Pereira
Henri Pereiravor 1 Jahr

I believe this will a the future of robots , Lego type diy assembly of the hardware and open source and ai for the rest

Profilbild von Radek Voltr
Radek Voltrvor 1 Jahr

Love it. How much $ is budget for arm?

Profilbild von Jonathan Stephens
Jonathan Stephensvor 1 Jahr

Not sure if Iโ€™m more impressed by the project or the teleoperator assembling that box!

Profilbild von SoloTech
SoloTechvor 1 Jahr

This is so good for many of us out there.

Profilbild von Hafiza
Hafizavor 1 Jahr

Awesome

Profilbild von ๏ผก๏ฝ‡๏ฝ…๏ฝŽ๏ฝ” ๏ฝ๏ฝ๏ฝ„๏ฝ…
๏ผก๏ฝ‡๏ฝ…๏ฝŽ๏ฝ” ๏ฝ๏ฝ๏ฝ„๏ฝ…vor 1 Jahr

can i order one?

Profilbild von Humanoid Network
Humanoid Networkvor 1 Jahr

Avengers assemble

Profilbild von AI_TechnoKing
AI_TechnoKingvor 1 Jahr

How much? ๐Ÿ’ฐ

Profilbild von Danijar Hafner
Danijar Hafnervor 1 Jahr

Congrats!! Legs next?

Profilbild von samakruTTi.base.eth ๐ŸŒธ
samakruTTi.base.eth ๐ŸŒธvor 1 Jahr

๐Ÿค–

Profilbild von Rob Cain
Rob Cainvor 1 Jahr

'we was promised robot legs' ;{

ร„hnliche Videos

๐Ÿš€RP1 is officially here. ๐ŸŒPutting control of robotics back in developersโ€™ hands. Introducing RP1 (ROBOTO 01) by RoboPartyโ€”a high-performance, fully open-source humanoid robotics platform for frontier robotics research and embodied AI model development. ๐Ÿค– Open across the full hardware and software stack: โ€ข Robot platform: mechanical CAD, bill of materials, and assembly documentation โ€ข Actuators: in-house ROMOMO joint designs and related technical resources โ€ข Control: electrical systems, firmware, low-level drivers, and motion control implementations โ€ข Development: simulation models, SDKs, data processing tools, and training tools โ€ข 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 validationโ€”supporting joint iteration across models, control, and hardware. From RPO to RP1, weโ€™re turning one teamโ€™s engineering experience into a starting point for many more. Opening the future of embodied AI to everyone ready to explore it. ๐Ÿ”—RP1 on GitHub: #RoboParty #RP1 #OpenSourceRobotics #EmbodiedAI

RoboParty

63,561 Aufrufe โ€ข vor 14 Tagen