ObotX - Open Source Robotics

Open robotics revolution is coming :) @united_robotics @RobotShop @UBTECHRobotics @agilityrobotics @Figure_robot @RobotShop @CMU_Robotics @united_robotics @science @LetsMakeRobots @Tesla_Optimus @TechCrunch @theaienterprise @MatthewBerman @mashable @TheHumanoidHub @verge

@TheReapsZ In human environments - flat flors and stairs. Also when cooperates with second robot - two arms. It also climbs a stairs - it's no problem for tripod.

@open_robotx 99% human tasks...🚩

Our blueprint for the "Optimal Universal Robot": ❌ Legs: Too complex, too expensive. ✅ Wheels: Fast, stable, 10x cheaper. ❌ Rotary Joints: Massive torque stress, custom gears. ✅ Of the shelf parts & linear actuators: High payload, extrem simplicity, off-the-shelf parts.

@xamgore Just no R2D2 sound...we will work on that :)

@open_robotx – Can’t open boxes and take out items – Can’t see exactly what it grabs – Can’t sort through expired products – Can’t move a cart – Can’t put stuff on its head – Can’t clean the floor – Can’t stop a shoplifter – Can’t make R2D2 sound 😬😬😬

@iamRezaSayar We plan to ship within 3 months. We invite for investment subscribtion on our website :)

@open_robotx this is so freaking awesome! 🔥🔥 do we have an ETA for the release date? 👀

@kchezzy88 Will be done in the next iteration. No problem for tripod.

@open_robotx What about stairs?

@MattTrainer For your personal/research purposes you can build it for free and do all what you want - just send us videos :). If you would like to sell, we take just 2% of sales :)

@open_robotx Open source but globally patented? How does your license work? Would love to build this in my shop but patent wars suck.

Progress on our universal mobile manipulator. We believe this is the optimal construction (cost-efficiency). How do you like it? :) Stay tuned for the next milestones.

Why are we still building monolithic robots? 🤖❌ In the 90s, we upgraded PCs part-by-part. We’re doing the same for robots. ✅ Exchangeable parts (hands, bases, sensors) ✅ Multiple simple robots cooperating on complex tasks ✅ Lower costs + easier maintenance

Universal mobile manipulators have a much greater chance of becoming the future of mass robotics than humanoid robots: 99% of the needed use cases are flat floors and stairs, where wheels are much more efficient (energy, speed, stability, cost, etc.). They also cost 10 x less

@yawarnihal nice!

Introducing ShapeR, a method for robust conditional 3D shape generation from casually captured sequences. ShapeR leverages a rectified flow transformer conditioned on per-object multimodal data to turn casual image sequences into full metric scene reconstructions. Project Page: facebookresearch.github.io/ShapeR Paper: arxiv.org/abs/2601.11514 Links to code and huggingface below ⬇️

@davsca1 Awsome!

Check out our latest work, "Actor-Critic Model Predictive Control: Differentiable Optimization meets Reinforcement Learning for Agile Flight," published in the IEEE Transactions on Robotics, where we reconcile #OptimalControl and #ReinforcementLearning, achieving the same super-human performance, but with superior generalizability, as our previous model-free deep RL! Code released! PDF: arxiv.org/pdf/2306.09852 Code: github.com/uzh-rpg/acmpc_… Full Video: youtube.com/watch?v=_qekrF… Model-free #ReinforcementLearning (RL) is known for its strong task performance and flexibility in optimizing general reward formulations. On the other hand, #ModelPredictiveControl (MPC) provides robustness, constraint handling, and powerful online replanning capabilities. In this work, we extend our previous AC-MPC paper (Romero, ICRA'24) by taking a deeper look at how both approaches can be unified. We introduce and extend Actor-Critic Model Predictive Control (AC-MPC), a framework that embeds a differentiable MPC inside an Actor-Critic RL architecture. This integration allows the MPC-based actor to perform short-term predictive optimization, while the critic facilitates long-horizon learning and exploration. We conduct a comprehensive study that highlights AC-MPC’s key advantages: - Better out-of-distribution generalization, both against unknown disturbances and changes in the quadrotor dynamics - Improved sample efficiency - A novel empirical analysis uncovering a relationship between the critic’s value function and the MPC cost function, providing deeper insight into their interplay. We validate our method in simulation and the real world on a quadcopter flying at superhuman speeds of up to 21 m/s, matching state-of-the-art model-free RL performance, and retaining the predictive structure of MPC for more reliable out-of-distribution behavior. Reference: Actor-Critic Model Predictive Control: Differentiable Optimization meets Reinforcement Learning for Agile Flight IEEE Transactions on Robotics (T-RO), 2025 PDF: arxiv.org/pdf/2306.09852 Full Video: youtube.com/watch?v=_qekrF… Code: github.com/uzh-rpg/acmpc_… Kudos to @roaguiangel, @EliJalbout, @realyunlong! @UZH_en @UZH_Science @UZHspacehub @AUTOASSESS_EU @ERC_Research @UZH_ai

@jungwonshin95 Awesome! maybe you could use such construction for your policy training research? youtube.com/watch?v=I4jUil…

We are hiring senior ML engineer, robot learning. Come build robots that work reliably in the real world. We're pushing robot policies beyond demos into production! Apply below.

@JonMSchwartz Maybe you could use such much less expensive arms with 10x payload? youtube.com/watch?v=I4jUil…

Just bots being bots

Link to our repo: github.com/obotx/mobile-m…

We are thrilled to announce the release of our latest open-source Mobile Manipulator Github repository. This release marks a significant milestone in our mission to make advanced robotics accessible to everyone. 🔗 Explore the repo in comments link. Please add star on Github

@lukas_m_ziegler It's possible to build similar working area using 3 of-the-shelf linear actuators only: youtube.com/watch?v=2buClx… What do you think?

This is not a mechanical frog! 🐸 It's a tripteron, a parallel-axis manipulator. Basically, a XYZ platform that moves in three directions using precision linear stages. The movement system is based on a kinematic design from Laval University, optimized for stability and efficiency with fewer moving parts. A key feature is the single long base axis, which simplifies the structure while allowing wide-range movement. The real beauty of mechanical engineering! 😮‍💨

Progress on our super simple universal manipulator, solving 99% humanoid use cases with 10x higher load capacity and 10x lower costs. Anyone interested in the source codes and construction repository? :) Please comment and follow to get updates. #robotics #humanoids

@RobotnikRobots Awesome! Maybe you could use such arms?

DONWNLOAD COMPARATIVE CHART⏬⏬ Mobile manipulators range: Which one suits your robotics project? drive.google.com/file/d/1F8IVHp…

@CobotMy Awesome! Maybe you could use such arms?

【Monday Inspire】🤖Smarter deliveries start with #myAGVPro!🎙️Voice control + 3D #SLAM navigation+ QR recognition = effortless #HRI.🛒Discover the future of #automation 👇 bit.ly/46iT7jt #Robotics #AI #tech

Mobile manipulator use case: arranging products on shelves in the store. Physically accurate simulation made in Google DeepMind MuJoCo. Full autonomy achieved with MPC strategy and PID operation.