ObotX - Open Source Robotics

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.

@amazon @amazonIN @AmazonUK

A humanoid robot just beat a human in a 10-hour pick-and-place stream. No breaks, no fatigue, pure efficiency. But at $100k+, the price tag is holding back a massive corporate shift. The real question: Do we actually need humanoids for this? #Robotics #Automation

@gs_ai_ It's awesome, but how the digital tween was done on this video? We can not find that in your repo. Btw. does your simulation engine work with closed loop invers ekinematics like ours? thank you

We are back again :) After three weeks of quiet building. Introducing Genesis World 1.0, our latest simulation platform, the second release in our full-stack suite. Open-sourced. Robotics is still bottlenecked by the 1× speed of the physical world. Every model, checkpoint, and data recipe eventually needs to be tested on physical hardware, slowly, expensively, and with limited coverage. One hour in reality can become 100 days in simulation. That is how robotics model iteration moves from a wall-clock bottleneck to a compute problem. To make this work, simulation has to be both fast and trustworthy. Over the past year, we rebuilt the entire stack: a GPU-accelerated cross-platform compiler, penetration-free multi-physics contact solvers, unified rigid and deformable physics, and a photo-realistic renderer purpose-built for physical AI applications. We built Nyx, a high-performance path-traced rendering engine for robotics application. Genesis World 1.0 achieves near realtime performance with our latest development for penetration-free IPC solver, supporting various types of deformables beyond rigid bodies. It supports contact-rich, dexterous manipulation simulation across different embodiments: unitree, sharpa, wuji, genesis hand and various types of grippers. Under the hood is Quadrants, our effort in pushing forward cross-platform GPU-accelerated computation. Quadrants started as a fork of Taichi, and we rebuilt most of the critical parts for optimizing simulation workloads, giving 10x faster launch time and up to 4.6x runtime performance compared to the initial Genesis release. Together, they bring us to an unprecedentedly low sim-to-real gap, enabling zero-shot real-to-sim model evaluation and much faster iteration of GENE. All available today. Genesis World 1.0: github.com/Genesis-Embodi… Quadrants: github.com/Genesis-Embodi… Nyx: github.com/Genesis-Embodi…

@InPostPL @DHLGlobal @UPS @FedEx

@asvfertz It's a case of costs and complexity.

@open_robotx humanoid is about the versatility so yeah, we dont actually need humanoid to do this but at the same time, if humanoid can, then why not?

@joeteicher Please watch full video - this constructon can pick up from ground.

@open_robotx This is a trivial demo task not fully realistic. And what happens if a package falls and goes under the table? A humanoid can bend down and get it, it could even crawl under if necessary.

@Deepans36819800 @AgilexRobotics @adcock_brett Awesome! Maybe you could help us in our pick and place solution?

Just some final bug fixes (arm slowing down between 00:06 to 00:12) before we come to human productivity. Running @AgilexRobotics piper arms continuously for 10 hours now. 200 hours next?? Inspired by @adcock_brett lol

The actual cost of humanoid robots (a few kilograms of payload). Would you buy one, or would you prefer to try our universal mobile manipulator design? :)

@jonathanhawkins @threejs @AgilexRobotics Awesome! What RL algorithms have you used? We are using OMPL for our pick and place solution.

For this hackathon I taught a robot to beat you in Jenga. It sims every possible move, picks the block that's the best move, then an RL policy pushes it out. Built in MuJoCo & @threejs, running on a real @AgilexRobotics arm.

Working on connecting Nav2, and MoveIt in ROS for the most efficient and convenient "pick and place" solution in universal robotics. What do you think? #robotics #physicalAI

Fast and simple pick and place example using @OpenRoboticsOrg ROS and default MoveIt. Check out our repo to play with that. #openrobotics #ROS #MoveIt #OpenSource

Exciting news! 🚀 We’ve released the first Motion Planning & ROS package for our open-source mobile manipulator. Select an object & a shelf—the system calculates the optimal base, arm, and hand trajectories for seamless pick-and-place. 🤖🦾 Code: github.com/obotx/open-sou…

We are proud to announce that we are a finalist in a prestigious robotics contest. It's an honour to be in such a great group of innovative companies. #robotics #ai #humanoids

@AntonioSitongLi Awsome! Maybe you could hrlp us build something like this? youtube.com/watch?v=LuVObV…

Fully assembled, say hello to the future of cheap humanoids!

@antoinemarcel Wow, thats awesome! Could you help us build: youtube.com/watch?v=LuVObV…

since I got a robot, I’ve been getting lazier and lazier

@Arcanous98 Nice, could you please recommend how to get mesh out from such GS? Thank you a lot

Introducing Neural Harmonic Textures: our new method for real-time novel view synthesis that outperforms all 3DGS and NeRF derivatives including (finally) ZipNeRF in terms of quality across all benchmarks. The code is released (Apache 2.0): (research.nvidia.com/labs/sil/proje…) 🧵

Think humanoids are the only way to conquer stairs? Think again. 🤖🚀 New universal mobile manipulators are proving that wheels can climb too #Robotics #Innovation #FutureTech #Automation

@davidfeldt Awesome! Can we add ? : youtube.com/watch?v=LuVObV…

Building hardware has never been easier. Most people still don't know where to start blueprint.am

@zshobbs Wow, would you help us build this?: youtube.com/watch?v=LuVObV…

Hello from London and bail!! Back at it.

@_murc_ Per Unit, monthly $100 for software

$1500, per month? Seems high, I don't really like the design. It's fine in an empty supermarket with big aisles. Now fill it with people, including kids, that gangly mofo shifting positions & swinging around, knocking over elderly, while tripping everyone else. But hey, I'm a keyboard warrior with zero robotics experience...so WTF do I know. Good luck! I love robots.

BIG NEWS: ObotX raised $120M! 🚀 Forget over-engineered jumping humanoids. We’re scaling universal mobile manipulators using engineering simplicity and off-the-shelf parts. The goal: 10M robots, $1B MRR from monthly software subscription controlling the robot. Details below👇