Excited to announce Tau Robotics (@taurobots). We are building a general AI for robots. We start by building millions of robot arms that learn in the real world. In the video, two robot arms are fully autonomous and controlled by a single neural network conditioned on different language instructions (four axes and five axes robot arms). The other two arms are teleoperated. The entire hardware cost in the video is about $1400. The video is at 1.5x speed.

We are hiring engineers @taurobots to scale robot learning to millions of robots. If you are experienced in reinforcement/imitation learning or have experience building robots, send me a message.

Collecting some data on our robot playground @taurobots

@frank_pinnola A few hundred dollars

Robots are teleoperated in the video, 1.5x speed

@seclink @taurobots The arm design is open source:

@marshallk @taurobots yes

There is now a MuJoCo simulation for the low-cost robot arm. This can be used for testing and reinforcement learning. Contributed by @arbwes.

@lukas_m_ziegler

The $250 open-source robot arm is on the front page of Hacker News currently. Nice discussion at

@thejamesvance @gazorp5 I'll use a learned simulator. The low-cost robot arms make it possible to build a massive robot farm in the real world and collect a dataset to learn a world model.

@0xreklaw Maybe they can already. I haven’t tried it yet

@gazorp5 Yes, but I’m working on the autonomous execution

@YeojMars I've used the Creality Ender 3 V3 SE and the Bambu Lab P1P. The P1P is better but also more expensive.

@kenny__shaw The latency is almost 10x lower when connected to a macbook. The U2D2 works fine with Linux. Also see here:

@HououinTyouma That's easy to do. But you'll probably have to add one more axis.

The design is inspired by the ALOHA project from @tonyzzhao and the lower-cost version GELLO by @philippswu.