1/ I've created a detailed beginner-friendly guide on how to assemble a low-cost dextrous robotic hand for ~$450 using parts available entirely on Amazon. The hand utilizes a tendon-drive design with 17 DoF and can be easily teleoperated via webcam.
Dima Yanovsky
54 posts
co-founder of prox | cs @mit
- 1/ We figured out how to use monkey brain data to operate robotic arms. We then trained a model to generate synthetic brain data from robotic arm movements and made the first-ever synthetic brain data generation browser game. Project Jenkins (open-source) by @anzahorodnii & me
00:00 - Replying to @yanovskyd2/ We made the brain generation model run entirely in-browser using @onnxruntime. We coded a game where you can move a joystick and generate synthetic brain data in real time. This is the first OSS brain data generation model running in browser! Try it: 808robots.com/projects/jenki…
00:00 - Replying to @yanovskyd and @iotdesignshopYou can find the entire assembly guide, BOM and STL files here: 808robots.com/projects/dexha…
- Replying to @yanovskyd2/ Affordable dexterous robotic hands are essential for advancing robotics research, but off-the-shelf options cost thousands to tens of thousands of dollars. huge barrier for most people.
- 1/Robotics foundation models need internet-scale data to train, and we bet simulation datasets will help reach this scale. It's time to build tools enabling this. So, we're releasing first public app for robot data collection in Vision Pro and a platform to curate datasets
00:00 - Replying to @yanovskyd5/ Check out @anzahorodnii for the breakdown of the neuroscience ML behind the project Here is the web game to generate brain data: 808robots.com/projects/jenki… Here is the project page: 808robots.com/projects/jenki… Arxiv: arxiv.org/abs/2503.14847
- Replying to @yanovskyd3/ It all started when we took a dataset of monkey brain activity during various hand movements. @anzahorodnii trained a model to decode this into velocities, and I configured a robot arm to recreate the movements this monkey was thinking about.
- Replying to @yanovskyd7/ The challenge was that default solvers have no awareness of the robot's surroundings, sometimes creating trajectories through the table that caused the arm to slam into it. We used the ikpy library to create kinematics chains for both Koch V1.1 (@taurobotics) robotic arms.
00:00
00:00 - i got to teleoperate robot hands with my hands using the vision pro. @yanovskyd is literally the coolest roboticst ever. crazy new robotics foundation models will be made with this data. we're so back.
00:00
00:00 - Replying to @yanovskyd3/ my project builds on the Dexhand V1 by Rob Knight and @iotdesignshop. i've edited the original design so you can assemble the arm entirely from parts ordered from Amazon. i've also created a 7-page guide with step-by-step videos, images, and clear instructions.
- Replying to @yanovskyd4/ We then decided to cook more. What if we could go the other way and train a model to take robot movements and generate synthetic neural data that would correspond to thinking about these movements? After many days of work, @anzahorodnii trained the right model that can do it!
- Replying to @yanovskyd6/ One big hurdle on the robotics side was working with inverse kinematics. The robots received coordinates to move to, then inverse kinematics solvers calculated servo angle positions to reach that point.






