FrodoBots

Been tinkering with @OpenClaw — built an agent that drives a @Frodobots Rover deployed in Africa. Releasing soon with @BitRobotNetwork 🤖

We have SLAM on the Robocap! 🎉 Visualized with @rerundotio Using @NVIDIAAIDev cuVSLAM for GPU-accelerated multicamera tracking. I basically wrote zero code myself and fully used Claude Code for this. It worked because I had so many existing examples to point to that it just wrote everything the way I would have. A few technical wins: 1. Used rattler-build from @prefix_dev to package the compiled cuVSLAM CUDA binaries, which made it SUPER easy to use across repos. This also means it works on the DGX Spark (ARM64) out of the box. 2. Zero-setup experience: git clone && pixi run track-robocap auto-downloads a 100MB dataset from HuggingFace and tracks frames. 3. Real-time 3D visualization with trajectories, landmarks, pose graphs, and video playback in Rerun. Still visual-only (not visual-inertial yet), and loop closure needs some debugging. Next steps are getting this into a Gradio interface, then into daggr, and extending it to work with other datasets from exoego-forge. The last piece I'm excited about: Rerun's RRD files now support layers for incremental data. Planning to build pipelines that go from raw sensor data → slam -> human pose → depth estimation → etc. Repo here: github.com/rerun-io/roboc…

Very excited about all the cool stuff I'll be shipping in the next few months with @rerundotio and @BitRobotNetwork =]. Been looking forward to getting this hardware for a while

🚨 EXTENDED: @frodobots and @ET_Fugi Season 2 Quests now run until January 2nd! The mission: 🤖 Pilot your bot ✅ Complete tasks 📈 Stack Qualified Miles 💰 Earn up to 60 USDC More time to grind. More time to earn. Drive your bot now → ygg.link/Frodobots

We kept hitting the same wall: expensive hardware, limited access, and autonomy experiments stuck inside the lab. So we teamed up with @frodobots and @LeRobotHF to change that. Introducing the Earth Rover Mini+ : a <$300 open-source autonomous rover that’s already driving in cities worldwide. With 7TB+ of real teleop data and seamless LeRobot integration, you can train and deploy policies remotely over 4G in minutes. No more “sim-only” constraints. No more wondering where or how to deploy. Just real robots, real streets, real data and its completely opensource Start building on Earth Rover now And a special shoutout the team who made this happen at SIGRobotics: @saketh0621 @SomrishiB @Hassoonu618 @MittalAarsh

Very excited to release this together with @frodobots and @BitRobotNetwork, awesome to see them open sourcing the robot and dataset! Explore the dataset on the Hugging Face Hub and checkout Earth Rover Mini+ in LeRobot!