Voxel Grid Obstacle Avoidance on Jetson Orin Nano with a RealSense D436
chrismatthieu · x · 2026-09-05
A weekend build: voxel grid obstacle avoidance using an NVIDIA Jetson Orin Nano and a RealSense D436 stereo depth camera. Depth shows where things are; a voxel grid turns it into a 3D map of occupied vs. free space so the robot can decide where it can safely move. Demo video included, source code linked in the YouTube comments.
More from Embodied
- Humanoid robots lose balance without power, so companies avoid homes with small children — binarybits · 2026-09-05
- Tesla Cybercab picks up rider at hotel for breakfast in first-hand test — EricETesla · 2026-09-05
- MuJoCo Menagerie hits PyPI: load any robot model in one line, no 2GB clone — kevin_zakka · 2026-09-05
- Fable 5.1 boosts robot arm block-in-bowl success from 5% to 40% with 1.5x fewer tokens — ycombinator · 2026-09-05
- One policy controlling 4 different robot hands for in-hand manipulation rejected by CoRL — YuXiang_IRVL · 2026-09-05
- Shenzhen collapses hardware iteration to hours — why physical tech builders go to Huaqiangbei — zakelfassi · 2026-09-05