Custom BB-SLAM hits 0.02m accuracy with pure visual odometry, no LiDAR or IMU
broodsugar · x · 2026-09-18
The Bracket Bot team showed off BB-SLAM, a fully custom visual SLAM system developed over 6 months: no LiDAR, no IMU, just pure visual odometry producing 0.02m-accurate dense voxel maps. In the demo, a robot navigates using a sparse map previously captured by a phone, with the robot's own dense perception overlaid—enabling deployment in minutes. Built on Auki's collaborative perception and mapping.
More from Embodied
- Muse agent installs PyTorch and depth model on its own VM to drive a robot — armand_ruiz · 2026-09-18
- Two Agentic Robots Clean a Room Together, Coordinating by Voice — chris_j_paxton · 2026-09-18
- AI Edit Conjured a Stranger Into a Horse Photo — Apple's Sensor-Signed Reference Image Is the Answer — APPSO · 2026-09-18
- Waymo Announces Expansion to Singapore — ramanan · 2026-09-18
- DARPA surgical AI competition kicks off, veterans liken it to the 2004 self-driving challenge — Laparoscopes · 2026-09-18
- visloc-rs: Pure Rust library for visual & visual-inertial SLAM, SfM and localization — rsasaki0109 · 2026-09-18