SSIO: self-supervised inertial odometry trains across pedestrians, drones, quadrupeds and humanoids without labels
GuanyaShi · x · 2026-10-29
Researchers from Amazon FAR, CMU, UC Berkeley and Stanford present SSIO, the first fully self-supervised learned inertial odometry. An IMU-integration teacher generates short-window velocity targets, and the student learns to predict long-horizon velocity changes better than its teacher. Optional pose-graph distillation refines it further. New embodiments need no mocap, RTK or SLAM ground truth — only unlabeled IMU data. One unchanged recipe matches the supervised AirIO baseline across six datasets spanning pedestrians, drones, quadrupeds and a humanoid. Code and models are open on GitHub and Hugging Face.
More from Embodied
- University of Virginia's robot at International Lunabotics competition looks impressively smooth — TinfoilTricorn · 2026-10-29
- Neuralink's first speech restoration data: ALS participant hits 75 WPM in week one — shivon · 2026-10-29
- MOSS, a mostly 3D-printed litter-picking rover, hits 100 GitHub stars; kits coming — chrismatthieu · 2026-10-29
- Odyssey-3 world model simulates general environments in real time with greater physical accuracy — Scobleizer · 2026-10-29
- One year after 1X opened $20,000 NEO humanoid robot pre-orders, 2026 delivery still in doubt — ChrisGPT · 2026-10-29
- Asimov's open-source humanoid robot is making incredible progress in the open — jonstephens85 · 2026-10-29