Kairos extends 3D scene graphs to 4D to forecast pedestrian presence and directional flow
zhenjun_zhao · x · 2026-09-24
Kairos extends hierarchical 3D scene graphs into 4D scene graphs, storing per-voxel directional mixtures and presence rates so robots can forecast when and where people will move. Spectral predictors output presence probability plus full directional distributions with calibrated credible intervals. Evaluated on a robot-collected campus dataset and a mall and station concourse recorded for eleven months, it rivals dedicated occupancy/flow models trained on full detection streams despite learning from only the fraction a patrolling robot observes.
More from Embodied
- X-Planner: event-structured task planning front-end for long-horizon robot manipulation — Howard Lu · 2026-09-24
- Amazon announces $100M+ robotics manufacturing hub in Indiana to accelerate warehouse automation — Polymarket · 2026-09-24
- Pollen × Hugging Face launch $399 open-source biped Microduck, preorders open Aug 2026 — victormustar · 2026-09-24
- Quadruped robot built to run a marathon on a single battery charge published in Nature — ChongZzZhang · 2026-09-24
- Skild AI CEO Deepak Pathak: robotics stalled 70 years for lack of a general brain — AI Engineer · 2026-09-24
- Hugging Face Adds Episodes Player to All LeRobot Robotics Datasets — mishig25 · 2026-09-24