OmniSense: the world model as projected perception in a volume.
A Physical AI system's world model, including where and what it is, is a function of sensing projected over a volume by a mesh of nodes: some attached to the system itself, some on peer systems, some anchored in the space. The mesh resolves the volume into three states: positive space (occupied, reconstructed by line-of-sight optical: vision, stereo, LiDAR, event), negative space (confirmed empty, carved along each clear ray), and the unknown behind barriers, which spatial RF (Wi-Fi, UWB, mmWave) sees through to resolve, occupied and empty alike. A system perceives itself not from within but from the whole mesh at once, driving the unknown toward zero.
omnisense on GitHub ↗Sense → perceive → model → simulate → act, as a function of volume, location, and projection. Toggle Single agent ↔ OmniSense to see occlusion close.
↓ Whitepaper · PDFRead online◆ Living paperTechnical Report TR-2026-08 · Institute for Physical AI @ JBI
A mesh of ordinary nodes can resolve a room into occupied, empty and unknown, and it works today. The limit is not the algorithm but where the nodes sit and what they can hear, which turns the frontier into a deployment-geometry question with a measurable answer. Move the nodes, measure again, and you can say exactly how much of the unknown you bought.
One of eight, and only one of them is physics. How we read a frontier →