Detect change · Predict outcomes · Guide action
We join what site capture shows with what the ledgers and drawings say, so what is where and what has changed stays in one place, for site teams now and robots next.
One 16-minute walk with a 360° camera · 2026-09-10
YODO LABS Inc.Formerly PixelX Inc.
YODO Asset World works out where the camera is standing from the image itself, so the unit in frame resolves to one ledger row even among identical machines. What the site already knows about that one unit opens on the spot, with nothing fixed to the asset and nothing to scan.
From mines to city streets, we have worked alongside six kinds of site. At the airport and in the factory, robots have started to use the record too.
Ricoh (technology partnership)Full write-up coming soon
SakyureFull write-up coming soon
GHDFull write-up coming soon
NEDO · METIFull write-up coming soon
Full write-up coming soon
A robot senses that something is there. What it is, and what has happened to it, sits in the record, and it is the same record people on site already read.
What one camera, person or robot has seen reaches all the others, so a robot can pick up where a person left off.
The record rests on four technologies, set out below.
A single handheld pass returns the site in real units, every object bound to a ledger row by where it stands. A planner can collide against it, a work order can cite it.
The second visit is the hard part: the same unit, a different device, distance and angle. Recognise it and captures accrue into a record, every earlier state still recoverable.
Condition forecasts come off the rounds a site already walks, with nothing instrumented. The forecast stays inside what the rounds have observed, and what comes back is a dated work item.
Spatial questions are usually answered from flat frames, with the depth inferred afterwards. This model works natively in 3D: it outlines the region it is about to measure inside the point cloud, then reads the number off that geometry, so number and evidence arrive together.
Cofounder & CEO
Former strategy consultant at Strategy& (PwC) and Westpac Banking Group. Scaled a SEA start-up insurer from zero to 150M in insured exposure in two years, leveraging automation and AI.
Robotics Lead
15 years building autonomous systems across Amazon (Astro), Google Wing, and Figure AI. Full-stack autonomy from sensor fusion and perception through to real-time decision making.
Research Advisor
Professor at The University of Osaka and Visiting Professor at Stanford University. Computational Imaging, Computer Vision, AI Optics.
We work with robotics teams and industry partners who are putting people and robots into the same changing spaces.
Start with one inspection video. See what YODO Asset World finds.
We are hiring, starting with a founding business member. If no listed role fits, write to us anyway.
