The Half-Life of an Address
Every address and point of interest has an expiration date. Here's what causes the decay, and what actually slows it down.
Blog
Notes from
Notes from
the field.
Thoughts on geo data collection, field data, GIS and AI workflow automation — from the team that runs the programmes.
Mystery Visits, Rebuilt: Scenarios, Sampling, Scoring
The three design decisions that decide whether your mystery visit data is evidence or anecdote — and how AI is changing all three.
What a Shopping Mall Digital Twin Actually Contains — and How It Gets Built
A working reference for what goes into an indoor digital twin of a mall or large building, and the field methods used to capture and maintain it.
Probe Requests, MAC Randomisation, and What Retail Analytics Can Still Measure
Phones stopped broadcasting a stable identifier years ago. Here's what mall and store foot-traffic analytics can actually still count — and what it can't.
The Object Ledger: Turning Field Photos Into Proof
A single photo shows what something looked like. A dataset proves what it is, where it sits, and whether it still matches the record.
POI Data Explained: How Points of Interest Get Collected and Verified
Every map pin is a claim about reality. Here's what it takes to make that claim true, and keep it true.
Mystery Shopping Explained: What It Measures and What It Cannot
A field guide to what a mystery visit can prove, how AI is changing the mechanics behind it, and why the same checklist means something different in Berlin than it does in Boston.
Indoor Mapping Explained: LiDAR, Photogrammetry, and Mobile Scanning Compared
Three capture methods, three accuracy profiles, one very different failure mode once you're standing in a glass-fronted atrium at 3am.
The Ambient Census: How Malls Actually Count You
Every phone in your pocket is quietly raising its hand. Here's what happens to that signal between your pocket and a mall's quarterly footfall report.
The Pothole Ledger
A road-monitoring dataset uploaded this month shows what happens when field photography, GPS, and computer vision converge on infrastructure — and where the method still needs a human check.
The Map Isn't Finished: Inside Europe's Street-Level Data Gap
A live HERE and Mapillary campaign is paying Europeans to photograph their own cities. The reason why says more about geodata quality than any market report.
The Mystery Shop That Never Clocks Out
Mystery-visit programs built for quarterly PDF reports are being rebuilt around computer-vision verification and continuous checks. Here's what's actually shipping, and what's still marketing.
Mapping Debt: The Bill Every Mall Eventually Pays
Munich just staged the industry's biggest reality-capture showcase in years. Malls are the reason it's needed.
The Robot Hand That Forgets How to Feel
A September op-ed on tactile sensor wear explains why touch data goes bad long before anyone notices. The same physics shows up in every camera rig collecting egocentric training data in the field.
The Robot Shipment Number Everyone Misread
Humanoid robot shipments nearly tripled in H1 2026. Three research firms can't agree on what most of those robots are actually doing.
Market Research Just Set a Fraud-Detection Floor. Robotics Hasn't.
A new industry benchmark shows quality verification became standard practice in insights work this year. Physical AI data collection is still treating it as optional.
45 Stations, 400 Hours a Day: What a Robot Data Factory Actually Looks Like
A recent operational disclosure from data-infrastructure vendor Unidata shows what egocentric capture looks like once it stops being a research project and becomes a running facility.
Floor Truth: The Data Warehouses Won't Fake
A warehouse robotics company just said the quiet part out loud: the mess is the product. Here's why that logic applies far beyond robotics.
The Body-Zone Problem: Why Robot Data Collection Isn't One Job
A RoboBusiness talk on humanoid motion just named the real bottleneck: hands, hips, and torsos need completely different data. Field research has the same problem.
The 90% Problem: What Synthetic Respondents Still Can't Verify
ESOMAR just formalized rules for AI-generated survey respondents. The accuracy numbers are real, and so are the gaps underneath them.
One Million Datasets Later, Robotics Still Doesn't Have Enough Good Data
Hugging Face crossed one million public datasets this week. For teams building physical AI, that milestone measures noise almost as much as it measures progress.
The Excavator With a Second Job
SoftBank just backed a construction robotics company whose machines survey the site while they dig it. That's not a small detail.
Robot Training Data Finally Has a Price Tag
Three separate reports published this August put real dollar figures on robot training data for the first time. The numbers explain why data collection just moved from the lab to the field.
The Two-Terabyte Tractor: What Agtonomy's Update Really Measures
A multi-point turning feature grabbed the headline. The real story is buried in the data-throughput number nobody asked about.
The Robot Dataset That Fired Its Labeling Team
A new arXiv dataset turns 204,000 clips of human hands into 17 million affordance labels, without a single human annotator marking a frame.
The Desk Distance Problem
AI can summarize ten thousand survey responses before lunch. It still can't tell you whether the shelf tag was actually there.
The Robot-Data Trade Just Got a Street Address
A startup put cameras on a thousand real heads. A new retail dataset just proved that where you point the camera matters more than how much footage you collect.
Figure AI's "Index" Dataset Just Confirmed the Robot Data Race Is an Operations Race
A dataset announcement from Figure AI, paired with fresh moves from LG, Nvidia, and SEER Robotics, shows the real bottleneck in physical AI isn't models — it's field-grade data infrastructure.
Ego2Robot Turns Human Hand Video Into 18,561 Hours of Robot Training Data
A new synthesis pipeline claims to be the largest ego-to-robot dataset to date. Here's what it actually measured — and what it didn't.
The Translation Tax: What a Robot Dataset Teaches Fieldwork
A new arXiv paper on converting human video into robot training data quietly explains why raw field data almost never arrives ready to use.
Why a $22M Robot-Data Startup Is Really a Logistics Company
A headset startup just raised real money to record human hands. The harder problem it's actually solving isn't the camera.
The Robot Park Boom: Why Physical AI Now Runs on Data Infrastructure
Two funding announcements and a dataset paper from the last month show the same thing: robotics companies are now building physical operations, not just models.
The Egocentric Video Data Glut: Why Robotics Teams Still Discard 90% of Bulk Footage
Public egocentric datasets crossed a million hours in 2026, but teams report discarding 90% of bulk footage before training. Why coverage-designed collection is the complement bulk data can't replace.
The EU AI Act's High-Risk Deadline Just Moved to 2027 — Here's What Actually Changes
The EU pushed high-risk AI obligations to December 2027. What the delay does and doesn't change for teams collecting training data now.
How Egocentric Video Is Collected — and Why It's Suddenly In Demand
What it actually takes to capture first-person training video, and why robotics labs can't get enough of it.