After seeing that nothing out there worked, I decided to start Hyper, a startup with the mission to build accurate indoor navigation, and scale it to a billion people. I’ll skip us forward — past the years of fundraising, hiring, R&D, failed pilots, successful pilots — and tell

Once we started to work with large global retailers, we needed a better way to scale this process. Ideally, the staff at the store could do this themselves — rather than us flying our team across the world — and then we could lower the cost and timelines. So we built a self-serve

As the icing on top, precise location feeds into our other area of research: AR navigation. We’ve refined this user experience to be best-in-class, driven by Hyper-accurate location. Most of Hyper’s story still hasn’t been told. One day I’ll explain how we worked secretively for

Many people are asking what comes next: we’re seeking acquisition opportunities, to help us take this technology to a billion people. My DMs are open, as always. Maybe we can make this the start of the next act!

@AndrewHartAR 🤔 is it possible to "fake" a gps sattellite ? i.e. if u made each ceiling corner a sattelite pointing inwards

@AndrewHartAR what a load of crock. less than 0.1% of this "need" is to help the person being tracked. The rest is monitoring, control, and feeding unwanted ads.

@AndrewHartAR Call me old fashioned, but I don't want stores tracking my every move to sell me more stuff.

@AndrewHartAR This feels either a) totally made up or b) a moron in retail Why? Roughly 30% of sales come from customers looking around to find what they need. It’s why planograms and shelf positioning is constantly moved 🤣

@AndrewHartAR This is a really hard problem. I’m curious though. If your tech is so good, why hasn’t adoption been higher ? Why are people still using beacons? Also why sell the tech instead of build it up ?

@AndrewHartAR This 🩵 I tried doing this with the magnetic field navigation you describe combined with the stores planogram data in 2015. InGuide, worked like a charm but failed as all the major retail chains I talked to insisted that it is better for their business to have people wandering

@AndrewHartAR i wonder how the customer feels if they found out they are being tracked, unbenounced to them, at stores.

@AndrewHartAR Great progress over the years, nice work. Could this be used in connection with surveillance on example a warehouse/Terminal, so when a Barcode is scanned the excat location is captured. Making it possible to track shipments via surveillance much easier. When a shipment is

@AndrewHartAR Wasn't it solved with iBeacon? using Bluetooth instead of GPS?

@AndrewHartAR I built something like this for hospital equipment. They would lose track of pumps and tools and stuff. We attached tiny widgets on the devices and they would render in a 3d map kind of like minority report. I can't remember what the trackers were called it's been so long. We

@AndrewHartAR we have done this successfully a decade ago when Apple & Android didn’t randomise the MAC addresses it was quite easy to triangulate signal strength from minimum 3 sensors however after randomisation of MAC addresses it has become complicated & the cost doesn’t justify demand

@AndrewHartAR Doesn’t online ordering and in store pickup negate the need for this somewhat?

@AndrewHartAR This would solve all of the summon issues for Tesla.

@AndrewHartAR Awesome that you got this to work so well. It’s a bit weird to me that Apple was unable to do something like this despite the obvious utility of this sort of thing and their unrivaled resources (plus their ability to put any sensors they want into the devices!).

@AndrewHartAR this is cool! can see wild applications built with this kinda accuracy. congrats and best of luck!

@AndrewHartAR Isn't it simpler to just use an IKEA style directory? Aisle x, column y, shelf z ... Anytime a product is replenished, its QR code is scanned and the location QR code is scanned by the store employee. That ensures that the data is always up to date. And customers can just search

@AndrewHartAR So this is non-visual SLAM problem, right? I think there are works on soundwave-based SLAM, you can maybe augment this with IMU signal and maybe GPS to help with outliers

@AndrewHartAR This will work extremely well in conventions

@AndrewHartAR pretty neat! A friend of mine won a Facebook hackathon a while back doing something similar but that involved taking a picture of a fire escape map, and then using AR and CV to determine where you were and how to get to the exit

@AndrewHartAR Do they need to be on the stores WiFi for this to work?

@AndrewHartAR Back in college, @leafamrit and I were building Bellbots while solving this problem. Instead of using bluetooth beacons, we used RFID tags’ carpets. It was such a fantastic experience independently R&Ding on this problem. Your post has made me want to go back to solving it.

@AndrewHartAR @Google buy this

@AndrewHartAR Great post, thanks for sharing. Do you know what MapsPeople use?

@AndrewHartAR That’s interesting. I remember around that year partly solved how Amazon sales increase regionally based on physical store locations that see products in-person but buy online. Interesting geo data! Reminded me of this

@AndrewHartAR So many times in my life I thought about this idea..I always thought the reason nobody wants to deliver these navigation help is caused in psychological reasons..people would spent less time and buy less things they wouldnt need.

@AndrewHartAR This is fascinating! Solving real-world navigation challenges for retail has a massive impact. Love seeing true innovation in action—can't wait to see how accurate location tech evolves from here!

@AndrewHartAR Fascinating problem! I've been struggling with indoor navigation at conferences. How did you solve the accuracy issue?

@AndrewHartAR We followed your work closely at Walmart until they pulled out of XR in 2023.

@AndrewHartAR Really cool. 5G is another solution.

@AndrewHartAR worked adjacent to this at uber. this is a super difficult problem and i'm really excited to see people continuing to work on solutions here!

@AndrewHartAR First of all, good job. Now, meme time:

@AndrewHartAR This is very reminiscent of those cringy linked-in posts I keep seeing on here