[HN Gopher] How Hyper built a 1M-accurate indoor GPS
___________________________________________________________________
How Hyper built a 1M-accurate indoor GPS
Author : AndrewHart
Score : 83 points
Date : 2025-07-29 15:01 UTC (3 days ago)
(HTM) web link (andrewhart.me)
(TXT) w3m dump (andrewhart.me)
| ENadyr wrote:
| Whoa, 1m is really impressive! I've played around with stuff like
| https://github.com/dmsl/anyplace for https://www.emfcamp.org/
| back in the day, but that was around 5m at best. Bet you a
| robotics startup will scoop it up!
| AndrewHart wrote:
| Thanks. Very interested in robotics so that'd be an ideal home,
| given the SLAM + sensors tech stack.
| mentar wrote:
| How does your system handle the massive variance in sensor
| quality (accelerometer, gyro, WiFi radio) between a high-end
| iPhone and a budget Android device? Does the 1m accuracy hold up
| across the board, or does it degrade gracefully? Getting this
| right seems critical for scaling to a 'billion people'
| AndrewHart wrote:
| All of the videos shown on the speed-run of our technology is
| on 4 year-old Android devices, such as Samsung S21, Pixel 6
| etc.. We always test and gather statistics on older devices to
| fairly represent what's available, rather than latest-and-
| greatest.
| monegator wrote:
| So, devices that were top of the line a few years ago. But
| what about budget devices? in the 100-200 range new? I
| remember my old xiaomi started literally running in circles
| as the phone heated up 10-15 minutes after starting
| navigation: If i stood still the position would move in a
| circle of a few meters of radius.
|
| Incidentally, the devices you metion are what i also use to
| develop, because those line of products actually behave as
| they should, per documentation. But most bugs and crashes
| always come from budget and no name devices because both the
| hardware and firmware is crap
| numpad0 wrote:
| Peripheral chips aren't differentiated by user values like the
| end products that use them. You don't get more preciser sensors
| in high end phones. Everyone gets the same thing. You pay more
| only for more materials.
|
| Sensors that are actually a lot better than standard offerings
| would also be subject to and/ofs of ITAR or EAR or MTCR or
| local equivalents thereof, so progress in IMU appears to have
| been stagnating a bit due to that issue. Sony Semiconductor
| Solutions had a Arduino IDE compatible clustered IMU board that
| they say you can see rotation of Earth in data, they ended up
| selling it with scary warnings and without any of the cool
| stuffs.
| contingencies wrote:
| This is the correct answer. They're all the same. The notion
| that Apple has some kind of edge here is farcical.
| AlotOfReading wrote:
| There's a fair bit of quality difference between different
| chips and better chips have gotten cheaper. More importantly,
| default filtering quality has improved with more powerful uCs
| on the IMU package, which is what most cheap phone vendors
| are probably using.
|
| The ITAR stuff is way more fun though. It's great to read
| between the lines for the intended customer in the datasheet.
| thijson wrote:
| There's something called a Kalman filter:
|
| https://en.wikipedia.org/wiki/Kalman_filter
|
| It can combine several inaccurate sources and output a result
| that is more accurate than any one of them.
|
| I was at an Amazon Fresh grocery store, and saw squares in the
| ceiling that look like QR codes. I guess that's how they are
| mapping the store.
| mifydev wrote:
| Congrats on the launch, that looks dope! I'm curious, will this
| be able to run on an embedded robotics hardware?
| AndrewHart wrote:
| Yes - one of the limitations with mobile is engaging the
| camera/quality of the SLAM. With a robot, they're already using
| SLAM with strong tracking, and controlling the hardware stack
| means no device limitations (uncalibrated sensors, limited WiFi
| pings etc.)
| rstuart4133 wrote:
| Very, very impressive, if (intentionally?) a little vague on how
| you got to 1m accuracy given you WiFi only gives you 3m.
|
| I guess you must use the constraints on the directions a person
| can walk imposed by the shelves and other structures to give you
| orientation of the accelerometers. Which in turn means the person
| doing the ground truth mapping must walk down every aisle, and
| into every gap. That's not so difficult if your staff are doing
| it, but I bet you have trouble training the store staff gathering
| that data to do it well.
|
| Best of British.
| AndrewHart wrote:
| Thanks for the feedback. I wanted to keep it balanced to be
| accessible but also insightful.
|
| To answer your point: we have the digital map, can use that to
| understand obstacles etc in the space. In some of those larger
| stores you see in the visual, we typically survey the entire
| store within 2-3 hours, it's low-effort work, not a blocker.
| subhajeet2107 wrote:
| Why do you need a human to do the initial mapping ? why can't you
| use a Roomba or a smaller hardware for this task
| tecleandor wrote:
| It's been said in one of the comments that the initial mapping
| by a human takes like 2-3 hours. Knowing the speed of a Roomba,
| I guess that it would take much more time to do it. And
| 'humans' are COTS devices available on any department store
| (sorry ;P).
| jvdvegt wrote:
| Also the wifi signal might be different at Roomba-height.
| leoedin wrote:
| A stick seems like a very low tech solution to this
| problem!
| chiph wrote:
| Many times these stores have floor cleaning machines - either
| robotic or driven by a human. An employee could zip-tie their
| sensor to it, let it do its cleaning trip around the store, and
| return to collect the data later.
|
| This would allow an employee to do several stores in a town in
| a single day. And potentially less chance of a workers-
| compensation claim being filed if they fall down while walking
| around looking at their device.
| mastercheif wrote:
| FYI only one of your videos is displaying in HDR on your
| homepage, making the others seem dim in comparison.
|
| It's the Built for simple campus navigation video.
|
| I'd recommend converting it to SDR.
| grizzles wrote:
| In my view, you need to 'streetview' the world's shopping malls
| and make this a free app, the Hyper Browser. Add product search &
| reviews and drive traffic away from non-customer stores.
| ndriscoll wrote:
| > They wanted to bring indoor maps and navigation to their retail
| stores... It turns out that this doesn't just apply to retail.
| Every office, university campus, events venue, hotel, airport,
| warehouse, factory -- basically everywhere indoors have some need
| to navigate people around, provide relevant information, and
| improve efficiency.
|
| You'd think they would add this information to openstreetmap then
| or at least put a map on their website (and put it in the public
| domain so others like OSM can add it to their maps). Or put it in
| the store so people can take a picture. I go into target and
| there are posters saying to install an app for maps. Put the map
| on the poster!
|
| > and they could pop up relevant promotions along the way
|
| Oh, right, they don't want to provide information. They want to
| track people and spam them.
| voidUpdate wrote:
| I was with them until they said that it's going to give me ads
| while I'm walking around
| Den_VR wrote:
| The dream of augmented reality was brilliant until the
| obvious consequences were recognized
| imglorp wrote:
| You might think shoppers finding their product in a store
| quickly would delight customers and pay for itself quickly.
|
| But it seems instead of stores simply depending on the sale,
| they also now demand impulse purchases, which mean they want
| you wandering the store looking in multiple places for your
| quarry: the casino model. So if they delight a customer with
| direct route to the sale, they need to make up that windfall
| elsewhere?S
|
| So they fall back on surveil, profile, and market plus
| selling your profile to others? Is this is why we can't have
| nice things?
| rf15 wrote:
| Finding a product quickly is actually the opposite of what
| a store owner would want, because it means you are spending
| less time on looking at the other products.
|
| Yes I hate that attitude too.
| moritonal wrote:
| Major grocery shops routinely swap their profitable items
| with the popular items. They do this to stop the customer
| going into auto-pilot and instead forcing them into
| actually looking for what they want. So no, shoppers
| finding their product does not pay for itself.
| voidUpdate wrote:
| This is exactly why we can't have nice things. There has
| been a lot of study in how to manipulate shoppers to get
| them to buy more things in your shops, from playing in-
| store music that is slower so they walk slower, to putting
| expensive stuff at eye-level, to putting common things at
| the back of the shop so you have to walk past everything
| else to get to them
| SkyPuncher wrote:
| It depends on the segment. All of the hardware stores near
| me have websites that list the exact aisle and bay product
| is in. They've seemed to figure out it's a competitive
| disadvantage to make their customers wander.
|
| It's not entirely clear to me if grocers and other retail
| will end up taking the same route. Grocery service is
| increasingly move to hands-off (pickup or delivery) and
| other segments seem to be moving heavily on-line (including
| gig-delivery). It seems like they'll continue to punish
| foot traffic while encouraging customers to do online or
| hands-off buying.
| ranger207 wrote:
| Little bit of a tangent, but as a customer I am not
| "delighted" when I find a product quickly and easily; I am
| merely not frustrated. Finding what I'm looking for is the
| baseline experience, having to search for what I'm looking
| for makes me annoyed and less likely to buy anything other
| than what I need so I can just get out of there.
|
| In my experience, any product or service advertising itself
| as "delighting" customers actually means that they're
| overall making the baseline experience worse, and their
| product/service is just reducing the frustration they're
| introducing.
| mpeg wrote:
| If you had read the article you would see: 1/
| they need to collect ground truth data for their algorithm to
| work, it doesn't magically work everywhere. 2/ the
| ground truth data was collected mostly by their clients, it is
| not their data to give away for free
|
| I honestly don't see a problem with this technology, and I am a
| huge privacy advocate. First off, it uses the wifi signal
| strength + a model based on ground truth data to accurately
| position you in a map. This means that it's entirely opt-in,
| they can't accurately track you if you aren't using their app /
| connected to their wifi (yes I know some data does go out to
| wifi access points even if not connected, but I doubt it would
| be enough for this kind of tracking, and it can be disabled by
| the user)
|
| Yes, they mention promotions, but again the promotions would be
| opt-in - if I use their app to find a product I'm looking for,
| they might suggest other products along the way that I might
| also find useful, or they might take me in a route that passes
| right by them. This is no different to the way retailers stock
| up their shelves already, placing products next to others you
| might want, and moving necessity items around when they want to
| direct you to another part of the store.
|
| I don't know, I think it's a bit harsh to criticise this when
| the technology has so many applications outside of retail. I
| would love this in a museum or library, and even in retail I
| absolutely hate those interactive map displays that modern
| shopping malls have, where only one person can use them at a
| time and you have to navigate through 200 store names for the
| one you actually want to visit
| yodon wrote:
| > If you had read the article you would see:
|
| (1) It's clear from the use of quotes that the person you're
| replying to did read the article.
|
| (2) from the official HN Guidelines[0]: Please don't comment
| on whether someone read an article. "Did you even read the
| article? It mentions that" can be shortened to "The article
| mentions that".
|
| [0]: https://news.ycombinator.com/newsguidelines.html
| ndriscoll wrote:
| The criticism was directed at retailers. If they want to
| provide indoor maps... why not just do that? For my Target
| example, there's even a convenient place to put them in
| store: the posters that say to download an app to see a map.
| There's also a standard place where they can add their indoor
| maps for free without needing anyone's permission
| (openstreetmap). Or put them online with a public domain
| disclaimer and someone else will eventually probably do it.
|
| Edit: In Target's case, they do apparently also put it on
| their website if you go hunting for it, but the ubiquitous
| pushing of apps is still annoying vs just putting it right
| there in the store as well, and perhaps offering a QR code +
| text link to the online version. They're clearly using it as
| bait to install their tracking/ads trojan. Also their online
| map for my store is east-west inverted for some reason (the
| east end of the building is on the left, the north on top),
| which would be immediately obvious if they mapped it to their
| building in OSM.
| voidUpdate wrote:
| Honestly, I've wanted a system for a while where shops can
| provide a map, and I can search for an item and it will show me
| where in the shop that item is. I don't think I've ever been in a
| shop big enough where I'd need satnav to tell me how to get there
| though, is that an American thing?
| Philip-J-Fry wrote:
| Tesco in the UK literally has this but only for staff. If you
| work for Tesco you can access any shop, view a map, view where
| stock is on a shelf, check stock numbers and expected delivery
| and all that stuff.
|
| Things that would absolutely be an amazing QOL improvement for
| any shopper. But they won't let you have it because they WANT
| you to bumble your way around a shop. They don't want you to
| know where things are. That's why they move shelves around
| seemingly at random.
| leoedin wrote:
| I actually find this feature of supermarkets quite useful.
| Online shopping is far less discoverable - the end result is
| I forget things from my online shop quite often.
| voidUpdate wrote:
| I find exceptionally annoying when I don't know if I need
| to look for my preferred moisturizer in "skincare" or
| "premium skincare" or some other section I've not seen yet
| (yes this is a common issue for me). If I could just load
| up their (horribly slow and memory heavy) website, go to
| the store locator and actually see where it is in the shop
| instead of "yeah we have it in stock, _somewhere_ ", that
| would be very useful
| Philip-J-Fry wrote:
| For me the end result is I buy random crap from the shop
| that I don't need. Sometimes it's good because it's new and
| I wanna try it, but sometimes it's just me being a pig.
|
| I don't forget anything because I have a list.
| aaronax wrote:
| Home Depot, Lowe's, Menards, and Wal-Mart are examples off the
| top of my head that have this product locator functionality on
| their websites.
| le-mark wrote:
| I used this at Menards two days ago. The product location
| told me where the item was. Turned out that aisle g94 wasn't
| aisle 94 but a kiosk at the end of aisle 27 on the other side
| of the store (these numbers are made up I don't recall the
| specifics). I still had to ask a human where it was. So yeah
| not there yet and this type of service could really help.
| ckrapu wrote:
| Do you think the basic physics and sensor tolerances would let
| you go to 10^-2 meters if the environment (e.g. wifi station
| placements, location of RF-interfering elements) was designed by
| you?
| zokier wrote:
| If you want high performance indoor positioning , look into 5G
| carrier phase positioning which claims cm-level accuracy. Fuse
| that with IMU and optical sensing and you certainly should get
| decent results
| skunkworker wrote:
| I've personally used one of these before in a performance
| where you needed individual based tracking, the chips were
| active UWB radios and sensors were placed and calibrated
| around the stage, I believe it was < 10cm accuracy and quite
| an interesting sensation to walk with lights following you
| perfectly and quickly.
|
| https://kinexon.com/products/kinexon-rtls was what was used.
| 0xbadcafebee wrote:
| Interestingly, a version of this technology was built by a
| government contractor some years ago, because they too wanted to
| track people indoors. I don't think it used a smartphone
| though...
|
| I think an acquisition would be unfortunate. This could become
| really huge / useful to the world without being locked up as a
| private company's IP. Personally I would license it rather than
| sell it, as well as offering offline apps and limited SaaS. You
| don't need an established enterprise to sell it commercially; you
| just need a sexy product and some industry vets with contacts. If
| you do end up going that way, and need someone in IT Ops / DevOps
| / SysEng stuff to work on the "going enterprise with a billion
| users", give me a shout.
| dabumere wrote:
| This is very, very impressive. I have three questions. How do you
| know where you are within the store? Do you manually upload the
| floorplan? How does it know where all the items in the store are?
| mhb_eng wrote:
| Really interesting. Feels like it would be a natural addition to
| a company like Brain (https://www.braincorp.com/) who is already
| using robots to regularly perform those kinds of survey missions
| and have an overlapping customer base.
| hhhc wrote:
| This looks really cool. Can you also handle multi floor plans? I
| think that indoor multi floor plans is the most difficult
| challenge in this area...
| mastermage wrote:
| Shinjuku Station has called they need this.
| amelius wrote:
| If indoor is so inaccurate, how does Apple find AirTags then?
| Dachande663 wrote:
| Apple use UWB[0] for nearby location sensing.
|
| [0] https://en.wikipedia.org/wiki/Apple_silicon#Apple_U1
| SkyPuncher wrote:
| My understanding is they use bluetooth for coarse positioning
| (e.g. you're within 30 feet) then they use a special chip
| (ultra-wide band) for the precision location (within a foot or
| two).
|
| Of course, there's a good bit of magic within all of that to
| make it work seamlessly.
| amelius wrote:
| Sounds to me like it is not a difficult problem except for
| the fact that they want to make it work with existing
| smartphones (both iOS and Android).
| jspann wrote:
| This is a very cool project / startup! I'm curious, how do you
| get the ground truth data? Is that just you marking down where
| you are as you walk through the store?
| MobileVet wrote:
| Love reading about these types of R&D efforts, especially when
| they are successful. I started in robotics in 01 and was present
| at some of the first commercial vSLAM efforts and materially
| contributed to a hardware solution utilizing IR beacons on the
| ceiling. We also looked at RF radio mapping at the time, but the
| computational power wasn't there. Great to see how far it has
| come and LOVE that it doesn't require infrastructure!
|
| I am curious how deeply you have had to study the impact of how
| busy the store is with your signal error? Considering that humans
| are bags of water which is quite detrimental to RF signals, my
| guess is that your error increases along with the density of
| people.
| dimatura wrote:
| The few examples they show do look pretty good for a wifi-based
| method, although who knows how cherry-picked they are. I wonder
| how much the "SLAM" part is contributing and how sensitive that
| is to the sensor quality on the phone. I would've assumed that
| they'd be using vision, which seems to be the method of choice
| for other companies like niantic. The ground-truth data part for
| vision would certainly be more onerous, though.
| cyanydeez wrote:
| He explains it fairly well if you understand how you'd go from
| wifi accuracy to SLAM. THE WIFI was providing 3m accuracy and
| the SLAM down to 1M. how much it provides is those two numbers.
| I'm sure the algorithms are complex but he points out that SLAM
| is corrected by the actual maps made by the self service app.
| So it's fairly easy to understand: the map provides a
| probability space, the wifi puts you within 3m and the SLAM is
| use to fill in the blanks with help from the probability space.
| londons_explore wrote:
| How fast do the WiFi signal strength maps get out of date?
|
| Just someone changing the angle of an antenna or shifting a pile
| of stock near the router has to have a pretty big impact on
| signal strength.
|
| And obviously a WiFi system upgrade where all the Mac addresses
| change must be a fairly big change and effectively gives a full
| service outage for all the users till you remap.
| ChoGGi wrote:
| I go on the home depot website, pick my store, and find the
| product.
|
| It tells me how many are in stock, aisle number, and bay number.
| No need for an app or walking advertisements.
| hoppingturtles wrote:
| So they're not using GPS at all. Got it.
| dang wrote:
| " _Please respond to the strongest plausible interpretation of
| what someone says, not a weaker one that 's easier to
| criticize. Assume good faith._"
|
| https://news.ycombinator.com/newsguidelines.html
| jacobzweig wrote:
| Awesome breakdown of the challenges of indoor navigation! One
| thing I was curious about... given that many modern phones now
| have UWB radios built in, was UWB ever considered as part of the
| solution stack? From what I understand UWB can get to sub meter
| accuracy, and I know it's used in several sports applications
| where precise tracking is really critical.
|
| Is the constraint more about infrastructure (installing anchors,
| device compatibility, power) or something else that made you lean
| towards WiFi + SLAM fusion instead?
___________________________________________________________________
(page generated 2025-08-01 23:01 UTC)