How Hyper built a 1M-accurate indoor GPS • Hacker News Board

Re: How Hyper built a 1M-accurate indoor GPS

#71

Post by AndrewHart » Sat, Aug 02, 2025, 3:44 PM UTC

Neywiny wrote: post #63

Huge respect to anybody who ships a product, even software. I have yet to use any indoor navigation or even have that offered, but it would be nice. Question is, is SLAM the correct term? I thought mapping meant like the device doesn't have any prior knowledge of the environment and is, well, mapping it. This more feels like sensor fusion with a kalman filter.

The motion tracking system used by ARKit/ARCore is called SLAM, combination of sensors + camera data if available.

Re: How Hyper built a 1M-accurate indoor GPS

#72

Post by 8n4vidtmkvmk » Sat, Aug 02, 2025, 5:21 PM UTC

subhajeet2107 wrote: post #10

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

IIUC, the black dots have to be mapped by hand. I.e. the human has to drop pins on the map. A Roomba doesn't know where it is a-priori

Re: How Hyper built a 1M-accurate indoor GPS

#73

Post by Neywiny » Sat, Aug 02, 2025, 8:17 PM UTC

AndrewHart wrote: post #71

Neywiny wrote: post #63

Huge respect to anybody who ships a product, even software. I have yet to use any indoor navigation or even have that offered, but it would be nice. Question is, is SLAM the correct term? I thought mapping meant like the device doesn't have any prior knowledge of the environment and is, well, mapping it. This more feels like sensor fusion with a kalman filter.

The motion tracking system used by ARKit/ARCore is called SLAM, combination of sensors + camera data if available.

Sure, but my point was that just because something uses the same inputs and gets a similar output doesn't mean the processing is the same. This is just localization. Which is still impressive. But I'm not understanding there being any mapping going on.

Re: How Hyper built a 1M-accurate indoor GPS

#74

Post by AnnaMere » Sat, Aug 02, 2025, 8:44 PM UTC

How could one calculate the GPS of the floors?

Peoples at x, y (lat, lng) ain't the same when placed them in multiple floors?

Re: How Hyper built a 1M-accurate indoor GPS

#75

Post by LarMachinarum » Sat, Aug 02, 2025, 11:18 PM UTC

when I read "1m-accurate indoor GPS", my first gut reaction was along the lines of "so what? Nowadays outdoor differential/rover GPS/GNSS has The thing is: that would require additional hardware though, whereas the relevant limiting criterion of the project presented in the article is obviously that it has to run with just the hardware provided by common mobile phones. Which is what makes the project interesting despite the comparatively lower precision.