Since then, WiFiSLAM has answered some of our questions on their blog (here) - here is an excerpt from their article:
- The demo video includes no maps constraints. It is purely accelerometer, gyroscope, and compass.
- We are able to get better-than-typical accuracy because we are taking non-traditional pattern-matching approaches to sensor fusion rather than the conventional “double-integration + Kalman filter” techniques used traditionally.
- We held the phone in front of us, trying to mimic a typical smartphone user who is following a map and walking while looking at their phone. Nothing super-specific.
See their blog article for more details of their sensor fusion technology and how it's deployed.
As we've written for over a year, we believe that sensor fusion has a huge potential that is only starting to be tapped. Our reports on indoor location positioning technology have detailed research in the area, both by mobile software companies and by chip makers. The chip makers are particularly exciting, since hardware support could allow sensor fusion to run pervasively without loading down the smartphone CPU.
Some say that 2012 was the year that indoor location technology bloomed, but from what we report about research still in progress, we think that the best is yet to come.....