Hacker News Reader

I wonder if it uses the machine vision aspect to prevent the typical problem of accelerometer drift. e.g. by orienting itself relative to walls/other stationary things.

Also, imagine making a 3D "scanner" that you can scan objects with into a virtual world, or print out on a 3D printer.

View on HN

Accelerometers usually don't have significant drift - digital gyroscopes do. The acceleromters are quite noisy though (and measure both gravity and acceleration). From some of the brief images in the intro movie it looks like the cameras are doing tracking and alignment of "interesting" features. Things like that fall into the Simultaneous Localization and Mapping (SLAM) technology area. Very cool stuff.

Well, maybe was I just unlucky, but I tried to use an IMU for my SLAM and was shocked by the extravagant amount of drift of accelerometers.

Do you mean the accelerometer values drifted over time (i.e. the direction of gravity shifted on a stable accelerometer) or do you mean the value when doubly integrated drifted?

Right: the doubly integrated values shifted while the sensor didn't move.

*drifted

Reply on news.ycombinator.com