Hacker News Reader

Comment by mrguyorama | Hacker News Reader

Damn, I was really hoping this was a turnkey solution for SLAM (Simultaneous location and mapping) as I really want to make a silly little rover that knows it's location and can drive around my apartment.

Anyone know anything like that?

View on HN

I can't find it now (so I'm going to describe it and hope HN remembers) but a thing went by here a few months ago, there was a drone flying down a staircase with a camera on it and it was doing some sort of SLAM that way... mapping the staircase while tracking drone's location.

- - - -

edit: Found it!

XIVO: X Inertial-aided Visual Odometry and Sparse Mapping

https://github.com/ucla-vision/xivo

https://news.ycombinator.com/item?id=20882200

For a true turn-key solution you probably need the entire stack from sensors up to software. Intel's RealSense cameras (the T265 specifically) is probably the most reasonably priced option for a hobbyist with reasonable APIs. Visual and visual-inertial SLAM are not at a point where open-source packages are robust and easy to use with an arbitrary sensor stack and environment.

If you only have 2D motion and can spend more money or mess around with unsupported hardware (salvaged Neato vacuum) a laser rangefinder is also a decent option.

Do you know how Real sense compares to the Kinect 3(aka4)?

Hardly turn-key, I'm afraid, but I'd look into UcoSLAM ( http://www.uco.es/investiga/grupos/ava/node/62 ). As I understand it, if you have a robot with a camera that can see special markers, it can work out its location.

If you have an extra smartphone, you can use some of the AR SDKs out there. ARKit has the ability to relocalize itself to a stored map ( e.g. your apartment ) The 6D.ai SDK can even do meshing for obstacle avoidance.

Reply on news.ycombinator.com