Society of Robots - Robot Forum
Software => Software => Topic started by: neo01124 on January 10, 2008, 08:58:13 AM
-
I want to implement a SLAM based algorithm on an autonomous bot and i read through the forum for help, i could gather an idea of the thing using the SLAM for dummies guide but i couldnt understand the implementation using the EKF i.e. i have no prior knowledge of filtering, etc.
I want to know what sort of text (concerning maths as well as filtering,etc) i should have read before trying to implement a SLAM type of technique.
-
im doin a search also ,,just like you
you can google (simultanious localization and mapping) it gives too much stuff.
tell me if you got to see a good tutor
-
in terms of hardware, if you want to do SLAM you need tons of memory and processing power . . . a laptop on your bot basically . . . microcontrollers can't handle it . . .
one SLAM method I've seen is mask fitting. basically you have a big map (a matrix), and a recent local map (a smaller matrix). your algorithm must figure out how your new local map fits as a puzzle piece to your larger map. it must account for rotations and differences and noise, too.
basically you are developing a jigsaw puzzle solver for robots, but where no piece fits perfectly.
-
exactly , actually i did some matlab functions that help in catenating those matrixes and make the mother matrix
till now i programmed one function to do a catenation of two matrixes using information of distance and angle
matlab already has a good function to do rotation of matrix, basically im using the image processing box it helps a lot.
again, any providing of the algorithm as a whole would be great