from “SLAM for Dummies”
Secondly SLAM is more like a concept than a single algorithm
There are many steps involved in SLAM and these different steps can be implemented using a number of different algorithms
- explained in more detail when we get to the iSAM section when explaining our algo
… these different steps can be implemented using a number of different algorithms.
^ uses data from 2 sensors, we are limited to one sensor
- part of the reason we are having the error/issue we are having right now
- context and background of project; Virtana
- my internship proposal document
- blogposts
Outline
- Our goal
- building a Software library that preforms vSLAM on iMX
- Why novel?
- new compute sys; for our edification (see notes and recordings from Chris)
- TagSLAM video example — this is what our output should kinds look like
- explain the basics SLAM steps
- What we were able to do; front-end; detecting markers, etc…
- Where GTSAM/iSAM2 comes in
- Error faced, research done, solutions attempted.
2024 Internship_ Real-time, fiducial-based vSLAM for Virtana's tiny ARM-based indoor drone platform.pdf
https://docs.google.com/presentation/d/1cwpV6XDcgefxqLpIwF9RNdaZoSjOdhlqe3jLBv7aN3g/edit#slide=id.g2f162d68a9e_1_87
ZakareeyahInternshipFinalReport.pdf