Square Root SAM
December 2023
·
1 min read
As part of a class project, I implemented an online, EKF-based SLAM algorithm in a simulated robot soccer environment as well as on the Victoria Park dataset. This method estimates both the current state of a mobile robot and the locations of stationary landmarks based on noisy sensor data and imperfect motion commands.
To maintain academic integrity, my implementation of this method is kept private in a Github repository. This project involved skills in:
- State estimation
- SLAM
- Probability theory
- Data association
- Dynamic systems
- Python
The following figures show the performance of the SLAM algorithm for robot soccer (top) and the Victoria Park dataset (bottom). In both cases, data association algorithms were run to associate measurements with known/new landmarks.
