Implementation of extended Kalman filter-based simultaneous localization and mapping: a point feature approach

The implementation of extended Kalman filter-based simultaneous localization and mapping is challenging as the associated system state and covariance matrices along with the memory requirements become significantly large as the information space increases. Unique and consistent point features representing a segment of the map would be an optimal choice to control the size of covariance matrix and maximize the operating speed in a real-time scenario. A two-wheel differential drive mobile robot equipped with a Laser Range Finder with 0.02 m resolution was used for the implementation. Unique point features from the environment were extracted through an elegant line fitting algorithm, namely split only technique. Finally, the implementation showed remarkably good results with a success rate of 98% in feature identification and ±0.08 to ±0.11 m deviation in the generated map.