Sensor Fusion For Navigation of Autonomous Ground Vehicles

Public Deposited
Resource Type
  • This thesis proposes an adaptive visual-inertial loosely-coupled sensor fusion method that uses an Error State Kalman Filter (ESKF) and Fuzzy Logic Controller (FLC). The method applies to GPS denied zones. In previous attempts, researchers either tried to tune the Kalman Filter in the most precise way possible. This work aims to tune the Kalman Filter and makes it adaptive to overcome the disadvantages of previous methods and minimize the error of the estimated trajectories obtained by the Kalman Filter. The fuzzy system is trained via the Particle Swarm Optimization (PSO) algorithm to achieve this goal. The results show that the proposed adaptive Kalman Filter improves the accuracy and outperforms other methods of tuning Kalman Filters. In addition, our proposed approach outperforms the conventional Extended Kalman Filter (EKF) methods.

Thesis Degree Level
Thesis Degree Name
Thesis Degree Discipline
Rights Notes
  • Copyright © 2022 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
Date Created
  • 2022


In Collection: