Optimizing Mobile Robot Localization: Drones-Enhanced Sensor Fusion with Innovative Wireless Communication

Inam Ullah, Deepak Adhikari, Habib Khan, Shabir Ahmad, Christian Esposito, Chang Choi

Abstract: Localization is one of the key techniques for 5G/B5G Wireless Sensor Networks (WSNs) research, which determines the application predictions of WSNs to an excessive range. Non-line-of-sight (NLOS) propagation causes most WSN localization errors in complex network environments, like indoors. Extended Kalman Filter (EKF) is a traditional technique that executes inadequately in an NLOS environment, with a focus on the integration of drones or UAVs. The article evaluates the performance of mobile robot localization using EKF in WSN environments. It highlights the importance of improved Internet of Things (IoT) technologies and examines how enhanced 5G communication capabilities and drones or Unmanned Aerial Vehicles (UAVs) effectively overcome obstacles in indoor networks. EKF is a linear estimation of the standard Kalman Filter (KF) and is competent to operate professionally in non-linear classifications. Generally, EKF is based on an iterative method of approximating the statistics of the current state from the previous form. It is also based on the observation framework's linearization around the mean of the existing condition. It has minor calculation difficulty and involves short memory related to the Bayesian procedures, making it appropriate for low-power mobile objects. In this paper, the authors evaluate the localization and tracking presentation of EKF while considering several attributes, such as (a) position, (b) velocity, (c) time, and (d) coverage. The performance of this technique is evaluated using its features and provided with a high level of accuracy.