Smart Wheelchair Localization and Navigation Based on Multi-Sensor Data Fusion Using Hybrid-Filter Method (HF)

Abstract

Mobility for disabled individuals is a crucial issue in their daily lives. The navigation system is one of the most commonly employed techniques for smart wheelchairs in the domain of mobile robotic-Maurice Audin, providing them with autonomy and social integration opportunities. Indeed, its simplicity and reliability can bring benefits to the users. This paper deals with intelligent wheelchair navigation through the development of multi-sensor data fusion using a hybrid filter (HF) approach by combining the extended Kalman filter (EKF) and the modified particle filter (PF). This combination overcomes the limitations of each other and leverages their respective strengths to achieve more accurate and robust localization. Indeed, the proposed hybrid filter aims to minimize estimation errors and improve the dynamic localization and navigation system. The applicability and effectiveness of the developed HP approach are demonstrated by simulation, and the results obtained were compared with those found in the literature. It has been found that the mean absolute error (MAE) and the percentage estimation error of the present method are better than those of EKF and both data fusion methods.