Empowering autonomous indoor navigation with informed machine learning techniques

Abstract

This paper proposes the application of informed machine learning technique to enhance the performance of an autonomous indoor navigation system by leveraging prior knowledge and additional data during training. The system includes simultaneous localization and mapping method for perform two prime functionalities of the localization, and mapping. By integrating machine learning, the system achieves a higher level of autonomy. It involves incorporating extra data alongside a priori knowledge gained from system training, resulting in improved efficiency and autonomy. The optimization of the proposed system model's training process utilizes the stochastic gradient descent algorithm to efficiently handle large volumes of real-time data. Through simulations, the effectiveness of the suggested informed machine learning technique is demonstrated, showcasing its superior performance in autonomous indoor navigation.