A COMPREHENSIVE REVIEW OF INDOOR LOCALIZATION: SOLUTIONS, ARCHITECTURES, CHALLENGES, AND FUTURE DIRECTIONS
The concept of indoor localization has become a fundamental technology of contemporary location-based services in areas like smart buildings, healthcare, emergency response, logistics, and Industry 4.0. Nevertheless, indoor settings are extremely difficult compared to outdoor settings where Global Navigation Satellite Systems (GNSS) can offer good positioning, indoor settings are still a challenge with multipath propagation, Non-Line-of-Sight (NLoS) effects, signal attenuation and dynamic environment variations. The need to overcome these constraints is the main issue that inspired this work. The objective of the research is to both present a cohesive and detailed overview of the indoor localization systems, including their development, mathematical basis and the new technological trends in their development. To do this, the research employs a systematic review approach that incorporates the viewpoints of wireless communications, artificial intelligence, and computational architectures. These include important technological advances of early Radio Frequency Identification (RFID) systems to current Wireless Fidelity (Wi-Fi), Bluetooth Low Energy (BLE), Ultra-Wideband (UWB), and emerging technologies of Visible Light Communication (VLC) and hybrid sensor-fusion systems. Geometric (trilateration, triangulation, ToA, TDoA, AoA), fingerprinting, and probabilistic filtering methods (Kalman and particle filters) are mathematically modelled and discussed, as well as machine learning-improved localization models. The study findings indicate that there is no best localization method that will always be optimal; instead, the performance is a trade-off between accuracy, infrastructure needs, and environmental sturdiness. Under favourable conditions, UWB-based systems can be used to achieve sub-decimetre accuracy, and Wi-Fi and BLE fingerprinting techniques can be used to achieve meter-level accuracy with greater versatility in the complex indoor environment. Moreover, hybrid methods that combine sensor fusion, machine learning, and adaptive algorithms can enhance the localization performance in NLoS and dynamic scenarios rather than in a single way. On the basis of these results, the paper suggests the application of interdisciplinary, data-driven, and hybrid localization structures integrating geometric, fingerprinting, and learning-based approaches. The systems of the future must be focused on the ease of scaling and environmental flexibility and privacy protection using methods like federated learning, edge intelligence, and secure data sharing. As a set of enablers in the development of a ubiquitous, high-precision indoor positioning and seamless indoor-outdoor navigation, emerging technologies, such as 5G/6G-enabled Joint Communication and Sensing (JCAS), Reconfigurable Intelligent Surfaces (RIS), and AI-driven localization, are identified.
Authors : Giwa, A.M., Salka, T.D., Yusuf, B.J., Michael, I., Yusuf, A.A., Luqman, A.M., Waba, P.I. and Mamden, T.C.
Category : Open Access Volume (Issue) : 12(1) Date Uploaded : 5th August 2026