IoT Sensor Selection for Target Localization: A Reinforcement Learning based Approach

Internet of things (IoT) is a key enabler for target localization, where IoT-based sensors work towards identifying target's location in an area of interest (AoI). Appropriate selection of IoT sensors, while considering their energy constraints and confidence in the data they provide, is crucial to preserve the network lifetime and improve the efficiency of the localization task. The contemporary localization systems focus on optimizing nodes’ placement, and their selection. However, these systems can prove inefficient when deployed in new environments, since they lack adaptability and dynamicity. Machine learning, specifically reinforcement learning (RL), is well-suited to build robust target localization systems. Nevertheless, there exist some limitations in the current RL-based localization systems, which include– 1) they are application specific and require prior knowledge about the source characteristics (source type and strength), 2) they are geared towards a fixed environment (area size and number of sensors), 3) they use sensor-equipped agent traversing the AoI, which lacks scalability. Therefore, this work presents a comprehensive active sensor selection mechanism, coupled with a data-driven Q-learning approach, for target localization. The trained RL model guides the localization task to find a source with unknown location and intensity, irrespective of the environment or the source characteristics without retraining. A state-space reduction technique is proposed to diminish the curse of dimensionality and enhance the generalization ability of the RL model, thus realizing a scalable and adaptable system. The proposed approach is compared with a benchmark which is the only other work that utilizes sensor selection in localization tasks, where the results indicate that a more efficient, scalable, and adaptable localization is achieved.