Intelligent Robotic Navigation Using Hybrid Sensor Networks
TL;DR
The study concludes that hybrid sensor networks are essential for future autonomous robotic systems, with future research focusing on deep reinforcement learning, cloud robotics, edge computing, cognitive navigation, and IoRT-based architectures.
Abstract
Intelligent robotic navigation has become an important research area for autonomous systems operating in dynamic and uncertain environments. Before 2019, advancements in robotics, artificial intelligence, embedded systems, and wireless communication improved autonomous robots used in healthcare, agriculture, transportation, military, and service applications. Traditional single-sensor systems faced challenges such as low localization accuracy and poor environmental perception. To address these issues, Hybrid Wireless Sensor Networks (HWSNs) combined sensors like LiDAR, GPS, IMUs, cameras, ultrasonic sensors, and RFID to enhance navigation, obstacle detection, mapping, and reliability. Research focused on sensor fusion, SLAM, Kalman filtering, fuzzy logic, neural networks, machine learning, and real-time obstacle avoidance. The proposed hybrid framework supports accurate localization, autonomous mapping, and efficient path planning for indoor and outdoor environments. Experimental results show that hybrid sensor systems improve navigation accuracy, reduce localization errors, and enhance obstacle detection efficiency. The study concludes that hybrid sensor networks are essential for future autonomous robotic systems, with future research focusing on deep reinforcement learning, cloud robotics, edge computing, cognitive navigation, and IoRT-based architectures.