Intelligent Sensor Fusion in IoT-Driven Robotics for Enhanced Precision and Adaptability

Abstract

Speedy evolution of Internet of Things in robotics has mandated the creation of intelligent sensor fusion methods to ensure better precision and responsiveness. IoT integration with cloud and edge computing has become pivotal for decision-making and processing in real time as robotics and automation are advancing. This paper examines how sensor fusion based on artificial intelligence make robotic systems more efficient, reliable and fault-tolerant. Convergence of AI and IoT not only enhances automation but also enables perfect communication between smart devices and the surrounding environment. This proposes new framework combining multi-sensor data fusion with state-of-the-art machine learning techniques such as Kalman filtering, Bayesian networks and LSTM for timebased analysis. Methodology enhances fault tolerance, decreases latency and optimizes execution of control through MRAC. Cloud and edge computing enabled by IoT provide real-time processing of data and feedback loops to ensure uncompromised performance. Performance is tested based on critical parameters like RMSE and MSE which prove to be much improved in terms of accuracy and efficiency. Comparative study identifies advantage of hybrid fusion over conventional ones with accuracy of 98.8 percent followed by deep learning fusion and Kalman filtering at 90.2 and 85.4 percentage respectively. Outcome identifies strength of intelligent sensor fusion in IoT-enabled robotics as a scalable and robust solution for real-world scenarios.