ANFIS-Driven Optimization of Indoor Navigation Systems for Automated Guided Vehicles Utilizing UWB Signals

This paper chronicles the fusion of the Adaptive Neural Fuzzy Inference System (ANFIS) and Ultra Wideband (UWB) technology for navigation system optimization in Indoor Autonomous Guided Vehicles (AGVs). In the Industry 4.0 era, the significance of accurate, effective and flexible AGV systems cannot be overemphasized in the industrial applications of today. UWB has centimetre-level location accuracy because of its low power consumption and large bandwidth, and is therefore very suitable for challenging indoor environments. In response to the challenge of high installation costs and environmental sensitivity, the ANFIS model is utilized to integrate the learning ability of artificial neural networks with the inference ability of fuzzy logic in order to increase the accuracy and effectiveness of UWB signal data processing. The real-time adaptive navigation of the system is also supported by dynamically adjusting the motor control according to the vehicle position using Pulse Width Modulation (PWM). The approach enables AGVs to adapt to environmental changes in a flexible manner, improving their performance in dynamic industrial environments. Future work can involve the investigation of UWB integration with other sensors or sensor technologies or application in cluster robotics to enable coordination and navigation in dynamic environments to be improved.