ENHANCING AUTOMATED GUIDED VEHICLE SPEED REDUCTION CONTROL THROUGH EXPERT SYSTEMS

Abstract

Automated guided vehicles (AGVs) play a pivotal role in modern industrial and logistics operations, offering efficiency and flexibility. However, ensuring their safe navigation remains a critical challenge, particularly in dynamic environments. This abstract proposes a novel approach to improving AGV control by leveraging expert systems for speed reduction management. The research begins by identifying the complexities and safety concerns associated with AGV speed reduction, such as obstacle detection, pedestrian proximity, and terrain variations. Expert knowledge from AGV engineers, safety regulations, and relevant literature, a comprehensive rule base is developed to encapsulate the nuanced decision-making processes involved in speed reduction control. The core of the proposed system lies in its inference engine, which employs advanced reasoning techniques such as fuzzy logic or rule-based reasoning to process the rule base and make real-time decisions regarding speed adjustments. By integrating this expert system seamlessly into the AGV's control architecture, the research aims to enhance its adaptability and responsiveness to dynamic operating conditions. Validation in simulated and real-world scenarios is conducted to evaluate the effectiveness and reliability of the proposed approach. Performance metrics are analyzed to assess improvements in safety, efficiency, and overall AGV speed control with an expert system based on operational data and user feedback, ensuring ongoing optimization and adaptation to evolving requirements.