Edge-Computing Assisted Robotic Vision Systems: Test Automation, Fault Prediction & Recovery

Abstract

This dissertation investigates the integration of edge-computing technologies into robotic vision systems, focusing on enhancing test automation, fault prediction, and recovery processes. The research articulates the critical gap in operational efficiency and reliability within existing robotic vision systems due to delayed data processing and insufficient fault management strategies. Through a comprehensive analysis of real-time performance metrics, fault occurrence logs, and corresponding recovery times, the findings demonstrate a significant reduction in system downtime and an increase in fault detection accuracy, thereby optimizing the functionality of robotic vision applications. The key results reveal that implementing edge-computing not only facilitates immediate data analysis and decision-making but also substantially improves the predictive capabilities for system failures, leading to more resilient automation strategies. These advancements hold considerable significance in the healthcare sector, where robotic vision systems are increasingly deployed for surgical assistance and diagnostics, enhancing patient safety and operational workflow. The broader implications of this study suggest that by fostering robust edge-computing frameworks, healthcare institutions can leverage improved robotic systems to enhance clinical outcomes, reduce costs associated with system failures, and ultimately support the transition towards more intelligent and responsive healthcare environments. This research contributes to the ongoing dialogue regarding the adoption of innovative technologies in healthcare, positing edge-computing as a pivotal element in the future development of reliable and efficient robotic solutions.