MATHEMATICAL MODEL OF BLOCK PROCESS PLANNING IN SYSTEMS OF ALLOCATION OF TASK BETWEEN PEOPLE AND COLLABORATIVE ROBOTS IN THE FRAMEWORK OF INDUSTRIES 5.0

Abstract

This article considers the current problem of task allocation between humans and collaborative robots in the context of Industry 5.0 using block process planning. The main focus is on analyzing the interaction between operators and automated systems operating in a shared production environment. The main goal is to ensure harmonious cooperation between humans and robots by optimizing task allocation, taking into account a number of important factors, such as time and resource constraints, the complexity of the operations performed, the level of autonomy of robotic systems, and the priority of performing different stages of production. As part of the study, a mathematical model is proposed that includes cost and benefit functions that allow assessing x1the effectiveness of planning. The model also contains numerous time and resource constraints that are critical to maintaining the productivity, safety, and flexibility of modern production systems. To verify its operability, software in Python was developed that allows not only to automatically carry out the planning process, but also to evaluate the overall effectiveness of the proposed task allocation strategies. The conducted experimental studies have shown that the success of planning depends to a large extent on the balance of time and resource parameters. The conducted experiments have shown that the success of planning depends on the balance of time and resource parameters: at values and all constraints are met, and the cost function fluctuates within 30–80. In contrast, in the case of insufficient resources, the system exhibits increased sensitivity, which makes the performance of some tasks impossible or inefficient. The results obtained confirm that the developed model is resistant to parameter changes and provides optimal task distribution in most production scenarios. Prospects for further research include extending the model for dynamic environments, integrating machine learning algorithms for forecasting, and improving the adaptive planning process.