Forecasting the Feasibility of Autonomous Mobile Robots Performing Tasks Using AutoML

In modern production systems based on Industry 4.0 solutions, Autonomous Mobile Robots (AMRs) are increasingly used. The specific operation of these robots makes it impossible to fully predict the route they will cover during transport tasks. This is due to the possibility of changing the route when obstacles are detected on the previously marked transport route. Changing the route involves a change in the robot’s energy consumption, which determines the need to constantly monitor the robot’s operation and predict the possibility of carrying out transport tasks. This study presents a predictive model using Automated Machine Learning (AutoML) to forecast the energy consumption of AMRs during tasks. Focusing on optimizing AMRs’ operational efficiency, it highlights the necessity of a predictive approach to manage tasks and energy consumption. The model is based on extensive data analysis, considering various operational parameters and their impact on energy usage. It demonstrates high accuracy in predicting energy needs for different missions, suggesting potential for integrating diverse AMRs into a unified management system. This research contributes to enhancing AMRs’ utility in industrial settings, offering a path toward improved automation and efficiency.