The authors of this article analyzed the problem of logistic robotics. This paper presents a method for robot navigation in a known environment. The method consists of two steps. The first step is to model the system, assign vector marks to the prominent edges of the virtual environment map, and direct the robot to reach these marks. The second step is to enable the robot to execute a specific task based on the given paths and deal with the local obstacles avoidance independently. The identification of the prominent point, the computation of the vector mark, and optimal path calculation are performed on the computer model using colored Petri nets in the software ‘Centaurus CPN’. The proposed approach was extended to simulate the work of a logistic robot, which has to take boxes and deliver them to certain places in storages. The experimental investigation has shown that the simulated mobile robots with the proposed navigation system were efficiently moving along the planned path. The analysis of the vector tree reveals that it takes 0.389 s to compute and graphically represent it. The occupation of certain places in storages is visualized and shown in experimental graphics.

Generative artificial intelligence tools are increasingly being used to support engineering tasks; however, their applicability to process identification, controller tuning, and control performance prediction remains insufficiently investigated. This article evaluates the capabilities of GenAI systems to identify dynamic process models, design PI and PID controllers, and predict closed-loop performance metrics. Five benchmark process models representing first-order, delayed, integrated, and second-order dynamics were considered. Open-loop and closed-loop datasets were provided to two AI systems, which were then requested to identify process models, propose controller parameters, and predict overshoot, settling time, integral of time-weighted absolute error, and disturbance rejection time. The generated controller settings were validated using MATLAB/Simulink simulations, and both absolute and relative prediction errors were calculated. The results show that both AI systems could generate feasible controller parameters that produced stable closed-loop responses for most of the processes investigated. However, significant discrepancies were observed between predicted and simulated performance indicators. The integrating process exhibited the highest prediction errors, indicating substantial difficulties in interpreting integrating dynamics. The results suggest that current GenAI systems can support preliminary controller design and process analysis but cannot yet replace simulation-based validation for accurate quantitative performance assessment.