Recent industrial robotics covers a broad part of the manufacturing spectrum and other human everyday life applications; the performance of these devices has become increasingly important. Positioning accuracy and repeatability, as well as operating speed, are essential in any industrial robotics application. Robot positioning errors are complex due to the extensive combination of their sources and cannot be compensated for using conventional methods. Some robot positioning errors can be compensated for only using machine learning (ML) procedures. Reinforced machine learning increases the robot’s positioning accuracy and expands its implementation capabilities. The provided methodology presents an easy and focused approach for industrial in situ robot position adjustment in real-time during production setup or readjustment cases. The scientific value of this approach is a methodology using an ML procedure without huge external datasets for the procedure and extensive computing facilities. This paper presents a deep q-learning algorithm applied to improve the positioning accuracy of an articulated KUKA youBot robot during operation. A significant improvement of the positioning accuracy was achieved approximately after 260 iterations in the online mode and initial simulation of the ML procedure.

Positioning accuracy in robotics is a key issue for the manufacturing process. One of the possible ways to achieve high accuracy is the implementation of machine learning (ML), which allows robots to learn from their own practical experience and find the best way to perform the prescribed operation. Usually, accuracy improvement methods cover the generation of a positioning error map for the whole robot workspace, providing corresponding correction models. However, most practical cases require extremely high positioning accuracy only at a few essential points on the trajectory. This paper provides a methodology for the online deep Q-learning-based approach intended to increase positioning accuracy at key points by analyzing experimentally predetermined robot properties and their impact on overall accuracy. Using the KUKA-YouBot robot as a test system, we perform accuracy measurement experiments in the following three axes: (i) after a long operational break, (ii) using different loads, and (iii) at different speeds. To use this data for ML, the relationships between the robot’s operating time from switching on, load, and positioning accuracy are defined. In addition, the gripper vibrations are evaluated when the robot arm moves at various speeds in vertical and horizontal planes. It is found that the robot’s degrees of freedom (DOFs) clearances are significantly influenced by operational heat, which affects its static and dynamic accuracy. Implementation of the proposed ML-based compensation method resulted in a positioning error decrease at the trajectory key points by more than 30%.

Automation techniques for controlled job execution in the excavation process are extremely useful for excavator tool trajectory generation, digging process simulation, and new tools or machines' developmental testing. Proper choice of sensors for excavator tool position determination is crucial for the successful implementation of automated systems. We used an industrial robotic arm to simulate excavator operation and determine the characteristics of available sensors. Four inertial measurement units (IMU) sensors mounted on the industrial robotic arm are used to estimate the joints positions and compare results with data from internal robot sensors. The obtained findings suggest that the chosen sensors are appropriate for the estimation of joint angle. It was found that the X axis error should be less than 2.27 degrees. If the Z axis is inevitable for some control task, additional sensors can be used to establish reference points for yaw angle calculation.

Accurate monitoring of robotic Tool Centre Point (TCP) trajectories is essential for ensuring precision, repeatability, and quality in industrial processes such as welding, milling, and assembly. The proposed framework integrates computer vision techniques with trajectory analysis to facilitate the monitoring of robotic operations. The system integrates an industrial robot with an HD camera and Python-based OpenCV processing to visualize and evaluate deviations in real time. The methodology is structured into three stages: (i) contour detection and preprocessing of visual data, (ii) trajectory tracking and visualization, and (iii) accuracy evaluation through nearest-neighbor point cloud analysis and Euclidean distance metrics. The findings demonstrate the system's capacity to reliably detect pointer motion, remove irrelevant background information and compute deviations with millimeter-scale precision. A comparative investigation was conducted to determine the accuracy, consistency, and robustness of automated monitoring in comparison to manual observation.