This paper presents the development of a robotic workstation that integrates a collaborative robot as an assistant, leveraging advanced computer vision techniques to enhance human–robot interaction. The system employs state-of-the-art computer vision models, YOLOv7 and YOLOv8, for precise tool detection and gesture recognition, enabling the robot to seamlessly interpret operator commands and hand over tools based on gestural cues. The primary objective is to facilitate intuitive, non-verbal control of the robot, improving collaboration between human operators and robots in dynamic work environments. The results show that this approach enhances the efficiency and reliability of human–robot cooperation, particularly in manufacturing settings, by streamlining tasks and boosting productivity. By integrating real-time computer vision into the robot’s decision-making process, the system demonstrates heightened adaptability and responsiveness, creating the way for more natural and effective human–robot collaboration in industrial contexts.

The forest constitutes an essential and irreplaceable component of life for all organisms, with its primary significance lying in its role in creating a breathable atmosphere on Earth. Forests are vital for human health and well-being and hold significant ecological and economic value for humanity. This study aims to propose a method for identifying forest stands using artificial intelligence techniques. A custom dataset was developed, comprising high-quality satellite images that capture various structures such as forests, fields, roads, buildings, and lakes. This dataset was employed to train models from the category of convolutional neural networks that operate on the principle of instance segmentation. Several models, including YOLOv8, YOLOv5 and Mask R-CNN, were tested and compared. An optimal model was selected based on parameters such as detection accuracy, total training time, and the precision of labeling detected image elements. The selected model was then evaluated using images not included in the original training dataset to simulate real-world deployment scenarios. The final accuracy of best model achieved 91.67%. This model can detect the presence of forest stands in satellite images, as well as other features such as roads, buildings etc. The proposed method offers potential benefits for forest technicians, who can integrate it with other methods to monitor forest cover effectively.

This paper presents the implementation of ORB-SLAM3 for visual odometry on a low-power ARM-based system, specifically the Jetson Nano, to track a robot’s movement using RGB-D cameras. Key challenges addressed include the selection of compatible software libraries, camera calibration, and system optimization. The ORB-SLAM3 algorithm was adapted for the ARM architecture and tested using both the EuRoC dataset and real-world scenarios involving a mobile robot. The testing demonstrated that ORB-SLAM3 provides accurate localization, with errors in path estimation ranging from 3 to 11 cm when using the EuRoC dataset. Real-world tests on a mobile robot revealed discrepancies primarily due to encoder drift and environmental factors such as lighting and texture. The paper discusses strategies for mitigating these errors, including enhanced calibration and the potential use of encoder data for tracking when camera performance falters. Future improvements focus on refining the calibration process, adding trajectory correction mechanisms, and integrating visual odometry data more effectively into broader systems.