This paper extends the topic of monocular pose estimation of an object using Aruco tags imaged by RGB cameras. The accuracy of the Open CV Camera calibration and Aruco pose estimation pipelines is tested in detail by performing standardized tests with multiple Intel Realsense D435 Cameras. Analyzing the results led to a way to significantly improve the performance of Aruco tag localization which involved designing a 3D Aruco board, which is a set of Aruco tags placed at an angle to each other, and developing a library to combine the pose data from the individual tags for both higher accuracy and stability.

In this work, we extend the previously proposed approach of improving mutual perception during human–robot collaboration by communicating the robot’s motion intentions and status to a human worker using hand-worn haptic feedback devices. The improvement is presented by introducing spatial tactile feedback, which provides the human worker with more intuitive information about the currently planned robot’s trajectory, given its spatial configuration. The enhanced feedback devices communicate directional information through activation of six tactors spatially organised to represent an orthogonal coordinate frame: the vibration activates on the side of the feedback device that is closest to the future path of the robot. To test the effectiveness of the improved human–machine interface, two user studies were prepared and conducted. The first study aimed to quantitatively evaluate the ease of differentiating activation of individual tactors of the notification devices. The second user study aimed to assess the overall usability of the enhanced notification mode for improving human awareness about the planned trajectory of a robot. The results of the first experiment allowed to identify the tactors for which vibration intensity was most often confused by users. The results of the second experiment showed that the enhanced notification system allowed the participants to complete the task faster and, in general, improved user awareness of the robot’s movement plan, according to both objective and subjective data. Moreover, the majority of participants (82%) favoured the improved notification system over its previous non-directional version and vision-based inspection.

In this paper, we investigated the effect of the incidence angle of a laser ray on the reflected laser intensity. A dataset on this dependence is presented for materials usually used in the industry, such as transparent and non-transparent plastics and aluminum alloys with different surface roughness. The measurements have been performed with a laser line triangulation sensor and a UR10e robot. The presented results are proposing where to place the sensor relative to the scanned object, thus increasing the reliability of the sensor data collection.

The article describes a method of simulated 3D scanning of triangle meshes based on ray casting which is used to find the optimal configuration of a real 3D scanner turntable. The configuration include the number of scanners, their elevation above the rotary table and the number of required rotation steps. The evaluation is based on the percentage of the part surface covered by the resulting point cloud, which determines the ability to capture all details of the shape. Principal component analysis is used as a secondary criterion to also evaluate the ability to capture the overall general proportions of the model.

Researchers often deal with the synthesis of the kinematic structure of a robotic manipulator to determine the optimal manipulator for a given task. This approach can lower the cost of the manipulator and allow it to achieve poses that might be unreachable by universal manipulators in an existing constrained environment. Numerical methods are broadly used to find the optimum design but they often require an estimated initial kinematic structure as input, especially if local-optimum-search algorithms are used. This paper presents four different algorithms for such an estimation using the standard Denavit–Hartenberg convention. Two of the algorithms are able to reach a given position and the other two can reach both position and orientation using Bézier splines approximation and vector algebra. The results are demonstrated with three chosen example poses and are evaluated by measuring manipulability and the total link length of the final kinematic structures.

This work focuses on improving a camera system for sensing a workspace in which dynamic obstacles need to be detected. The currently available state-of-the-art solution (MoveIt!) processes data in a centralized manner from cameras that have to be registered before the system starts. Our solution enables distributed data processing and dynamic change in the number of sensors at runtime. The distributed camera data processing is implemented using a dedicated control unit on which the filtering is performed by comparing the real and expected depth images. Measurements of the processing speed of all sensor data into a global voxel map were compared between the centralized system (MoveIt!) and the new distributed system as part of a performance benchmark. The distributed system is more flexible in terms of sensitivity to a number of cameras, better framerate stability and the possibility of changing the camera number on the go. The effects of voxel grid size and camera resolution were also compared during the benchmark, where the distributed system showed better results. Finally, the overhead of data transmission in the network was discussed where the distributed system is considerably more efficient. The decentralized system proves to be faster by 38.7% with one camera and 71.5% with four cameras.