OBJECT IDENTIFICATION METHOD FOR INTEGRATION WITH ROBOTIC SYSTEMS

The aim of the research is to develop a methodology for identifying and determining the location of objectsunder conditions of low visibility and potential changes in their shape, with a focus on extracting partscreated using selective laser sintering (SLS) from a powder medium. The study examines two fundamentallydifferent approaches to forming control algorithms for a robotic manipulator. The first approach, trust-based, isbased on the assumption of minimal displacement of the object during manipulation. The manipulator movesalong a trajectory calculated from a preliminary three-dimensional model without correction until the momentof capture. This method is characterized by high operational speed and minimal computational costs. However,it carries risks such as object deformation due to environmental resistance, displacement of the part upon contactwith the tool, and the inability to capture the object if it deviates significantly from its nominal position.The second approach, cautious, involves the gradual removal of powder layers to visualize the object and adjustthe trajectory before capture. This method includes several stages: removing the top layer of the medium topartially expose the part, analyzing data to refine the object's position, and constructing an adaptive trajectoryconsidering possible displacement. Special attention in the article is given to data generation for training neuralnetworks, which are used for object identification under noisy conditions. Two methods of artificial modeling ofpowder coatings are considered. The primitive method involves expanding the vertices of a three-dimensionalmodel along their normals with the addition of random noise. The improved method proposes differentiatedpowder distribution considering local surface curvature. Subsequent experimental results showed that training aneural network using real data has low efficiency. Recognition accuracy ranged from 60% to 75%, which isattributed to the small sample size and the influence of external factors such as lighting and interference. At thesame time, the use of synthetic data, prepared according to the methodology presented in the study, increasedrecognition accuracy to 92%. The practical significance of the work lies in the development of a methodologyfor searching, detecting, and identifying a part immersed in powder, which can be used to automate postprocessingprocesses in industries utilizing selective laser sintering. The developed solutions are adapted forintegration into robotic systems operating under conditions of limited visibility. The proposed methods can bescaled to a wide range of tasks in additive manufacturing and robotics, making them promising for implementationin industrial processes.