This article deals with methods of navigation and mapping of mobile robots in an indoor environment, for example, laboratories, building corridors, and so on. It explains the proposed solution of global navigation in more detail through the application of potential field method and its transformation into the topological map. Two separate software tools were designed for simulation of wheeled mobile robot behavior in the authors’ workplace. The first software uses the metric form of space representation and it can simulate tactic level of global navigation, while the second one deals with its transformation into the topological map and can be used for strategic level of global navigation. This is how we can get the so-called multilayer map system suitable for different tasks of mobile robot navigation and path planning.

Kinematically-redundant manipulators present considerable difficulties, especially from the view of control. A high number of degrees of freedom are used to control so-called secondary tasks in order to optimize manipulator motion. This paper introduces a new algorithm for the control of kinematically-redundant manipulator considering three secondary tasks, namely a joint limit avoidance task, a kinematic singularities avoidance task, and an obstacle avoidance task. For path planning of end-effector from start to goal point, the potential field method is used. The final inverse kinematic model is designed by a Jacobian-based method considering weight matrices in order to prioritize particular tasks. Our approach is based on the flexible behavior of priority value due to the acceleration of numerical simulation. The results of the simulations show the advantage of our approach, which results in a significant decrease of computing time.

Industrial cameras starting to play a significant role in current industrial environment and they represent a strong tool for robotics mainly in cases when they are combined with high-speed robots. However, there are still some difficulties in vision system integration. The capability of such system (e.g. assembly or technological system) depends on several factors, for instance, the camera position, lightning conditions, pattern recognition algorithms, precise setup, as well as well-trained programmer and engineer. The skills of the engineering staff and the precise analysis of conditions and process requirements seem to be crucial for successful solution, what was proved also in our experimental test. The main aim of the article is development and complex performance analysis of robotized screwing application with integrated vision system, concretely the case study of automated assembly system in automotive industry—bolting tightening robotized station as a part of car seat assembly process. The main key elements of the designed workplace are industrial robot FANUC M-20iA/20M with integrated iRVision system containing the industrial camera Sony XC-56. The real influence of inaccuracies during the design process, gradual “step-by-step” refinement, and final influence of all changings on the final quality and efficiency of designed system was demonstrated. At the end, we reached the point where the total number of screwing operations with NOK results (not OK / negative results) is about six single negative results per day, which represents less than 0.1% of all recognitions (overall reliability is higher than 99.9%).

The article discusses the possibility of object detector usage in field of automated visual inspection for objects with specific parameters, specifically various types of defects occurring on the surface of a car tire. Due to the insufficient amount of input data, as well as the need to speed up the development process, the Transfer Learning principle was applied in a designed system. In this approach, the already pre-trained convolutional neural network AlexNet was used, subsequently modified in its last three layers, and again trained on a smaller sample of our own data. The detector used in the designed camera inspection system with the above architecture allowed us to achieve the accuracy and versatility needed to detect elements (defects) whose shape, dimensions and location change with each occurrence. The design of a test facility with the application of a 12-megapixel monochrome camera over the rotational table is briefly described, whose task is to ensure optimal conditions during the scanning process. The evaluation of the proposed control system with the quantification of the recognition capabilities in the individual defects is described at the end of the study. The implementation and verification of such an approach together with the proposed methodology of the visual inspection process of car tires to obtain better classification results for six different defect classes can be considered as the main novel feature of the presented research. Subsequent testing of the designed system on a selected batch of sample images (containing all six types of possible defect) proved the functionality of the entire system while the highest values of successful defect detection certainty were achieved from 85.15% to 99.34%.

The article deals with the application of vision guided parallel robot FANUC M-1iA for automated assembly process. Vision system is used for object identification and filtering the data about its position and orientation. Control system based on iR Vision system can process data collected from...

This paper describes the design of machine tool based on the mechanism with parallel kinematic structure (PKS) called hexapod. The advantages of mechanisms with PKS predetermine them to the field of machining and robotics. Machine tool is designed like fully automated device contains system for automatic tool and part changing too. There was necessary to solve also a question of operation safety according to the real risk of injury. Some information about the design process, main requirements, the problems and the final solution can be found in this paper.