Industrial robots are mostly designed for tasks where working conditions are well known and do not change over time. However, there are many examples where robots require vision sensor-based control in order to perform complex operations and react to changes in the environment. Other areas where there is need for combining vision sensors with manipulators are quality inspection tasks of large or complex structured objects. The paper presents an overview of the methods used in robotic vision systems, taking into account their specific requirements and advantages. Experimental studies of a selected 2D/3D sensors mounted on industrial manipulators are presented including analysis of collected 3D points clouds. Additionally, a system of a reconfigurable manipulator that interchangeably uses various sensors and tools in complex inspection tasks is presented.

A method for quality inspection of food packaging based on hybrid imaging and machine-learning techniques is presented. The proposed inspection system integrates thermal and visible-light imaging, enabling detection and classification of faults such as weak seals, creases and contamination. For the purpose of the study data acquisition is automated with the use of an industrial manipulator, ensuring repeatability and consistent positioning of samples. Using the acquired images, the temperature distribution in the sealing area and selected process parameters, a predictive model for burst-pressure testing was developed. The proposed workflow includes attribute selection, hyperparameter optimization and the application of regression algorithms. The proof-of-concept results demonstrate a strong alignment between predicted and measured values, as well as high model stability. The best-performing model, ElasticNet, achieved an R² of 0.815 and an MAE of 0.028 kgf/cm², confirming its potential for non-destructive quality control of packaging.

For years now, the industrial manipulators have substituted human in many types of works during the manufacturing process. With robots the production rate increases, as does the quality of the product. The application of industrial manipulators increases the safety in the factories which in turn leads to savings. However, there are several difficulties in introduction of robotics into the production line. One of them is usually large cost of purchase and implementation of the robot. The proposed concept of the intelligent system for tool exchange is to address the stated issue. The aim of the system is to provide a mechanism for quick tool exchange supported by a decision making module that will constitute the self-reconfigurable industrial manipulator that is able to assess the situation at the production line, recognize the product and make decision on the operations to be performed, their sequence and which tool to use to perform that operation. Such a system of manipulator equipped with functions for reconfiguration and adaptation will be a solution for all applications where the production assortment changes quickly and is made in short series, and in particular for SMEs, which cannot afford purchase of several robots. They would buy one instead and let it perform variable tasks.The article briefly presents the concept of the hardware part of the exchange system, which includes both construction and the electronic modules for the tools, and concentrates on the concept of software expert system and database that allows intelligent decision making. The software control of the system is divided into four levels: the basic level, technical level, task level and procedure level. The basic level defines the movement of the robot such as: positioning, rotation, approach to the position etc. This level uses to control system of the applied manipulator and the data contained in the electronic modules of the tools. The basic level reflects the typical low-level control of the manipulator. The technical level defines the technical movement of the robot, small procedures related to the calibration of the tools, operation with the tool magazine (picking up and putting away) and related to tool maintenance – locking, unlocking, power supply, air supply and similar. The task level defines the operations related to the task performed on the object. Depending on the defined task the proper tool is selected (e.g. gripper, camera or a laser scanner) and, based on the data collected from sensors, performs the operation (e.g. scans the surface of the object). The highest level of control is totally independent on the hardware control system of the manipulator and the hardware of the robotic stand. Using the available databases and the recognition systems (e.g. cameras) makes decisions on what type of object appears on the production line and what operation is to be performed. The operations are defined as metacode that is interpreted and performed by lower control levels structurally bound to the control system of the manipulator.

The article presents a method and device for checking the correctness of the thermal sealing process in foil food packaging in the form of the so-called pouches. The seal inspection process is performed using a destructive method, which involves introducing compressed air into the packaging using a probe and measuring the pressure at which the seal bursts. The pouch inspection process is carried out routinely every given number of packages produced, as determined by the manufacturer. The developed device consists of two main elements: control and measurement module (controlling the packaging inspection process and presenting measurement results) and an actuator module (in the form of a probe and metal plates between which the pouch is placed during the inspection process). The article presents sample results of saved pressure values for correct and faulty seals and an example chart of changes in the working pressure in the packaging during the measurement process. Packaging inspection in the food industry is one of the critical production stages included in the HACCP system, contributing to improving food safety and reducing the amount of food waste. The developed solution is a new product offer of Łukasiewicz-ITeE addressed to producers, especially from the food industry. A series of packaging inspection devices has been implemented in one of the domestic poultry plants. After modifying the actuator module to take into account the packaging specification, the device has the ability to inspect other types of containers intended for sealing, such as trays, bowls, etc.

Stress in glass products arises from poor thermal conductivity and different cooling conditions of the outer and inner layers. Excessive stress levels and their uneven distribution adversely affect the mechanical and thermal strength, as well as the safety of glass products. To remove stresses, glass products undergo a controlled thermal process called annealing. After the process, it is important to determine the magnitude and distribution of remaining residual stresses. The photoelastic method based on the phenomenon of forced birefringence is used to study stresses. Measurement methods using a handheld polarimeter are sensitive to the influence of the human factor. For this reason, when the same product is inspected by different quality control employees, it is possible to obtain significantly different results. Another disadvantage is the need to break the product each time to measure the bottom thickness. The aim of this work was to replace the entirely manual stress monitoring method still used in some glassworks. This article presents an automated, non-destructive method and device for measuring residual stresses at the bottom of glass products. The developed method allows for fully automatic measurement of unit stresses (normalized to thickness) in round, open-top glass products. Automation involves performing measurements using a four-axis manipulator, a commercially available polarimeter with a polarizing camera, and a dedicated measurement system for determining the bottom thickness using the contact method. The authors describe the developed method, the selection of hardware solutions, and the method of implementation in an automatic stress monitoring device. The article presents sample measurement results in the form of color maps of stress distribution at the bottom of a glass product.

The article discusses the application of digital twins in modern production plants. Challenges for the industry are presented. Next, the concept of a Digital Twin (DT) is introduced. An overview of technologies utilised by DT is provided and specific applications of the DT are discussed: to the logistics and manufacturing processes. The predictive quality control is covered as an important element of a DT. Finally, the problem of integration of digital technologies into plants systems is addressed. The modern challenges for the industry are mainly related to contradictive market requirements, such as high quality v. low price. There are difficulties for workers, too, who lose their positions or are forced to change their specialisations. The DT technologies are mostly related to sensorics and communications, which enable a bidirectional relation between the DT and the process. This constitutes an actual advantage and contributes to the effectiveness of production plants.