This article deals with the creation of a digital twin for an experimental assembly system based on a belt conveyor system and an automatized line for quality production check. The point of interest is a Bowden holder assembly from a 3D printer, which consists of a stepper motor, plastic components, and some fastener parts. The assembly was positioned in a fixture with ultra high frequency (UHF) tags and internet of things (IoT) devices for identification of status and position. The main task was parts identification and inspection, with the synchronization of all data to a digital twin model. The inspection system consisted of an industrial vision system for dimension, part presence, and errors check before and after assembly operation. A digital twin is realized as a 3D model, created in CAD design software (CDS) and imported to a Tecnomatix platform to simulate all processes. Data from the assembly system were collected by a programmable logic controller (PLC) system and were synchronized by an open platform communications (OPC) server to a digital twin model and a cloud platform (CP). Digital twins can visualize the real status of a manufacturing system as 3D simulation with real time actualization. Cloud platforms are used for data mining and knowledge representation in timeline graphs, with some alarms and automatized protocol generation. Virtual digital twins can be used for online optimization of an assembly process without the necessity to stop that is involved in a production line.

Small series production with a high level of variability is not suitable for full automation. So, a manual assembly process must be used, which can be improved by cooperative robots and assisted by augmented reality devices. The assisted assembly process needs reliable object recognition implementation. Currently used technologies with markers do not work reliably with objects without distinctive texture, for example, screws, nuts, and washers (single colored parts). The methodology presented in the paper introduces a new approach to object detection using deep learning networks trained remotely by 3D virtual models. Remote web application generates training input datasets from virtual 3D models. This new approach was evaluated by two different neural network models (Faster RCNN Inception v2 with SSD, MobileNet V2 with SSD). The main advantage of this approach is the very fast preparation of the 2D sample training dataset from virtual 3D models. The whole process can run in Cloud. The experiments were conducted with standard parts (nuts, screws, washers) and the recognition precision achieved was comparable with training by real samples. The learned models were tested by two different embedded devices with an Android operating system: Virtual Reality (VR) glasses, Cardboard (Samsung S7), and Augmented Reality (AR) smart glasses (Epson Moverio M350). The recognition processing delays of the learned models running in embedded devices based on an ARM processor and standard x86 processing unit were also tested for performance comparison.

Pneumatic artificial muscle-based robotic systems usually necessitate the use of various nonlinear control techniques in order to improve their performance. Their robustness to parameter variation, which is generally difficult to predict, should also be tested. Here a fast hybrid adaptive control is proposed, where a conventional PD controller is placed into the feedforward branch and a fuzzy controller is placed into the adaptation branch. The fuzzy controller compensates for the actions of the PD controller under conditions of inertia moment variation. The fuzzy controller of Takagi-Sugeno type is evolved through a genetic algorithm using the dynamic model of a pneumatic muscle actuator. The results confirm the capability of the designed system to provide robust performance under the conditions of varying inertia.

The area of soft robotics has been subject to intense research efforts in the past two decades and constitutes a paradigm for advanced machine design in future robotic applications. However, standard methods for industrial robotics may be difficult to apply when analyzing soft robots. Deep learning, which has undergone rapid and transformative advancements in recent years, offers a set of powerful tools for analyzing and designing complex soft machines capable of operating in unstructured environments and interacting with humans and objects in a delicate manner. This review summarizes the most important state‐of‐the‐art deep learning architectures classified under supervised, unsupervised, semisupervised, and reinforcement learning scenarios and discusses their main features and benefits for different soft robotic applications, including soft robot manipulators, soft grippers, soft sensors, and e‐skins, as well as bioinspired soft robots. Specific properties of recent deep learning architectures and the usefulness of their features in addressing various types of issues found in soft robotics are analyzed. The existing challenges and future prospects are identified and discussed in view of the enhanced integration of both areas, which improves the performance of next‐generation soft machines operating in real‐world conditions.

The assisted assembly of customized products supported by collaborative robots combined with mixed reality devices is the current trend in the Industry 4.0 concept. This article introduces an experimental work cell with the implementation of the assisted assembly process for customized cam switches as a case study. The research is aimed to design a methodology for this complex task with full digitalization and transformation data to digital twin models from all vision systems. Recognition of position and orientation of assembled parts during manual assembly are marked and checked by convolutional neural network (CNN) model. Training of CNN was based on a new approach using virtual training samples with single shot detection and instance segmentation. The trained CNN model was transferred to an embedded artificial processing unit with a high-resolution camera sensor. The embedded device redistributes data with parts detected position and orientation into mixed reality devices and collaborative robot. This approach to assisted assembly using mixed reality, collaborative robot, vision systems, and CNN models can significantly decrease assembly and training time in real production.