There are a multitude of electronic marketplaces that facilitate buyers and sellers in their transactions over the Internet. For Business-to-Business (B2B) transactions, related EDI standards are well established to handle system interoperability in the e-Commerce process. But in Business-to-Customer (B2C) transactions, from the end-user perspective, there is often a lock-in experience to the dedicated software application provided by the respective electronic marketplaces, without the possibility to use a single front-end application to handle business in different electronic shop systems. Standardized interfaces for this purpose are not sufficiently defined or established. In this work, the asset administration shell technology is evaluated in providing such a standardized interface, to achieve system interoperability of marketplaces towards end-customer applications.

This paper presents an approach to abstract capabilities of hardware components, such as a robot, and to store the necessary data for accessing that capability in Asset Administration Shells (AAS). It uses an ontology based on the Capability, Skills, and Services (CSS) model, enhanced with the possibility to describe physical relations between components. Capabilities describe abstract abilities realized through technology-neutral skills, exemplified in Docker containers using a standardized interface to communicate. The case study, bin picking, illustrates the system's application and requirements. Two user types are identified: the hardware manufacturers who can abstract and store component capabilities in an AAS, and the user who can load these shells in order to orchestrate the process program. This paper details the system's design, implementation, and evaluation, demonstrating its functionality through the case study.

Predictive maintenance and reliability analysis have notoriously imperfect and unbalanced data because of few failure tests. This challenge limits the capability of supervised learning. Data-driven methods, especially deep learning, show great potential in capturing such complex relationships in many domains. Those methods rely heavily on the amount of data to extract meaningful representations. In contrast, data-poor domains depend on the use of simple architectures with a limited amount of trainable parameters. In this work, we show how pretraining with supervised contrastive learning can lead to better representations in data-poor domains such as the lifetime estimation on the example of solder joint. With such pre-trained models we are able to outperform end-to-end learning methods. Furthermore, we show that the learned representations improve classification tasks as well as rearession tasks.

Industrial manufacturing is currently undergoing a transformation from mass production with inflexible production systems to individual production with adaptable cells. In order to ensure this adaptability of these systems, technologies such as plug & produce are needed, to integrate, modify and remove devices at runtime. Therefor an exact description of the system, the products and the capabilities / skills of the devices is essential as well as a network for communication between the devices. Deterministic data transmission is particularly important for distributed control systems. We propose an architecture for plug & produce mechanisms with hard real-time capable communication paths between the cyber-physical components using OPC UA PubSub over TSN and the ability to load and execute real-time critical tasks at runtime.

In this work, we describe a ROS-based method for whole-body control (WBC) of mobile manipulators in the context of safe human-robot interaction. Our method is based on cyclic quadratic programming (QP) with a set of simultaneously active tasks that define constraints. The importance of different tasks is captured through priorities and weights. Robot behavior can be changed at run-time by re-configuring the active tasks through ROS interfaces. We evaluate the suitability of our method for safe human-robot collaboration in a Gazebo simulation. We show that our method lets the mobile manipulator perform evasive motions while staying consistent with other tasks if possible. At the same time, self-collisions and static obstacles are avoided. If a given safety threshold is crossed, the robot comes to a safe stop. Operation continues once the distance is high enough again.

The inspection of large structures is increasingly carried out with the help of Unmanned Aerial Vehicles (UAVs). When navigating relative to the structure, multiple data sources can be used to determine the position of the UAV. Examples include track data from an installed camera and sensor data from the orientation sensors of the UAV. This paper deals with the fusion of this data and its use for navigation alongside the structure. For the sensor fusion, a concept is developed using a Kalman filter and evaluated simulatively in a prototype. The calculated position data are also fed into a vector flight control system, which dynamically calculates and flies a trajectory along the component using the potential field method. This is done taking into account obstacles detected by the onboard sensors of the UAV. The established concept is then implemented with the Robot Operating System (ROS) and evaluated simulatively.

A key aspect of Industry 4.0 is the continuous interconnectedness of components. The standardized industrial communication protocol OPC UA offers a solution to this problem by enabling the exchange of data between the shop floor level and the inter-enterprise level. Due to the integration of the Time Sensitive Network (TSN) into OPC UA, it is now even possible to exchange information in real-time. Especially on the shop floor, there are numerous heterogeneous distributed devices from sensors to robots which must communicate with each other in real-time to achieve a distributed industrial control. Therefore, we propose an approach to combine real-time communication over TSN with OPC UA Programs to synchronize multiple distributed OPC UA Programs and exchange process data between them without losing real-time guarantees. This can be seen as the enabler of Plug-and-Produce with real-time requirements.

Components made from carbon fiber reinforced plastics (CFRP) offer attractive stability properties for the automotive or aerospace industry despite their light weight. To automate CFRP production, resin transfer molding (RTM) based on thermoset plastics is commonly applied. However, this manufacturing process has its shortcomings in quality and costs. The project CosiMo aims for a highly automated and cost-attractive manufacturing process using cheaper thermoplastic materials. In a thermoplastic RTM (T-RTM) process, the polymerization of ε-caprolactam to polyamide 6 is investigated using an intelligent mold tooling. Multiple sensor types integrated into the mold allow for tracking of process-relevant variables, such as material flow and polymerization state. In addition to monitoring the T-RTM process, a digital twin visualizes progress and makes predictions about issues and countermeasures based on machine learning.

Automation mechanisms are increasingly established in the field of visual inspections. UAVs can be used for particularly large components, such as those used in ship production and for critical infrastructures. This paper concentrates on the problem of visual inspection in the field of perspective-dependent route planning. It is shown how the requirements for such a system can be implemented and elaborated. Furthermore we investigate how sensor positions can be calculated offline, based on optical and geometrical requirements and how a trajectory can be planned which contains the found sensor positions for each given area on the component. It is shown how the systems architecture can be designed in order to be able to adapt it to different requirements for the planning of sensor positions and trajectory. The implementation was tested in a simulation environment, evaluated using a benchmark data set and it was shown how above-average results can be achieved on this data set.

Multi-functional cells with cooperating teams of robots promise to be flexible, robust, and efficient and, thus, are a key to future factories. However, their programming is tedious and AI-based planning for multiple robots is computationally expensive. In this work, we present a modular and efficient two-layer planning approach for multi-robot assembly. The goal is to generate the program for coordinated teams of robots from an (enriched) 3D model of the target assembly. Although the approach is both motivated and evaluated with LEGO, which is a challenging variant of blocks world, the approach can be customized to different kinds of assembly domains.

Smart factories of the future will be equipped with dynamic and task-specific teams of robots in order to manufacture custom-tailored products.For this, it is necessary to facilitate the planning of appropriate task sequences for cooperating robots.In this paper, we introduce a modular and domain-guided planning approach for multiple robots.Due to its modularity, the approach can be adapted to different assembly problems.Moreover, domain knowledge is used to guide the planning towards feasible solutions.We evaluate the approach with different examples from the blocks world domain (i.e. LEGO R DUPLO R ).This evaluation shows that this domain-guided approach outperforms classical planning based on state space search such as A * .

Considering initiatives like Industry 4.0 or the Industrial Internet of Things, robots will play an important role in intelligent factories, producing highly customized products with high variability and in small lot sizes. In this setting, complexity of planning and programming such robotic applications grows due to the drastic increase in flexibility, performance and robustness required. In this paper, we propose a tool-supported methodology for the development of control software for dynamically forming multi-functional robot teams. The main challenges for achieving this overall goal are modeling of robot team skills, techniques for automatically deriving process steps from the products’ construction plans, finding allocations of those steps to possible robot teams with compatible skills and calculating collision-free execution schedules with a high degree of parallelization to improve cycle times. The proposed approach integrates process experts and automation experts on all level s. Two case studies will serve as test beds to the developed approach: production of carbon-fiber reinforced polymers and assembly of furniture.

When automating small-batch manufacturing processes, the time spent for process planning and robot programming becomes more important.This paper proposes an automated process including construction plan analysis, process planning and execution to reduce the amount of manual work required.The process starts by analyzing the structure of the desired product and deriving required process step results, then uses heuristic search to find possible production steps and task assignments, and concludes by simulating or executing the resulting production plan.The approach is evaluated on a case study with a simulated robot automatically building different LEGO R DUPLO R structures starting from a 3D model defining the desired product.

Recently, the need for safe human-robot-interaction has become increasingly important, and with it the requirement to reliably detect persons in the workspace of a robot. Capacitive sensors mounted to the robot structure can be used to measure the presence of conductive objects and, hence, allow the detection of persons. However, various objects in the workspace can influence capacitive sensor measurements. Thus, we propose to record an environment model containing the expected sensor values for relevant robot poses. Using this model, distance estimation and real-time reaction can be performed even in the presence of additional conductive objects in the workspace. A demonstration of our approach was shown at the Hannover Messe 2015.

Multi-functional robot cells will play an important role in smart factories of the future.Equipped with flexible toolings, teams of robots will be able to realize manufacturing processes with growing complexity.However, to efficiently support small batch sizes and a multitude of process variants, powerful software tools are required.This paper illustrates the challenges that developers face in multi-functional robot cells, using the example of CFRP production.The vision of a new programming environment for such future flexible automation systems is sketched.

Simple robot applications can be run on a single computer, but when it comes to more complex applications or multiple mobile robots, software distribution becomes important.When structuring mobile robot systems and applications, distribution has to be considered on various levels.This paper proposes to distinguish between real-time level, system level, application level and regarding the world model.Advantages and disadvantages of distribution on each level are analyzed, and examples are given how this distribution is realized in the robotics frameworks OROCOS, ROS and the Robotics API.The results are demonstrated using a case study of two cooperating youBots handing over a work-piece while in motion, which is shown in simulation as well as in real life.

During the last two decades, software development has evolved continuously into an engineering discipline with systematic use of methods and tools to model and implement software. For example, object-oriented analysis and design is structuring software models according to real-life objects of the problem domain and their relations. However, the industrial robotics domain is still dominated by old-style, imperative robot programming languages, making software development difficult and expensive. For this reason, we introduce the object-oriented Robotics Application Programming Interface (Robotics API) for developing software for industrial robotic applications. The Robotics API offers an abstract, extensible domain model and provides common functionality, which can be easily used by application developers. The advantages of the Robotics API are illustrated with an application example.

The application of industrial robots is strongly limited by the use of old-style robot programming languages. Due to these languages, the development of robotic software is a complex and expensive task requiring technical expertise and time. Hence, the use of industrial robots is often not a question of technical feasibility but of economic efficiency. This paper introduces a new architectural approach making available modern concepts of software engineering for industrial robots. The core idea is to hide the real-time critical robot control from application developers. Instead, common functionality is provided by a generic and extensible application programming interface and can be easily used. Hence, this approach can lead to an industrialization of software development for industrial robotics.