This paper presents a method for inductance calculation of coils based on a machine learning algorithm. To show the feasibility of the approach, we generate a set of artificial training data describing a configuration of two planar spiral coils in varying dimensions and positions to each other in order to calculate their self- and mutual inductance. Afterwards, the data is used to train and evaluate three different machine learning models. Our evaluation shows that multiple linear regression with polynomial features reaches almost the same precision as the reference FASTHENRY2, but is orders of magnitude faster. With this novel machine learning based algorithm we enable new applications, where real-time prediction of inductances or coupling factors is advantageous.

ARENA2036 is a joint research campus incorporating production assets from different industrial and academic partners. To allow the implementation of cross-partner value streams and workflows, a common middleware for online date exchange and asset operation is mandatory. We implemented a generic and lightweight middleware which follows the concept of Asset Administration Shells as specified by the Platform I4.0. However, to allow for easy adaption and setup by a diverse range of partners we simplified modeling requirements and complexity of the actual data exchange. The result is a specification for the assets’ self-descriptions in form of submodels (For many people, the term “submodel" implies the existence of a “model", which does not exist here. In order to have a consistent terminology with the standard of the Platform I4.0, we will use the term “submodel" here. For the future, we propose the term “aspect model" instead.) and a convention on how to map this onto MQTT. Additionally, we integrated means for online discovery and state monitoring of all connected assets.

Future production methods like cyber physical production systems (CPPS), flexibly linked assembly structures and the matrix production are characterized by highly flexible and reconfigurable cyber physical work cells. This leads to frequent job changes and shifting work environments. The resulting complexity within production increases the risk of process failures and therefore requires longer job qualification times for workers, challenging the overall efficiency of production. During operation, cyber physical work cells generate data, which are specific to the individual process and interaction data. Based on the asset administration shell for Industry 4.0, this paper develops an administration shell for the production workforce, which contains personal data (e.g. qualification level, language skills, machine access, preferred display and interaction settings). Using worker and process specific data as well as interaction data, allows supporting, training and instating workers according to their individual capabilities. This matching of machine requirements and worker skills serves to optimize the allocation of workers to workstations regarding the ergonomic workplace setup and the machine efficiency. This paper concludes with an user-friendly, intuitive design approach for a personalized machine user interface. The presented use-cases are developed and tested at the ARENA2036 (Active Research Environment for the Next Generation of Automobiles) research campus.

Demanding high heat flux applications, as for example plasma-facing components of future nuclear fusion devices, ask for the development of advanced materials. For such components, copper alloys are currently regarded as heat sink materials while monolithic tungsten is foreseen as directly plasma-facing material. However, the combination of these materials in one component is problematic since they exhibit different thermomechanical characteristics and their optimum operating temperatures do not overlap. In this context, an improvement can be achieved by applying composite materials that make use of drawn tungsten fibres as reinforcement. For the manufacturing processes of these composites, suitable tungsten fibre preform production methods are needed. In the following, we will show that tungsten fibres can be processed to suitable preforms by means of well-established textile techniques as studies regarding the production of planar weavings (wire distances of 90–271 µm), circular braidings (multilayered braidings with braiding angle of 60° and 12°) as well as multifilamentary yarns (15 tungsten filaments with 16 µm diameter) are presented. With such different textile preforms tungsten fibre-reinforced tungsten (W f /W) with a density of over 99% and pore-free tungsten fibre-reinforced copper W f /Cu composites were produced which proves their applicability with respect to a composite material production processes.

The exhaust of power and particles is regarded as a major challenge in view of the design of a magnetic confinement nuclear fusion demonstration power plant (DEMO). In such a reactor, highly loaded plasma facing components (PFCs), like the divertor targets, have to withstand both severe heat flux loads and considerable neutron irradiation. Existing divertor target designs make use of monolithic tungsten (W) and copper (Cu) material grades that are combined in a PFC. Such an approach, however, bears engineering difficulties as W and Cu are materials with inherently different thermomechanical properties and their optimum operating temperature windows do not overlap. Against this background, W Cu composite materials are promising candidates regarding the application to the heat sink of highly loaded PFCs. The present contribution summarises recent results regarding the manufacturing and characterisation of such W Cu composite materials produced by means of liquid Cu melt infiltration of open porous W preforms. On the one hand, this includes composites manufactured by infiltrating powder metallurgically produced W skeletons. On the other hand, W Cu composites based on textile technologically produced fibrous reinforcement preforms are discussed. (C) 2017 The Author(s). Published by Elsevier B.V.

The RoboCup Logistics League (RCLL) has seen major rule changes increasing the complexity, e.g. by raising the number of product variants from 3 to almost 250, and introducing new challenges like the handling of physical processing machines. We describe various aspects of our system that allowed to improve the performance in 2015 and our efforts to advance the league as a whole.

Although manufacturers and producers are having to meet increasingly volatile customer requirements, current production automation concepts do not yet offer the necessary flexibility. It is necessary to develop novel approaches. This paper presents an overview of a prototypical architecture for the realization of cyber-physical production systems (CPPS). This enables the horizontal and vertical integration of production systems and the resultant potentials are described.

At the Institute Cluster IMA/ZLW & IfU (Institute of Information Management in Mechanical Engineering / Center for Learning and Knowledge Management & Institute for Management Cybernetics) of the RWTH Aachen University, the interdisciplinary student laboratory "DLR_School_Lab RWTH Aachen" is operated. The laboratories' objective is to attract secondary school students to study fields affiliated to science, technology, engineering and mathematics (STEM) through active experimentation with robots. Concrete application scenarios from the fields of aeronautics, space, energy and transport research - with a special focus on robotics and artificial intelligence - give insight into the different scientific disciplines and arouse a desire for more. The DLR_School_Lab RWTH Aachen has been operated since June 2013 and offers hands-on experiments for secondary school classes. Based on the experiences of the last years this paper describes the concept of the DLR_School_Lab RWTH Aachen and its experiments. Furthermore the didactic concept of the extracurricular science lab is presented.

As the demand for close cooperation between human and robots grows, robot manufacturers develop new lightweight robots, which allow for direct human-robot interaction without endangering the human worker. However, enabling direct and intuitive interaction between robots and human workers is still challenging in many aspects, due to the nondeterministic nature of human behavior. This work focuses on the main problems of interactive object transfer between a human worker and an industrial robot: the recognition of the object with partial occlusion by barriers including the hand to the human worker, the evaluation of object grasping affordance, and coping with inaccessible grasping points. The proposed visual servoing system integrates different vision modules where each module encapsulates a number of visual algorithms responsible for visual servoing control in humanrobot collaboration. The goal is to extract high-level information of a visual event from a dynamic scene for recognition and manipulation. The system consists of several modules as sensor fusion, calibration, visualization, pose estimation, object tracking, classification, grasping planning and feedback processing. The general architecture and main approaches are presented as well as the future developments planned.

Obwohl die Anforderungen in der modernen Produktionstechnik durch wechselnde Kundenwünsche bestimmt werden, unterstützen aktuelle Automatisierungslösungen vor allem die geforderte Flexibilität für Losgröße 1 nicht in ausreichendem Maße. Der Beitrag gibt einen Überblick über eine prototypische Architektur für agentenbasierte cyber-physische Produktionssysteme. Mit dieser Architektur wird die standortübergreifende horizontale und vertikale Integration von Produktionssystemen vorgestellt und verschiedene sich daraus ergebende Potenziale werden aufgezeigt.

The RoboCup Logistics League is one of the youngest application-and industry-oriented leagues. Even so, the complexity and level of difficulty has increased over the years. We describe decisive technical and organizational aspects of our hardware and software systems and (human) team structure that made winning the RoboCup and German Open competitions possible in 2014.

A new trend in automation is to deploy so-called cyber-physical systems (CPS) which combine computation with physical processes. The novel RoboCup Logistics League Sponsored by Festo (LLSF) aims at such CPS logistic scenarios in an automation setting. A team of robots has to produce products from a number of semi-finished products which they have to machine during the game. Different production plans are possible and the robots need to recycle scrap byproducts. This way, the LLSF is a very interesting league offering a number of challenging research questions for planning, coordination, or communication in an application-driven scenario. In this paper, we outline the objectives of the LLSF and present steps for developing the league further towards a benchmark for logistics scenarios for CPS. As a major milestone we present the new automated referee system which helps in governing the game play as well as keeping track of the scored points in a very complex factory scenario.

In this paper we discuss the characteristics and difficulties of the production ramp-up processes in general and the resulting challenges for logistics during ramp-up. Ramp-up as a non-linear, socio-technical system presents companies with great challenges with regard to ensuring a satisfactory product quality and quantity. One of the main obstacles of the ramp-up environment is the robustness against informational deficits such as missing availability of data, fast state changes and information uncertainties. Internal turbulences on the shop floor level and a changing target system present the ramp-up system with further challenges. In this context, we discuss the characteristics and difficulties of ramp-up processes in general and the resulting challenges for ramp-up logistics, especially with respect to autonomous logistics by means of mobile transportation robots. To overcome the problem of missing models and simulations for ramp-up management we propose the RoboCup Logistics League as a test bench for new approaches for ramp-up logistics. We therefore map the identified characteristics of ramp-up processes to the RoboCup Logistics League and show the suitability of the game based approach for serious research on ramp-up management. The Robocup Logistics League has an automated referee and an overhead tracking systems. These systems allow for logging of events together with transportation routes and robot positions. With this information the behavior of the logistic system can be analyzed and automated benchmark procedures for logistics tasks can be established.

Compared to current industry standards future production systems will be more flexible and robust and will adapt to unforeseen states and events. Industrial robots will interact with each other as well as with human coworkers. To be able to act in such a dynamic environment, each acting entity ideally needs complete knowledge of its surroundings, concerning working materials as well as other working entities. Therefore new monitoring methods providing complete coverage for complex and changing working areas are needed. While single 3-D sensors already provide detailed information within their field of view, complete coverage of a complete work area can only be achieved by relying on a multitude of these sensors. However, to provide useful information all data of each sensor must be aligned to each other and fused into an overall world picture. To be able to align the data correctly, the position and orientation of each sensor must be known with sufficient exactness. In a quickly changing dynamic environment, the positions of sensors are not fixed, but must be adjusted to maintain optimal coverage. Therefore, the sensors need to autonomously align themselves in real time. This can be achieved by adding defined markers with given geometrical patterns to the environment which can be used for calibration and localization of each sensor. As soon as two sensors detect the same markers, their relative position to each other can be calculated. Additional anchor markers at fixed positions serve as global reference points for the base coordinate system. In this paper we present a prototype for a self-aligning monitoring system based on a robot operating system (ROS) and Microsoft Kinect. This system is capable of autonomous real-time calibration relative to and with respect to a global coordinate system as well as to detect and track defined objects within the working area.

In this team description paper, we outline the approach of the Carologistics team with an emphasis on the high-level reasoning system and our simulation to develop it. We outline the hardware modifications and describe our software systems and describe our efforts towards a fully autonomous referee box. The team members in 2014 are Daniel Ewert, Alexander Ferrein, Nicolas Limpert, Matthias Lobach, Randolph Maasen, Victor Matare, Tobias Neumann, Tim Niemueller, Florian Nolden, Sebastian Reuter, Johannes Rothe, and Frederik Zwilling.

Edges provide important visual information by corresponding to discontinuities in the physical, photometrical and geometrical properties of scene objects, such as significant variations in the reflectance, illumination, orientation and depth of scene surfaces. The significance has drawn many people to work on the detection and extraction of edge features. The characteristics of 3D point clouds and 2D digital images are thought to be complementary, so the combined interpretation of objects with point clouds and image data is a promising approach to describe an object in computer vision area. However, the prerequisite for different levels of integrated data interpretation is the geometric referencing between the 3D point cloud and 2D image data, and a precondition for geometric referencing lies in the extraction of the corresponding features.Addressing the wide-ranged applications of edge detection in object recognition, image segmentation and pose identification, this paper presents a novel approach to extract 3D edges. The main idea is combining the edge data from a point cloud of an object and its corresponding digital images. Our approach is aimed to make use of the advantages of both edge processing and analysis of point clouds and image processing to represent the edge characteristics in 3D with increased accuracy.On the 2D image processing part, an edge extraction is applied on the image by using the Canny edge detection algorithm after the raw image data pre-processing. An easily-operating pixel data mapping mechanism is proposed in our work for corresponding 2D image pixels with 3D point cloud pixels. By referring to the correspondence map, 2D edge data are merged into 3D point cloud. On the point cloud part, the border extracting operator is performed on the range image. As a preparation work, the raw point cloud data are used to generate a range image. Edge points in the range image, points with range, are converted to 3D point type with the application of the Point Cloud Library (PCL) to define the edges in the 3D point cloud.