TY - JOUR A1 - Engemann, Heiko A1 - Cönen, Patrick A1 - Dawar, Harshal A1 - Du, Shengzhi A1 - Kallweit, Stephan T1 - A robot-assisted large-scale inspection of wind turbine blades in manufacturing using an autonomous mobile manipulator JF - Applied Sciences N2 - Wind energy represents the dominant share of renewable energies. The rotor blades of a wind turbine are typically made from composite material, which withstands high forces during rotation. The huge dimensions of the rotor blades complicate the inspection processes in manufacturing. The automation of inspection processes has a great potential to increase the overall productivity and to create a consistent reliable database for each individual rotor blade. The focus of this paper is set on the process of rotor blade inspection automation by utilizing an autonomous mobile manipulator. The main innovations include a novel path planning strategy for zone-based navigation, which enables an intuitive right-hand or left-hand driving behavior in a shared human–robot workspace. In addition, we introduce a new method for surface orthogonal motion planning in connection with large-scale structures. An overall execution strategy controls the navigation and manipulation processes of the long-running inspection task. The implemented concepts are evaluated in simulation and applied in a real-use case including the tip of a rotor blade form. KW - mobile manipulation KW - large-scale inspection KW - wind turbine production KW - autonomous navigation KW - surface-orthogonal path planning Y1 - 2021 U6 - http://dx.doi.org/10.3390/app11199271 SN - 2076-3417 N1 - Belongs to the Special Issue "Advances in Industrial Robotics and Intelligent Systems" VL - 11 IS - 19 SP - 1 EP - 22 PB - MDPI CY - Basel ER - TY - JOUR A1 - Engemann, Heiko A1 - Du, Shengzhi A1 - Kallweit, Stephan A1 - Cönen, Patrick A1 - Dawar, Harshal T1 - OMNIVIL - an autonomous mobile manipulator for flexible production JF - Sensors Y1 - 2020 SN - 1424-8220 U6 - http://dx.doi.org/10.3390/s20247249 N1 - Special issue: Sensor Networks Applications in Robotics and Mobile Systems VL - 20 IS - 24, art. no. 7249 SP - 1 EP - 30 PB - MDPI CY - Basel ER - TY - CHAP A1 - Engemann, Heiko A1 - Du, Shengzhi A1 - Kallweit, Stephan A1 - Ning, Chuanfang A1 - Anwar, Saqib T1 - AutoSynPose: Automatic Generation of Synthetic Datasets for 6D Object Pose Estimation T2 - Machine Learning and Artificial Intelligence. Proceedings of MLIS 2020 N2 - We present an automated pipeline for the generation of synthetic datasets for six-dimension (6D) object pose estimation. Therefore, a completely automated generation process based on predefined settings is developed, which enables the user to create large datasets with a minimum of interaction and which is feasible for applications with a high object variance. The pipeline is based on the Unreal 4 (UE4) game engine and provides a high variation for domain randomization, such as object appearance, ambient lighting, camera-object transformation and distractor density. In addition to the object pose and bounding box, the metadata includes all randomization parameters, which enables further studies on randomization parameter tuning. The developed workflow is adaptable to other 3D objects and UE4 environments. An exemplary dataset is provided including five objects of the Yale-CMU-Berkeley (YCB) object set. The datasets consist of 6 million subsegments using 97 rendering locations in 12 different UE4 environments. Each dataset subsegment includes one RGB image, one depth image and one class segmentation image at pixel-level. Y1 - 2020 SN - 978-1-64368-137-5 U6 - http://dx.doi.org/10.3233/FAIA200770 N1 - Frontiers in Artificial Intelligence and Applications. Vol 332 SP - 89 EP - 97 PB - IOS Press CY - Amsterdam ER - TY - JOUR A1 - Kunkel, Maximilian Hugo A1 - Gebhardt, Andreas A1 - Mpofu, Khumbulani A1 - Kallweit, Stephan T1 - Quality assurance in metal powder bed fusion via deep-learning-based image classification JF - Rapid Prototyping Journal Y1 - 2019 U6 - http://dx.doi.org/10.1108/RPJ-03-2019-0066 SN - 1355-2546 VL - 26 IS - 2 SP - 259 EP - 266 ER - TY - JOUR A1 - Franko, Josef A1 - Du, Shengzhi A1 - Kallweit, Stephan A1 - Duelberg, Enno Sebastian A1 - Engemann, Heiko T1 - Design of a Multi-Robot System for Wind Turbine Maintenance JF - Energies N2 - The maintenance of wind turbines is of growing importance considering the transition to renewable energy. This paper presents a multi-robot-approach for automated wind turbine maintenance including a novel climbing robot. Currently, wind turbine maintenance remains a manual task, which is monotonous, dangerous, and also physically demanding due to the large scale of wind turbines. Technical climbers are required to work at significant heights, even in bad weather conditions. Furthermore, a skilled labor force with sufficient knowledge in repairing fiber composite material is rare. Autonomous mobile systems enable the digitization of the maintenance process. They can be designed for weather-independent operations. This work contributes to the development and experimental validation of a maintenance system consisting of multiple robotic platforms for a variety of tasks, such as wind turbine tower and rotor blade service. In this work, multicopters with vision and LiDAR sensors for global inspection are used to guide slower climbing robots. Light-weight magnetic climbers with surface contact were used to analyze structure parts with non-destructive inspection methods and to locally repair smaller defects. Localization was enabled by adapting odometry for conical-shaped surfaces considering additional navigation sensors. Magnets were suitable for steel towers to clamp onto the surface. A friction-based climbing ring robot (SMART— Scanning, Monitoring, Analyzing, Repair and Transportation) completed the set-up for higher payload. The maintenance period could be extended by using weather-proofed maintenance robots. The multi-robot-system was running the Robot Operating System (ROS). Additionally, first steps towards machine learning would enable maintenance staff to use pattern classification for fault diagnosis in order to operate safely from the ground in the future. Y1 - 2020 U6 - http://dx.doi.org/10.3390/en13102552 SN - 1996-1073 VL - 13 IS - 10 SP - Article 2552 PB - MDPI CY - Basel ER - TY - JOUR A1 - Limpert, Nicolas A1 - Wiesen, Patrick A1 - Ferrein, Alexander A1 - Kallweit, Stephan A1 - Schiffer, Stefan T1 - The ROSIN Project and its Outreach to South Africa JF - R&D Journal Y1 - 2019 VL - 35 SP - 1 EP - 6 ER - TY - CHAP A1 - Engemann, Heiko A1 - Badri, Sriram A1 - Wenning, Marius A1 - Kallweit, Stephan T1 - Implementation of an Autonomous Tool Trolley in a Production Line T2 - Advances in Service and Industrial Robotics. RAAD 2019. Advances in Intelligent Systems and Computing, vol 980 Y1 - 2019 SN - 978-3-030-19648-6 U6 - http://dx.doi.org/10.1007/978-3-030-19648-6_14 SP - 117 EP - 125 PB - Springer CY - Cham ER - TY - CHAP A1 - Wiesen, Patrick A1 - Engemann, Heiko A1 - Limpert, Nicolas A1 - Kallweit, Stephan T1 - Learning by Doing - Mobile Robotics in the FH Aachen ROS Summer School T2 - European Robotics Forum 2018, TRROS18 Workshop Y1 - 2018 SP - 47 EP - 58 ER - TY - CHAP A1 - Ferrein, Alexander A1 - Schiffer, Stefan A1 - Kallweit, Stephan T1 - The ROSIN Education Concept - Fostering ROS Industrial-Related Robotics Education in Europe T2 - ROBOT 2017: Third Iberian Robotics Conference Y1 - 2018 SN - 978-3-319-70836-2 U6 - http://dx.doi.org/10.1007/978-3-319-70836-2_31 N1 - Advances in Intelligent Systems and Computing, vol 694; (AISC, volume 694) SP - 370 EP - 381 PB - Springer CY - Cham ER - TY - JOUR A1 - Michaux, F. A1 - Mattern, P. A1 - Kallweit, Stephan T1 - RoboPIV: how robotics enable PIV on a large industrial scale JF - Measurement Science and Technology N2 - This work demonstrates how the interaction between particle image velocimetry (PIV) and robotics can massively increase measurement efficiency. The interdisciplinary approach is shown using the complex example of an automated, large scale, industrial environment: a typical automotive wind tunnel application. Both the high degree of flexibility in choosing the measurement region and the complete automation of stereo PIV measurements are presented. The setup consists of a combination of three robots, individually used as a 6D traversing unit for the laser illumination system as well as for each of the two cameras. Synchronised movements in the same reference frame are realised through a master-slave setup with a single interface to the user. By integrating the interface into the standard wind tunnel management system, a single measurement plane or a predefined sequence of several planes can be requested through a single trigger event, providing the resulting vector fields within minutes. In this paper, a brief overview on the demands of large scale industrial PIV and the existing solutions is given. Afterwards, the concept of RoboPIV is introduced as a new approach. In a first step, the usability of a selection of commercially available robot arms is analysed. The challenges of pose uncertainty and importance of absolute accuracy are demonstrated through comparative measurements, explaining the individual pros and cons of the analysed systems. Subsequently, the advantage of integrating RoboPIV directly into the existing wind tunnel management system is shown on basis of a typical measurement sequence. In a final step, a practical measurement procedure, including post-processing, is given by using real data and results. Ultimately, the benefits of high automation are demonstrated, leading to a drastic reduction in necessary measurement time compared to non-automated systems, thus massively increasing the efficiency of PIV measurements. Y1 - 2018 U6 - http://dx.doi.org/10.1088/1361-6501/aab5c1 SN - 1361-6501 N1 - Special Section on the 12th International Symposium on Particle Image Velocimetry (PIV 2017) VL - 29 IS - 7 SP - 074009 PB - IOP CY - Bristol ER -