@inproceedings{AlhwarinFerreinGebhardtetal.2015, author = {Alhwarin, Faraj and Ferrein, Alexander and Gebhardt, Andreas and Kallweit, Stephan and Scholl, Ingrid and Tedjasukmana, Osmond Sanjaya}, title = {Improving additive manufacturing by image processing and robotic milling}, series = {2015 IEEE International Conference on Automation Science and Engineering (CASE), Aug 24-28, 2015 Gothenburg, Sweden}, booktitle = {2015 IEEE International Conference on Automation Science and Engineering (CASE), Aug 24-28, 2015 Gothenburg, Sweden}, doi = {10.1109/CoASE.2015.7294217}, pages = {924 -- 929}, year = {2015}, language = {en} } @article{EngemannCoenenDawaretal.2021, author = {Engemann, Heiko and C{\"o}nen, Patrick and Dawar, Harshal and Du, Shengzhi and Kallweit, Stephan}, title = {A robot-assisted large-scale inspection of wind turbine blades in manufacturing using an autonomous mobile manipulator}, series = {Applied Sciences}, volume = {11}, journal = {Applied Sciences}, number = {19}, publisher = {MDPI}, address = {Basel}, issn = {2076-3417}, doi = {10.3390/app11199271}, pages = {1 -- 22}, year = {2021}, abstract = {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.}, language = {en} } @article{EngemannDuKallweitetal.2020, author = {Engemann, Heiko and Du, Shengzhi and Kallweit, Stephan and C{\"o}nen, Patrick and Dawar, Harshal}, title = {OMNIVIL - an autonomous mobile manipulator for flexible production}, series = {Sensors}, volume = {20}, journal = {Sensors}, number = {24, art. no. 7249}, publisher = {MDPI}, address = {Basel}, isbn = {1424-8220}, doi = {10.3390/s20247249}, pages = {1 -- 30}, year = {2020}, language = {en} } @incollection{EngemannDuKallweitetal.2020, author = {Engemann, Heiko and Du, Shengzhi and Kallweit, Stephan and Ning, Chuanfang and Anwar, Saqib}, title = {AutoSynPose: Automatic Generation of Synthetic Datasets for 6D Object Pose Estimation}, series = {Machine Learning and Artificial Intelligence. Proceedings of MLIS 2020}, booktitle = {Machine Learning and Artificial Intelligence. Proceedings of MLIS 2020}, publisher = {IOS Press}, address = {Amsterdam}, isbn = {978-1-64368-137-5}, doi = {10.3233/FAIA200770}, pages = {89 -- 97}, year = {2020}, abstract = {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.}, language = {en} } @inproceedings{EngemannWiesenKallweitetal.2018, author = {Engemann, Heiko and Wiesen, Patrick and Kallweit, Stephan and Deshpande, Harshavardhan and Schleupen, Josef}, title = {Autonomous mobile manipulation using ROS}, series = {Advances in Service and Industrial Robotics}, booktitle = {Advances in Service and Industrial Robotics}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-61276-8}, doi = {10.1007/978-3-319-61276-8_43}, pages = {389 -- 401}, year = {2018}, language = {en} } @inproceedings{FerreinKallweitScholletal.2015, author = {Ferrein, Alexander and Kallweit, Stephan and Scholl, Ingrid and Reichert, Walter}, title = {Learning to Program Mobile Robots in the ROS Summer School Series}, series = {Proceedings 6th International Conference on Robotics in Education (RiE 15)}, booktitle = {Proceedings 6th International Conference on Robotics in Education (RiE 15)}, pages = {6 S.}, year = {2015}, abstract = {The main objective of our ROS Summer School series is to introduce MA level students to program mobile robots with the Robot Operating System (ROS). ROS is a robot middleware that is used my many research institutions world-wide. Therefore, many state-of-the-art algorithms of mobile robotics are available in ROS and can be deployed very easily. As a basic robot platform we deploy a 1/10 RC cart that is wquipped with an Arduino micro-controller to control the servo motors, and an embedded PC that runs ROS. In two weeks, participants get to learn the basics of mobile robotics hands-on. We describe our teaching concepts and our curriculum and report on the learning success of our students.}, language = {en} } @article{FrankoDuKallweitetal.2020, author = {Franko, Josef and Du, Shengzhi and Kallweit, Stephan and Duelberg, Enno Sebastian and Engemann, Heiko}, title = {Design of a Multi-Robot System for Wind Turbine Maintenance}, series = {Energies}, volume = {13}, journal = {Energies}, number = {10}, publisher = {MDPI}, address = {Basel}, issn = {1996-1073}, doi = {10.3390/en13102552}, pages = {Article 2552}, year = {2020}, abstract = {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.}, language = {en} } @incollection{KallweitGottschalkWalenta2016, author = {Kallweit, Stephan and Gottschalk, Michael and Walenta, Robert}, title = {ROS based safety concept for collaborative robots in industrial applications}, series = {Advances in robot design and intelligent control : proceedings of the 24th International Conference on Robotics in Alpe-Adria-Danube Region (RAAD). (Advances in intelligent systems and computing ; 371)}, booktitle = {Advances in robot design and intelligent control : proceedings of the 24th International Conference on Robotics in Alpe-Adria-Danube Region (RAAD). (Advances in intelligent systems and computing ; 371)}, publisher = {Springer}, address = {Cham}, organization = {International Conference on Robotics in Alpe-Adria-Danube Region <24, 2015, Bucharest>}, isbn = {978-3-319-21289-0 (Print) ; 978-3-319-21290-6 (E-Book)}, doi = {10.1007/978-3-319-21290-6_3}, pages = {27 -- 35}, year = {2016}, abstract = {The production and assembly of customized products increases the demand for flexible automation systems. One approach is to remove the safety fences that separate human and industrial robot to combine their skills. This collaboration possesses a certain risk for the human co-worker, leading to numerous safety concepts to protect him. The human needs to be monitored and tracked by a safety system using different sensors. The proposed system consists of a RGBD camera for surveillance of the common working area, an array of optical distance sensors to compensate shadowing effects of the RGBD camera and a laser range finder to detect the co-worker when approaching the work cell. The software for collision detection, path planning, robot control and predicting the behaviour of the co-worker is based on the Robot Operating System (ROS). A first prototype of the work cell shows that with advanced algorithms from the field of mobile robotics a very flexible safety concept can be realized: the robot not simply stops its movement when detecting a collision, but plans and executes an alternative path around the obstacle.}, language = {en} } @inproceedings{SchleupenEngemannBagherietal.2017, author = {Schleupen, Josef and Engemann, Heiko and Bagheri, Mohsen and Kallweit, Stephan and Dahmann, Peter}, title = {Developing a climbing maintenance robot for tower and rotor blade service of wind turbines}, series = {Advances in Robot Design and Intelligent Control : Proceedings of the 25th Conference on Robotics in Alpe-Adria-Danube Region (RAAD16)}, booktitle = {Advances in Robot Design and Intelligent Control : Proceedings of the 25th Conference on Robotics in Alpe-Adria-Danube Region (RAAD16)}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-49058-8}, doi = {10.1007/978-3-319-49058-8_34}, pages = {310 -- 319}, year = {2017}, language = {en} } @inproceedings{WiesenEngemannLimpertetal.2018, author = {Wiesen, Patrick and Engemann, Heiko and Limpert, Nicolas and Kallweit, Stephan}, title = {Learning by Doing - Mobile Robotics in the FH Aachen ROS Summer School}, series = {European Robotics Forum 2018, TRROS18 Workshop}, booktitle = {European Robotics Forum 2018, TRROS18 Workshop}, pages = {47 -- 58}, year = {2018}, language = {en} }