Refine
Year of publication
- 2021 (293) (remove)
Institute
- Fachbereich Gestaltung (94)
- Fachbereich Medizintechnik und Technomathematik (56)
- IfB - Institut für Bioengineering (36)
- Fachbereich Elektrotechnik und Informationstechnik (27)
- Fachbereich Luft- und Raumfahrttechnik (24)
- Fachbereich Wirtschaftswissenschaften (24)
- Fachbereich Energietechnik (23)
- Fachbereich Bauingenieurwesen (15)
- INB - Institut für Nano- und Biotechnologien (15)
- Fachbereich Chemie und Biotechnologie (12)
Document Type
- Article (109)
- Bachelor Thesis (89)
- Conference Proceeding (52)
- Part of a Book (17)
- Book (9)
- Master's Thesis (4)
- Report (4)
- Doctoral Thesis (2)
- Review (2)
- Conference: Meeting Abstract (1)
- Other (1)
- Part of a Periodical (1)
- Preprint (1)
- Working Paper (1)
Keywords
- Corporate Design (6)
- Animation (5)
- Fotografie (4)
- Illustration (4)
- Nachhaltigkeit (4)
- UX Design (4)
- App (3)
- Botanik (3)
- Dokumentation (3)
- Gamification (3)
Zugriffsart
- weltweit (119)
- campus (67)
- bezahl (34)
- fachbereichsweit (FB4) (1)
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.
In this paper we investigate the use of deep neural networks for 3D object detection in uncommon, unstructured environments such as in an open-pit mine. While neural nets are frequently used for object detection in regular autonomous driving applications, more unusual driving scenarios aside street traffic pose additional challenges. For one, the collection of appropriate data sets to train the networks is an issue. For another, testing the performance of trained networks often requires tailored integration with the particular domain as well. While there exist different solutions for these problems in regular autonomous driving, there are only very few approaches that work for special domains just as well. We address both the challenges above in this work. First, we discuss two possible ways of acquiring data for training and evaluation. That is, we evaluate a semi-automated annotation of recorded LIDAR data and we examine synthetic data generation. Using these datasets we train and test different deep neural network for the task of object detection. Second, we propose a possible integration of a ROS2 detector module for an autonomous driving platform. Finally, we present the performance of three state-of-the-art deep neural networks in the domain of 3D object detection on a synthetic dataset and a smaller one containing a characteristic object from an open-pit mine.