Refine
Year of publication
- 2021 (24) (remove)
Document Type
- Conference Proceeding (11)
- Part of a Book (8)
- Article (5)
Language
- English (24) (remove)
Keywords
- autonomous driving (2)
- robotic process automation (2)
- 3D object detection (1)
- Bloom’s Taxonomy (1)
- Competence Developing Games (1)
- Computational modeling (1)
- Deep learning (1)
- Enterprise Architecture (1)
- Frequency Doubler (1)
- GPU (1)
- Game-based learning (1)
- Harmonic Radar (1)
- Heuristic algorithms (1)
- IT security education (1)
- Implementation Case (1)
- Keyword analysis (1)
- LiDAR (1)
- Mixed-integer nonlinear programming (1)
- Optimization (1)
- Powertrain (1)
Institute
- Fachbereich Elektrotechnik und Informationstechnik (24) (remove)
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.
This chapter describes three general strategies to master uncertainty in technical systems: robustness, flexibility and resilience. It builds on the previous chapters about methods to analyse and identify uncertainty and may rely on the availability of technologies for particular systems, such as active components. Robustness aims for the design of technical systems that are insensitive to anticipated uncertainties. Flexibility increases the ability of a system to work under different situations. Resilience extends this characteristic by requiring a given minimal functional performance, even after disturbances or failure of system components, and it may incorporate recovery. The three strategies are described and discussed in turn. Moreover, they are demonstrated on specific technical systems.
The initial idea of Robotic Process Automation (RPA) is the automation of business processes through a simple emulation of user input and output by software robots. Hence, it can be assumed that no changes of the used software systems and existing Enterprise Architecture (EA) is
required. In this short, practical paper we discuss this assumption based on a real-life implementation project. We show that a successful RPA implementation might require architectural work during analysis, implementation, and migration. As practical paper we focus on exemplary lessons-learned and new questions related to RPA and EA.