Hochschule Bonn-Rhein-Sieg
Publikationsserver der Hochschule Bonn-Rhein-Sieg - pub H-BRSNot a member yet
7939 research outputs found
Sort by
A Neuromorphic Approach to Obstacle Avoidance in Robot Manipulation
No full textNeuromorphic computing aims to mimic the computational principles of the brain in silico and has motivated research into event-based vision and spiking neural networks (SNNs). Event cameras (ECs) capture local, independent changes in brightness, and offer superior power consumption, response latencies, and dynamic ranges compared to frame-based cameras. SNNs replicate neuronal dynamics observed in biological neurons and propagate information in sparse sequences of ”spikes”. Apart from biological fidelity, SNNs have demonstrated potential as an alternative to conventional artificial neural networks (ANNs), such as in reducing energy expenditure and inference time in visual classification. Although potentially beneficial for robotics, the novel event-driven and spike-based paradigms remain scarcely explored outside the domain of aerial robots.
To investigate the utility of brain-inspired sensing and data processing in a robotics application, we developed a neuromorphic approach to real-time, online obstacle avoidance on a manipulator with an onboard camera. Our approach adapts high-level trajectory plans with reactive maneuvers by processing emulated event data in a convolutional SNN, decoding neural activations into avoidance motions, and adjusting plans in a dynamic motion primitive formulation. We conducted simulated and real experiments with a Kinova Gen3 arm performing simple reaching tasks involving static and dynamic obstacles. Our implementation was systematically tuned, validated, and tested in sets of distinct task scenarios, and compared to a non-adaptive baseline through formalized quantitative metrics and qualitative criteria.
The neuromorphic implementation facilitated reliable avoidance of imminent collisions in most scenarios, with 84% and 92% median success rates in simulated and real experiments, where the baseline consistently failed. Adapted trajectories were qualitatively similar to baseline trajectories, indicating low impacts on safety, predictability and smoothness criteria. Among notable properties of the SNN were the correlation of processing time with the magnitude of perceived motions (captured in events) and robustness to different event emulation methods. Preliminary tests with a DAVIS346 EC showed similar performance, validating our experimental event emulation method. These results motivate future efforts to incorporate SNN learning, utilize neuromorphic processors, and target other robot tasks to further explore this approach
Fluid Dynamics Network: Topology-Agnostic 4D Reconstruction via Fluid Dynamics Priors
No full textRepresenting 3D surfaces as level sets of continuous functions over R3 is the common denominator of neural implicit representations, which recently enabled remarkable progress in geometric deep learning and computer vision tasks. In order to represent 3D motion within this framework, it is often assumed (either explicitly or implicitly) that the transformations which a surface may undergo are homeomorphic: this is not necessarily true, for instance, in the case of fluid dynamics. In order to represent more general classes of deformations, we propose to apply this theoretical framework as regularizers for the optimization of simple 4D implicit functions (such as signed distance fields). We show that our representation is capable of capturing both homeomorphic and topology-changing deformations, while also defining correspondences over the continuously-reconstructed surfaces
Analytical Chemistry I
No full textThis workbook takes you through the successful work Harris, Textbook of Quantitative Analysis and is designed primarily for self-study. In five parts, the lecture content of analytical chemistry is summarized and explained using selected examples. Basic concepts of analytical chemistry are presented as well as the principle and various techniques of dimensional analysis and chromatography. UV/VIS, infrared and Raman spectroscopy are used to explain the investigation of molecularly present compounds, and selected techniques of atomic spectroscopy conclude the introduction to the fundamentals of analysis. The textbook's essential sections and illustrations are repeatedly referred to, which facilitates independent learning of the fundamentals of analytical chemistry
Elektronik für Entscheider: Grundwissen für Wirtschaft und Technik
No full textDieses Buch gibt Nichtingenieuren, die sich beruflich mit Elektronik beschäftigen, die Möglichkeit, sich ein Stück auf dieses Fachgebiet zu begeben, um Aufgaben, Sprache und Vorgehensweise von Ingenieuren zu verstehen. Ziel ist es dabei nicht, nach dem Lesen dieses Buches eine elektronische Schaltung entwickeln zu können. Im Vordergrund steht vielmehr ein generelles Verständnis für die Zusammenhänge und Grundbegriffe der Elektronik. (Verlagsangaben
Project Management: MBA Essentials
No full textCompanies are increasingly developing into dynamic and project-oriented organizations. Globalization, innovations and organizational dynamics require more and more projects, and thus a more project-oriented corporate organization and management. As a rule, managers as well as employees already work parallel to their line function in projects or completely from project to project.
At the same time, cross-company and especially international value chains lead to the cooperation of cross-departamental and intercultural teams. For this, the specialists and executives need above all knowledge and experience in project management and the corresponding concepts as well as in the special form of cooperation, team development and communication. Because the most problems in project management are not caused by project goals and methods, but by the many different problem-solving behavior and attitudes, e.g. between engineers and business people, different departments or the different country cultures. The international IT project specialist Tom DeMarco puts it in a nutshell (in Peopleware - Productive Projects and Teams: The major problems of our work are not so much technological as socio-logical in nature. In terms of content here, in contrast to traditional professional textbooks, not only the technologies are priority, but also the social and intercultural aspects of project work.
The book is aimed equally at students of all disciplines with a focus on managerial and project-related work as well as practitioners and entrepreneurs in all private business sectors as well as in NGOs, public projects or PPPs as public-private partnership
A Comparison of Vector-based Approaches for Document Similarity Using the RELISH Corpus
No full textThe continuously increasing number of biomedical scholarly publications makes it challenging to construct document recommendation algorithms that can efficiently navigate through literature. Such algorithms would help researchers in finding similar, relevant, and related publications that align with their research interests. Natural Language Processing offers various alternatives to compare publications, ranging from entity recognition to document embeddings. In this paper, we present the results of a comparative analysis of vector-based approaches to assess document similarity in the RELISH corpus. We aim to determine the best approach that resembles relevance without the need for further training. Specifically, we employ five different techniques to generate vectors representing the text in the documents. These techniques employ a combination of various Natural Language Processing frameworks such as Word2Vec, Doc2Vec, dictionary-based Named Entity Recognition, and state-of-the-art models based on BERT. To evaluate the document similarity obtained by these approaches, we utilize different evaluation metrics that account for relevance judgment, relevance search, and re-ranking of the relevance search. Our results demonstrate that the most promising approach is an in-house version of document embeddings, starting with word embeddings and using centroids to aggregate them by document
