Stefan ReitmannTechnische Universität Bergakademie Freiberg · Institute of Computer Science
Stefan Reitmann
Doctor of Engineering
Interested in collaborative AI/VR&AR/robotics/simulation projects
About
34
Publications
7,966
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
172
Citations
Citations since 2017
Introduction
My research focus is on the interaction of AI, robotics and VR/AR for intelligent autonomous systems. In particular, I am interested in how a robot's AI can be trained in simulated virtual worlds and on the basis of synthetic data, e.g. by simulation of virtual sensors (LiDAR, sonar) or related to the behavior of virtual agents, e.g. in game engines (Unity, Unreal). Furthermore I investigate the opportunities of VR/AR for telerobotics.
Additional affiliations
September 2022 - October 2022
September 2020 - May 2022
Position
- Lecturer
Description
- Introduction to 3D Computer Graphics
September 2019 - present
Education
October 2015 - October 2020
September 2015 - October 2020
October 2009 - August 2015
Publications
Publications (34)
This paper shows a way to model moving swarms of fish in water bodies and detect them using virtual sensors. Real waters (e.g. lakes) can be explored and analyzed with sonar sensors based on sound waves. For automatic Artificial Intelligence (AI)-based detection of moving objects, such as fish, in sensor data, there is often a lack of training data...
This paper discusses and explores applications of virtual worlds generated from heterogenous kinds of open geodata, such as 2D maps, digital elevation models and aerial photographs. Two workflows are presented for generation of such virtual worlds and their integration into the Unreal and Godot game engines. The feature-richness of game engines the...
Evaluating the performance of complex systems, such as air traffic management (ATM), is a challenging task. When regarding aviation as a time-continuous system measured in value-discrete time series via performance indicators and certain metrics, it is important to use sufficiently targeted mathematical models within the analysis. A consistent iden...
Efficient airport operations depend on appropriate actions and reactions to current constraints. Local weather events and their impact on airport performance may have network-wide effects. The classification of expected weather impacts enables efficient consideration in airport operations on a tactical level. We classify airport performance with re...
We derive absolute observation stability and instability results for controlled evolutionary inequalities which are based on frequency-domain characteristics of the linear part of the inequalities. The uncertainty parts of the inequalities (nonlinearities which represent external forces and constitutive laws) are described by certain local and inte...
This paper deals with the issue of evaluating and analyzing geometric point sets in three-dimensional space. Point sets or point clouds are often the product of 3D scanners and depth sensors, which are used in the field of autonomous movement for robots and vehicles. Therefore, for the classification of point sets within an active motion, not fully...
This paper deals with the issue of evaluating and analyzing geometric point sets in three-dimensional space. Point sets or point clouds are often the product of 3D scanners and depth sensors, which are used in the field of autonomous movement for robots and vehicles. Therefore, for the classification of point sets within an active motion, not fully...
As part of the RoBiMo project, a measuring system for holistic, spatially resolved recording of the condition and processes in inland waters is to be developed. This system should measure regular, continuous and spatially re-solved parameters of water quality in stagnant inland waters. Forthat, the swimming robot "Elisabeth" from the TU Bergakademi...
Common Machine-Learning (ML) approaches for scene classification require a large amount of training data. However, for classification of depth sensor data, in contrast to image data, relatively few databases are publicly available and manual generation of semantically labeled 3D point clouds is an even more time-consuming task. To simplify the trai...
With this collaborative work of the Freiberg University of Mining and Technology and the St. Petersburg State University capabilities and characteristics of Spiking Neural Networks in the field of computer vision and environmental robotics are to be explored and analyzed. We aim at providing an adaptive recognition and classification model for temp...
Der Luftverkehr stellt ein komplexes Gesamtsystem dar, in welchem eine Prozessoptimierung aufgrund zahlreicher und verschiedenartiger Arbeitsabläufe verschiedener Unternehmen nur durch eine übergeordnete Leistungsbewertung möglich ist. Hierfür wurde im Bereich des leistungsbasierten Flughafenmanagements - sowohl auf wissenschaftlicher, als auch ind...
Today, supervised learning is a common method for classification and segmentation tasks. The data foundation is often insufficient for suitable training of such an artificial intelligence, especially if predefined sensor technology has to be considered. For this reason, we have developed an add-on package for the open source software Blender, which...
Die Projekte RoBiMo (Robotergestütztes Binnengewässer-Monitoring) und AIRGEMM (Artificial Intelligence and Robotics for GeoEnvironmental Modelling and Monitoring) an der Technischen Universität Bergakademie Freiberg wollen zu einer deutlichen Verbesserung des Gewässermanagements beitragen. Bisherige Einschränkungen der Frequenz und Intensität der Ü...
Classification of weather impacts on airport operations will allow efficient consideration of local weather events in network-wide analysis. We use machine learning approaches in our contribution to correlate weather data from meteorological reports and airport performance data, which contains flight plan data with scheduled, actual movements and d...
Classification of weather impacts on airport operations will allow efficient consideration of local weather events in network-wide analysis. We use machine learning approaches to correlate weather data from meteorological reports and airport performance data contains of flight plan data with scheduled and actual movements as well as delays. In part...
Reliable and predictable ground operations are essential for punctual air traffic movements. Uncertainties in the airborne phase have significantly less impact on flight punctuality than deviations in aircraft ground operations. The ground trajectory of an aircraft primarily consists of the handling processes at the stand, defined as the aircraft t...
In this paper we compute the impact of weather events to airport performance, which is measured as deviation of actual and scheduled timestamps (delay). Weather phenomena are categorized by the Air Traffic Management Airport Performance (ATMAP) weather algorithm, which aims to quantify weather conditions at European airports. A comprehensive datase...
In this paper we compute the impact of weather events to airport performance, which is measured as deviation of actual and scheduled timestamps (delay). Weather phenomena are categorized by the Air
Traffic Management Airport Performance weather algorithm, which aims to quantify weather conditions at European airports. A comprehensive dataset of fli...
In this paper we address the prediction of aircraft boarding using a machine learning approach. Reliable process predictions of aircraft turnaround are an important element to further increase the punctuality of airline operations. In this context, aircraft turnaround is mainly controlled by operational experts, but the critical aircraft boarding i...
In this paper we compute the impact of weather events to airport performance, which is measured as deviation of actual and scheduled timestamps (delay). Weather phenomena are categorized by the Air Traffic Management Airport Performance weather algorithm, which aims to quantify weather conditions at European airports. A comprehensive dataset of fli...
Reliable and predictable ground operations are essential for 4D aircraft trajectories. Uncertainties in the airborne phase have significantly less impact on flight punctuality than deviations in aircraft ground operations. The ground trajectory of an aircraft primarily consists of the handling processes at the stand, defined as the aircraft turnaro...
The performance analysis of complex systems like Air Traffic Management (ATM) is a challenging task. To overcome statistical complexities through analyzing non-linear time series we approach the problem with machine learning methods. Therefore we understand ATM (and its identified system model) as a system of coupled and interdependent sub-systems...
Understanding and quantifying aviation as a whole system of coupled and interdependent sub-systems is a
challenging task. To overcome resulting complexities and dynamic effects we approach the problem from an analytical and operational point of view. Both differ in their required data inputs as well as their methods to analyze and identify interdep...
Projects
Projects (4)
We use Blender as a central tool for various tasks combining computer vision and machine learning. We implemented virtual sensors such as LiDAR, sonar and several camera systems in Blender to generate labeled synthetic data for machine learning applications. To create reference 3D worlds we use procedural modelling, as well as GAN and other ANN architectures to create synthetic geometry.
Future aviation requires air traffic providers, operators, and researchers to implement new procedures and technologies for an efficient and environment-friendly air transportation network. Data analytics and machine learning (ML) techniques are well suited for aviation to extract information from the large amounts of generated data, to predict future situations based on historical information and to assist humans in taking optimal decisions. The rationale is to try to learn how to imitate the behavior of operators rather than having them explain and model an incomplete set of rules they are assumed to follow.
A high degree of standardisation in operational processes is required to ensure efficient and effective air traffic management, during the flight stages and ground-handling stages. Deviations and disruptions in the complex and closely interlinked handling processes often lead to delays, which as the day progresses can have an increasingly negative effect on airline operations – and indeed of the entire air traffic network. Ground-handling processes can be collectively considered under the term ‘turnaround’ and consist of the unloading and loading of freight and baggage, refuelling, cleaning, inflight catering, and the boarding and disembarking of passengers. In this context, aircraft turnaround is mainly controlled by operational experts. On the other hand, the critical aircraft-boarding process is to a large extent driven by passengers, and the speed of boarding is influenced by their prior experience of flying and their willingness or ability to follow procedures. Passengers also demand ever-greater efficiency and comfort from their travel experiences, and 60% of passengers see non-efficient queuing at the boarding gate as major ‘pain point’ in their desired seamless journey.
