Sven Tomforde

Christian-Albrechts-Universität zu Kiel | CAU · AG Intelligente Systeme

With deep learning based perception tasks on radar input data gaining more attention for autonomous driving, the use of new data interfaces, specifically range-beam-doppler tensors, are explored to maximize the performance of corresponding algorithms. Surprisingly, in past publications, the Doppler information of this data has only played a minor r...

Organic Computing enables self-* properties in technical systems for mastering them in the face of complexity and for improving robustness and efficiency. Key technology for self-improving adaptation decisions is reinforcement learning (RL). In this paper, we argue that traditional deep RL concepts are not applicable due to their limited interpreta...

With deep learning based perception tasks on radar input data gaining more attention for autonomous driving, the use of new data interfaces, specifically range-beam-doppler tensors, are explored to maximize the performance of corresponding algorithms. Surprisingly, in past publications, the Doppler information of this data has only played a minor r...

We propose to establish a research direction based on Reinforcement Learning in the scope of Cross Domain Fusion. More precisely, we combine the algorithmic approach of evolutionary rule-based Reinforcement Learning with the efficiency and performance of Deep Reinforcement Learning, while simultaneously developing a sound mathematical foundation. A...

The control of urban traffic signals typically works on the basis of predefined plans or as a centralised planning system. At least in research work, a locally organised, self-adaptive approach has been established as a more robust, scalable and efficient alternative. In all three cases, the best case scenario is that the system reacts to observed...

We propose to establish a research direction based on Reinforcement Learning in the scope of Cross Domain Fusion. More precisely, we combine the algorithmic approach of evolutionary rule-based Reinforcement Learning with the efficiency and performance of Deep Reinforcement Learning, while simultaneously developing a sound mathematical foundation. A...

Transmitting low-level radar data from a sensor to dedicated compute units is impractical in real-time automotive applications due to the large amount of data. Nevertheless, the low-level radar data has shown promising results in perception tasks. To that end, we develop a categorical variational autoencoder to be run partially on the sensor, encod...

Every year, traffic congestion costs the global economy billions of dollars in lost productivity, particularly in urban areas. Traffic congestion is a complex problem, as traffic conditions may change at any time. Tidal-flow lanes can be utilised as a feasible traffic-congestion-mitigation strategy to balance the fluctuating traffic demands through...

Context Smart and adaptive Systems, such as self-adaptive and self-organising (SASO) systems, typically consist of a large set of highly autonomous and heterogeneous subsystems that are able to adapt their behaviour to the requirements of ever-changing, dynamic environments. Their successful operation is based on appropriate modelling of the intern...

Due to the ongoing trend towards a decarbonisation of energy use, the power system is expected to become the backbone of all energy sectors and thus the fundamental critical infrastructure. High penetration with distributed energy resources demands the coordination of a large number of prosumers, partly controlled by home energy management systems...

Intelligent systems have the ability to improve their behaviour over time taking observations, experiences or explicit feedback into account. Traditional approaches separate the learning problem and make isolated use of techniques from different field of machine learning such as reinforcement learning, active learning, anomaly detection or transfer...

Due to the decarbonisation of energy use, the power system is expected to become the backbone of all energy sectors and thus the basic critical infrastructure. High penetration with distributed energy resources demands the coordination of a large number of prosumers, partly controlled by home energy management systems (HEMS), to be designed in such...

Despite its advantages as an inexpensive, weather-robust and long-range sensor which additionally provides velocity information, radar sensors still lead a shadowy existence compared to lidar and camera when it comes to fulfilling the requirements of fully autonomous driving. In this work, we focus on fully leveraging raw radar tensor data instead...

The concept of self-adaptation and self-organisation (SASO) is a modern approach to cope with the ever-increasing complexity and interconnectedness of large-scale component systems. The basic idea is to react to environmental dynamics and disturbances by re-configuring the productive behaviour and/or the relations to other systems. However, this ma...

The research initiative “self-improving system integration” (SISSY) was established with the goal to master the ever-changing demands of system organisation in the presence of autonomous subsystems, evolving architectures, and highly-dynamic open environments. It aims to move integration-related decisions from design-time to run-time, implying a fu...

“Self-improving system integration” (SISSY) is a research initiative that aims to master the ever-changing demands of system organisation in the presence of highly-dynamic autonomous subsystems, evolving architectures, and unpredictable open environments. In contrast to traditional system modelling, design and development – typically performed by e...

Today, people are surrounded by smart and connected devices. Gartner Inc. estimated that 8.4 billion devices were connected in the Internet-of-Things worldwide in 2017, reaching 20.4 billion by 2020. The growing number of mobile and embedded devices in combination with the omnipresence of (wireless) network connections facilitates new applications,...

Engineering collective adaptive systems (CAS) with learning capabilities is a challenging task due to their multi-dimensional and complex design space. Data-driven approaches for CAS design could introduce new insights enabling system engineers to manage the CAS complexity more cost-effectively at the design-phase. This paper introduces a systemati...

Engineering collective adaptive systems (CAS) with learning capabilities is a challenging task due to their multidimensional and complex design space. Data-driven approaches for CAS design could introduce new insights enabling system engineers to manage the CAS complexity more cost-effectively at the design-phase. This paper introduces a systematic...

Self-improving system integration (SISSY) aims at mastering the challenges of system organisation decisions for subsystems with highly dynamic behaviours. This is achieved by increased decision freedom of these subsystems, i.e., by moving the corresponding design decisions from design-time to run-time and from engineers to the systems themselves. A...

Self-adaptation and self-organization (SASO) have been introduced to the management of technical systems as an attempt to improve robustness and administrability. In particular, both mechanisms adapt the system’s structure and behavior in response to dynamics of the environment and internal or external disturbances. By now, adaptivity has been cons...

This book constitutes the proceedings of the 33rd International Conference on Architecture of Computing Systems, ARCS 2020, held in Aachen, Germany, in May 2020.* The 12 full papers in this volume were carefully reviewed and selected from 33 submissions. 6 workshop papers are also included. ARCS has always been a conference attracting leading-edge...

Self-adaptation has been proposed as a mechanism to counter complexity in control problems of technical systems. A major driver behind self-adaptation is the idea to transfer traditional design-time decisions to runtime and into the responsibility of systems themselves. To deal with unforeseen events and conditions, systems need creativity—typicall...

The field of collaborative interactive learning (CIL) aims at developing and investigating the technological foundations for a new generation of smart systems that support humans in their everyday life. While the concept of CIL has already been carved out in detail (including the fields of dedicated CIL and opportunistic CIL) and many research obje...

Self-adaptation has been proposed as a mechanism to counter complexity in control problems of technical systems. A major driver behind self-adaptation is the idea to transfer traditional design-time decisions to runtime and into the responsibility of systems themselves. In order to deal with unforeseen events and conditions, systems need creativity...

This book presents the results of the OC-DDC 2018. Successful participants have been invited to extend their abstracts submitted to the event towards a full book chapter by taking reviews and feedback received at the event in Wurzburg into account. The participants prepared an initial extended abstract, helped to perform a sophisticated review proc...

Allowing for self-adaptation in technical systems is intended to tackle the ever-increasing complexity resulting from the open, interconnected, and mobile characteristics of information and communication technology. Typically, self-adaptation is established by means of a feedback loop concept, e.g., in terms of the monitor-analyse-plan-execute (-kn...

Self-adaptation techniques are applied to technical systems in order to achieve goals such as increasing the robustness or improving the performance. Designing and developing self-adaptive systems differs fundamentally from traditional processes , which resulted in specific meta design processes, e.g., driven by the Organic Computing (OC) initiativ...

Collective self-adaptive systems (CSAS) are distributed and interconnected systems composed of multiple agents that can perform complex tasks such as environmental data collection, search and rescue operations, and discovery of natural resources. By providing individual agents with learning capabilities, CSAS can cope with challenges related to dis...

Personal devices such as smart phones are increasingly utilized in everyday life. Frequently, activity recognition is performed on these devices to estimate the current user status and trigger automated actions according to the user’s needs. In this article, we focus on improving the self-awareness of such systems in terms of detecting theft: We eq...

Personal wearables such as smartphones or smartwatches are increasingly utilized in everyday life. Frequently, activity recognition is performed on these devices to estimate the current user status and trigger automated actions according to the user’s needs. In this article, we focus on the creation of a self-adaptive activity recognition system ba...

Self-adaptation and self-organisation (SASO) are increasingly used in information and communication technology to master complexity and keep the administrative effort at an acceptable level. However, using SASO mechanisms is not an end in itself – the primary goal is typically to allow for a higher autonomy of systems in order to react appropriatel...

The academic success of individual students differs widely and it depends on various factors, ranging from financial to social and to health aspects. In this article, we propose a concept for a novel productivity tracking system that provides the basis for a self-assessment of academic behaviour and that can be used by students to support their aca...

Nowadays, information and communication technology (ICT) has become a key driver for future health-enabling and ambient assisted living technologies. These future health-enabling living environments proactively anticipate the inhabitants' needs and adapt their behaviour accordingly. They further continuously monitor the behaviour of the inhabitants...

Smart Homes sammeln eine Fülle von Daten über ihre Bewohner. Gut genutzt werden diese allerdings nicht. Smart Homes sind im Wesentlichen reaktiv. Im Hinblick auf die Gesundheitsversorgung ist der Wandel zu proaktiven Smart Homes vielversprechend. Um proaktive Smart Homes Wirklichkeit werden zu lassen, sollte zunächst ein vollständiges Bild dieser k...

Smart Homes sammeln eine Fülle von Daten über ihre Bewohner. Gut genutzt werden diese allerdings nicht. Smart Homes sind im Wesentlichen reaktiv. Im Hinblick auf die Gesundheitsversorgung ist der Wandel zu proaktiven Smart Homes vielversprechend. Um proaktive Smart Homes Wirklichkeit werden zu lassen, sollte zunächst ein vollständiges Bild dieser k...

Personal devices such as smart phones are increasingly utilised in everyday life. Frequently, Activity Recogni- tion is performed on these devices to estimate the current user status and trigger automated actions according to the user’s needs. In this article, we focus on improving the self-awareness of such systems in terms of detecting theft: We...

In this paper, we show how an evolutionary rule-based machine learning technique can be applied to tackle the task of self-configuration of smart camera networks. More precisely, the Extended Classifier System (XCS) is utilized to learn a configuration strategy for the pan, tilt, and zoom of smart cameras. Thereby, we extend our previous approach,...

In human society, individuals have long voluntarily organized themselves in groups, which embody, provide and/or facilitate a range of different social concepts, such as governance, justice, or mutual aid. These social groups vary in form, size, and permanence, but in different ways provide benefits to their members. In turn, members of these group...