Search

Registration of histological serial sections is a challenging task. Serial sections exhibit distortions and damage from sectioning. Missing information on how the tissue looked before cutting makes a realistic validation of 2D registrations extremely difficult. This work proposes methods for ground-truth-based evaluation of registrations. Firstly, we present a methodology to generate test data for registrations. We distort an innately registered image stack in the manner similar to the cutting distortion of serial sections. Test cases are generated from existing 3D data sets, thus the ground truth is known. Secondly, our test case generation premises evaluation of the registrations with known ground truths. Our methodology for such an evaluation technique distinguishes this work from other approaches. Both under- and over-registration become evident in our evaluations. We also survey existing validation efforts. We present a full-series evaluation across six different registration methods applied to our distorted 3D data sets of animal lungs. Our distorted and ground truth data sets are made publicly available.

This contribution presents a control strategy which, due to the implemented inertia, is able to provide instantaneous power requirements. An approach is used to analyze and assess the grid behavior and island grid capability. For this purpose, a small-signal stability analysis shows the influence of the grid strength and the operating point on the stability of the converter system. Furthermore, a dynamic simulation investigation demonstrates the performance of the converter system in case of grid disconnection and subsequent stand-alone operation. Apart from external state changes, the response to internal reference values is considered under various specified synchronization dynamics.

This paper proposes a robust phase-locked-loop (PLL) approach to identify the grid voltage angle and frequency using the sliding discrete Fourier transform (sDFT). Due to the structure of the sDFT-PLL a separation of fundamental and harmonic oscillation as well as an analysis of the positive sequence is performed. Consequently, distortions in the negative sequence or DC offsets as well as harmonics become strongly attenuated and cannot affect the identified measured values. This PLL method is designed for the application in grid-forming control algorithms, in order to achieve a reduced dynamic response to grid state changes. Thus, by applying the PLL, an adjustment of the contribution for the supply of instantaneous active power – synthetic inertia against angle changes – shall be possible. In this paper, the mathematical model of the PLL approach is described and analyses are executed to determine the stability limit depending on the control dynamics. The robustness against grid distortions is confirmed by simulative and experimental investigations.

In recent years the need for manipulation tasks in the industrial as well as in the service robotics domain that require compliant interaction with the environment rose. Since then, an increased number of publications use a model-driven approach to describe these tasks. High-level tasks and sequences of skills are coordinated to achieve a desired motion for e.g., screwing, polishing, or snap mounting [1], [2]. Even though the awareness of the environment, especially in terms of contact situations, is essential for successful task execution, it is too often neglected or considered insufficiently.In this paper, we present a model-based approach, using domain-specific languages (DSL), that enables the explicit modeling of the environment in terms of contact situations. Decoupling the environment model from the skills, fosters exchangeability and allows the adaptation to different environmental situations. This way, an explicit but non-invasive link is established to the skills, enabling the environment model to provide a context to constrain the execution of the skills. Further, we present a synthesis from the modeled contact situations to a real-time component-based control architecture, which executes the skills subject to the active environmental context. A dual arm yoga mat rolling task is used to show the impact of the environment model on the skill execution.

Modern production requires flexible systems to fulfill customer desires of highly specialized products down to a batch size of one. Collaborative robots are considered as the key element for a versatile and flexible production in a state-of-the-art and modular production environment. Although modularization is a well known concept since the 80s, the composition of modular fabrication units and the flexible programming of robots are still challenging and depend strongly on the experience of the industrial engineer. For this reason, we present an assisted approach for interactive workspace setup targeting the operator to plan and commission efficiently applications containing collaborative robots in flexible production systems. As a central contribution, we introduce a planning workflow to take the human-in-the-loop for the workspace configuration of the robot and the arrangement of components in the modular production system. We evaluate our contribution quantitatively in an initial experimental setup performing the automatized layout in complex configurations to showcase its effectiveness.

Autonomous learning of robotic manipulation tasks is a desirable proposition for the future of industrial manufacturing to increaseflexibility and reduce manual engineering effort. In particular assembly tasks that require contact-rich manipulation skills are challenging to accomplish with classical robotic control methods. The Reinforcement Learning (RL) framework provides a possibility to learn complex behaviors based on interaction with the environment. Although a lot of research has been done robotic assembly tasks remain a challenge for pure learning-based systems. In this paper we give an overview on grey-box learning approaches that integrate prior knowledge and learning based methods. Different dimensions of knowledge injection are identified, and knowledge representations are described. These representations are discussed in the context of industrial assembly processes to answer the question: how can process experts model their knowledge to boost RL approaches in the context of industrial assembly?

AI technologies are applied to automatically assess students’ homework texts and to provide intelligent recommendations based on both students’ current learning knowledge and whole domain knowledge. Several traditional machine learning methods are evaluated and compared in order to find a suitable method for customizing personalized assessment results.

The use of Personal Voice Assistants (PVAs)1 such as Alexa and the Google Assistant is rising steadily, but there is a lack of research investigating common issues and requests of PVAs in the context of smart home control. We address this research question with an online survey (n = 65), using a qualitative evaluation of users’ problems and improvement requests. Our analysis leads to a partly hierarchic clustering of issues & recommendations for interaction capabilities of PVAs into seven basic categories, allowing us in turn to derive implications and to condense them into design guidelines for future Human-Agent Interaction (HAI) with PVAs. Specifically, we formulate and elaborate the concepts Authentication & Authorization, Activity-Based Interaction, Situated Dialogue, and Explainability & Transparency as key topics for making progress towards smooth interaction with smart homes.

Nowadays, renewable energies are fed into the grid via converter systems. Compared to conventional feed-in via synchronous generators, which exhibit the behavior of a controlled voltage source, converter-based systems behave like a controlled current source. This is primarily accounted to the control algorithms that are implemented in the converter systems and require a significant change in the energy transition. Essential grid functionalities are currently covered by conventional power plants, which are reliable and constantly connected to the grid but must be substituted by renewable energy sources in the long term to comply with the requirements of the energy transition. In order to evaluate a modern control method, a DFT-based control method is used as a basis and afterwards implemented on a conventional MMC STATCOM. Based on this model, the performance is investigated and discussed by means of simulation in the course of the paper.

Due to the progress of the energy transition, an increasing percentage of converter-based grid components leads to a change of the grid characteristics. Increased controllability is able to improve the operation of future power grids and contribute to a stable grid operation. This contribution presents the magnetically integrated concept of a hybrid transformer. This concept enables increased voltage and current scalability in terms of converter components, increased controllability of the distribution grid as well as additional system services. In order to implement these extended properties of the transformer, a modification of the magnetic core as well as the winding configuration is necessary.

The specification and analysis of the timing are an integral part of a robotics system that requires to be highly reliable. Especially since the demand for robots, which are applied in collaborative environments, is increasing drastically, robots need to be even more reliable and safe. In this paper, we propose a workflow for timing specification and analysis of real-time sensitive component-based robotics systems. Further, we introduce CoSiMA, a C++ based architecture that combines technologies, which are well-known in the domain of robotics. CoSiMA offers the ability to model, simulate, deploy, and analyze a robotics system on different robotic platforms. In addition to that, it offers a real-time safe mechanism to collect execution time data of a system, run in simulation or on the real hardware, to investigate and ensure the desired behavior of the robot. In order to depict the proposed workflow, we implemented an experimental system using CoSiMA, which lets the humanoid robot COMAN perform a Zero Moment Point-based walk on a straight line.

Efficient storage and querying of long-term human-robot interaction data requires application developers to have an in-depth understanding of the involved domains. It is an error prone task that can immensely impact the interaction experience of humans with robots and artificial agents. In the development cycle of HRI applications, queries towards storage solutions are often created once, copied into according components, and are rarely revisited. Beyond possible syntactical errors (especially impacting query design time), any change in the underlying storage solution structure results in semantic errors at run time which are not easy to spot in existing applications. To address this issue, we present a model-driven software development approach to create a long-term storage system to be used in highly interactive HRI scenarios. We created multiple domain specific languages that allow us to model the domain and seamlessly embed its concepts into a query language. Along with corresponding model-to-model and model-to-text transformations we generate a fully integrated workbench facilitating data storage and retrieval. It supports developers in the query design process and allows in-tool query execution without the need to have prior in-depth knowledge of the domain. We evaluated our work in an extensive user study and can show that the generated tool yields multiple advantages compared to the usual query design approach.

In complex technical systems like robotics platforms, a manifold of issues can impair their dependability. While common testing and simulation methods largely focus on functional aspects, the utilization of resources like CPU, network bandwidth, or memory is only rarely tested systematically. With this contribution we propose a novel Domain-Specific Language (DSL) for modeling performance tests for individual robotics components with the aim to establish a systematic testing process for detecting regressions regarding the resource utilization. This DSL builds upon a testing framework from previous research and aims to significantly reduce the effort and complexity for creating performance tests. The DSL is built using the MPS language workbench and provides a feature-rich editor with modern editing aids. An evaluation indicates that developing performance tests requires only one third of the work in comparison to the original Java-based API.

Many studies emphasize the importance of infant-directed speech: stronger articulated, higher-quality speech helps infants to better distinguish different speech sounds. This effect has been widely investigated in terms of the infant's perceptual capabilities, but few studies examined whether infant-directed speech has an effect on articulatory learning. In earlier studies, we developed a model that learns articulatory control for a 3D vocal tract model via goal babbling. Exploration is organized in the space of outcomes. This so called goal space is generated from a set of ambient speech sounds. Similarly to how speech from the environment shapes infant's speech perception, the data from which the goal space is learned shapes the later learning process: it determines which sounds the model is able to discriminate, and thus, which sounds it can eventually learn to produce. We investigate how speech sound quality in early learning affects the model's capability to learn new vowel sounds. The model is trained either on hyperarticulated (tense) or on hypoarticulated (lax) vowels. Then we retrain the model with vowels from the other set. Results show that new vowels can be acquired although they were not included in early learning. There is, however, an effect of learning order, showing that models first trained on the stronger articulated tense vowels easier accommodate to new vowel sounds later on.

The manufacturing of individualized products down to batch size 1 poses ongoing challenges for the design and integration of future production systems. Today's production lines with a high degree of automation achieve high efficiency, but usually come with high costs for adaptation to product variants. In order to combine full automation with high flexibility, we propose a concept for the dynamic composition of automation components in a modular production system that facilitates the rapid adaptation of collaborative and robot-supported manufacturing processes. To achieve this, we integrate self-descriptive automation components at runtime into the control architecture of the production system using a Plug-and-Produce approach. While the location and orientation of automation components in the modular production system are derived from physical human-robot interaction, the adaptation and verification of the robot behavior is made possible through a simulation-based planning subsystem. Once this dynamic reconfiguration process by the machine setter is finished, the adapted production process is executed in a fully automated way with high efficiency. A case study carried out in an industrial collaboration project on flexible assembly demonstrates the benefits of the presented approach.

Unintended changes in the utilization of resources like CPU and memory can lead to severe problems for the operation of robotics and intelligent systems. Still, systematic testing for such performance regressions has largely been ignored in this domain. We present a method to specify and execute performance tests for individual components of component-based robotics systems based on their component interfaces. The method includes an automatic analysis of each component revision against previous ones that reports potential changes to the resource usage characteristics. This informs developers about the impact of their changes. We describe the design of the framework and present evaluation results for the automatic detection of performance changes based on tests for a variety of robotics components.

We present a novel fault detection method for application in component-based robotic systems. In contrast to existing work, our method specifically addresses faults in the software system of the robot using a data-driven methodology which exploits the inter-process communication of the system. This enables an application of the approach without expert knowledge or availability of complex software models. We specifically focus on performance bugs, which slowly degrade the performance of the system and are thereby harder to detect but also most valuable for automatic recovery. Using a data set recorded on a RoboCup@Home platform we demonstrate the performance and applicability of our method and analyze the types of faults that can be detected by the method.

Even though research on autonomous robots and human-robot interaction accomplished great progress in recent years, and reusable soft- and hardware components are available, many of the reported findings are only hardly reproducible by fellow scientists. Usually, reproducibility is impeded because required information, such as the specification of software versions and their configuration, required data sets, and experiment protocols are not mentioned or referenced in most publications. In order to address these issues, we recently introduced an integrated tool chain and its underlying development process to facilitate reproducibility in robotics. In this contribution we instantiate the complete tool chain in a unique user study in order to assess its applicability and usability. To this end, we chose three different robotic systems from independent institutions and modeled them in our tool chain, including three exemplary experiments. Subsequently, we asked twelve researchers to reproduce one of the formerly unknown systems and the associated experiment. We show that all twelve scientists were able to replicate a formerly unknown robotics experiment using our tool chain.

In this paper, we present an empirical study with children at the age of 4 and 5 years to reveal whether they engage with a robot in an interaction. For our analysis, we developed a score assessing the interaction level. It consists of emotional involvement, engagement and independence of the child in the interaction. For the interaction, an autonomous system was equipped with a designed dialogic structure. It consisted of a repertoire of (pre-recorded) interaction protocols that a robot can apply in an interaction. The results from the evaluation suggest that the implementation was successful as most of the studied children engaged in the interaction with the robot. The results also reveal some gender differences. The long-term aim of the study is to develop an autonomous system that can be applied in an interaction with young children.

For conventional and electrified bicycles (EB) there are two dangerous braking situations that could be addressed by electronic assistance systems similar to motorcycles: bicycle nose-over and front wheel lockup. The publicly funded research project “BikeSafe” at Pforzheim University, Germany, uses analytical methods, simulation models and a test bike to investigate these critical braking situations and to set up a prototype system to avoid them. Frequently and wrongly front wheel lockup is seen as the reason for bicycle nose-over — two completely different phenomena. However, under certain conditions both can appear at the same time. After a brief presentation of the “BikeSafe” project, this paper deals with the conditions and parameter settings under which these critical situations occur. Findings of an analysis using analytical vehicle dynamics approaches are presented and compared with results from literature and simulations. Full understanding of these phenomena is a prerequisite for the development of a functional prototype assistance system.