Refine
Departments, institutes and facilities
- Fachbereich Informatik (41)
- Institute of Visual Computing (IVC) (9)
- Fachbereich Wirtschaftswissenschaften (4)
- Institut für Verbraucherinformatik (IVI) (3)
- Fachbereich Ingenieurwissenschaften und Kommunikation (2)
- Fachbereich Sozialpolitik und Soziale Sicherung (1)
- Zentrum für Ethik und Verantwortung (ZEV) (1)
Document Type
- Report (73) (remove)
Year of publication
Language
- English (73) (remove)
Keywords
- Robotik (5)
- Benutzeroberfläche (2)
- Deep Learning (2)
- Machine Learning (2)
- Virtuelle Realität (2)
- maschinelles Lernen (2)
- 3D Segmentation (1)
- 3D-Scanner (1)
- 802.11 (1)
- Adaptation (1)
Friction effects impose a requirement for the supplementary amount of torque to be produced in actuators for a robot to move, which in turn increases energy consumption. We cannot eliminate friction, but we can optimize motions to make them more energy efficient, by considering friction effects in motion computations. Optimizing motions means computing efficient joint torques/accelerations based on different friction torques imposed in each joint. Existing friction forces can be used for supporting certain types of arm motions, e.g standing still.
Reducing energy consumption of robot's arms will provide many benefits, such as longer battery life of mobile robots, reducing heat in motor systems, etc.
The aim of this project is extending an already available constrained hybrid dynamic solver, by including static friction effects in the computations of energy optimal motions. When the algorithm is extended to account for static friction factors, a convex optimization (maximization) problem must be solved.
The author of this hybrid dynamic solver has briefly outlined the approach for including static friction forces in computations of motions, but without providing a detailed derivation of the approach and elaboration that will show its correctness. Additionally, the author has outlined the idea for improving the computational efficiency of the approach, but without providing its derivation.
In this project, the proposed approach for extending the originally formulated algorithm has been completely derived and evaluated in order to show its feasibility. The evaluation is conducted in simulation environment with one DOF robot arm, and it shows correct results from the computation of motions. Furthermore, this project presents the derivation of the outlined method for improving the computational efficiency of the extended solver.
Human and robot tasks in household environments include actions such as carrying an object, cleaning a surface, etc. These tasks are performed by means of dexterous manipulation, and for humans, they are straightforward to accomplish. Moreover, humans perform these actions with reasonable accuracy and precision but with much less energy and stress on the actuators (muscles) than the robots do. The high agility in controlling their forces and motions is actually due to "laziness", i.e. humans exploit the existing natural forces and constraints to execute the tasks.
The above-mentioned properties of the human lazy strategy motivate us to relax the problem of controlling robot motions and forces, and solve it with the help of the environment. Therefore, in this work, we developed a lazy control strategy, i.e. task specification models and control architectures that relax several aspects of robot control by exploiting prior knowledge about the task and environment. The developed control strategy is realized in four different robotics use cases. In this work, the Popov-Vereshchagin hybrid dynamics solver is used as one of the building blocks in the proposed control architectures. An extension of the solver’s interface with the artificial Cartesian force and feed-forward joint torque task-drivers is proposed in this thesis.
To validate the proposed lazy control approach, an experimental evaluation was performed in a simulation environment and on a real robot platform.
In this paper, we provide a participatory design study of a mobile health platform for older adults that provides an integrative perspective on health data collected from different devices and apps. We illustrate the diversity and complexity of older adults’ perspectives in the context of health and technology use, the challenges which follow on for the design of mobile health platforms that support active and healthy ageing (AHA) and our approach to addressing these challenges through a participatory design (PD) process. Interviews were conducted with older adults aged 65+ in a two-month study with the goal of understanding perspectives on health and technologies for AHA support. We identified challenges and derived design ideas for a mobile health platform called “My-AHA”. For researchers in this field, the structured documentation of our procedures and results, as well as the implications derived provide valuable insights for the design of mobile health platforms for older adults.
Low Cost Displays
(2010)
Advanced driver assistance systems (ADAS) are technology systems and devices designed as an aid to the driver of a vehicle. One of the critical components of any ADAS is the traffic sign recognition module. For this module to achieve real-time performance, some preprocessing of input images must be done, which consists of a traffic sign detection (TSD) algorithm to reduce the possible hypothesis space. Performance of TSD algorithm is critical.
One of the best algorithms used for TSD is the Radial Symmetry Detector (RSD), which can detect both Circular [7] and Polygonal traffic signs [5]. This algorithm runs in real-time on high end personal computers, but computational performance of must be improved in order to be able to run in real-time in embedded computer platforms.
To improve the computational performance of the RSD, we propose a multiscale approach and the removal of a gaussian smoothing filter used in this algorithm. We evaluate the performance on both computation times, detection and false positive rates on a synthetic image dataset and on the german traffic sign detection benchmark [29].
We observed significant speedups compared to the original algorithm. Our Improved Radial Symmetry Detector is up to 5.8 times faster than the original on detecting Circles, up to 3.8 times faster on Triangle detection, 2.9 times faster on Square detection and 2.4 times faster on Octagon detection. All of this measurements were observed with better detection and false positive rates than the original RSD.
When evaluated on the GTSDB, we observed smaller speedups, in the range of 1.6 to 2.3 times faster for Circle and Regular Polygon detection, but for Circle detection we observed a decreased detection rate than the original algorithm, while for Regular Polygon detection we always observed better detection rates. False positive rates were high, in the range of 80% to 90%.
We conclude that our Improved Radial Symmetry Detector is a significant improvement of the Radial Symmetry Detector, both for Circle and Regular polygon detection. We expect that our improved algorithm will lead the way to obtain real-time traffic sign detection and recognition in embedded computer platforms.
Extraction of text information from visual sources is an important component of many modern applications, for example, extracting the text from traffic signs on a road scene in an autonomous vehicle. For natural images or road scenes this is a unsolved problem. In this thesis the use of histogram of stroke widths (HSW) for character and noncharacter region classification is presented. Stroke widths are extracted using two methods. One is based on the Stroke Width Transform and another based on run lengths. The HSW is combined with two simple region features– aspect and occupancy ratios– and then a linear SVM is used as classifier. One advantage of our method over the state of the art is that it is script-independent and can also be used to verify detected text regions with the purpose of reducing false positives. Our experiments on generated datasets of Latin, CJK, Hiragana and Katakana characters show that the HSW is able to correctly classify at least 90% of the character regions, a similar figure is obtained for non-character regions. This performance is also obtained when training the HSW with one script and testing with a different one, and even when characters are rotated. On the English and Kannada portions of the Chars74K dataset we obtained over 95% correctly classified character regions. The use of raycasting for text line grouping is also proposed. By combining it with our HSW-based character classifier, a text detector based on Maximally Stable Extremal Regions (MSER) was implemented. The text detector was evaluated on our own dataset of road scenes from the German Autobahn, where 65% precision, 72% recall with a f-score of 69% was obtained. Using the HSW as a text verifier increases precision while slightly reducing recall. Our HSW feature allows the building of a script-independent and low parameter count classifier for character and non-character regions.
Motion capture, often abbreviated mocap, generally aims at recording any kind of motion -- be it from a person or an object -- and to transform it to a computer-readable format. Especially the data recorded from (professional and non-professional) human actors are typically used for analysis in e.g. medicine, sport sciences, or biomechanics for evaluation of human motion across various factors. Motion capture is also widely used in the entertainment industry: In video games and films realistic motion sequences and animations are generated through data-driven motion synthesis based on recorded motion (capture) data.
Although the amount of publicly available full-body-motion capture data is growing, the research community still lacks a comparable corpus of specialty motion data such as, e.g. prehensile movements for everyday actions. On the one hand, such data can be used to enrich (hand-over animation) full-body motion capture data - usually captured without hand motion data due to the drastic dimensional difference in articulation detail. On the other hand, it provides means to classify and analyse prehensile movements with or without respect to the concrete object manipulated and to transfer the acquired knowledge to other fields of research (e.g. from 'pure' motion analysis to robotics or biomechanics).
Therefore, the objective of this motion capture database is to provide well-documented, free motion capture data for research purposes.
The presented database GraspDB14 in sum contains over 2000 prehensile movements of ten different non-professional actors interacting with 15 different objects. Each grasp was realised five times by each actor. The motions are systematically named containing an (anonymous) identifier for each actor as well as one for the object grasped or interacted with.
The data were recorded as joint angles (and raw 8-bit sensor data) which can be transformed into positional 3D data (3D trajectories of each joint).
In this document, we provide a detailed description on the GraspDB14-database as well as on its creation (for reproducibility).
Chapter 2 gives a brief overview of motion capture techniques, freely available motion capture databases for both, full body motions and hand motions, and a short section on how such data is made useful and re-used. Chapter 3 describes the database recording process and details the recording setup and the recorded scenarios. It includes a list of objects and performed types of interaction. Chapter 4 covers used file formats, contents, and naming patterns. We provide various tools for parsing, conversion, and visualisation of the recorded motion sequences and document their usage in chapter 5.
For many practical problems an efficient solution of the one-dimensional shallow water equations (Saint-Venant equations) is important, especially when large networks of rivers, channels or pipes are considered. In order to test and develop numerical methods four test problems are formulated. These tests include the well known dam break and hydraulic jump problems and two steady state problems with varying channel bottom, channel width and friction.
This report has been prepared by the SETAC Europe Scientific Task Group on Global And RegionaL Impact Categories (SETAC-Europe/STG-GARLIC) that is installed by the 2nd SETAC Europe working group on life cycle impact assessment (WIA-2). This document is background to a chapter written by the same authors under the title “Climate change, stratospheric ozone depletion, photo-oxidant formation, acidification and eutrophication” in Udo de Haes et al. (2002). The chapter summarises the work of the STG-GARLIC and aims to give a state-of-the-art review of the best available practice(s) regarding category indicators and lists of concomitant characterisation factors for climate change, stratospheric ozone depletion, photo-oxidant formation, acidification, and aquatic and terrestrial eutrophication. Backgrounds on each of the specific impact categories are given in another background report from Klöpffer and Potting (2001).
This background report provides details on a selection of general issues relevant in relation to LCA and characterisation of impact in LCA. The document starts with a short introduction of the LCA methodology and impact assessment in LCA for non LCA-experts. LCA experts, on the other hand, will usually not be familiar in-depth with scientific and political backgrounds of the specific impact categories. A review of this is given. Also the discussion is provided about the issue of the position of the category indicator in the causality chain, and into the related issue of spatial differentiation. These two issues appeared to be one of the core items for SETAC-Europe/STG-GARLIC.
Design of a declarative language for task-oriented grasping and tool-use with dextrous robotic hands
(2014)
Apparently simple manipulation tasks for a human such as transportation or tool use are challenging to replicate in an autonomous service robot. Nevertheless, dextrous manipulation is an important aspect for a robot in many daily tasks. While it is possible to manufacture special-purpose hands for one specific task in industrial settings, a generalpurpose service robot in households must have flexible hands which can adapt to many tasks. Intelligently using tools enables the robot to perform tasks more efficiently and even beyond the designed capabilities. In this work a declarative domain-specific language, called Grasp Domain Definition Language (GDDL), is presented that allows the specification of grasp planning problems independently of a specific grasp planner. This design goal resembles the idea of the Planning Domain Definition Language (PDDL). The specification of GDDL requires a detailed analysis of the research in grasping in order to identify best practices in different domains that contribute to a grasp. These domains describe for instance physical as well as semantic properties of objects and hands. Grasping always has a purpose which is captured in the task domain definition. It enables the robot to grasp an object in a taskdependent manner. Suitable representations in these domains have to be identified and formalized for which a domain-driven software engineering approach is applied. This kind of modeling allows the specification of constraints which guide the composition of domain entity specifications. The domain-driven approach fosters reuse of domain concepts while the constraints enable the validation of models already during design time. A proof of concept implementation of GDDL into the GraspIt! grasp planner is developed. Preliminary results of this thesis have been published and presented on the IEEE International Conference on Robotics and Automation (ICRA).
Reversible logic synthesis is an emerging research topic with different application areas like low-power CMOS design, quantum- and optical computing. The key motivation behind reversible logic synthesis is the optimization of the heat dissipation problem current architectures show, by reducing it to theoretically zero [2].
The Global Compact for Safe, Orderly and Regular Migration defines Global Skill Partnerships (GSP) as an innovative means of strengthen skills development among origin countries and countries of destination in mutually beneficial manner. However, GSPs are very limited in number and scope, and empirical analyses of them are, to date, relatively rare. This study helps fill this gap in data by presenting and examining existing GSPs or GSP-like approaches (e.g., transnational training partnerships). The aim of the study is to take stock of the various conceptual discourses on and practical experience with transnational skill partnerships. Using Kosovo as a case study, the study details the structure of such partnerships and the processes they entail. It documents the experience of those involved and catalogues the factors contributing to success. On this basis, the authors propose a means of categorizing the various practices that will help structure the empirical diversity of such approaches and render them conceptually feasible: Transnational Skills and Mobility Partnerships (TSMP).
This project investigated the viability of using the Microsoft Kinect in order to obtain reliable Red-Green-Blue-Depth (RGBD) information. This explored the usability of the Kinect in a variety of environments as well as its ability to detect different classes of materials and objects. This was facilitated through the implementation of Random Sample and Consensus (RANSAC) based algorithms and highly parallelized workflows in order to provide time sensitive results. We found that the Kinect provides detailed and reliable information in a time sensitive manner. Furthermore, the project results recommend usability and operational parameters for the use of the Kinect as a scientific research tool.
Education is widely seen as an important means of addressing both national and international problems, such as political or religious extremism, poverty, and hunger. If publicly available educational resources (OERs) shall help overcoming the educational gap, localization is one of the major issues we need to deal with. Educators as well as learners need to be supported to determine adaptation needs. This paper provides a list of possible in-fluence factors on educational scenarios which are defined as context metadata. In the given form, the list needs to be understood as an addendum for the paper entitled ‘Open Educational Resources: Education for the World?’ from Thomas richter and Maggie McPherson; It is being published in the volume 3, issue 2 of the Journal Distance Education in 2012.
Rural areas often lack affordable broadband Internet connectivity, mainly due to the CAPEX and especially OPEX of traditional operator equipment [HEKN11]. This digital divide limits the access to knowledge, health care and other services for billions of people. Different approaches to close this gap were discussed in the last decade [SPNB08]. In most rural areas satellite bandwidth is expensive and cellular networks (3G,4G) as well as WiMAX suffer from the usually low population density making it hard to amortize the costs of a base station [SPNB08].
High-dimensional and multi-variate data from dynamical systems such as turbulent flows and wind turbines can be analyzed with deep learning due to its capacity to learn representations in lower-dimensional manifolds. Two challenges of interest arise from data generated from these systems, namely, how to anticipate wind turbine failures and how to better understand air flow through car ventilation systems. There are deep neural network architectures that can project data into a lower-dimensional space with the goal of identifying and understanding patterns that are not distinguishable in the original dimensional space. Learning data representations in lower dimensions via non-linear mappings allows one to perform data compression, data clustering (for anomaly detection), data reconstruction and synthetic data generation.
In this work, we explore the potential that variational autoencoders (VAE) have to learn low-dimensional data representations in order to tackle the problems posed by the two dynamical systems mentioned above. A VAE is a neural network architecture that combines the mechanisms of the standard autoencoder and variational bayes. The goal here is to train a neural network to minimize a loss function defined by a reconstruction term together with a variational term defined as a Kulback-Leibler (KL) divergence.
The report discusses the results obtained for the two different data domains: wind turbine time series and turbulence data from computational fluid dynamics (CFD) simulations.
We report on the reconstruction, clustering and unsupervised anomaly detection of wind turbine multi-variate time series data using a variant of a VAE called Variational Recurrent Autoencoder (VRAE). We trained a VRAE to cluster normal and abnormal wind turbine series (two class problem) as well as normal and multiple abnormal series (multi-class problem). We found that the model is capable of distinguishing between normal and abnormal cases by reducing the dimensionality of the input data and projecting it to two dimensions using techniques such as Principal Component Analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE). A set of anomaly scoring methods is applied on top of these latent vectors in order to compute unsupervised clustering. We have achieved an accuracy of up to 96% with the KM eans + + algorithm.
We also report the data reconstruction and generation results of two dimensional turbulence slices corresponding to CFD simulation of a HVAC air duct. For this, we have trained a Convolutional Variational Autoencoder (CVAE). We have found that the model is capable of reconstructing laminar flows up to a certain degree of resolution as well generating synthetic turbulence data from the learned latent distribution.
SISAL: User manual
(1990)
CASTLE is a co-design platform developed at GMD SET institute. It provides a number of design tools for configuring application specific design flows. This paper presents a walk through the CASTLE co-design environment, following the design flow of a video processing system. The design methodology and the tool usage for this real life example are described, as seen from a designers point of view. The design flow starts with a C/C++ program and gradually derives a register-transfer level description of a processor hardware, as well as the corresponding compiler for generating the processor opcode. The main results of each design step are presented and the usage of the CASTLE tools at each step is explained.
Nowadays Field Programmable Gate Arrays (FPGA) are used in many fields of research, e.g. to create prototypes of hardware or in applications where hardware functionality has to be changed more frequently. Boolean circuits, which can be implemented by FPGAs are the compiled result of hardware description languages such as Verilog or VHDL. Odin II is a tool, which supports developers in the research of FPGA based applications and FPGA architecture exploration by providing a framework for compilation and verification. In combination with the tools ABC, T-VPACK and VPR, Odin II is part of a CAD flow, which compiles Verilog source code that targets specific hardware resources. This paper describes the development of a graphical user interface as part of Odin II. The goal is to visualize the results of these tools in order to explore the changing structure during the compilation and optimization processes, which can be helpful to research new FPGA architectures and improve the workflow.
This report summarises and integrates two different tracks of research for the purpose of envisioning and preparing a joint research project proposal. Soft- and hardware systems have become increasingly complex and act "concurrently", both with respect to memory access (i.e. information flow) and computational resources (i.e. "services"). The software development metaphor of cloud-storage, cloud-computing and service-oriented design has been anticipated by artificial intelligence (AI) research at least 30 years ago (parallel and distributed computation already dates back to the 1950’s and 1970s). What is known as a "service" today is what in AI is known as the capability of an agent; and the problem of information flow and consistency has been a headstone of information processing ever since. Based on a real-world robotics application we demonstrate how an increasingly abstract description of collaborating or competing agents correspond to a set of concurrent processes.
Formal concept analysis (FCA) as introduced in [4] deals with contexts and concepts. Roughly speaking, a context is an environment that is equipped with some kind of "knowledge". Such contexts are also known as information or knowledge representation systems where the knowledge consists of (intensional) descriptions relating sets of objects to sets of properties. Given extsensional and intensional descriptions (the latter one in terms of binary attributes), they can be arranged in a taxonomy or concept lattice.
The problem of filtering relevant information from the huge amount of available data is tackled by using models of the user's interest in order to discriminate interesting information from un-interesting data. As a consequence, Machine Learning for User Modeling (ML4UM) has become a key technique in recent adaptive systems. This article presents the novel approach of conceptual user models which are easy to understand and which allow for the system to explain its actions to the user. We show that ILP can be applied for the task of inducing user models from even sparse feedback by mutual sample enlargement. Results are evaluated independently of domain knowledge within a clear machine learning problem definition. The whole concept presented is realized in a meta web search engine, OySTER.
Machine Learning seems to offer the solution to the central problem in recommender systems: Learning to recommend interesting items from observations. However, one tends to run into similar problems each time one tries to apply out-of-the-box solutions from Machine Learning. This article relates the problem of recommendation by user modeling closely to the machine learning problem and explicates some inherent dilemmas. A few examples will illustrate specific approaches and discuss underlying assumptions on the domain or how learned hypotheses relate to requirements on the user model. The article concludes with a tentative 'checklist' that one might like to consider when thinking about to use Machine Learning in User Adaptive environments such as recommender systems.