Inst. Technische Informatik und Mikroelektronik

174 Items

Recent Submissions
Robust motion generation for mobile manipulation — integrating control and planning under uncertainty

Sieverling, Arne (2019)

This thesis contributes to algorithmic approaches for the motion generation problem for mobile manipulators. This problem is unsolved in unstructured environments, where the robot does not have access to precise models but must infer the state of the world with its sensors. The challenges for motion generation in these problems arise from the uncertainty prevalent in real world sensors, the dif...

Exploiting SAR Tomography for Supervised Land-Cover Classification

D’Hondt, Olivier ; Hänsch, Ronny ; Wagener, Nicolas ; Hellwich, Olaf (2018-11-05)

In this paper, we provide the first in-depth evaluation of exploiting Tomographic Synthetic Aperture Radar (TomoSAR) for the task of supervised land-cover classification. Our main contribution is the design of specific TomoSAR features to reach this objective. In particular, we show that classification based on TomoSAR significantly outperforms PolSAR data provided relevant features are extract...

Capsule Networks for Object Detection in UAV Imagery

Mekhalfi, Mohamed Lamine ; Bejiga, Mesay Belete ; Soresina, Davide ; Melgani, Farid ; Demir, Begüm (2019-07-17)

Recent advances in Convolutional Neural Networks (CNNs) have attracted great attention in remote sensing due to their high capability to model high-level semantic content of Remote Sensing (RS) images. However, CNNs do not explicitly retain the relative position of objects in an image and, thus, the effectiveness of the obtained features is limited in the framework of the complex object detecti...

Classification of PolSAR Images by Stacked Random Forests

Hänsch, Ronny ; Hellwich, Olaf (2018-02-23)

This paper proposes the use of Stacked Random Forests (SRF) for the classification of Polarimetric Synthetic Aperture Radar images. SRF apply several Random Forest instances in a sequence where each individual uses the class estimate of its predecessor as an additional feature. To this aim, the internal node tests are designed to work not only directly on the complex-valued image data, but also...

Robot grasping by exploiting compliance and environmental constraints

Eppner, Clemens (2019)

Grasping is a crucial skill for any autonomous system that needs to alter the physical world. The complexity of robot grasping stems from the fact that any solution comprises various components: Hand design, control, perception, and planning all affect the success of a grasp. Apart from picking solutions in well-defined industrial scenarios, general grasping in unstructured environment is still...

Approximating Memory-bound Applications on Mobile GPUs

Maier, Daniel ; Mammeri, Nadjib ; Cosenza, Biagio ; Juurlink, Ben (2019)

Approximate computing techniques are often used to improve the performance of applications that can tolerate some amount of impurity in the calculations or data. In the context of embedded and mobile systems, a broad number of applications have exploited approximation techniques to improve performance and overcome the limited capabilities of the hardware. On such systems, even small performance...

VComputeBench: A Vulkan Benchmark Suite for GPGPU on Mobile and Embedded GPUs

Mammeri, Nadjib ; Juurlink, Ben (2018-12-13)

GPUs have become immensely important computational units on embedded and mobile devices. However, GPGPU developers are often not able to exploit the compute power offered by GPUs on these devices mainly due to the lack of support of traditional programming models such as CUDA and OpenCL. The recent introduction of the Vulkan API provides a new programming model that could be explored for GPGPU ...

Strain sensor placement evaluation

Wall, Vincent ; Zöller, Gabriel ; Brock, Oliver (2019-05)

This dataset contains sensor data acquired (pressure, strain, and Motion Capture data) of PneuFlex with various sensor layouts.

Soft hand teleoperation

Erdogan, Can ; Schröder, Armin ; Eppner, Clemens ; Brock, Oliver (2019-05)

The dataset consists of rosbags that contain the cyber-glove and force-torque sensor data of teleoperation experiments.

Stiffness control by cocontraction

Höppner, Hannes (2019-05)

The dataset provides data on the coupling between force and stiffness during pinch-grasping by humans, and the possibility to decouple the coupling by cocontraction. The dataset contains motion tracking data, grip force data and muscle contraction measurements.

RBO Hand 2 simulation model

Pozzi, Maria ; Miguel, Eder ; Deimel, Raphael ; Malvezzi, Monica ; Bickel, Bernd ; Brock, Oliver ; Prattichizzo, Domenico (2019-05)

This dataset contains readily usable FEM models and code for simulating a single PneuFlex actuator, which is used in the RBO Hands.

Co-design of Plan and Environment

Abele, Jessica ; Brock, Oliver (2019-04-08)

This dataset contains CAD models of the designed environment constraints which optimize the wall and corner EC primitives.

Environmental Constraints Exploitation

Páll, Előd ; Abele, Jessica ; Sieverling, Arne ; Eppner, Clemens ; Wortmann, Johannes ; Erdogan, Can ; Brock, Oliver (2019-04-08)

This dataset contains point cloud data of the experimental setup, links to the repositories of EC primitive detectors and grasp planner.

Human hand grasping experiments: raw grasping data

Heinemann, Fabian ; Puhlmann, Steffen ; Eppner, Clemens ; Álvarez-Ruiz, José ; Meartens, Marianne ; Brock, Oliver (2019-05)

This dataset contains grasping data from human grasping experiments. The sensors used are: FT-Sensor (for contact forces), Touchpad (contact traces), MoCap-System (Hand position and orientation), Cyberglove (finger postures).

Human hand grasping experiments: annotated grasps segments

Heinemann, Fabian ; Puhlmann, Steffen ; Eppner, Clemens ; Álvarez-Ruiz, José ; Meartens, Marianne ; Brock, Oliver (2019-05)

This dataset contains segmented labelling data from human hand grasping experiments. The human experiment data was labelled by 3 independent labellers.

Predictable GPUs Frequency Scaling for Energy and Performance

Fan, Kaijie ; Cosenza, Biagio ; Juurlink, Ben (2019)

Dynamic voltage and frequency scaling (DVFS) is an important solution to balance performance and energy consumption, and hardware vendors provide management libraries that allow the programmer to change both memory and core frequencies. The possibility to manually set these frequencies is a great opportunity for application tuning, which can focus on the best applicationdependent setting. Howev...

State Representation Learning with Robotic Priors for Partially Observable Environments Data

Morik, Marco ; Rastogi, Divyam ; Brock, Oliver (2019)

We introduce Recurrent State Representation Learning (RSRL) to tackle the problem of state representation learning in robotics for partially observable environments. To learn low dimensional state representations, we combine a Long Short Term Memory network with robotic priors. RSRL introduces new priors with landmarks and combines them with existing robotics priors in literature to train the r...

GPU power modeling and architectural enhancements for GPU energy efficiency

Lucas, Jan (2019)

Graphics Processing Units (GPUs) can now be found in nearly every PC and smartphone. Initially designed for 3D graphics, they evolved into general purpose accelerators, able to outperform CPUs on many tasks. The architecture of GPUs is optimized for massively parallel applications. This reduces the required control logic but also results in lower performance in applications with irregular contr...

Neuer Optimierungsansatz für die Entwicklung hochkomplexer monolithisch integrierter Indiumphosphid Mach-Zehnder Terabit Transmitterchips

Rausch, Marko (2019)

Um dem auch zukünftig stark ansteigenden Datenverkehrsaufkommen gerecht zu werden, bedarf es leistungsfähiger optischer Daten- und Kommunikationsnetze stetig steigender Kapazität. Das ist nur zu erreichen durch eine ständige Weiterentwicklung aller erforderlichen Netzkomponenten im Hinblick auf Bandbreite, Signalqualität, Leistungsaufnahme und Komplexität (speziell Sender, Router und Empfänger)...

SLC: Memory Access Granularity Aware Selective Lossy Compression for GPUs

Lal, Sohan ; Lucas, Jan ; Juurlink, Ben (2019)

Memory compression is a promising approach for reducing memory bandwidth requirements and increasing performance, however, memory compression techniques often result in a low effective compression ratio due to large memory access granularity (MAG) exhibited by GPUs. Our analysis of the distribution of compressed blocks shows that a significant percentage of blocks are compressed to a size that ...