Refine
H-BRS Bibliography
- yes (606)
Departments, institutes and facilities
- Fachbereich Informatik (606) (remove)
Document Type
- Conference Object (606) (remove)
Year of publication
Keywords
- Virtual Reality (8)
- Robotics (7)
- Usable Security (7)
- CUDA (5)
- Machine Learning (5)
- 3D user interface (4)
- Benchmarking (4)
- Usable Privacy (4)
- machine learning (4)
- virtual reality (4)
An essential measure of autonomy in assistive service robots is adaptivity to the various contexts of human-oriented tasks, which are subject to subtle variations in task parameters that determine optimal behaviour. In this work, we propose an apprenticeship learning approach to achieving context-aware action generalization on the task of robot-to-human object hand-over. The procedure combines learning from demonstration and reinforcement learning: a robot first imitates a demonstrator’s execution of the task and then learns contextualized variants of the demonstrated action through experience. We use dynamic movement primitives as compact motion representations, and a model-based C-REPS algorithm for learning policies that can specify hand-over position, conditioned on context variables. Policies are learned using simulated task executions, before transferring them to the robot and evaluating emergent behaviours. We additionally conduct a user study involving participants assuming different postures and receiving an object from a robot, which executes hand-overs by either imitating a demonstrated motion, or adapting its motion to hand-over positions suggested by the learned policy. The results confirm the hypothesized improvements in the robot’s perceived behaviour when it is context-aware and adaptive, and provide useful insights that can inform future developments.
Robust Indoor Localization Using Optimal Fusion Filter For Sensors And Map Layout Information
(2014)
This paper presents the b-it-bots RoboCup@Work team and its current hardware and functional architecture for the KUKA youBot robot.We describe the underlying software framework and the developed capabilities required for operating in industrial environments including features such as reliable and precise navigation, flexible manipulation and robust object recognition.
Despite perfect functioning of its internal components, a robot can be unsuccessful in performing its tasks because of unforeseen situations. These situations occur when the behavior of the objects in the robot’s environment deviates from its expected values. For robots, such deviations are exhibited in the form of unknown external faults which prohibit them from performing their tasks successfully. In this work we propose to use naive physics knowledge to reason about such faults in the robotics domain. We propose an approach that uses naive physics concepts to find information about the situations which result in a detected unknown fault. The naive physics knowledge is represented by the physical properties of objects which are formalized in a logical framework. The proposed approach applies a qualitative version of physical laws to these properties for reasoning about the detected fault. By interpreting the reasoning results the robot finds the information about the situations which can cause the fault. We apply the proposed approach to the scenarios in which a robot performs manipulation tasks of picking and placing objects. Results of this application show that naive physics holds great promise for reasoning about unknown ex- ternal faults in robotics.
A plethora of architectural patterns and elements for developing service-oriented applications can be gathered from the state-of-the-art. Most of these approaches are merely applicable for single-tenant applications. However, less methodical support is provided for scenarios, in which multiple different tenants with varying requirements access the same application stack concurrently. In order to fill this gap, both novel and existing architectural patterns, architectural elements, as well as fundamental design decisions must be considered and integrated into a framework that leverages the devel- opment of multi-tenant application. This paper addresses this demand and presents the SOAdapt framework. It promotes the development of adaptable multi-tenant applications based on a service-oriented architecture that is capable of incorporating specific requirements of new tenants in a flexible manner.
In the fermentation process sugars are transformed into lactic acid. pH meters have traditionally been used for fermentation process monitoring based on acidity. More recently, near infrared (NIR) spectroscopy has proven to provide an accurate and non-invasive method to detect when the transformation of sugars into lactic acid is finished. The fermentation process when sugars are transformed into lactic acid. This research proposes the use of simplified NIR spectroscopy using multispectral optical sensors as a simpler and less expensive measure to end the fermentation process. The NIR spectrum of milk and yogurt is compared to find and extract features that can be used to design a simple sensor to monitor the yogurt fermentation process. Multispectral images in four selected wavebands within the NIR spectrum are captured and show different spectral remission characteristics for milk, yogurt and water, which support the selection of these wavebands for milk and yogurt classification.
LiDAR-based Indoor Localization with Optimal Particle Filters using Surface Normal Constraints
(2023)
Nowadays, we input text not only on stationary devices, but also on handheld devices while walking, driving, or commuting. Text entry on the move, which we term as nomadic text entry, is generally slower. This is partially due to the need for users to move their visual focus from the device to their surroundings for navigational purposes and back. To investigate if better feedback about users' surroundings on the device can improve performance, we present a number of new and existing feedback systems: textual, visual, textual & visual, and textual & visual via translucent keyboard. Experimental comparisons between the conventional and these techniques established that increased ambient awareness for mobile users enhances nomadic text entry performance. Results showed that the textual and the textual & visual via translucent keyboard conditions increased text entry speed by 14% and 11%, respectively, and reduced the error rate by 13% compared to the regular technique. The two methods also significantly reduced the number of collisions with obstacles.
Emotion and gender recognition from facial features are important properties of human empathy. Robots should also have these capabilities. For this purpose we have designed special convolutional modules that allow a model to recognize emotions and gender with a considerable lower number of parameters, enabling real-time evaluation on a constrained platform. We report accuracies of 96% in the IMDB gender dataset and 66% in the FER-2013 emotion dataset, while requiring a computation time of less than 0.008 seconds on a Core i7 CPU. All our code, demos and pre-trained architectures have been released under an open-source license in our repository at https://github.com/oarriaga/face classification.
The goal of this work is to develop an integration framework for a robotic software system which enables robotic learning by experimentation within a distributed and heterogeneous setting. To meet this challenge, the authors specified, defined, developed, implemented and tested a component-based architecture called XPERSIF. The architecture comprises loosely-coupled, autonomous components that offer services through their well-defined interfaces and form a service-oriented architecture. The Ice middleware is used in the communication layer. Additionally, the successful integration of the XPERSim simulator into the system has enabled simultaneous quasi-realtime observation of the simulation by numerous, distributed users.
Adapting plans to changes in the environment by finding alternatives and taking advantage of opportunities is a common human behavior. The need for such behavior is often rooted in the uncertainty produced by our incomplete knowledge of the environment. While several existing planning approaches deal with such issues, artificial agents still lack the robustness that humans display in accomplishing their tasks. In this work, we address this brittleness by combining Hierarchical Task Network planning, Description Logics, and the notions of affordances and conceptual similarity. The approach allows a domestic service robot to find ways to get a job done by making substitutions. We show how knowledge is modeled, how the reasoning process is used to create a constrained planning problem, and how the system handles cases where plan generation fails due to missing/unavailable objects. The results of the evaluation for two tasks in a domestic service domain show the viability of the approach in finding and making the appropriate goal transformations.
In this paper, we present XPERSim, a 3D simulator built on top of open source components that enables users to quickly and easily construct an accurate and photo-realistic simulation for robots of arbitrary morphology and their environments. While many existing robot simulators provide a good dynamics simulation, they often lack the high quality visualization that is now possible with general-purpose hardware. XPERSim achieves such visualization by using the Object-Oriented Graphics Rendering Engine 3D (Ogre) engine to render the simulation whose dynamics are calculated using the Open Dynamics Engine (ODE). Through XPERSim’s integration into a component-based software integration framework used for robotic learning by experimentation, XPERSIF, and the use of the scene-oriented nature of the Ogre engine, the simulation is distributed to numerous users that include researchers and robotic components, thus enabling simultaneous, quasi-realtime observation of the multiple-camera simulations.
ProtSTonKGs: A Sophisticated Transformer Trained on Protein Sequences, Text, and Knowledge Graphs
(2022)
While most approaches individually exploit unstructured data from the biomedical literature or structured data from biomedical knowledge graphs, their union can better exploit the advantages of such approaches, ultimately improving representations of biology. Using multimodal transformers for such purposes can improve performance on context dependent classication tasks, as demonstrated by our previous model, the Sophisticated Transformer Trained on Biomedical Text and Knowledge Graphs (STonKGs). In this work, we introduce ProtSTonKGs, a transformer aimed at learning all-encompassing representations of protein-protein interactions. ProtSTonKGs presents an extension to our previous work by adding textual protein descriptions and amino acid sequences (i.e., structural information) to the text- and knowledge graph-based input sequence used in STonKGs. We benchmark ProtSTonKGs against STonKGs, resulting in improved F1 scores by up to 0.066 (i.e., from 0.204 to 0.270) in several tasks such as predicting protein interactions in several contexts. Our work demonstrates how multimodal transformers can be used to integrate heterogeneous sources of information, paving the foundation for future approaches that use multiple modalities for biomedical applications.
Target meaning representations for semantic parsing tasks are often based on programming or query languages, such as SQL, and can be formalized by a context-free grammar. Assuming a priori knowledge of the target domain, such grammars can be exploited to enforce syntactical constraints when predicting logical forms. To that end, we assess how syntactical parsers can be integrated into modern encoder-decoder frameworks. Specifically, we implement an attentional SEQ2SEQ model that uses an LR parser to maintain syntactically valid sequences throughout the decoding procedure. Compared to other approaches to grammar-guided decoding that modify the underlying neural network architecture or attempt to derive full parse trees, our approach is conceptually simpler, adds less computational overhead during inference and integrates seamlessly with current SEQ2SEQ frameworks. We present preliminary evaluation results against a recurrent SEQ2SEQ baseline on GEOQUERY and ATIS and demonstrate improved performance while enforcing grammatical constraints.