A5023547226- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Muscle activation and electromyography studies
- Robot Manipulation and Learning
- Neuroscience and Neural Engineering
- Stroke Rehabilitation and Recovery
- Gaze Tracking and Assistive Technology
- Blind Source Separation Techniques
- Prosthetics and Rehabilitation Robotics
- Neural and Behavioral Psychology Studies
- Advanced Memory and Neural Computing
- Human-Automation Interaction and Safety
- Tactile and Sensory Interactions
- Healthcare Technology and Patient Monitoring
- Human Pose and Action Recognition
- Reinforcement Learning in Robotics
- ECG Monitoring and Analysis
- Wireless Body Area Networks
- Motor Control and Adaptation
- Hand Gesture Recognition Systems
- Educational Games and Gamification
- AI-based Problem Solving and Planning
- Robotics and Automated Systems
- Functional Brain Connectivity Studies
- Teaching and Learning Programming
German Research Centre for Artificial Intelligence
2015-2025
University of Duisburg-Essen
2022-2025
University of Bremen
2012-2021
Robotics Research (United States)
2015
Reinforcement learning (RL) enables robots to learn its optimal behavioral strategy in dynamic environments based on feedback. Explicit human feedback during robot RL is advantageous, since an explicit reward function can be easily adapted. However, it very demanding and tiresome for a continuously explicitly generate Therefore, the development of implicit approaches high relevance. In this paper, we used error-related potential (ErrP), event-related activity electroencephalogram (EEG), as...
The rehabilitation of patients should not only be limited to the first phases during intense hospital care but also support and therapy guaranteed in later stages, especially daily life activities if patient’s state requires this. However, aid given patient needed as much it is required. To allow this, automatic self-initiated movement patient-cooperative control strategies have developed integrated into assistive systems. In this work, we give an overview different kinds neuromuscular...
The feeling of embodiment, i.e., experiencing the body as belonging to oneself and being able integrate objects into one's bodily self-representation, is a key aspect human self-consciousness has been shown importantly shape cognition. An extension such feelings toward robots argued crucial for assistive technologies aiming at restoring, extending, or simulating sensorimotor functions. Empirical theoretical work illustrates importance sensory feedback embodiment also immersion; we focus on...
The goal of this study was to analyze the human ability external force discrimination while actively moving arm. With approach presented here, we give an overview for whole arm just-noticeable differences (JNDs) controlled movements separately executed wrist, elbow, and shoulder joints. work originally motivated in design phase actuation system a wearable exoskeleton, which is used teleoperation scenario where feedback should be provided subject. amount has calibrated according abilities. In...
Goal: Current brain-computer interfaces (BCIs) are usually based on various, often supervised, signal processing methods. The disadvantage of supervised methods is the requirement to calibrate them with recently acquired subject-specific training data. Here, we present a novel algorithm for dimensionality reduction (spatial filter), that ideally suited single-trial detection event-related potentials (ERPs) and can be adapted online new subject minimize or avoid calibration time. Methods:...
Assistive devices, like exoskeletons or orthoses, often make use of physiological data that allow the detection prediction movement onset. Movement onset can be detected at executing site, skeletal muscles, as by means electromyography. intention analysis brain activity, recorded by, e.g., electroencephalography, in behavior subject eye analysis. These different approaches used depending on kind neuromuscular disorder, state therapy assistive device. In this work we conducted experiments...
A current trend in the development of assistive devices for rehabilitation, example exoskeletons or active orthoses, is to utilize physiological data enhance their functionality and usability, by predicting patient’s upcoming movements using electroencephalography (EEG) electromyography (EMG). However, these modalities have different temporal properties classification accuracies, which results specific advantages disadvantages. To use analysis rehabilitation devices, processing should be...
This paper proposes an application oriented approach that enables to transfer a classifier trained within experimental scenario into more complex or specific rehabilitation situation which do not allow collect sufficient training data reasonable amount of time. The proposed is limited be applied the same type event-related potential. We show detect certain brain pattern can used successfully another pattern, expected similar first one. In particular transferred between two different types...
Abstract This paper briefly introduces the Project “AudEeKA”, whose aim is to use speech and other bio signals for emotion recognition improve remote, but also direct, healthcare. article takes a look at cases, goals challenges, of researching implementing possible solution. To gain additional insights, main-goal project divided into multiple sub-goals, namely recognition, stress detection classification from physiological signals. Also, similar projects are considered project-specific...
In neuroscience large amounts of data are recorded to provide insights into cerebral information processing and function. The successful extraction the relevant signals becomes more challenging due increasing complexities in acquisition techniques questions addressed. Here, automated signal machine learning tools can help process data, e.g., separate noise. With presented software pySPACE (http://pyspace.github.io/pyspace), algorithms be compared applied automatically on time series either...
The ability of today's robots to autonomously support humans in their daily activities is still limited. To improve this, predictive human-machine interfaces (HMIs) can be applied better future interaction between human and machine. infer upcoming context-based behavior relevant brain states the have detected. This achieved by reading (BR), a passive approach for single trial EEG analysis that makes use supervised machine learning (ML) methods. In this work we propose BR able detect concrete...
Advanced man-machine interfaces (MMIs) are being developed for teleoperating robots at remote and hardly accessible places. Such MMIs make use of a virtual environment can therefore the operator immerse him-/herself into robot. In this paper, we present our MMI multi-robot control. Our adapt to changes in task load engagement online. Applying approach embedded Brain Reading improve user support efficiency interaction. The level was inferred from single-trial detectability P300-related brain...
A challenge in brain computer interface (BCI) applications is the reduction of time required for acquisition training data, which needed a user specific calibration BCI. This paper proposes an application oriented approach to minimize by transferring classifier between different types error related potentials (ErrPs). trained detect certain pattern used later expected be similar first one. In here presented approach, two tasks (interaction task/observation task) are performed within one...
DATA REPORT article Front. Hum. Neurosci., 22 January 2024Sec. Brain-Computer Interfaces Volume 18 - 2024 | https://doi.org/10.3389/fnhum.2024.1304311