Veröffentlichungen

@inproceedings{nokeyo,

title = {Robot or Employee? Exploring People’s Choice for or Against an Interaction with a Social Robot},

author = {Marcel Finkel and Lara Timm and Lukas Erle and Alexander Arntz and André Helgert and Carolin Straßmann and Sabrina C. Eimler},

url = {https://link.springer.com/chapter/10.1007/978-981-96-3522-1_38},

doi = {https://doi.org/10.1007/978-981-96-3522-1_38},

isbn = {978-981-96-3522-1},

year  = {2025},

date = {2025-03-25},

urldate = {2024-11-01},

booktitle = {Proceedings of the International Conference on Social Robotics},

pages = {446–459},

publisher = {Springer Nature},

abstract = {Employing social robots in public spaces to support employees at work is a frequently discussed scenario. However, the success of robotic systems often depends on people’s willingness to initiate interactions with them. This makes understanding people’s usage decisions crucial, yet only limited research has been done on why people select publicly accessible social robots over alternatives, such as human employees. Amongst various factors, people’s diversity characteristics are likely to influence this decision, such as people’s locus of control when using technology and their self-efficacy in human-robot interaction. To investigate this choice for or against using a robot, a field study (N = 65) was conducted in two public libraries in the Ruhr area (Germany). Participants had to decide to interact with a robot or an employee and were subsequently asked to explain their decision via a questionnaire and an interview. Results reveal that the decision could neither be explained by people’s locus of control when using technology nor by other diversity characteristics. Furthermore, no significant differences in self-efficacy in human-robot interaction between users who chose the robot instead of the human employee were found. Finally, the qualitative findings point to general interest in robots and people’s differences in dealing with novelty as reasons for their choice. Overall, our findings offer insights into the decision for or against the usage of a robot, which are relevant to both, research and the deployment of social robots in public spaces.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nokeyn,

title = {A Technical User Study on an Authoring Tool for Simplifying VR Study Setups in HRI Research},

author = {André Helgert and Sabrina C. Eimler and Tom Gross},

year  = {2025},

date = {2025-03-03},

urldate = {2025-03-03},

booktitle = {Proceedings of the 2025 ACM/IEEE International Conference on Human-Robot Interaction},

pages = {550-558},

publisher = {IEEE Press},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10896148,

title = { Merging Realities: Exploring Mixed Reality as a Research Tool for Human-Robot Interaction in Real-World Settings },

author = {Jan Schulten and Andre Helgert and Alexander Arntz and Carolin StraBmann and Sabrina C. Eimler},

url = {https://doi.ieeecomputersociety.org/10.1109/AIxVR63409.2025.00029},

doi = {10.1109/AIxVR63409.2025.00029},

year  = {2025},

date = {2025-01-01},

booktitle = {2025 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)},

pages = {147-153},

publisher = {IEEE Computer Society},

address = {Los Alamitos, CA, USA},

abstract = {The application of Virtual Reality (VR) in Human-Robot Interaction (HRI) research is growing due to its capacity to create adaptable yet controlled study environments. While VR often achieves data validity comparable to real-world studies, it faces limitations when physical interaction with robots is required. Mixed Reality (MR) offers a potential solution by enabling interactions with virtual robots in real-world settings, allowing participants to engage with realistic, interactive simulations that adapt to physical environments. Given the limited use of MR in HRI studies and the need for further understanding of its effectiveness in generating transferable results, this study examines MR's potential as a tool for simulating social-robot interaction. We conducted a study involving 21 participants interacting with a virtual robot performing navigation tasks in a real library and assessed self-efficacy, presence, technology acceptance, perceived realism, and social characteristics of the robot. The results show that most participants perceived the interaction with the robot as successful, the engagement was high and the robot interaction with MR provided excellent usability. These results suggest that MR has potential as a research and training tool for simulating human-robot interaction in navigation tasks within public spaces.},

keywords = {Training;Solid modeling;Navigation;Merging;Human-robot interaction;Mixed reality;Virtual reality;Libraries;Usability;Robots},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10896073,

title = { Beyond Coding: Empowering HRI Researchers with an Authoring Tool for Simplified VR Studies },

author = {Andre Helgert and Sabrina C. Eimler and Tom Gross},

url = {https://doi.ieeecomputersociety.org/10.1109/AIxVR63409.2025.00056},

doi = {10.1109/AIxVR63409.2025.00056},

year  = {2025},

date = {2025-01-01},

booktitle = {2025 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)},

pages = {290-295},

publisher = {IEEE Computer Society},

address = {Los Alamitos, CA, USA},

abstract = {Although Virtual Reality (VR) is a promising tool in today's Human-Robot Interaction (HRI) research, the technical hurdle of creating high-quality and customized VR applications for one's own research prevents its comprehensive use. To address this problem, we present a VR authoring tool for HRI research, allowing non-technical researchers to create individual study designs in a simplified manner with predefined environments, robots, and measurement methods. Furthermore, the authoring tool has a highly modularized structure so that it can be adapted to a wide range of use cases. Technical details are presented, covering UI/UX decisions in the study design process and the visual programming interface for the creation of the interaction scheme of the robot, as well as the data management system that transfers researchers' study setups into a suitable VR application. The VR authoring tool is intended to bridge the gap between the practical applicability of VR as a research tool and the required technical implementation expertise for VR applications.},

keywords = {Visualization;Authoring systems;Human-robot interaction;Virtual reality;Programming;Encoding;Artificial intelligence;Robots},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1145/3706599.3720278,

title = {Prompt it Colorful with Rainbow Bot: Enhancing Video-Based Collaborative Learning by using a Multi-Party AI-Driven Chatbot},

author = {Andre Helgert and Latoya Weis and Carolin Strassmann},

url = {https://doi.org/10.1145/3706599.3720278},

doi = {10.1145/3706599.3720278},

isbn = {9798400713958},

year  = {2025},

date = {2025-01-01},

booktitle = {Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

series = {CHI EA '25},

abstract = {Multi-party AI-driven chatbots remain largely unexplored, despite their potential to enhance internal communication and coordination within student learning groups. These benefits are increasingly feasible with the advent of large language models (LLMs), which enable more efficient content generation and chatbot customization. To bridge this gap, we carried out an exploratory study to examine students’ perceptions, practical applications, and concerns regarding the use of multi-party AI-driven chatbots in video-based collaborative learning environments. Based on the findings, we designed the Rainbow Bot, an optimized multi-party AI-driven chatbot. It features an interactive reflection process to strengthen group dynamics, customization options to adjust response length and content focus, and a unique color scheme for visual clarity. By combining colors from group members in refined prompts, Rainbow Bot fosters collaboration and promotes shared understanding within teams. Future work will assess its effectiveness in real educational settings, with a focus on its impact on group dynamics and collaborative learning outcomes.},

keywords = {AI-driven chatbots, Artifical Intelligence, Chatbot, Collaborative Learning, Higher Education, Multi-party AI-driven chatbots},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{icnr2024,

title = {Deep-learning-based identification of individual motion characteristics from upper-limb trajectories towards disorder stage evaluation},

author = {Tim Sziburis and Susanne Blex and Tobias Glasmachers and Ioannis Iossifidis},

editor = {Jose L. Pons and Jesus Tornero and Metin Akay},

year  = {2024},

date = {2024-11-30},

urldate = {2024-11-01},

booktitle = {Converging Clinical and Engineering Research on Neurorehabilitation V - Proceedings of the 6th International Conference on Neurorehabilitation (ICNR2024)},

publisher = {Springer International Publishing},

address = {La Granja, Spain},

series = {Biosystems and Biorobotics},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nokey,

title = {Integrating Collaborative Video-Based Learning for Transdisciplinary Case Work in Pedagogical and Health-Related Education},

author = {André Helgert and Nadine Elstrodt-Wefing and Michelle Möhring and Carolin Straßmann },

url = {https://www.helmeto2024.it/storage/2024/11/BOA_HELMETO2024.pdf},

isbn = {978-88-99978-67-9},

year  = {2024},

date = {2024-11-12},

urldate = {2024-11-12},

booktitle = {HELMeTO 2024 - Book of Abstracts},

pages = {17-19},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nokey,

title = {Generative AI in Higher Education - Perspectives from Students and Teaching Staff},

author = {Lukas Erle and Thomas Hoss and Isabel Peltzer and Sabrina C. Eimler},

url = {https://www.helmeto2024.it/storage/2024/11/BOA_HELMETO2024.pdf},

isbn = {978-88-99978-67-9},

year  = {2024},

date = {2024-11-12},

urldate = {2024-11-12},

booktitle = {HELMeTO 2024 - Book of Abstracts},

pages = {173-175},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{StochasticProcessModel2024,

title = {Stochastic Process Model Derived Indicators of Overfitting for Deep Architectures: Applicability to Small Sample Recalibration of sEMG Decoders},

author = {Stephan Johann Lehmler and Ioannis Iossifidis},

url = {https://abstracts.g-node.org/conference/BC24/abstracts#/uuid/72f03ff1-61dc-443c-92c2-b623d672ce15},

year  = {2024},

date = {2024-09-18},

urldate = {2024-09-24},

booktitle = {BC24 : Computational Neuroscience & Neurotechnology Bernstein Conference 2024},

publisher = {BCCN Bernstein Network Computational Networkvphantom},

abstract = {Our recent work presents a stochastic process model of the activations within an ANN and shows a promising indicator to distinguish memorizing from generalizing ANNs. The average λ, or mean firing rate (MFR), of a hidden layer, shows stable differences between memorizing and generalizing networks, comparatively independent of the underlying data used for evaluation. We first show the performance of this indicator during training on benchmark computer vision datasets such as MNIST and CIFAR-10. In a second step, we extend the work to the real-life use case of calibrating a pre-trained model to a new user. We focus on decoding surface electromyographic (sEMG) signals, which are highly variable within and between users, and therefore necessitate frequent user calibration. Especially in situations when user calibration has to only rely on a small number of samples, degradation in performance overtime due to memorization and overfitting is a not unlikely outcome. In those cases, traditional regularization methods that function by observing the performance on a validation set, such as early stopping, don’t necessarily work, because they are evaluated on data from the same subject and set of movements, which features are being memorized. Our new indicators of memorization could help as stable indicators for model performance and give live insights during model calibration when more samples from the new users would be necessary. We evaluate the usefulness of the MFR-indicator for identifying the moment a pre-trained sEMG decoder starts to memorize given inputs},

keywords = {Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{DecodingUpperLimb2024,

title = {Decoding Upper Limb Movements},

author = {Marie Dominique Schmidt and Ioannis Iossifidis},

url = {https://abstracts.g-node.org/conference/BC24/abstracts#/uuid/4725140f-ce7c-4ac5-b694-c627ceeb8d98},

year  = {2024},

date = {2024-09-18},

urldate = {2024-09-24},

publisher = {BCCN Bernstein Network Computational Networkvphantom},

abstract = {The upper limbs are essential for performing everyday tasks that require a wide range of motion and precise coordination. Planning and timing are crucial to achieve coordinated movement. Sensory information about the target and current body state is critical, as is the integration of prior experience represented by prelearned inverse dynamics that generate the associated muscle activity. We propose a generative model that uses a recurrent neural network to predict upper limb muscle activity during various simple and complex everyday movements. By identifying movement primitives within the signal, our model enables the decomposition of these movements into a fundamental set, facilitating the reconstruction of muscle activity patterns. Our approach has implications for the fundamental understanding of movement control and the rehabilitation of neuromuscular disorders with myoelectric prosthetics and functional electrical stimulation.},

keywords = {BCI, Machine Learning, Muscle activity},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ControversialOpinionsModel2024,

title = {Controversial Opinions on Model Based and Model Free Reinforcement Learning in the Brain},

author = {Felix Grün and Ioannis Iossifidis},

url = {https://abstracts.g-node.org/conference/BC24/abstracts#/uuid/18e92e07-e4b1-43af-b2ac-ea282f4e81e7},

year  = {2024},

date = {2024-09-18},

urldate = {2024-09-24},

publisher = {BCCN Bernstein Network Computational Networkvphantom},

abstract = {Dopaminergic Reward Prediction Errors (RPEs) are a key motivation and inspiration for model free, temporal difference reinforcement learning methods. Originally, the correlation of RPEs with model free temporal difference errors was seen as a strong indicator for model free reinforcement learning in brains. The standard view was that model free learning is the norm and more computationally expensive model based decision-making is only used when it leads to outcomes that are good enough to justify the additional effort. Nowadays, the landscape of opinions, models and experimental evidence, both electrophysiological and behavioral, paints a more complex picture, including but not limited to mechanisms of arbitration between the two systems. Model based learning or hybrid models better capture experimental behavioral data, and model based signatures are found in RPEs that were previously thought to be model free or hybrid [1]. The evidence for clearly model free learning is scarce [2]. On the other hand, multiple approaches show how model based behavior and RPEs can be produced with fundamentally model free reinforcement learning methods [3, 4, 5]. We point out findings that seem to contradict each other, others that complement each other, speculate which ideas are compatible with each other and give our opinions on ways forward, towards understanding if and how model based and model free learning from rewards coexist and interact in the brain.},

keywords = {Machine Learning, Reinforcement learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{AdaptiveBraincomputerInterfaces2024,

title = {Adaptive Brain-Computer Interfaces Based on Error-Related Potentials and Reinforcement Learning},

author = {Aline Xavier Fidencio and Christian Klaes and Ioannis Iossifidis},

url = {https://abstracts.g-node.org/conference/BC24/abstracts#/uuid/03d3dd16-4c50-43d8-b878-abcfa7857386},

year  = {2024},

date = {2024-09-18},

urldate = {2024-09-24},

booktitle = {BC24 : Computational Neuroscience & Neurotechnology Bernstein Conference 2024},

publisher = {BCCN Bernstein Network Computational Networkvphantom},

abstract = {Error-related potentials (ErrPs) represent the neural signature of error processing in the brain and numerous studies have demonstrated their reliable detection using non-invasive techniques such as electroencephalography (EEG). Over recent decades, the brain-computer interface (BCI) community has shown growing interest in leveraging these intrinsic feedback signals to enhance system performance. However, the effective use of ErrPs in a closed-loop setup crucially depends on accurate single-trial detection, which is typically achieved using a subject-specific classifier (or decoder) trained on samples recorded during extensive calibration sessions before the BCI system can be deployed. In our research, we explore the potential of simulated EEG data for training a truly generic ErrP classifier. Utilizing the SEREEGA simulator, we demonstrate that EEG data can be generated in a cost-effective manner, allowing for controlled and systematic variations in data distribution to accommodate uncertainties in ErrP generation. A classifier trained solely on the generated data exhibits promising generalization capabilities across different datasets and performs comparably to a leave-one-subject-out approach trained on real data (Xavier Fidêncio et al., 2024). In our experiments, we deliberately provoked ErrPs when the BCI misinterpreted the user's intention, resulting in incorrect actions. Subjects engaged in a game controlled via keyboard and/or motor imagery (imagining hand movements), with EEG data recorded using various EEG systems for comparison. Considering the challenges in obtaining clear ErrP signals for all subjects and the limitations identified in existing literature (Xavier Fidêncio et al., 2022), we hypothesize whether a measurable error signal is consistently generated at the scalp level when subjects encounter erroneous conditions, and how this influences closed-loop setups that incorporate ErrPs for improved BCI performance. To address these questions, we assess the effects of the occurrence-to-detection ratio of ErrPs in the classification pipeline using simulated data and explore the impact of error misclassification rates in an ErrP-based learning framework, which employs reinforcement learning to enhance BCI performance.},

keywords = {BCI, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{3DMovementAnalysis2024,

title = {3D Movement Analysis of the Ruhr Hand Motion Catalog of Human Center-Out Transport Trajectories},

author = {Stephan Johann Lehmler and Ioannis Iossifidis},

url = {https://abstracts.g-node.org/conference/BC24/abstracts#/uuid/719bca6f-9fb9-4e53-96a5-a7b36b67c012},

year  = {2024},

date = {2024-09-18},

urldate = {2024-09-18},

booktitle = {BC24 : Computational Neuroscience & Neurotechnology Bernstein Conference 2024},

publisher = {BCCN Bernstein Network Computational Networkvphantom},

abstract = {The Ruhr Hand Motion Catalog of Human Center-Out Transport Trajectories [1] is a compilation of three-dimensional task-space motion data simultaneously measured by two motion tracking systems. The first one, an optical motion capture system, provided robust reference data. The second recording system consisted of a single state-of-the-art IMU to demonstrate the feasibility of portable applications. The transport object was moved in 3D space from a unified start position to one of nine target positions, equidistantly aligned on a semicircle. Ten trials were performed per target and hand, resulting in 180 trials per participant in total. 31 participants (11 female, 20 male, age 21-78) without known movement disorders took part in the experiment. Based on those experimental data, we analyze several characteristics of upper-limb trajectories. All data are rotated so that the straight connection of the defined start and target positions composes the y-axis. By doing so, we explore properties which are independent of the directly measured target location for each task and focus on common properties shared between all target movements. Particularly, we investigate how individual or target-dependent differences can still be quantified after rotation. Furthermore, we model the measured movements by means of dynamical systems (extended attractor dynamics). Differences between the transportation movements to different targets would result in varying parameter sets. The investigated motion characteristics include the symmetry of velocity peaks and the polynomial target dependence of planarity attributes. To compare the diversity of trajectories in time and space, we introduce a novel variability measure for the planarity of hand paths regarding plane angles and path amplitudes within the plane. These aspects can expose differences between trials (intra-subject) and participants (inter-subject), explored in the modelling process and applied as a methodological framework for pathological analysis. For this, further measurements with patients experiencing movement disorders are planned for future examination. The separability can also be evaluated by machine learning of task classification and user identification. This can provide information on the potential of data-driven pathological analysis to extend the model-based approach since the described experiment and study are conducted in the context of developing a portable glove for the diagnosis of movement disorders.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nokey,

title = {Conceptualizing and Designing a Virtual Reality Authoring Tool for Human-Robot Interaction Studies - Learnings and Guidance from Expert Interviews },

author = {André Helgert and Carolin Straßmann and Sabrina C. Eimler},

editor = {ACM},

doi = {https://doi.org/10.1145/3670653.3670664},

year  = {2024},

date = {2024-09-01},

urldate = {2024-09-01},

booktitle = {MuC '24: Proceedings of Mensch und Computer 2024},

pages = {331-341},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10445597,

title = {Teamwork Makes the Dream Work: A Virtual Reality-based Human-Robot Collaboration Sandbox Simulating Multiple Teams},

author = {Alexander Arntz and Agostino Di Dia and Tim Riebner and Carolin Straßmann and Sabrina C. Eimler},

doi = {10.1109/AIxVR59861.2024.00057},

issn = {2771-7453},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {2024 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)},

pages = {335-339},

abstract = {We present a virtual reality-based Human-Robot Collaboration sandbox that allows the representation of multiple teams composed of humans and robots. Within the sandbox, virtual robots and humans can collaborate with their respective partners and interact with other teams to coordinate the required procedures while accomplishing a shared task. For this purpose, the virtual reality sandbox is equipped with a variety of interaction mechanics that enable a range of different shared tasks. The network integration allows for multiple users within the virtual environment. The VR application contains a library of different industrial robots that can act autonomously controlled by machine learning agents and interact with the user through verbal commands. The sandbox is specifically designed to serve as a research tool to explore new concepts and validate existing approaches in the domain of Human-Robot Collaboration involving autonomous robots in a series of upcoming studies.},

keywords = {Robot kinematics;Virtual assistants;Virtual environments;Industrial robots;Libraries;Teamwork;Task analysis;Human-Robot Collaboration;Virtual Reality;Machine Learning;Artificial Intelligence},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1007/978-3-031-60412-6_4,

title = {Enabling Safe Empirical Studies for Human-Robot Collaboration: Implementation of a Sensor Array Driven Control Interface},

author = {Alexander Arntz},

editor = {Masaaki Kurosu and Ayako Hashizume},

isbn = {978-3-031-60412-6},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {Human-Computer Interaction},

pages = {42–57},

publisher = {Springer Nature Switzerland},

address = {Cham},

abstract = {In response to the growing relevance of collaborative robots, the need for empirical user studies in the domain of Human-Robot Collaboration become increasingly important. While collaborative robots incorporate internal safety features, their usage for user studies remains associated with inherent safety risks. This project addresses these challenges by introducing a toolbox for a robot arm to conduct Wizard-of-Oz studies by using advanced controls complemented by a sophisticated security system leveraging microcontrollers and human presence detection sensors. This approach unifies both control systems within a single application, seamlessly monitoring and synchronizing their respective inputs. The gamepad control scheme offers Wizard-of-Oz study supervisors an intuitive means of interacting with the robot, enabling precise and responsive control while maintaining safety. Meanwhile, the security system, built on microcontroller technology and human presence detection sensors, acts as a vigilant guardian, continuously assessing the robot's surroundings for potential risks. This integrated application not only empowers users with effective control over the xArm 7 but also provides real-time feedback on the security status, enhancing the overall safety and usability of collaborative robots in various industrial settings. By bridging the gap between human operators and robots, this project contributes to the evolution of safer and more user-friendly human-robot collaboration.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10445600,

title = {Enhancing Human-Robot Interaction Research by Using a Virtual Reality Lab Approach},

author = {Alexander Arntz and André Helgert and Carolin Straßmann and Sabrina C. Eimler},

doi = {10.1109/AIxVR59861.2024.00058},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {2024 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)},

pages = {340-344},

abstract = {Human-robot interaction (HRI) research often faces limitations in real-world environments due to uncontrollable external factors. This applies in particular to field study setups in public spaces, as these can limit the validity of the study results, e.g. due to unpredictable and unsystematic changes in the environment, noise, people passing, etc. Especially for interdisciplinary studies involving psychological perspectives, virtual reality (VR) has emerged as a promising solution, offering realistic, controlled, and reproducible environments. Also, recent technological advancements enable detailed observation of human behavior and physiological responses via eye tracking, physiological assessments, and motion capture. To effectively add value by using VR as a tool, immersion, and presence in the virtual environment are essential preconditions. Besides, the manipulability of the VR environment during runtime is a bonus in exploring human behavior in interaction with robot-enriched spaces. As a methodological innovation in HRI studies, this paper presents a VR lab as a research tool that provides a virtual model of the robot Pepper along with interfaces for easy navigation and adaptive robot behavior. Moreover, the presented Wizard of Oz dashboard allows to flexibly react to the scenery by allowing the manipulation of several robot parameters during runtime. With the help of the VR lab, a framework for a variety of interdisciplinary research purposes in human-robot interaction (not only) in public spaces is provided.},

keywords = {Technological innovation;Solid modeling;Runtime;Human-robot interaction;Virtual environments;Physiology;Robots;Virtual Reality;Human-Robot Interaction;Empirical Studies;Research Platform;Study Tool;Wizard of Oz},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10445553,

title = {Virtual Reality for Tinnitus Education: Inspiring Awareness and Proactive Behavioral Changes},

author = {Dan Heilmann and André Helgert and Sabrina C. Eimler},

doi = {10.1109/AIxVR59861.2024.00049},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {2024 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)},

pages = {294-300},

abstract = {Tinnitus is a prevalent symptom in otorhinolaryngology affecting a substantial portion of the population. Factors contributing to tinnitus include acoustic stress, sensory overload, and neurological and psychological disturbances. Although associated comorbidities can be treated, tinnitus lacks a definitive cure. Consequently, preventive measures and awareness about its consequences are crucial. Virtual Reality (VR) emerges as a potential tool for assistance as it offers (often appealing) immersive simulations, combining visual and auditory perceptual inputs supporting a feeling of being in a real physical environment. As it could help to effectively recreate the experience of tinnitus in everyday situations, VR may facilitate a deep sense of empathy and comprehension. As a first step in designing the application, a pre-study collected scenarios among people (N = 32) with tinnitus symptoms. These were subsequently implemented in the VR application and evaluated by students (N = 22) without tinnitus symptoms. The application aims to recreate distressing scenarios, to elicit empathy and educate unaffected individuals.},

keywords = {Visualization;Solid modeling;Sociology;Psychology;Virtual reality;Human factors;Statistics;virtual reality;tinnitus;sensitization;immersion;simulation;health promotion;awareness},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1145/3610978.3640741,

title = {Unlocking Potentials of Virtual Reality as a Research Tool in Human-Robot Interaction: A Wizard-of-Oz Approach},

author = {André Helgert and Carolin Straßmann and Sabrina C. Eimler},

url = {https://doi.org/10.1145/3610978.3640741},

doi = {10.1145/3610978.3640741},

isbn = {9798400703232},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction},

pages = {535–539},

publisher = {Association for Computing Machinery},

address = {Boulder, CO, USA},

series = {HRI '24},

abstract = {Wizard-of-Oz (WoZ) systems represent a widespread method in HRI research. While they are cost-effective, flexible and are often preferred over developing autonomous dialogs in experimental settings, they are typically tailored to specific use cases. In addition, WoZ systems are mainly used in lab studies that deviate from real world scenarios. Here, virtual reality (VR) can be used to immerse the user in a real world interaction scenario with robots. This article highlights the necessity for a modularized and customizable WoZ system, using the benefits of VR. The proposed system integrates well-established features like speech and gesture control, while expanding functionality to encompass a data dashboard and dynamic robot navigation using VR technology. The discussion emphasizes the importance of developing technical systems, like the WoZ system, in a modularized and customizable way, particularly for non-technical researchers. Overcoming usability hurdles is crucial to establishing this tool's role in the HRI research field.},

keywords = {accessibility, social robots, virtual reality, Wizard-of-Oz},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{xavierfidencioExploringErrorrelatedPotentials2023,

title = {Exploring Error-related Potentials in Adaptive Brain-Machine Interfaces: Challenges and Investigation of Occurrence and Detection Ratios},

author = {Aline Xavier Fidencio and Christian Klaes and Ioannis Iossifidis},

year  = {2023},

date = {2023-09-15},

urldate = {2023-09-15},

booktitle = {BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

abstract = {Non-invasive techniques like EEG can record error-related potentials (ErrPs), neural signals associated with error processing and awareness. ErrPs are generated in response to self-made and external errors, including those produced by the BMI. Since ErrPs are implicitly elicited and don’t add extra workload for the subject, they serve as a natural and intrinsic feedback source for developing adaptive BMIs. In our study, we assess the occurrence of interaction ErrPs in an adaptive BMI that combines ErrPs and reinforcement learning. We intentionally provoke ErrPs when the BMI misinterprets the user’s intention and performs an incorrect action. Subjects participated in a game controlled by a keyboard and/or motor imagery (imagining hand movements), and EEG data were recorded using an eight-electrode gel-based EEG system. Results reveal that obtaining a distinct ErrPs signal for each subject is more challenging than anticipated. Current practices report the ErrP in terms of over all subjects and trials difference grand average (error minus correct). This approach has, however, the limitation of masking the inter-trial and subject variability, which are relevant for the online single-trial detection of such signals. Moreover, the reported ErrPs waveshape exhibit differences in terms of components observed, as well as their respective latencies, even when very similar tasks are used. Consequently, we conducted additional individualized data analysis to gain deeper insights into the single-trial nature of the ErrPs. As a result, we determined the need for a better understanding and further investigation of how effectively the ErrPs waveforms generalize across subjects, tasks, experimental protocols, and feedback modalities. Given the challenges in obtaining a clear signal for all subjects and the limitations found in existing literature (Xavier Fidêncio et al., 2022), we hypothesize whether an error signal measurable at the scalp level is consistently generated when subjects encounter erroneous conditions. To address this question, we will assess the occurrence-to-detection ratio of ErrPs using invasive and non-invasive recording techniques, examining how uncertainties regarding error generation in the brain impact the learning pipeline.},

keywords = {BCI, EEG, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sziburisVariabilityStudyHuman2023,

title = {Variability Study of Human Hand Motion during 3D Center-out Tasks Captured for the Diagnosis of Movement Disorders},

author = {Tim Sziburis and Susanne Blex and Ioannis Iossifidis},

year  = {2023},

date = {2023-09-15},

urldate = {2023-09-15},

booktitle = {BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

abstract = {Variability analysis bears the potential to differentiate between healthy and pathological human movements [1]. Our study is conducted in the context of developing a portable glove for the diagnosis of movement disorders. This proposal has methodical as well as technical requirements. Generally, the identification of movement disorders via an analysis of motion data needs to be confirmed within the given setup. Typically, rhythmic movements like gait or posture control are examined for their variability, but here, the characteristic pathological traits of arm movement like tremors are under observation. In addition, the usability of a portable sensor instead of a stationary tracking system has to be validated. In this part of the project, human motion data are recorded redundantly by both an optical tracking system and an IMU. In our setup, a small cylinder is transported in three-dimensional space from a unified start position to one of nine target positions, which are equidistantly aligned on a semicircle. 10 trials are performed per target and hand, resulting in 180 trials per participant in total. 31 participants (11 female and 20 male) without known movement disorders, aged between 21 and 78 years, took part in the study. In addition, the 10-item EHI is used. The purpose of the analysis is to compare different variability measures to uncover differences between trials (intra-subject variability) and participants (inter-subject variability), especially in terms of age and handedness effects. Particularly, a novel variability measure is introduced which makes use of the characteristic planarity of the examined hand paths [2]. For this, the angle of the plane which best fits the travel phase of the trajectory is determined. In addition to neurological motivation, the advantage of this measure is that it allows the comparison of trials of different time spans and to different target directions without depending on trajectory warping. In the future, measurements of the same experimental setup with patients experiencing movement disorders are planned. For the subsequent pathological analysis, this study provides a basis in terms of methodological considerations and ground truth data of healthy participants. In parallel, the captured motion data are modelled utilizing dynamical systems (extended attractor dynamics approach). For this approach, the recorded and modelled data can be compared by the variability measures examined in this study.},

keywords = {movement model},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{schmidtLinkMuscleActivity2023,

title = {The Link between Muscle Activity and Upper Limb Kinematics},

author = {Marie Dominique Schmidt and Ioannis Iossifidis},

year  = {2023},

date = {2023-09-15},

urldate = {2023-09-15},

booktitle = {BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

abstract = {The upper limbs are crucial in performing daily tasks that require strength, a wide range of motion, and precision. To achieve coordinated motion, planning and timing are critical. Sensory information about the target and the current body state is essential, as well as integrating past experiences, represented by pre-learned inverse dynamics that generate associated muscle activity. We propose a generative model that predicts upper limb muscle activity from a variety of simple and complex everyday motions by means of a recurrent neural network. The model shows promising results, with a good fit for different subjects and abstracts well for new motions. We handle the high inter-subject variation in muscle activity using a transfer learning approach, resulting in a good fit for new subjects. Our approach has implications for fundamental movement control understanding and the rehabilitation of neuromuscular diseases using myoelectric prostheses and functional electrical stimulation. Our model can efficiently predict both muscle activity and motion trajectory, which can assist in developing more effective rehabilitation techniques.},

keywords = {BCI, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{grunInvestigationInterplayModelBased2023,

title = {Investigation of the Interplay of Model-Based and Model-Free Learning Using Reinforcement Learning},

author = {Felix Grün and Ioannis Iossifidis},

year  = {2023},

date = {2023-09-15},

urldate = {2023-09-15},

booktitle = {BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

abstract = {The reward prediction error hypothesis of dopamine in the brain states that activity of dopaminergic neurons in certain brain regions correlates with the reward prediction error that corresponds to the temporal difference error, often used as a learning signal in model free reinforcement learning (RL). This suggests that some form of reinforcement learning is used in animal and human brains when learning a task. On the other hand, it is clear that humans are capable of building an internal model of a task, or environment, and using it for planning, especially in sequential tasks. In RL, these two learning approaches, model-driven and reward-driven, are known as model based and model-free RL approaches. Both systems were previously thought to exist in parallel, with some higher process choosing which to use. A decade ago, research suggested both could be used concurrently, with some subject-specific weight assigned to each [1]. Still, the prevalent belief appeared to be that model-free learning is the default mechanism used, replaced or assisted by model-based planning only when the task demands it, i.e. higher rewards justify the additional cognitive effort. Recently, Feher da Silva et al. [2] questioned this belief, presenting data and analyses that indicate model-based learning may be used on its own and can even be computationally more efficient. We take a RL perspective, consider different ways to combine model-based and model-free approaches for modeling and for performance, and discuss how to further study this interplay in human behavioral experiments.},

keywords = {Machine Learning, Reinforcement learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Schweizer2023,

title = {Keep calm - The role of resilience in the interplay between neuroticism and phubbing },

author = {Anne-Marie Schweizer and Johanna Börsting},

editor = {André Melzer and Gary Lee Wagener},

url = {https://doi.org/10.26298/1981-5555},

year  = {2023},

date = {2023-09-06},

urldate = {2023-09-06},

booktitle = {Proceedings of the 13th Conference of the Media Psychology Division (DGPs)},

publisher = {Melusina Press},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Schwarze2023,

title = {Picturing diversity: Exploring children’s perception of intergroup differences },

author = {Veronica Schwarze and Sabrina C. Eimler and Nicole C. Krämer},

editor = {André Melzer and Gary Lee Wagener},

url = {https://doi.org/10.26298/1981-5555},

year  = {2023},

date = {2023-09-06},

booktitle = {Proceedings of the 13th Conference of the Media Psychology Division (DGPs)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Börsting2023,

title = {Tell me why - Combating racism on social media with knowledge},

author = {Johanna Börsting and Veronica Schwarze and Sabrina C. Eimler},

editor = {André Melzer and Gary Lee Wagener},

url = {https://doi.org/10.26298/1981-5555},

year  = {2023},

date = {2023-09-06},

booktitle = {Proceedings of the 13th Conference of the Media Psychology Division (DGPs)},

publisher = {Melusina Press},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Erle2023,

title = {Algorithmic Bias and Digital Divide – An Examination of Discrimination Experiences in Human-System Interactions (Poster)},

author = {Lukas Erle and Lara Timm and Carolin Straßmann and Sabrina C. Eimler},

editor = {André Melzer and Gary Lee Wagener},

url = {https://doi.org/10.26298/1981-5555},

year  = {2023},

date = {2023-09-06},

booktitle = {Proceedings of the 13th Conference of the Media Psychology Division (DGPs)},

publisher = {Melusina Press},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nokey,

title = {Imagine it was you - Empathy as the key for reducing cyberbullying on social media},

author = {Sabrina C. Eimler and Johanna Börsting and Veronica Schwarze},

editor = {André Melzer and Gary Lee Wagener},

url = {https://doi.org/10.26298/1981-5555},

year  = {2023},

date = {2023-09-06},

booktitle = {Proceedings of the 13th Conference of the Media Psychology Division (DGPs)},

publisher = {Melusina Press},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}