Hifza Javed, Nina Moorman, Thomas Weisswange, Nawid Jamali, "Dyadic Interactions and Interpersonal Perception: An Exploration of Behavioral Cues for Technology-Assisted Mediation", 15th International Conference on Applied Human Factors and Ergonomics (AHFE 2024), 2024.
AbstractMediators aim to shape group dynamics in various ways, such as improving trust and cohesion, balancing participation, and promoting constructive conflict resolution. Technological systems used to mediate human-human interactions must be able to continuously assess the state of the interaction and generate appropriate actions. To this end, an understanding of the collective affective state of the group is needed in order to produce meaningful acti...
Zhenpeng Shi, Nikolay Matyunin, Kalman Graffi, David Starobinski, "Uncovering CWE-CVE-CPE Relations with Threat Knowledge Graphs", ACM Transactions on Privacy and Security (TOPS), 2024.
AbstractSecurity assessment relies on public information on products, vulnerabilities and weaknesses. So far, databases in these categories have rarely been analyzed in combination. Yet, doing so could help predict unreported vulnerabilities and identify common threat patterns. In this paper, we propose a methodology for producing and optimizing a knowledge graph that aggregates knowledge from common threat databases (CPE, CVE, and CWE). We apply the thr...
Jihong Zhu, Michael Gienger, Giovanni Franzese, Jens Kober, "Do You Need a Hand? – An Interactive Robotic Dressing Assistance Scheme", IEEE Transactions on Robotics, 2024.
AbstractDeveloping physically assistive robots capable of dressing assistance has the potential to significantly improve the lives of the elderly and disabled population. However, most robotics dressing strategies used a single robot only, which greatly limited the performance of the dressing assistance. In fact, both arms are usually required when healthcare professionals perform the task. Inspired by them, we propose a bimanual cooperative schem...
Michael Gienger, "Explainable human-robot interaction & LLM-based robot planning", TU Delft, 2024.
AbstractThis invited lab talk covers research conducted in the Smile project related to the AR-supported learning and interaction framework, as well as of the recent LLM-based planning concepts....
Chao Wang, "Large Language Models for Multi-Modal Human-Robot Interaction", LMU Winterschool , 2024.
AbstractI will report our latest achievement based on the CHI LBW paper we submitted: https://arxiv.org/abs/2401.15174 A paper website is also created for better spreading (please see the "Supplementary Material"). Besides, I will show a real time demo of our system with camera, microphone and object with marker. The robot's behavior will be shown in RCS simulator and "inner thought" GUI. Student can also send me system prompt, then we can tune the r...
Felix Ocker and Julian Eggert, "Accessing Knowledge using Retrieval Augmented Generation", Honda Technical Forum 2023, 2023.
AbstractLanguage Models (LMs) provide an intuitive interface for humans via Natural Language. However, they hallucinate very convincingly and do not have access to proprietary data. This presentation gives insights into Retrieval Augmented Generation (RAG) as a technology for realizing the LM experience for large amounts of proprietary data. We present the underlying architecture, results achieved with an HRI-EU internal prototype for the TikiWiki, the "...
Patricia Wollstadt, Sebastian Schmitt, Michael Wibral, "A Rigorous Information-Theoretic Definition of Redundancy and Relevancy in Feature Selection Based on (Partial) Information Decomposition", Journal of Machine Learning Research, vol. 24, no. 131, pp. 1-44, 2023.
AbstractSelecting a minimal feature set that is maximally informative about a target variable is a central task in machine learning and statistics. Information theory provides a powerful framework for formulating feature selection algorithms---yet, a rigorous, information-theoretic definition of feature relevancy, which accounts for feature interactions such as redundant and synergistic contributions, is still missing. We argue that this lack is inherent...
Andrea Castellani, "Dealing with Inaccurate and Incomplete Labels in Industrial Streaming Data - Talk at Uni Creete (27.09.2023)", Crete University, Crete University, 2023.
AbstractMachine learning techniques are an essential option for processing large volumes of data and are capable to capture complex relationships within it. However, obtaining meaningfully annotated data is a real challenge and typically incurs large costs. Especially, in an industrial setting where few labelled data samples are available and drifting data features poses a severe challenge. In this talk, I will address: (1) how to efficiently train model...
Andrea Castellani, "Dealing with Inaccurate and Incomplete Labels in Industrial Streaming Data", Uni Bielefeld, Uni Bielefeld, 2023.
AbstractThe pressure to increase the energetic efficiency of industrial facilities has led to a strong increase in the number of installed measurement sensors. These collect large volumes of data that need to be processed and analyzed. As manual data processing methods are not appropriate due to the sheer amount of data, automated and intelligent solutions are needed. Machine learning techniques are a viable option for processing large volumes of da...
Daniel Gordon, Andreas Christou, Michael Gienger, Sethu Vijayakumar, "Adaptive Assistive Robotics: A Framework For Triadic Collaboration Between Humans and Robots", Royal Society Open Science, 2023.
AbstractRobots and other assistive technologies have a huge potential to help society in domains ranging from factory work to healthcare. However, safe and eff ective control of robotic agents in these environments is complex, especially when it involves close interactions and multiple actors. We propose an eff ective framework for optimising the behaviour of robots and complementary assistive technologies in systems comprising a mix of human and...