Search our Publications
Latest Publications
Archit Naik , "Leveraging 2D part segmentation for improved 6D object pose estimation", Technical Faculty at FAU Erlangen-Nürnberg, 2025.
AbstractEstimating the 6D pose of known objects from RGB-D data works well when the registration is properly initialized, but classical ICP often fails under large misalignments, object symmetries, or cluttered scenes. This thesis introduces SegmentICP, a training-free, CAD-based approach that leverages part information from 2D vision to make 3D registration more robust. SegmentICP uses a two- stage pipeline: (i) a part-aware initializer that aligns...
Download Bibtex file Per Mail Request
Christian Internó, Andrea Castellani, Sebastian Schmitt, Barbara Hammer , "Industrial Energy Disaggregation with Digital Twin-generated Dataset and Efficient Data Augmentation", Arxiv Preprint, 2025.
AbstractIndustrial Non-Intrusive Load Monitoring (NILM) is limited by the scarcity of high-quality datasets and the complex variability of industrial energy consumption patterns. To address data scarcity and privacy issues, we introduce the Synthetic Industrial Dataset for Energy Disaggregation (SIDED), an opensource dataset generated using Digital Twin simulations. SIDED includes three types of industrial facilities across three different geographic loc...
Download Bibtex file Per Mail Request
Melvin Wong, Jiao Liu, Thiago de Jesus de Araujo Rios, Stefan Menzel, Yew Soon Ong , "LLM2TEA: An Agentic AI Designer for Discovery with Generative Evolutionary Multitasking", IEEE Computational Intelligence Magazine, 2025.
AbstractThis paper presents LLM2TEA, a Large Language Model (LLM) driven MultiTask Evolutionary Algorithm, representing the first agentic AI designer of its kind operating with generative evolutionary multitasking (GEM). LLM2TEA enables the crossbreeding of solutions from multiple domains, fostering novel solutions that transcend disciplinary boundaries. Of particular interest is the ability to discover designs that are both novel for and conforming to r...
Download Bibtex file Download PDF
David Rother, Joni Pajarinen, Jan Peters, Thomas H Weisswange , "Open-Ended Coordination for Multi-Agent Systems Using Modular Open Policies", Autonomous Agents and Multi-Agent Systems, vol. 39, 2025.
AbstractSignificant advances addressing the challenge of learning policies for acting in multi-agent systems have been made through approaches for ad hoc teamwork, a paradigm where a team of agents must cooperate effectively without prior coordination or communication. Many existing approaches, however, struggle to perform well in open environments where the setting can change significantly during deployment. This paper presents a new reinforcement lear...
Download Bibtex file Per Mail Request
Petros Georgiadis, Martina Hasenjäger, Dimitris Voudouris, Christiane Wiebel , "On the temporal dynamics of head and eye movements for real-world walking behavior", Acta Psychologica, vol. 260, pp. 105680, 2025.
AbstractMost human actions are planned and performed based on visual information. Indeed, when interacting with the environment, humans typically direct their gaze to where relevant information for the task at hand can be found. While walking, humans shift their gaze by using both eye and head movements, and the relative contribution of the head is more pronounced when the navigated surface’s complexity increases. However, most work has examined average ...
Download Bibtex file Download PDF
Sebastian Brulin, Tamon Toyooka, Lydia Fischer, Florian Kreuchauff, Tobias Rodemann , "Comparative Assessment of Swappable Battery Stations (SBEV) and Stationary Charging Stations (BEV) in Urban Electric Vehicle Networks: An Activity-Based Simulation Approach", EVTeC 2025, 2025.
AbstractThis paper investigates the comparative performance of swappable battery stations (SBEV) and stationary charging stations (BEV) in urban electric vehicle networks using large-scale activity-based MATSim simulations to assess user behavior across various scenarios. Focusing on user and operator perspectives, we investigate the hypotheses that SBEVs offer shorter charging times for users, while operators benefit from lower infrastructure costs eith...
Download Bibtex file Download PDF
Elisabeth Menendez, Santiago Martinez, Carlos Balaguer, Michael Gienger, Anna Belardinelli , "SemanticScanpath: Combining Gaze and Speech for Situated Human-Robot Interaction Using LLMs", arxiv, 2025.
AbstractLarge Language Models (LLMs) have substan- tially improved the conversational capabilities of social robots. Nevertheless, for an intuitive and fluent human-robot inter- action, robots should be able to ground the conversation by relating ambiguous or underspecified spoken utterances to the current physical situation and to the intents expressed non verbally by the user, for example by using referential gaze. Here we propose a representati...
Download Bibtex file Per Mail Request
Felix Ocker and Julian Eggert , "Connecting the Dots: Retrieval-Augmented Generation with Graphs", Honda Data Days, 2025.
AbstractAn overview of GraphRAG and its applications for cognitive assistants and technical documents....
Download Bibtex file Per Mail Request
Thomas H Weisswange, Hifza Javed, Manuel Dietrich, Malte F. Jung, Nawid Jamali , "Design Implications for Robots that Facilitate Groups - A Scoping Review on Improving Group Interactions through Directed Robot Action", ACM Transactions on Human-Robot Interaction, 2025.
AbstractMany human activities are performed in groups---making decisions in workplace meetings, cooperating on a sports team, or meeting with friends for dinner. All these activities involve complex conditions and interaction processes that influence their outcomes in terms of performance, personal goals, and group objectives. As robots are increasingly being positioned within groups, improving these outcomes has emerged as an important application area ...
Download Bibtex file Download PDF
Leon Keller, Daniel Tanneberg, Jan Peters , "Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning", IEEE International Conference on Robotics and Automation (ICRA), 2025.
AbstractImitation learning is a popular method for teaching robots new behaviors. However, most existing methods focus on teaching short, isolated skills rather than long, multi-step tasks. To bridge this gap, imitation learning algorithms must not only learn individual skills but also an abstract understanding of how to sequence these skill to perform extended tasks effectively. This paper addresses this challenge by proposing a neuro-symbolic imitatio...
Download Bibtex file Download PDF
1 2 3 4 ... 170
Follow us
