Search our Publications
Latest Publications
Phillip Richter, Heiko Wersing, Anna-Lisa Vollmer , "Quantifying and Reducing Mental Model Mismatch for Cooperative Robot Teaching", 1st German Robotics Conference (GRC), 2025.
AbstractA major challenge in human-robot interaction (HRI) is the mental model mismatch, which arises when a human's understanding of a robot's capabilities differs from the robot's actual operational model. Such mismatches can result in ineffective teaching, suboptimal performance, and interaction breakdowns. This project aims to quantify mental model mismatch by formalizing and comparing human expectations with robot learning processes, enabling a stru...
Download Bibtex file Per Mail Request
Phillip Richter, Arthur Maximilian Noller, Heiko Wersing, Sven Wachsmuth, Anna-Lisa Vollmer , "AURORA: A Platform for Advanced User-driven Robotics Online Research and Assessment", 1st German Robotics Conference (GRC), 2025.
AbstractAURORA is a software platform, that facilitates scalable deployment of robotic simulations over the web for the Human-Robot Interaction (HRI) community. As robotics is becoming increasingly important in various disciplines, there is a growing need for accessible and scalable research methods. Traditional experiments often require expensive hardware and in-person participation, limiting accessibility and participant diversity. Our platform allows ...
Download Bibtex file Per Mail Request
Yew Soon Ong, Jiao Liu, Chin Chun Ooi, Abhishek Gupta, Stefan Menzel, Kalyanmoy Deb , "Special Session on Physics-Informed Evolutionary Learning and Optimization", IEEE Congress on Evolutionary Computation, 2025.
AbstractPhysics, as a foundational framework for describing the natural world, has been pivotal to scientific inquiry throughout human history. Physical information has long been integrated into various research domains, including evolutionary computation. Over the past two decades, such information has frequently been applied in data-driven contexts within evolutionary computing. By utilizing data from classical physics simulators - such as the finite e...
Download Bibtex file Per Mail Request
Steffen Limmer, Angus Kenny, Tapabrata Ray, Felix Lanfermann, Hemant Kumar Singh, Andrea Castellani , "Design of Fair and Interpretable Electric Vehicle Charging Policies through Genetic Programming", Applied Energy, vol. 404, 2025.
AbstractControlled charging of a group of electric vehicles (EVs) subject to power limits, such as those imposed by transformer capacity constraints, may result in inefficient and unfair energy distribution among EVs. The present work aims to learn fair and efficient charging policies on historical data using multi-objective genetic programming. Two variants of this approach are proposed and evaluated in simulation experiments. Compared to several baseli...
Download Bibtex file
Christiane Attig, Christiane Wiebel, Thomas Franke , "Balancing Autonomy and Automation: Meaningful User Experience in Smart Charging Agent Interactions", Tagung experimentell arbeitender Psychologen (TEAP), 2025.
AbstractEveryday life is increasingly permeated by interactions between humans and autonomous agents. One example is electric vehicle (EV) drivers using smart charging agents (SCA) based on automated information processing to manage limited interdependent resources (e.g., availability of electrical energy, charging times). These agents must not only manage resources effectively, but also ensure meaningful participation in charging decisions, thereby supp...
Download Bibtex file Per Mail Request
Radu Stoican , "Exploration in Few-Shot Meta-Reinforcement Learning", University of Manchester, School of Engineering, Department of Computer Science, University of Manchester, 2025.
AbstractReinforcement learning trains policies specialized for a single task. Meta-reinforcement learning (meta-RL) improves upon this by leveraging prior experience to train policies for few-shot adaptation to new tasks. However, existing meta-RL approaches often struggle to explore and learn tasks effectively. We introduce a novel meta-RL algorithm for learning to learn task-specific, sample-efficient exploration policies. We achieve this through t...
Download Bibtex file Per Mail Request
David Schmidt, Svenja Kenneweg, Julian Eggert, Jörg Deigmöller, Philipp Cimiano , "Fuzzy Temporal QA over RDF Data", KEOD 2025, 2025.
AbstractWe present a question answering system over RDF data that interprets vague temporal adverbials (e.g., "just", "recently") using a fuzzy probabilistic model. By extending the NeoDUDES QALD pipeline and integrating a temporally enriched knowledge graph based on smart home data, our approach maps vague expressions to time intervals via empirically grounded Gaussian functions. The system generates SPARQL queries with temporal filters, enabling compos...
Download Bibtex file
Mariam Arustashvili, Jörg Deigmöller, Heiko Paulheim , "Knowledge Graph Completion for Action Prediction on Situational Graphs - A Case Study on Household Tasks.", Semantics 2025, 2025.
AbstractKnowledge Graphs are used for various purposes, including the descrip- tion of household actions, e.g., for analyzing video footage. In that case, the infor- mation extracted from videos is notoriously incomplete, and completing the knowl- edge graph for enhancing the situational picture is essential. In this paper, we show that, while a standard link prediction problem, many link prediction algorithms are not fit for the job, and unable to ...
Download Bibtex file
Maria Bresich, Guenther Raidl, Steffen Limmer , "Revisiting Large Neighborhood Search With On-The-Fly Charging Station Insertion for the Electric Autonomous Dial-A-Ride Problem", ACM Transactions on Evolutionary Learning and Optimization, 2025.
AbstractWe address the electric autonomous dial-a-ride problem (E-ADARP), a challenging extension of the dial-a-ride problem with the goal of fi nding minimum cost routes serving given transportation requests with a fleet of electric and autonomous vehicles (EAVs). Special emphasis lies on the minimization of user excess ride time under consideration of the charging requirements of the EAVs while operational constraints have to be satisfied. We propose a...
Download Bibtex file
Tuan Vu Pham, Chao Wang, Heiko Wersing, Marc Hassenzahl , ""Teach Me About Objects!" – Experience-Driven Interaction for Teachable Robots", ACM Designing Interactive Systems Conference (DIS) 2025, 2025.
AbstractTo adapt to specific places and people, robots must recognize objects, which are typically taught by users—a tedious process. Inspired by anecdotes of positive teaching experiences shared by educators, sports coaches, and animal trainers, we developed seven experience-driven ways to make teaching a robot more engaging. For example, one interaction involved the robot prompting users to tell personal stories about the objects. A video vignette stud...
Download Bibtex file
1 ... 10 11 12 13 14 15 ... 183
Follow us
