Andreas Sochopoulos, Nikolaos Tsagkas, Joao Moura, Nikolay Malkin, Michael Gienger, Sethu Vijayakumar , "Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplings", Conference on Robot Learning, 2025.
AbstractDiffusion and flow matching policies have recently shown remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions. However, their computationally expensive inference, due to numerical integration of an ODE or SDE, limits their application as real-time controllers for robots. We introduce a methodology that utilizes conditional Optimal Transport couplings between noise and samples, in order t...
Ahmed Sadik, Muhammad Ashfaq, Niko Mäkitalo, Tommi Mikkonen , "Urban Air Mobility as a System of Systems: An LLM-Enhanced Holonic Approach", system of systems engineering conference 2025 - SOSE25, 2025.
AbstractUrban Air Mobility (UAM) is an emerging System of Systems (SoS) that presents significant challenges in system architecture, planning, task management, and execution. Traditional approaches often struggle with scalability, adaptability, and seamless resource integration within dynamic and complex environments. To overcome these limitations, this paper introduces an intelligent holonic architecture enhanced by Large Language Models (LLMs). By inco...
Felix Ocker , "From Prompt to Production: LLM-based Agents in Engineering, Robotics and Manufacturing", VDI GMA 3.35 "Agentensysteme", 2025.
AbstractTBD, got invited to give an overview of some prior work at VDI GMA 3.35 (agent systems) fully remote, no costs incurred...
Timm Lauser, Nergiz Yuca, Dustin Kern, Nikolay Matyunin, Stefan Katzenbeisser, Christoph Krauß , "Oblivious Plug&Charge: A Privacy-Preserving EV Charging Scheme based on ORAM", 3rd USENIX Symposium on Vehicle Security and Privacy (VehicleSec 25), pp. 221-232, 2025.
AbstractIn the rapidly developing Electric Vehicle (EV) charging infrastructure, ensuring user privacy during charging and billing processes has become a concern. Modern vehicles increasingly support Plug-and-Charge (PnC), a standard for direct authentication and billing of charging sessions without user interaction. However, within the PnC architecture, the exchange of sensitive data enables e-Mobility service providers and charging station operators to...
Jan Leusmann, Steeven Villa Salazar, Thomas Liang, Chao Wang, Albrecht Schmidt, Sven Mayer , "An Approach to Elicit Human-Understandable Robot Expressions to Support Human-Robot Collaboration", CHI 2025, 2025.
AbstractUnderstanding the intentions of robots is essential for natural and seamless human-robot collaboration. Ensuring that robots have means for non-verbal communication is a basis for intuitive and implicit interaction. For this, we contribute an approach to elicit and design human-understandable robot expressions. We outline the approach in the context of non-humanoid robots. We show that it enabled us to design robot expressions that signal curiosi...
Jose Almeida, Joao Soares, Steffen Limmer, Fernando Lezama, Sergio Ramos , "Integrating Autonomous Electric Vehicle Charging Stations in Local Energy Communities", International Conference on Power, Energy, and Electrical Engineering (CPEEE) 2025, 2025.
AbstractAutonomous electric vehicles (AEVs) represent a transformative technology that must be carefully considered in the design of modern energy management systems. Addressing the challenges associated with AEVs and their charging infrastructure while leveraging the opportunities they present is crucial. In this study, we propose the integration of inductive AEV charging stations into multiple local energy communities, treating these stations as commun...
Jan Leusmann and Sven Mayer , "Eliciting Understandable Architectonic Gestures for Robotic Furniture through Co-Design Improvisation", 2025 IEEE/ACM International Conference on Human-Robot Interaction (HRI’25), 2025.
AbstractThe vision of adaptive architecture proposes that robotic technologies could enable interior spaces to physically transform in a bidirectional interaction with occupants. Yet, it is still unknown how this interaction could unfold in an understandable way. Inspired by HRI studies where robotic furniture gestured intents to occupants by deliberately positioning or moving in space, we hypothesise that adaptive architecture could also convey intents ...
Ehsan Aliyan, Jose Almeida, Steffen Limmer, Sergio Ramos, Joao Soares , "Optimal Formation of Energy Communities under Technical-Spatial Constraints", International Conference on Power, Energy, and Electrical Engineering (CPEEE) 2025, 2025.
AbstractThe growing incorporation of renewable energy sources, electric vehicles, and energy storage systems within modern power systems has amplifi ed the need for effi cient energy management frameworks. This paper presents a novel optimization approach for clustering prosumers into energy community groups to enhance self-suffi ciency, operational efficiency, and economic performance. The proposed framework incorporates an initial number of prosumers w...
Jose Almeida, Joao Soares, Fernando Lezama, Steffen Limmer, Tobias Rodemann, Zita Vale , "A Systematic Review of Explainability in Computational Intelligence for Optimization", Computer Science Review, vol. 57, 2025.
AbstractThis systematic review explores the need for explainability in computational intelligence methods for optimization such as metaheuristics optimizers including evolutionary algorithms and swarm intelligence. The work is focusing on four research questions: 1) the contribution of Explainable AI (XAI) methods to interpreting metaheuristic performance; 2) the influence of problem features on search behavior and explainability; 3) the role of mathemat...
Fernando Lezama, Ricardo Faia, Steffen Limmer, Zahra Foroozandeh, Joao Soares, Sergio Ramos, Zita Vale , "A Scalable Three-Stage Model for Local Energy Community Management and Pricing", CSEE Journal of Power and Energy Systems, 2025.
AbstractThis study introduces and evaluates advanced optimization models for local energy community management, focusing on pricing and energy scheduling. We propose a novel three-stage approach to address the complexities of local energy community price determination and enhance model efficiency. The research builds upon previous works, analyzing a basic local energy community optimization model, modifying the formulation to a bi-level optimization mode...