Search our Publications
Latest Publications
Navid Hamid , "Neuro-Symbolic Systems for Constitutional Control in Advanced Air Mobility Systems", Thesis, 2025.
AbstractNeuro-Symbolic Systems that combine white-box models with advanced machine learning systems provide a new opportunity for designing missions for intelligent transportation systems (ITS). In this context, deep probabilistic logic programs which extend First Order Logic by assigning probabilities or distributions to variables which are learned by neural networks have specifically found popularity for representing laws and uncertainties associated w...
Download Bibtex file Per Mail Request
Felix Ocker , "Actionable intelligence: Tool use at scale for embodied agents", Honda Technical Forum, 2025.
AbstractIn recent years, the field of artificial intelligence has witnessed significant progress, particularly with the advent of powerful language models. This evolution has catalyzed a growing interest in autonomous agents capable of complex reasoning and decision-making. Central to their practical deployment is tool use - a mechanism that enables agents to interact with and act upon the world - and the planning capabilities required to orchestrate suc...
Download Bibtex file Per Mail Request
Fan Zhang , "General Manipulation for Assistive Robots", Intelligent systems and networks (ISN), Imperial College London, 2025.
AbstractWe present a framework for assistive robot manipulation, which focuses on two fundamental challenges: first, efficiently adapting large-scale models to downstream scene affordance understanding tasks, especially in daily living scenarios where gathering multi-task data involving humans requires strenuous effort; second, effectively learning robot action trajectories by grounding the visual affordance model. We tackle the first challenge by employ...
Download Bibtex file Per Mail Request
Fan Zhang , "General Manipulation for Assistive Robots", Heterogeneous Intelligent and Quantum Computing (HIQC) Lab, Southeast University, 2025.
AbstractWe present a framework for assistive robot manipulation, which focuses on two fundamental challenges: first, efficiently adapting large-scale models to downstream scene affordance understanding tasks, especially in daily living scenarios where gathering multi-task data involving humans requires strenuous effort; second, effectively learning robot action trajectories by grounding the visual affordance model. We tackle the first challenge by empl...
Download Bibtex file Per Mail Request
Andreas Sochopoulos, Nikolaos Tsagkas, Joao Moura, Nikolay Malkin, Michael Gienger, Sethu Vijayakumar , "Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplings", ArXiv, 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...
Download Bibtex file Per Mail Request
Fan Zhang , "General Robot Manipulation for Assistive Robotics", Autonomous Agents Research Group, The University of Edinburgh, 2025.
AbstractWe present a framework for assistive robot manipulation, which focuses on two fundamental challenges: first, efficiently adapting large-scale models to downstream scene affordance understanding tasks, especially in daily living scenarios where gathering multi-task data involving humans requires strenuous effort; second, effectively learning robot action trajectories by grounding the visual affordance model. We tackle the first challenge by employ...
Download Bibtex file Per Mail Request
Michael Gienger , "Hey robot, pass me the apple: LLMs meet physical support", Talk at Virtual Robotics Lab International Lecture Series, Peru (https://roboticslab.pe), online, 2025.
AbstractThe recent breakthroughs in Generative AI offer fantastic opportunities to research novel concepts for intelligent embodied agents. In this talk, I will introduce recent research in exploiting Large Language Models (LLMs) for robot task and motion planning. We combined reasoning, planning, and motion generation, and introduced a novel concept for correcting errors during planning and execution. I’ll show several results both in simulations and re...
Download Bibtex file Per Mail Request
Fan Zhang , "Robot Manipulation with Flow Matching", Imperial College London, 2025.
AbstractWe present a framework for assistive robot manipulation, which focuses on two fundamental challenges: first, efficiently adapting large-scale models to downstream scene affordance understanding tasks, especially in daily living scenarios where gathering multi-task data involving humans requires strenuous effort; second, effectively learning robot action trajectories by grounding the visual affordance model. We tackle the first challenge by employ...
Download Bibtex file Per Mail Request
Angie Nataly Melo Castillo, Markus Amann, Carlota Salinas Maldonado, Maytheewat Aramrattana, Thomas H Weisswange, Malte Probst , Miguel Ángel Sotelo , "Towards Incorporating Pedestrian Intention Predictions into Behavior Planning using Virtual Reality Co-Simulators", 36th IEEE Intelligent Vehicles Symposium (IV 2025): 14th Workshop on Human Factors in Intelligent Vehicles & Supporting Vehicle-Pedestrian Interactions, 2025.
AbstractInteraction modeling plays a huge role in understanding human behavior in traffic. This is especially relevant when it comes to interactions between vehicles and vulnerable road users such as pedestrians. Thus, pedestrian behavior prediction is an ongoing field of research in order to understand the pedestrians’ decision making. Most state-of-the-art prediction frameworks are trained on large-scale datasets and evaluated with respect to acknowled...
Download Bibtex file
Malte Probst , Raphael Wenzel, Tim Puphal, Monica Dasi, Nico Andreas Steinhardt, Sango Matsuzaki, Misa Komuro , "Finding the Easy Way Through-the Probabilistic Gap Planner for Social Robot Navigation", IEEE RO-MAN 2025, 2025.
AbstractIn Social Robot Navigation, autonomous agents need resolving many sequential interactions with other agents. State-of-the art planners can efficiently resolve the next, imminent interaction cooperatively and do not focus on longer planning horizons. This makes it hard to maneuver scenarios where the agent needs to find a good strategy to find gaps or channels in the crowd. We propose to decompose trajectory planning to two separate steps: Confli...
Download Bibtex file
1 ... 14 15 16 17 18 19 ... 183
Follow us
