About CARAML
The CARAML Project (A Cognitive Architecture for Robotic Arms coupling Machine Learning and Logic) is funded by the Hellenic Foundation for Research and Innovation (H.F.R.I.) under the 3rd Call for Research Projects to support Faculty Members and Researchers (Proposal ID: 25735).
The project explores cutting-edge Artificial Intelligence approaches at the intersection of Machine Learning and Symbolic Reasoning, focusing on neuro-symbolic AI methods that enhance robotic perception, cognition, and manipulation. CARAML aims to develop a cognitive architecture enabling robotic arms to grasp and manipulate previously unseen household objects under uncertainty, while providing human-understandable explanations of their decision-making processes.
The consortium is coordinated by Prof. Panos Trahanias (Institute of Computer Science, FORTH) and involves a research team of senior and junior scientists, software engineers, and external collaborators from Imperial College London, TU Wien, and University College London.
CARAML’s research covers domains such as robot perception, commonsense reasoning, knowledge representation, graph neural networks, generative AI, and explainable human-robot interaction.
