Currie, JoelMigno, GioelePiacenti, EnricoGiannaccini, Maria ElenaBach, PatricTommaso, Davide DeWykowska, Agnieszka2025-07-282025-07-282025-05-20Currie, J, Migno, G, Piacenti, E, Giannaccini, M E, Bach, P, Tommaso, D D & Wykowska, A 2025 'Towards Embodied Cognition in Robots via Spatially Grounded Synthetic Worlds' ArXiv. https://doi.org/10.48550/ARXIV.2505.14366ORCID: /0000-0002-3367-7056/work/184484392ORCID: /0000-0003-4493-2080/work/188766277ArXiv: http://arxiv.org/abs/2505.14366v1https://hdl.handle.net/2164/25772Accepted to: Intelligent Autonomous Systems (IAS) 2025 as Late Breaking Report Dataset availability: We release our synthetic dataset of minimal 3D scenes, each containing an RGB image, a natural language prompt, and a ground-truth 4×4 pose matrix. The dataset [6] is available at: https://huggingface.co/datasets/jwgcurrie/synthetic-distance.3668183engResearch Institute/Organisation.2040 Data and Artificial IntelligenceVisual Perspective TakingVisual Language ModelsSpatial ReasoningEmbodied-AIHuman-Robot InteractionQA75 Electronic computers. Computer scienceSupplementary DataDASLinkQA75Preprint10.48550/ARXIV.2505.14366https://arxiv.org/abs/2505.14366https://huggingface.co/datasets/jwgcurrie/synthetic-distance