Towards Embodied Cognition in Robots via Spatially Grounded Synthetic Worlds
| dc.contributor.author | Currie, Joel | |
| dc.contributor.author | Migno, Gioele | |
| dc.contributor.author | Piacenti, Enrico | |
| dc.contributor.author | Giannaccini, Maria Elena | |
| dc.contributor.author | Bach, Patric | |
| dc.contributor.author | Tommaso, Davide De | |
| dc.contributor.author | Wykowska, Agnieszka | |
| dc.contributor.institution | University of Aberdeen.Psychology | en |
| dc.contributor.institution | University of Aberdeen.Engineering | en |
| dc.contributor.institution | University of Aberdeen.Psychology | en |
| dc.date.accessioned | 2025-07-28T14:00:00Z | |
| dc.date.available | 2025-07-28T14:00:00Z | |
| dc.date.issued | 2025-05-20 | |
| dc.description | Accepted 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. | en |
| dc.format.extent | 3 | |
| dc.format.extent | 668183 | |
| dc.identifier | 306078556 | |
| dc.identifier | ddcf4a1c-5dd2-4ab2-9b2d-19bfc7ba5c94 | |
| dc.identifier.citation | Currie, 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.2505.14366 | en |
| dc.identifier.doi | 10.48550/ARXIV.2505.14366 | |
| dc.identifier.other | ORCID: /0000-0002-3367-7056/work/184484392 | |
| dc.identifier.other | ORCID: /0000-0003-4493-2080/work/188766277 | |
| dc.identifier.other | ArXiv: http://arxiv.org/abs/2505.14366v1 | |
| dc.identifier.uri | https://hdl.handle.net/2164/25772 | |
| dc.identifier.url | https://arxiv.org/abs/2505.14366 | en |
| dc.identifier.url | https://huggingface.co/datasets/jwgcurrie/synthetic-distance | en |
| dc.language.iso | eng | |
| dc.publisher | ArXiv | |
| dc.subject | Research Institute/Organisation. | en |
| dc.subject | 2040 Data and Artificial Intelligence | en |
| dc.subject | Visual Perspective Taking | en |
| dc.subject | Visual Language Models | en |
| dc.subject | Spatial Reasoning | en |
| dc.subject | Embodied-AI | en |
| dc.subject | Human-Robot Interaction | en |
| dc.subject | QA75 Electronic computers. Computer science | en |
| dc.subject | Supplementary Data | en |
| dc.subject | DAS | en |
| dc.subject | Link | en |
| dc.subject.lcc | QA75 | en |
| dc.title | Towards Embodied Cognition in Robots via Spatially Grounded Synthetic Worlds | en |
| dc.type | Preprint | en |
Files
Original bundle
1 - 1 of 1
