MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918384178823168 |
|---|---|
| author | Che, Lirong Wen, Shuo Huang, Shan Wang, Chuang Yang, Yuzhe Dudek, Gregory Wang, Xueqian Su, Jian |
| author_facet | Che, Lirong Wen, Shuo Huang, Shan Wang, Chuang Yang, Yuzhe Dudek, Gregory Wang, Xueqian Su, Jian |
| contents | Real-world robotic tasks are long-horizon and often span multiple floors, demanding rich spatial reasoning. However, existing embodied benchmarks are largely confined to single-floor in-house environments, failing to reflect the complexity of real-world tasks. We introduce MANSION, the first language-driven framework for generating building-scale, multi-floor 3D environments. Being aware of vertical structural constraints, MANSION generates realistic, navigable whole-building structures with diverse, human-friendly scenes, enabling the development and evaluation of cross-floor long-horizon tasks. Building on this framework, we release MansionWorld, a dataset of over 1,000 diverse buildings ranging from hospitals to offices, alongside a Task-Semantic Scene Editing Agent that customizes these environments using open-vocabulary commands to meet specific user needs. Benchmarking reveals that state-of-the-art agents degrade sharply in our settings, establishing MANSION as a critical testbed for the next generation of spatial reasoning and planning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_11554 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks Che, Lirong Wen, Shuo Huang, Shan Wang, Chuang Yang, Yuzhe Dudek, Gregory Wang, Xueqian Su, Jian Computer Vision and Pattern Recognition Artificial Intelligence Robotics Real-world robotic tasks are long-horizon and often span multiple floors, demanding rich spatial reasoning. However, existing embodied benchmarks are largely confined to single-floor in-house environments, failing to reflect the complexity of real-world tasks. We introduce MANSION, the first language-driven framework for generating building-scale, multi-floor 3D environments. Being aware of vertical structural constraints, MANSION generates realistic, navigable whole-building structures with diverse, human-friendly scenes, enabling the development and evaluation of cross-floor long-horizon tasks. Building on this framework, we release MansionWorld, a dataset of over 1,000 diverse buildings ranging from hospitals to offices, alongside a Task-Semantic Scene Editing Agent that customizes these environments using open-vocabulary commands to meet specific user needs. Benchmarking reveals that state-of-the-art agents degrade sharply in our settings, establishing MANSION as a critical testbed for the next generation of spatial reasoning and planning. |
| title | MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2603.11554 |