Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.17198 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914002059132928 |
|---|---|
| author | Ruan, Shouwei Wang, Liyuan Kang, Caixin Zhu, Qihui Liu, Songming Wei, Xingxing Su, Hang |
| author_facet | Ruan, Shouwei Wang, Liyuan Kang, Caixin Zhu, Qihui Liu, Songming Wei, Xingxing Su, Hang |
| contents | Spatial cognition enables adaptive goal-directed behavior by constructing internal models of space. Robust biological systems consolidate spatial knowledge into three interconnected forms: \textit{landmarks} for salient cues, \textit{route knowledge} for movement trajectories, and \textit{survey knowledge} for map-like representations. While recent advances in multi-modal large language models (MLLMs) have enabled visual-language reasoning in embodied agents, these efforts lack structured spatial memory and instead operate reactively, limiting their generalization and adaptability in complex real-world environments. Here we present Brain-inspired Spatial Cognition for Navigation (BSC-Nav), a unified framework for constructing and leveraging structured spatial memory in embodied agents. BSC-Nav builds allocentric cognitive maps from egocentric trajectories and contextual cues, and dynamically retrieves spatial knowledge aligned with semantic goals. Integrated with powerful MLLMs, BSC-Nav achieves state-of-the-art efficacy and efficiency across diverse navigation tasks, demonstrates strong zero-shot generalization, and supports versatile embodied behaviors in the real physical world, offering a scalable and biologically grounded path toward general-purpose spatial intelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17198 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From reactive to cognitive: brain-inspired spatial intelligence for embodied agents Ruan, Shouwei Wang, Liyuan Kang, Caixin Zhu, Qihui Liu, Songming Wei, Xingxing Su, Hang Artificial Intelligence Spatial cognition enables adaptive goal-directed behavior by constructing internal models of space. Robust biological systems consolidate spatial knowledge into three interconnected forms: \textit{landmarks} for salient cues, \textit{route knowledge} for movement trajectories, and \textit{survey knowledge} for map-like representations. While recent advances in multi-modal large language models (MLLMs) have enabled visual-language reasoning in embodied agents, these efforts lack structured spatial memory and instead operate reactively, limiting their generalization and adaptability in complex real-world environments. Here we present Brain-inspired Spatial Cognition for Navigation (BSC-Nav), a unified framework for constructing and leveraging structured spatial memory in embodied agents. BSC-Nav builds allocentric cognitive maps from egocentric trajectories and contextual cues, and dynamically retrieves spatial knowledge aligned with semantic goals. Integrated with powerful MLLMs, BSC-Nav achieves state-of-the-art efficacy and efficiency across diverse navigation tasks, demonstrates strong zero-shot generalization, and supports versatile embodied behaviors in the real physical world, offering a scalable and biologically grounded path toward general-purpose spatial intelligence. |
| title | From reactive to cognitive: brain-inspired spatial intelligence for embodied agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.17198 |