Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910152896020480 |
|---|---|
| author | Chen, Xu Xie, Shichao Gu, Zhining Jia, Lu Luo, Minghua Liu, Fei Chu, Zedong Shen, Yanfen Wu, Xiaolong Xu, Mu |
| author_facet | Chen, Xu Xie, Shichao Gu, Zhining Jia, Lu Luo, Minghua Liu, Fei Chu, Zedong Shen, Yanfen Wu, Xiaolong Xu, Mu |
| contents | Constructing structured spatial memory is essential for enabling long-horizon reasoning in complex embodied navigation tasks. Current memory construction predominantly relies on a decoupled, two-stage paradigm: agents first aggregate environmental data through exploration, followed by the offline reconstruction of spatial memory. However, this post-hoc and geometry-centric approach precludes agents from leveraging high-level semantic intelligence, often causing them to overlook navigationally critical landmarks (e.g., doorways and staircases) that serve as fundamental semantic anchors in human cognitive maps. To bridge this gap, we propose ABot-Explorer, a novel active exploration framework that unifies memory construction and exploration into an online, RGB-only process. At its core, ABot-Explorer leverages Large Vision-Language Models (VLMs) to distill Semantic Navigational Affordances (SNA), which act as cognitive-aligned anchors to guide the agent's movement. By dynamically integrating these SNAs into a hierarchical SG-Memo, ABot-Explorer mirrors human-like exploratory logic by prioritizing structural transit nodes to facilitate efficient coverage. To support this framework, we contribute a large-scale dataset extending InteriorGS with SNA and SG-Memo annotations. Experimental results demonstrate that ABot-Explorer significantly outperforms current state-of-the-art methods in both exploration efficiency and environment coverage, while the resulting SG-Memo is shown to effectively support diverse downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19034 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents Chen, Xu Xie, Shichao Gu, Zhining Jia, Lu Luo, Minghua Liu, Fei Chu, Zedong Shen, Yanfen Wu, Xiaolong Xu, Mu Computer Vision and Pattern Recognition Constructing structured spatial memory is essential for enabling long-horizon reasoning in complex embodied navigation tasks. Current memory construction predominantly relies on a decoupled, two-stage paradigm: agents first aggregate environmental data through exploration, followed by the offline reconstruction of spatial memory. However, this post-hoc and geometry-centric approach precludes agents from leveraging high-level semantic intelligence, often causing them to overlook navigationally critical landmarks (e.g., doorways and staircases) that serve as fundamental semantic anchors in human cognitive maps. To bridge this gap, we propose ABot-Explorer, a novel active exploration framework that unifies memory construction and exploration into an online, RGB-only process. At its core, ABot-Explorer leverages Large Vision-Language Models (VLMs) to distill Semantic Navigational Affordances (SNA), which act as cognitive-aligned anchors to guide the agent's movement. By dynamically integrating these SNAs into a hierarchical SG-Memo, ABot-Explorer mirrors human-like exploratory logic by prioritizing structural transit nodes to facilitate efficient coverage. To support this framework, we contribute a large-scale dataset extending InteriorGS with SNA and SG-Memo annotations. Experimental results demonstrate that ABot-Explorer significantly outperforms current state-of-the-art methods in both exploration efficiency and environment coverage, while the resulting SG-Memo is shown to effectively support diverse downstream tasks. |
| title | Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.19034 |