PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917070515470336 |
|---|---|
| author | Jin, Qunchao Wu, Yilin Chen, Changhao |
| author_facet | Jin, Qunchao Wu, Yilin Chen, Changhao |
| contents | Zero-shot object navigation (ZSON) in unseen environments remains a challenging problem for household robots, requiring strong perceptual understanding and decision-making capabilities. While recent methods leverage metric maps and Large Language Models (LLMs), they often depend on depth sensors or prebuilt maps, limiting the spatial reasoning ability of Multimodal Large Language Models (MLLMs). Mapless ZSON approaches have emerged to address this, but they typically make short-sighted decisions, leading to local deadlocks due to a lack of historical context. We propose PanoNav, a fully RGB-only, mapless ZSON framework that integrates a Panoramic Scene Parsing module to unlock the spatial parsing potential of MLLMs from panoramic RGB inputs, and a Memory-guided Decision-Making mechanism enhanced by a Dynamic Bounded Memory Queue to incorporate exploration history and avoid local deadlocks. Experiments on the public navigation benchmark show that PanoNav significantly outperforms representative baselines in both SR and SPL metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06840 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory Jin, Qunchao Wu, Yilin Chen, Changhao Computer Vision and Pattern Recognition Robotics Zero-shot object navigation (ZSON) in unseen environments remains a challenging problem for household robots, requiring strong perceptual understanding and decision-making capabilities. While recent methods leverage metric maps and Large Language Models (LLMs), they often depend on depth sensors or prebuilt maps, limiting the spatial reasoning ability of Multimodal Large Language Models (MLLMs). Mapless ZSON approaches have emerged to address this, but they typically make short-sighted decisions, leading to local deadlocks due to a lack of historical context. We propose PanoNav, a fully RGB-only, mapless ZSON framework that integrates a Panoramic Scene Parsing module to unlock the spatial parsing potential of MLLMs from panoramic RGB inputs, and a Memory-guided Decision-Making mechanism enhanced by a Dynamic Bounded Memory Queue to incorporate exploration history and avoid local deadlocks. Experiments on the public navigation benchmark show that PanoNav significantly outperforms representative baselines in both SR and SPL metrics. |
| title | PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2511.06840 |