GeNIE: A Generalizable Navigation System for In-the-Wild Environments
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_ | 1866912658816499712 |
|---|---|
| author | Wang, Jiaming Liu, Diwen Chen, Jizhuo Da, Jiaxuan Qian, Nuowen Man, Tram Minh Soh, Harold |
| author_facet | Wang, Jiaming Liu, Diwen Chen, Jizhuo Da, Jiaxuan Qian, Nuowen Man, Tram Minh Soh, Harold |
| contents | Reliable navigation in unstructured, real-world environments remains a significant challenge for embodied agents, especially when operating across diverse terrains, weather conditions, and sensor configurations. In this paper, we introduce GeNIE (Generalizable Navigation System for In-the-Wild Environments), a robust navigation framework designed for global deployment. GeNIE integrates a generalizable traversability prediction model built on SAM2 with a novel path fusion strategy that enhances planning stability in noisy and ambiguous settings. We deployed GeNIE in the Earth Rover Challenge (ERC) at ICRA 2025, where it was evaluated across six countries spanning three continents. GeNIE took first place and achieved 79% of the maximum possible score, outperforming the second-best team by 17%, and completed the entire competition without a single human intervention. These results set a new benchmark for robust, generalizable outdoor robot navigation. We will release the codebase, pretrained model weights, and newly curated datasets to support future research in real-world navigation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_17960 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GeNIE: A Generalizable Navigation System for In-the-Wild Environments Wang, Jiaming Liu, Diwen Chen, Jizhuo Da, Jiaxuan Qian, Nuowen Man, Tram Minh Soh, Harold Robotics Artificial Intelligence Reliable navigation in unstructured, real-world environments remains a significant challenge for embodied agents, especially when operating across diverse terrains, weather conditions, and sensor configurations. In this paper, we introduce GeNIE (Generalizable Navigation System for In-the-Wild Environments), a robust navigation framework designed for global deployment. GeNIE integrates a generalizable traversability prediction model built on SAM2 with a novel path fusion strategy that enhances planning stability in noisy and ambiguous settings. We deployed GeNIE in the Earth Rover Challenge (ERC) at ICRA 2025, where it was evaluated across six countries spanning three continents. GeNIE took first place and achieved 79% of the maximum possible score, outperforming the second-best team by 17%, and completed the entire competition without a single human intervention. These results set a new benchmark for robust, generalizable outdoor robot navigation. We will release the codebase, pretrained model weights, and newly curated datasets to support future research in real-world navigation. |
| title | GeNIE: A Generalizable Navigation System for In-the-Wild Environments |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2506.17960 |