SyNeT: Synthetic Negatives for Traversability Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908807436697600 |
|---|---|
| author | Kim, Bomena Lee, Hojun Park, Younsoo Hu, Yaoyu Scherer, Sebastian Shim, Inwook |
| author_facet | Kim, Bomena Lee, Hojun Park, Younsoo Hu, Yaoyu Scherer, Sebastian Shim, Inwook |
| contents | Reliable traversability estimation is crucial for autonomous robots to navigate complex outdoor environments safely. Existing self-supervised learning frameworks primarily rely on positive and unlabeled data; however, the lack of explicit negative data remains a critical limitation, hindering the model's ability to accurately identify diverse non-traversable regions. To address this issue, we introduce a method to explicitly construct synthetic negatives, representing plausible but non-traversable, and integrate them into vision-based traversability learning. Our approach is formulated as a training strategy that can be seamlessly integrated into both Positive-Unlabeled (PU) and Positive-Negative (PN) frameworks without modifying inference architectures. Complementing standard pixel-wise metrics, we introduce an object-centric FPR evaluation approach that analyzes predictions in regions where synthetic negatives are inserted. This evaluation provides an indirect measure of the model's ability to consistently identify non-traversable regions without additional manual labeling. Extensive experiments on both public and self-collected datasets demonstrate that our approach significantly enhances robustness and generalization across diverse environments. The source code and demonstration videos will be publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00814 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SyNeT: Synthetic Negatives for Traversability Learning Kim, Bomena Lee, Hojun Park, Younsoo Hu, Yaoyu Scherer, Sebastian Shim, Inwook Robotics Computer Vision and Pattern Recognition Reliable traversability estimation is crucial for autonomous robots to navigate complex outdoor environments safely. Existing self-supervised learning frameworks primarily rely on positive and unlabeled data; however, the lack of explicit negative data remains a critical limitation, hindering the model's ability to accurately identify diverse non-traversable regions. To address this issue, we introduce a method to explicitly construct synthetic negatives, representing plausible but non-traversable, and integrate them into vision-based traversability learning. Our approach is formulated as a training strategy that can be seamlessly integrated into both Positive-Unlabeled (PU) and Positive-Negative (PN) frameworks without modifying inference architectures. Complementing standard pixel-wise metrics, we introduce an object-centric FPR evaluation approach that analyzes predictions in regions where synthetic negatives are inserted. This evaluation provides an indirect measure of the model's ability to consistently identify non-traversable regions without additional manual labeling. Extensive experiments on both public and self-collected datasets demonstrate that our approach significantly enhances robustness and generalization across diverse environments. The source code and demonstration videos will be publicly available. |
| title | SyNeT: Synthetic Negatives for Traversability Learning |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.00814 |