Bounomodes: the grazing ox algorithm for exploration of clustered anomalies
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_ | 1866911047639629824 |
|---|---|
| author | Matloob, Samuel Dutta, Ayan Kreidl, O. Patrick Roy, Swapnonel Bölöni, Ladislau |
| author_facet | Matloob, Samuel Dutta, Ayan Kreidl, O. Patrick Roy, Swapnonel Bölöni, Ladislau |
| contents | A common class of algorithms for informative path planning (IPP) follows boustrophedon ("as the ox turns") patterns, which aim to achieve uniform area coverage. However, IPP is often applied in scenarios where anomalies, such as plant diseases, pollution, or hurricane damage, appear in clusters. In such cases, prioritizing the exploration of anomalous regions over uniform coverage is beneficial. This work introduces a class of algorithms referred to as bounomōdes ("as the ox grazes"), which alternates between uniform boustrophedon sampling and targeted exploration of detected anomaly clusters. While uniform sampling can be designed using geometric principles, close exploration of clusters depends on the spatial distribution of anomalies and must be learned. In our implementation, the close exploration behavior is learned using deep reinforcement learning algorithms. Experimental evaluations demonstrate that the proposed approach outperforms several established baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06960 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bounomodes: the grazing ox algorithm for exploration of clustered anomalies Matloob, Samuel Dutta, Ayan Kreidl, O. Patrick Roy, Swapnonel Bölöni, Ladislau Robotics A common class of algorithms for informative path planning (IPP) follows boustrophedon ("as the ox turns") patterns, which aim to achieve uniform area coverage. However, IPP is often applied in scenarios where anomalies, such as plant diseases, pollution, or hurricane damage, appear in clusters. In such cases, prioritizing the exploration of anomalous regions over uniform coverage is beneficial. This work introduces a class of algorithms referred to as bounomōdes ("as the ox grazes"), which alternates between uniform boustrophedon sampling and targeted exploration of detected anomaly clusters. While uniform sampling can be designed using geometric principles, close exploration of clusters depends on the spatial distribution of anomalies and must be learned. In our implementation, the close exploration behavior is learned using deep reinforcement learning algorithms. Experimental evaluations demonstrate that the proposed approach outperforms several established baselines. |
| title | Bounomodes: the grazing ox algorithm for exploration of clustered anomalies |
| topic | Robotics |
| url | https://arxiv.org/abs/2507.06960 |