Real-Time Instrument Planning and Perception for Novel Measurements of Dynamic Phenomena
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918135129440256 |
|---|---|
| author | Zilberstein, Itai Candela, Alberto Chien, Steve |
| author_facet | Zilberstein, Itai Candela, Alberto Chien, Steve |
| contents | Advancements in onboard computing mean remote sensing agents can employ state-of-the-art computer vision and machine learning at the edge. These capabilities can be leveraged to unlock new rare, transient, and pinpoint measurements of dynamic science phenomena. In this paper, we present an automated workflow that synthesizes the detection of these dynamic events in look-ahead satellite imagery with autonomous trajectory planning for a follow-up high-resolution sensor to obtain pinpoint measurements. We apply this workflow to the use case of observing volcanic plumes. We analyze classification approaches including traditional machine learning algorithms and convolutional neural networks. We present several trajectory planning algorithms that track the morphological features of a plume and integrate these algorithms with the classifiers. We show through simulation an order of magnitude increase in the utility return of the high-resolution instrument compared to baselines while maintaining efficient runtimes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03500 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-Time Instrument Planning and Perception for Novel Measurements of Dynamic Phenomena Zilberstein, Itai Candela, Alberto Chien, Steve Robotics Artificial Intelligence Advancements in onboard computing mean remote sensing agents can employ state-of-the-art computer vision and machine learning at the edge. These capabilities can be leveraged to unlock new rare, transient, and pinpoint measurements of dynamic science phenomena. In this paper, we present an automated workflow that synthesizes the detection of these dynamic events in look-ahead satellite imagery with autonomous trajectory planning for a follow-up high-resolution sensor to obtain pinpoint measurements. We apply this workflow to the use case of observing volcanic plumes. We analyze classification approaches including traditional machine learning algorithms and convolutional neural networks. We present several trajectory planning algorithms that track the morphological features of a plume and integrate these algorithms with the classifiers. We show through simulation an order of magnitude increase in the utility return of the high-resolution instrument compared to baselines while maintaining efficient runtimes. |
| title | Real-Time Instrument Planning and Perception for Novel Measurements of Dynamic Phenomena |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2509.03500 |