ARTPS: Depth-Enhanced Hybrid Anomaly Detection and Learnable Curiosity Score for Autonomous Rover Target Prioritization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Baydemir, Poyraz
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916925818273792
author Baydemir, Poyraz
author_facet Baydemir, Poyraz
contents We present ARTPS (Autonomous Rover Target Prioritization System), a novel hybrid AI system that combines depth estimation, anomaly detection, and learnable curiosity scoring for autonomous exploration of planetary surfaces. Our approach integrates monocular depth estimation using Vision Transformers with multi-component anomaly detection and a weighted curiosity score that balances known value, anomaly signals, depth variance, and surface roughness. The system achieves state-of-the-art performance with AUROC of 0.94, AUPRC of 0.89, and F1-Score of 0.87 on Mars rover datasets. We demonstrate significant improvements in target prioritization accuracy through ablation studies and provide comprehensive analysis of component contributions. The hybrid fusion approach reduces false positives by 23% while maintaining high detection sensitivity across diverse terrain types.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00042
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ARTPS: Depth-Enhanced Hybrid Anomaly Detection and Learnable Curiosity Score for Autonomous Rover Target Prioritization
Baydemir, Poyraz
Computer Vision and Pattern Recognition
Artificial Intelligence
68T45, 68T07, 68U10
I.2.10; I.4.8; I.5.4; J.2
We present ARTPS (Autonomous Rover Target Prioritization System), a novel hybrid AI system that combines depth estimation, anomaly detection, and learnable curiosity scoring for autonomous exploration of planetary surfaces. Our approach integrates monocular depth estimation using Vision Transformers with multi-component anomaly detection and a weighted curiosity score that balances known value, anomaly signals, depth variance, and surface roughness. The system achieves state-of-the-art performance with AUROC of 0.94, AUPRC of 0.89, and F1-Score of 0.87 on Mars rover datasets. We demonstrate significant improvements in target prioritization accuracy through ablation studies and provide comprehensive analysis of component contributions. The hybrid fusion approach reduces false positives by 23% while maintaining high detection sensitivity across diverse terrain types.
title ARTPS: Depth-Enhanced Hybrid Anomaly Detection and Learnable Curiosity Score for Autonomous Rover Target Prioritization
topic Computer Vision and Pattern Recognition
Artificial Intelligence
68T45, 68T07, 68U10
I.2.10; I.4.8; I.5.4; J.2
url https://arxiv.org/abs/2509.00042