Constrained Multi-Objective Bayesian Optimization for Unmanned Ground Vehicle-Oriented Detection Models
El-Cezeri Fen ve Mühendislik Dergisi · 30.06.2026 · (Advanced Online Publication) · 271-283
DOI: 10.31202/ecjse.1970237 ↗Kurz gefasst
Fachartikel in der Zeitschrift El-Cezeri Fen ve Mühendislik Dergisi, online erschienen am 30.06.2026. Verfasst von Koray Açıcı und 5 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben.
Abstract (Originalsprache)
Reliable perception of non-NATO armored vehicles is fundamental for Unmanned Ground Vehicle (UGV) operations in safety-critical, time-constrained environments. This study proposes a UGV-oriented framework integrating lightweight You Only Look Once (YOLO) architectures with a constrained multi-objective Bayesian optimization strategy. An original hybrid dataset of 10,640 ground-level images was constructed, featuring tanks, armored personnel carrier (APCs) main battle tank (MBT), self-propelled howitzers, and hard-negatives, excluding aerial views for domain consistency. Quantitative evaluation shows YOLOv9s achieves the highest accuracy reaching 97.33% mAP@50 and 0.8478 mAP@50–95, while maintaining a high recall of 92.11% and the highest Matthews Correlation Coefficient (MCC) score (0.8312). YOLO11s provides the highest sensitivity with a recall of 92.75%, whereas YOLOv5su delivers the lowest latency (13.82 ms) and highest throughput (72.4 FPS), highlighting critical trade-offs between detection accuracy and computational efficiency. To address accuracy-efficiency trade-offs, a Multi-Objective Tree-structured Parzen Estimator (MOTPE) based Bayesian optimization framework yielded Pareto-optimal configurations for Ambush, Reconnaissance, and Balanced mission modes. This approach enables adaptive, hardware-aware model selection while preserving mission-critical detection performance.
Zitieren
APA
Açıcı, K., Kökver, Y., Çatalca, H. H., Demir, Ö., Ekinci, F., & Güzel, M. S. (2026). Constrained Multi-Objective Bayesian Optimization for Unmanned Ground Vehicle-Oriented Detection Models. El-Cezeri Fen ve Mühendislik Dergisi, 271-283. https://doi.org/10.31202/ecjse.1970237
Vancouver
Açıcı K, Kökver Y, Çatalca HH, Demir Ö, Ekinci F, Güzel MS. Constrained Multi-Objective Bayesian Optimization for Unmanned Ground Vehicle-Oriented Detection Models. El-Cezeri Fen ve Mühendislik Dergisi. 2026:271-283. doi:10.31202/ecjse.1970237
BibTeX
@article{Ac2026,
author = {Açıcı, Koray and Kökver, Yunus and Çatalca, Hamza Halit and Demir, Özge and Ekinci, Fatih and Güzel, Mehmet Serdar},
title = {Constrained Multi-Objective Bayesian Optimization for Unmanned Ground Vehicle-Oriented Detection Models},
journal = {El-Cezeri Fen ve Mühendislik Dergisi},
year = {2026},
number = {Advanced Online Publication},
pages = {271--283},
doi = {10.31202/ecjse.1970237}
}
EUVIMED