Active Exploration for VLM-Guided Anomaly Inspection using a UAV

Master Thesis (2026)
Author(s)

T.L. van der Wal (TU Delft - Aerospace Engineering)

Contributor(s)

E.J.J. Smeur – Graduation committee member (TU Delft - Control & Simulation)

M. Popovic – Mentor (TU Delft - Control & Simulation)

Hermann Blum – Mentor (Universität Bonn)

C. Della Santina – Graduation committee member (TU Delft - Learning & Autonomous Control)

More Info
expand_more
Publication Year
2026
Language
English
Graduation Date
19-03-2026
Awarding Institution
Programme
Aerospace Engineering, Control & Simulation
Downloads counter
14
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Autonomous exploration by drones in unknown environments has traditionally focused on maximizing spatial coverage without semantic understanding. This thesis presents a framework that integrates vision-language models (VLMs) with adaptive path planning to enable anomaly-aware exploration and inspection. The system employs a three-phase approach: frontier-based exploration, continuous VLM-based anomaly detection, and inspection of detected anomalies. Comparative experiments demonstrated that YOLO+CLIP with negative embeddings achieved the highest F1 score of 0.7218 on the SegmentifyMeIfYouCan benchmark. Experiments showed that dedicated inspection yielded improvements over solely exploration observations. However, system-level evaluation across nine experimental runs revealed that the inspection phase took up most of the mission time (85.9% average), with varying anomaly detection consistency across anomaly instances. False positive analysis identified VLM error as the primary limitation (52% of false positives), followed by simulation artifacts (37%) and semantic ambiguity (11%). The framework successfully demonstrated the feasibility of coupling VLM-based anomaly detection with adaptive planning, though precision limitations and large inspection inefficiencies show opportunities for future work.

Files

License info not available