PhD in Multi-modal AI for UAV-based Structural Defect Analysis Eindhoven University of Technology in Netherlands

The Eindhoven University of Technology invites applications for a PhD position in Multi-modal AI for UAV-based Structural Defect Analysis, as part of the international STRUCTURE project. This research aims to advance the inspection and maintenance of critical transportation infrastructure by integrating advanced AI techniques with heterogeneous UAV-based sensor data. The project is a collaboration with industrial partners across Europe, focusing on automating and enhancing the inspection of bridges and viaducts using multi-modal sensing, autonomous UAV platforms, and AI-based analysis.

The PhD candidate will develop AI models capable of combining diverse sensor modalities, including RGB, thermal, LiDAR, acoustic arrays, GPR, and X-ray backscatter, to create unified and reliable representations of structural integrity. The research will involve constructing robust feature extraction pipelines, attention-based fusion architectures, and deep learning models for the detection and classification of defects such as cracks, voids, delamination, corrosion, and internal structural discontinuities. Vision Language Models, multi-modal AI solutions, and 3D scene reasoning approaches will be explored to achieve spatial understanding and cross-modal representation learning from heterogeneous sensor data. The work supports semantic interpretation, defect localization, temporal reasoning, and predictive maintenance in complex inspection environments.

Another key contribution is the development of predictive maintenance algorithms that integrate static data sources (geological maps, material properties, usage profiles) with dynamic sensor measurements (pressure, vibration, visual, acoustic, and X-ray signals). The candidate will investigate temporal modeling, multimodal analysis, and risk progression modeling to forecast deterioration patterns and estimate the remaining useful lifetime of infrastructure components. Model compression and optimization for edge deployment on UAV-mounted processors will be addressed to enable real-time inference.

The PhD student will join the AIMS laboratory within the Signal Processing Systems (SPS) group in the Department of Electrical Engineering at TU/e. The AIMS lab specializes in AI models for systems equipped with sensors of multiple modalities, with expertise in AI analysis of RGB, thermal, depth, LiDAR, acoustic, sonar, and radar sensor data, 3D reconstruction, and Edge AI for resource-constrained deployments. The research environment is interdisciplinary and international, offering collaboration with industrial partners for real-world data acquisition and large-scale validation on operational infrastructure.

Applicants must have a master’s degree in Electrical Engineering, Computer Science, Artificial Intelligence, or a closely related discipline, with experience in deep learning frameworks (e.g., PyTorch), machine learning, image or signal processing, and multi-modal sensor data. Fluency in English (C1 level) is required. The position offers full-time employment for four years, competitive salary and benefits, high-quality training programs, and support for international candidates. The application deadline is April 16, 2026. For further information, contact Dr.ir. Egor Bondarev ([email protected]) or Dr. Erkut Akdag ([email protected]).

To apply, submit a cover letter, CV with publications, and contact information for three references via the online application portal. Priority is given to complete applications. The vacancy will remain open until filled.