Max Robotics — Global Service Robot Directory + US Certification

About

Diana Davletshina is a researcher at the forefront of intelligent infrastructure monitoring, specializing in computer vision, robotics, and deep learning for pavement assessment. Her work centers on developing lightweight, deployable neural networks for autonomous crack detection and measurement—a critical challenge in civil infrastructure maintenance. In her most influential paper, “Segment-to-track for pavement crack with light-weight neural network on unmanned wheeled robot” (2024, 28 citations), she introduced a novel framework enabling real-time crack segmentation and tracking directly on mobile robots. She further advanced this line of research with “Crack segmentation-guided measurement with lightweight distillation network on edge device” (2025, 23 citations), demonstrating how knowledge distillation can compress models for efficient edge deployment. Davletshina also contributed to robust control systems in “Robust ELM-PID tracing control on autonomous mobile robot via transformer-based pavement crack segmentation” (2024, 17 citations). Notably, she co-created the CAMHighways dataset (2024, 8 citations), a comprehensive resource featuring over 40 km of UK highway data—including textured meshes, segmented point clouds, and orthomosaics—that serves as a benchmark for road asset analysis. Her work bridges the gap between cutting-edge AI and practical, field-deployable solutions for infrastructure health monitoring.