Lucia Migliorelli

Papers

Total Citations

H-Index

About

Lucia Migliorelli’s research lies at the intersection of assistive robotics and deep learning, with a focused mission to enhance rehabilitation technologies for mobility-impaired individuals. Her work centers on developing intelligent, real-time systems that decode human motion to improve the functionality and safety of smart walkers. Migliorelli’s most-cited paper, “Real-time human pose estimation on a smart walker using convolutional neural networks” (2021, 34 citations), introduced a novel approach to integrating lightweight CNNs directly into walker platforms, enabling instantaneous pose tracking without external sensors. This breakthrough was further extended in her 2023 study, “Deep learning-based approaches for human motion decoding in smart walkers for rehabilitation” (23 citations), which refined motion decoding algorithms to better support personalized rehabilitation protocols. Her contributions are notable for bridging the gap between high-accuracy computer vision and practical, low-latency assistive devices—a critical step toward autonomous, adaptive walking aids. By prioritizing real-time performance and clinical applicability, Migliorelli’s work has laid a foundation for next-generation rehabilitation tools that can respond intuitively to user intent, offering both quantitative and qualitative improvements in patient outcomes.