Anne Verroust-Blondet

Institut national de recherche en sciences et technologies du numérique, ITS (United Kingdom)

Papers

Total Citations

H-Index

About

Anne Verroust-Blondet is a researcher whose work sits at the intersection of autonomous robotics, mobile perception, and environmental mapping. Her primary contributions span Simultaneous Localization and Mapping (SLAM), 3D scene understanding, and motion planning — core challenges in building truly autonomous mobile systems capable of operating in complex, real-world environments. Her most influential work focuses on the reliability and robustness of SLAM systems. Her 2017 paper on failure detection for laser-based SLAM in urban and peri-urban environments (21 citations) addresses a critical gap: ensuring that autonomous robots can recognize when their localization is failing — a prerequisite for safe deployment. This was complemented by her 2018 work on SLAM correction prediction in large-scale urban environments (10 citations), which tackles the practical limitations of probabilistic SLAM models. Verroust-Blondet has also contributed to 3D semantic scene completion through LMSCNet (2020), a lightweight multiscale architecture leveraging LiDAR data that demonstrates strong performance on the SemanticKITTI benchmark. Additional work on dynamic obstacle avoidance and statistical occupancy grid modeling further reflects her broad expertise in robot perception and environmental representation — research areas essential to the future of autonomous navigation.