PhD Research Proposal
« MMW radar and optical camera fusion architecture for mobile robot perception in poorly structured environments and adverse weather conditions. »
Scientific field, context and objective.
The work proposed in this thesis focuses on enhancing mobile robot perception using mmW (millimeter wave) radar sensors combined with RGB optical cameras. The objective is to develop methods for accurate 3D environmental perception and robust semantic and panoptic segmentation, especially in challenging conditions like dust, rain, fog, and snow. Traditional LiDAR and camera data fusion techniques struggle under such conditions; hence, this research aims to leverage the complementary strengths of radar and RGB modalities.
Laboratory: Université Clermont-Auvergne,Institut Pascal (UMR 6602 CNRS/UCA/SIGMA), ISPR research group (Images, Perception Systems and Robotics).
PhD Research Proposal
« MMW radar and optical camera fusion architecture for mobile robot perception in poorly structured environments and adverse weather conditions. »
Keywords: MMW Radar, computer vision, robotics, artificial perception, deep learning, adverse weather conditions, unstructured environments
Scientific field, context and objective.
The work proposed in this thesis focuses on enhancing mobile robot perception using mmW (millimeter wave) radar sensors combined with RGB optical cameras. The objective is to develop methods for accurate 3D environmental perception and robust semantic and panoptic segmentation, especially in challenging conditions like dust, rain, fog, and snow. Traditional LiDAR and camera data fusion techniques struggle under such conditions; hence, this research aims to leverage the complementary strengths of radar and RGB modalities. The candidate will develop neural network architectures capable of semantically and geometrically precise segmentation from combined radar scans and RGB images, addressing the challenge of aligning data from sensors with different viewpoints and modalities.
The use of radar will enhance the capabilities of these existing sensors as part of a varied "sensor suite" for vehicles. Integrating information from several types of sensor will overcome the weaknesses of individual approaches, ensure redundancy and, ultimately, make vehicles safer and increasingly autonomous.
Laboratory: Université Clermont-Auvergne,Institut Pascal (UMR 6602 CNRS/UCA/SIGMA), ISPR research group (Images, Perception Systems and Robotics).
https://cap2025.fr/medias/fichier/phdproposal-radargb_1705920874774-pdf?ID_FICHE=159675&INLINE=FALSE
(c) GdR IASIS - CNRS - 2024.