Robust Multi-modal Place Recognition for Unstructured Environments via Geometric Priors

DirectorRiccardo Giubilato
PonenteCIVERA SANCHO, JAVIER
Titulaciones
Master Universitario en Robótica, Gráficos y Visión por Computador
Máster Universitario en Ingeniería Electrónica
Máster Universitario en Ingeniería Industrial
Máster Universitario en Ingeniería Informática
DuracionTBD
LugarMunich
Fecha Alta2026-04-19
Fecha Baja2027-04-19
ResumenReliable global localization and loop-closure detection are fundamental requirements for autonomous navigation in remote and unstructured environments, such as volcanic craters or planetary surfaces. While Visual Place Recognition (VPR) has seen significant progress in urban settings, traditional methods often struggle in natural terrains where perceptual aliasing (repetitive patterns) conditions are prevalent. This thesis aims to investigate how multi-modal sensor data, specifically the combination of visual and LiDAR data, can be leveraged to prioritize stable, high-fidelity geometric features. You will explore how to intelligently fuse these modalities to achieve robust localization, even when faced with sensor-specific limitations such as disparate fields of view (FOV) and varying sensing ranges. See the link for all the information: https://www.dlr.de/de/rm/jobs/studentische-arbeiten/masters-thesis-robust-multi-modal-place-recognition-for-unstructured-environments-via-geometric-priors
Detalles/ContactoThe master thesis will be done in DLR, Munich. DLR stands for Deutsches Zentrum für Luft- und Raumfahrt, which can be roughly translated as German Aerospace Center. Its main mission is the exploration of the Earth and the solar system, having the 2nd biggest budget for civilian space programs, only after NASA. The internship will be done in the Institute of Robotics and Mechatronics https://www.dlr.de/en/rm, in the Perception and Cognition department https://www.dlr.de/en/rm/about-us/departments/perception-and-cognition. Funding available. There will be a selection process by the DLR staff. The work developed will be research-oriented, ideally leading to a scientific publication (this is for example the output of a former internship + master thesis https://arxiv.org/pdf/2010.00052.pdf, https://youtu.be/9hWChyQGKJk). Contact: Javier Civera -> jcivera@unizar.es
Volver