Autonomous vehicles require efficient self-localisation mechanisms and cameras are the
most common sensors due to their low cost and rich input. However, the computational …

This paper introduces a novel unsupervised neural network model for visual information
encoding which aims to address the problem of large-scale visual localization. Inspired by …

Neuroscience research shows that, by relying on internal spatial representations provided
by the hippocampus and entorhinal cortex, mammals are able to build topological maps of …

Autonomous vehicles require precise and reliable self-localization to cope with dynamic
environments. The field of visual place recognition (VPR) aims to solve this challenge by …

Autonomous vehicles heavily rely on efficient self-localisation mechanisms. Cameras are
the most common kind of sensors to perform this task: they provide a rich input at very low …

Efficient encoding of visual information is essential to the success of vision-based navigation
tasks in large-scale environments. To do so, we propose in this article the Sparse Max-Pi …

Robotic navigation requires complex algorithms to build an accurate and robust
representation of a spatial environment. These systems must therefore constantly be able to …