Multi-Sensors System and Deep Learning Models for Object Tracking.

Autonomous navigation relies on the crucial aspect of perceiving the environment to ensure the safe navigation of an autonomous platform, taking into consideration surrounding objects and their potential movements. Consequently, a fundamental requirement arises to accurately track and predict these objects' trajectories. Three deep recurrent network architectures were defined to achieve this, fine-tuning their weights to optimize the tracking process. The effectiveness of this proposed pipeline has been assessed, with diverse tracking scenarios demonstrated in both sub-urban and highway environments. The evaluations have yielded promising results, affirming the potential of this approach in enhancing autonomous navigation capabilities.

LPMP: A Bio-Inspired Model for Visual Localization in Challenging Environments.

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 relying on the visual modality to recognize a place despite changes in the appearance of the perceived visual scene. In this paper, we propose to tackle the VPR problem following a neuro-cybernetic approach. To this end, the Log-Polar Max-Pi (LPMP) model is introduced. This bio-inspired neural network allows building a neural representation of the environment via an unsupervised one-shot learning. Inspired by the spatial cognition of mammals, visual information in the LPMP model are processed through two distinct pathways: a "what" pathway that extracts and learns the local visual signatures (landmarks) of a visual scene and a "where" pathway that computes their azimuth. These two pieces of information are then merged to build a visuospatial code that is characteristic of the place where the visual scene was perceived. Three main contributions are presented in this article: 1) the LPMP model is studied and compared with NetVLAD and CoHog, two state-of-the-art VPR models; 2) a test benchmark for the evaluation of VPR models according to the type of environment traveled is proposed based on the Oxford car dataset; and 3) the impact of the use of a novel detector leading to an uneven paving of an environment is evaluated in terms of the localization performance and compared to a regular paving. Our experiments show that the LPMP model can achieve comparable or better localization performance than NetVLAD and CoHog.