A Bio-Inspired Model for Robust Navigation Assistive Devices: A Proof of Concept

Abstract

This paper proposes an implementation and evaluation in a real-world environment of a new bio-inspired predictive navigation model for mobility control, suitable especially for visually impaired people. This model relies on the interactions between formal models of three types of neurons identified in the mammals’ brain implied in navigation tasks (namely place cells, grid cells, and head direction cells) to construct a topological model of the environment under the form of a decentralized navigation graph. The proposed model, previously tested in virtual environments, demonstrated a high tolerance to motion drift and robustness to environment changes. This paper presents an implementation of this navigation model, based on a stereoscopic camera, and evaluates its possibilities to map and guide a person in an unknown real environment. The evaluation results confirm the effectiveness of the proposed bio-inspired navigation model to build a path map and guide a person through this path, while remaining robust to environment changes, and estimating traveled distances with an error rate below 2% over test paths, up to 100 m. These results open the way toward efficient wearable assistive devices for visually impaired people navigation.