Low-level Active Visual Navigation: Increasing robustness of vision-based localization using potential fields

TL;DR

This paper introduces a low-level visual navigation method using potential fields to enhance localization robustness in mobile robots, especially suitable for resource-constrained aerial robots, demonstrated through simulations and real-world tests.

Contribution

The paper presents a novel potential field-based visual navigation algorithm that does not require mapping, enabling lightweight and robust localization for mini aerial robots.

Findings

Effective in guiding robots to goals while avoiding localization failure

Works with minimal computational resources and no mapping requirement

Validated through simulations and real quadrotor experiments

Abstract

This paper proposes a low-level visual navigation algorithm to improve visual localization of a mobile robot. The algorithm, based on artificial potential fields, associates each feature in the current image frame with an attractive or neutral potential energy, with the objective of generating a control action that drives the vehicle towards the goal, while still favoring feature rich areas within a local scope, thus improving the localization performance. One key property of the proposed method is that it does not rely on mapping, and therefore it is a lightweight solution that can be deployed on miniaturized aerial robots, in which memory and computational power are major constraints. Simulations and real experimental results using a mini quadrotor equipped with a downward looking camera demonstrate that the proposed method can effectively drive the vehicle to a designated goal through a path that prevents localization failure.