Scaling Local Control to Large-Scale Topological Navigation

TL;DR

This paper introduces a scalable and robust approach to large-scale visual topological navigation by accurately measuring local controller capabilities, achieving state-of-the-art results and good generalization to real robots and environments.

Contribution

It presents a novel method for scaling local control in topological navigation, addressing challenges of complexity and ambiguity in real-world images.

Findings

Achieves state-of-the-art trajectory following and planning in large environments.

Generalizes well to real robots and new environments without retraining.

Demonstrates robustness and scalability in visual topological navigation.

Abstract

Visual topological navigation has been revitalized recently thanks to the advancement of deep learning that substantially improves robot perception. However, the scalability and reliability issue remain challenging due to the complexity and ambiguity of real world images and mechanical constraints of real robots. We present an intuitive solution to show that by accurately measuring the capability of a local controller, large-scale visual topological navigation can be achieved while being scalable and robust. Our approach achieves state-of-the-art results in trajectory following and planning in large-scale environments. It also generalizes well to real robots and new environments without retraining or finetuning.