Data Scaling for Navigation in Unknown Environments

TL;DR

This study demonstrates that large-scale, diverse crowd-sourced data significantly improves the zero-shot generalization of visual navigation policies in unknown environments, with simple models outperforming complex ones.

Contribution

It is the first large-scale analysis showing data diversity outweighs quantity in training effective navigation policies for unseen environments.

Findings

Data diversity reduces navigation errors more than data quantity.

Doubling geographical locations decreases errors by ~15%.

Simple regression models outperform complex architectures with noisy data.

Abstract

Generalization of imitation-learned navigation policies to environments unseen in training remains a major challenge. We address this by conducting the first large-scale study of how data quantity and data diversity affect real-world generalization in end-to-end, map-free visual navigation. Using a curated 4,565-hour crowd-sourced dataset collected across 161 locations in 35 countries, we train policies for point goal navigation and evaluate their closed-loop control performance on sidewalk robots operating in four countries, covering 125 km of autonomous driving. Our results show that large-scale training data enables zero-shot navigation in unknown environments, approaching the performance of policies trained with environment-specific demonstrations. Critically, we find that data diversity is far more important than data quantity. Doubling the number of geographical locations in a training set decreases navigation errors by ~15%, while performance benefit from adding data from existing locations saturates with very little data. We also observe that, with noisy crowd-sourced data, simple regression-based models outperform generative and sequence-based architectures. We release our policies, evaluation setup and example videos at https://lasuomela.github.io/navigation_scaling/.