Learning to Drive Anywhere with Model-Based Reannotation

TL;DR

This paper introduces Model-Based Reannotation (MBRA), a framework that leverages passive data sources like crowd-sourced teleoperation and YouTube videos to train robust visual navigation policies, achieving state-of-the-art results in diverse environments.

Contribution

The paper presents MBRA, a novel method for relabeling passive datasets with a learned model, enabling training of generalizable navigation policies from large-scale unannotated data.

Findings

LogoNav achieves state-of-the-art performance in long-distance navigation.

Policies generalize well across indoor and outdoor environments.

Robust navigation demonstrated in crowded urban settings across multiple cities.

Abstract

Developing broadly generalizable visual navigation policies for robots is a significant challenge, primarily constrained by the availability of large-scale, diverse training data. While curated datasets collected by researchers offer high quality, their limited size restricts policy generalization. To overcome this, we explore leveraging abundant, passively collected data sources, including large volumes of crowd-sourced teleoperation data and unlabeled YouTube videos, despite their potential for lower quality or missing action labels. We propose Model-Based ReAnnotation (MBRA), a framework that utilizes a learned short-horizon, model-based expert model to relabel or generate high-quality actions for these passive datasets. This relabeled data is then distilled into LogoNav, a long-horizon navigation policy conditioned on visual goals or GPS waypoints. We demonstrate that LogoNav, trained using MBRA-processed data, achieves state-of-the-art performance, enabling robust navigation over distances exceeding 300 meters in previously unseen indoor and outdoor environments. Our extensive real-world evaluations, conducted across a fleet of robots (including quadrupeds) in six cities on three continents, validate the policy's ability to generalize and navigate effectively even amidst pedestrians in crowded settings.