UrbanVLA: A Vision-Language-Action Model for Urban Micromobility

TL;DR

UrbanVLA is a scalable vision-language-action model that enables reliable urban micromobility navigation by aligning route waypoints with visual observations and employing a two-stage training pipeline, outperforming existing methods.

Contribution

The paper introduces UrbanVLA, a novel route-conditioned VLA framework with a two-stage training process for scalable and robust urban navigation in micromobility applications.

Findings

UrbanVLA surpasses baselines by over 55% in SocialNav tasks.

It achieves reliable real-world navigation in large-scale urban environments.

The model demonstrates robustness against real-world uncertainties.

Abstract

Urban micromobility applications, such as delivery robots, demand reliable navigation across large-scale urban environments while following long-horizon route instructions. This task is particularly challenging due to the dynamic and unstructured nature of real-world city areas, yet most existing navigation methods remain tailored to short-scale and controllable scenarios. Effective urban micromobility requires two complementary levels of navigation skills: low-level capabilities such as point-goal reaching and obstacle avoidance, and high-level capabilities, such as route-visual alignment. To this end, we propose UrbanVLA, a route-conditioned Vision-Language-Action (VLA) framework designed for scalable urban navigation. Our method explicitly aligns noisy route waypoints with visual observations during execution, and subsequently plans trajectories to drive the robot. To enable UrbanVLA to master both levels of navigation, we employ a two-stage training pipeline. The process begins with Supervised Fine-Tuning (SFT) using simulated environments and trajectories parsed from web videos. This is followed by Reinforcement Fine-Tuning (RFT) on a mixture of simulation and real-world data, which enhances the model's safety and adaptability in real-world settings. Experiments demonstrate that UrbanVLA surpasses strong baselines by more than 55% in the SocialNav task on MetaUrban. Furthermore, UrbanVLA achieves reliable real-world navigation, showcasing both scalability to large-scale urban environments and robustness against real-world uncertainties.