An Efficient and Multi-Modal Navigation System with One-Step World Model

TL;DR

This paper introduces a lightweight, multi-modal navigation system with a one-step world model that significantly reduces inference latency, enabling real-time control and robust navigation in complex environments.

Contribution

The paper presents a novel one-step generation paradigm for world models using a 3D U-Net backbone, improving efficiency and enabling real-time multi-modal navigation.

Findings

Achieves high-frequency control with reduced latency.

Demonstrates superior navigation robustness in real-world tests.

Outperforms state-of-the-art baselines in efficiency and accuracy.

Abstract

Navigation is a fundamental capability for mobile robots. While the current trend is to use learning-based approaches to replace traditional geometry-based methods, existing end-to-end learning-based policies often struggle with 3D spatial reasoning and lack a comprehensive understanding of physical world dynamics. Integrating world models-which predict future observations conditioned on given actions-with iterative optimization planning offers a promising solution due to their capacity for imagination and flexibility. However, current navigation world models, typically built on pure transformer architectures, often rely on multi-step diffusion processes and autoregressive frame-by-frame generation. These mechanisms result in prohibitive computational latency, rendering real-time deployment impossible. To address this bottleneck, we propose a lightweight navigation world model that adopts a one-step generation paradigm and a 3D U-Net backbone equipped with efficient spatial-temporal attention. This design drastically reduces inference latency, enabling high-frequency control while achieving superior predictive performance. We also integrate this model into an optimization-based planning framework utilizing anchor-based initialization to handle multi-modal goal navigation tasks. Extensive closed-loop experiments in both simulation and real-world environments demonstrate our system's superior efficiency and robustness compared to state-of-the-art baselines.