SysNav: Multi-Level Systematic Cooperation Enables Real-World, Cross-Embodiment Object Navigation

TL;DR

SysNav is a multi-level system that integrates vision-language models with hierarchical planning to enable reliable, efficient, and cross-embodiment object navigation in complex real-world environments.

Contribution

The paper introduces SysNav, a novel three-level system that decouples semantic reasoning, navigation, and motion control for real-world cross-embodiment object navigation.

Findings

Achieves high success rate and efficiency in real-world experiments across three embodiments.

Demonstrates state-of-the-art performance on four simulation benchmarks.

First system capable of building-scale long-range object navigation in complex environments.

Abstract

Object navigation (ObjectNav) in real-world environments is a complex problem that requires simultaneously addressing multiple challenges, including complex spatial structure, long-horizon planning and semantic understanding. Recent advances in Vision-Language Models (VLMs) offer promising capabilities for semantic understanding, yet effectively integrating them into real-world navigation systems remains a non-trivial challenge. In this work, we formulate real-world ObjectNav as a system-level problem and introduce SysNav, a three-level ObjectNav system designed for real-world crossembodiment deployment. SysNav decouples semantic reasoning, navigation planning and motion control to ensure robustness and generalizability. At the high-level, we summarize the environment into a structured scene representation and leverage VLMs to provide semantic-grounded navigation guidance. At the mid-level, we introduce a hierarchical room-based navigation strategy that reserves VLM guidance for room-level decisions, which effectively utilizes its reasoning ability while ensuring system efficiency. At the low-level, planned waypoints are executed through different embodiment-specific motion control modules. We deploy our system on three embodiments, a custom-built wheeled robot, the Unitree Go2 quadruped and the Unitree G1 humanoid, and conduct 190 real-world experiments. Our system achieves substantial improvements in both success rate and navigation efficiency. To the best of our knowledge, SysNav is the first system capable of reliably and efficiently completing building-scale long-range object navigation in complex real-world environments. Furthermore, extensive experiments on four simulation benchmarks demonstrate state-of-the-art performance. Project page is available at: https://cmu-vln.github.io/.