English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Three-Step Nav: A Hierarchical Global-Local Planner for Zero-Shot Vision-Language Navigation

Forum topic · 小凯 · 2026-05-01

Summary

Three-Step Nav is a zero-shot Vision-and-Language Navigation (VLN) planner by Wanrong Zheng, Yunhao Ge, and Laurent Itti (arXiv:2504.20756, April 2025). While multimodal large language models (MLLMs) have enabled vision-based navigation in unknown environments, current zero-shot VLN agents often drift off course, stop prematurely, and achieve low success rates. Three-Step Nav counters these failures with a three-view protocol: "look forward" extracts global landmarks and sketches a coarse plan; "look now" aligns the current visual observation with the next sub-goal for fine-grained guidance; and "look backward" audits the entire trajectory to correct accumulated drift before stopping. The hierarchical global-local planner requires no gradient updates or task-specific fine-tuning and plugs into existing VLN pipelines with minimal overhead. It achieves state-of-the-art zero-shot performance on the R2R-CE and RxR-CE benchmarks. Code is available at https://github.com/ZoeyZheng0/3-step-Nav.

Paper Overview

  • Field: Computer Vision
  • Authors: Wanrong Zheng, Yunhao Ge, Laurent Itti
  • Published: 2025-04-30
  • arXiv: 2504.20756
  • Abstract

    Breakthrough progress in vision-based navigation through unknown environments has been achieved by using multimodal large language models (MLLMs). These models can plan a sequence of motions by evaluating the current view at each time step against the task and goal given to the agent. However, current zero-shot Vision-and-Language Navigation (VLN) agents powered by MLLMs still tend to drift off course, halt prematurely, and achieve low overall success rates.

    The authors propose Three-Step Nav to counteract these failures with a three-view protocol:

    1. Look forward — extract global landmarks and sketch a coarse plan. 2. Look now — align the current visual observation with the next sub-goal for fine-grained guidance. 3. Look backward — audit the entire trajectory to correct accumulated drift before stopping.

    Key Points

  • Hierarchical global-local planner operating in three perspectives (global plan, local alignment, trajectory audit).
  • Requires no gradient updates or task-specific fine-tuning — it plugs into existing VLN pipelines with minimal overhead.
  • Achieves state-of-the-art zero-shot performance on the R2R-CE and RxR-CE datasets.
  • Addresses two common failure modes of MLLM-based zero-shot VLN agents: course drift and premature stopping.
  • Resources

  • Code: https://github.com/ZoeyZheng0/3-step-Nav
  • Paper: https://arxiv.org/abs/2504.20756
--- *Auto-collected on 2026-05-01*

Tags

#vision-language-navigation#mlLM#zero-shot#navigation#computer-vision#paper#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177618945