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

Wanrong Zheng, Yunhao Ge, Laurent Itti

TL;DR: We introduce Three-Step Nav, a zero-shot VLN planner that leverages forward, current, and backward views to reduce drift and achieve state-of-the-art navigation performance without finetuning.

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. We propose Three-Step Nav to counteract these failures with a three-view protocol: First, "look forward" to extract global landmarks and sketch a coarse plan. Then, "look now" to align the current visual observation with the next sub-goal for fine-grained guidance. Finally, "look backward" audits the entire trajectory to correct accumulated drift before stopping. Requiring no gradient updates or task-specific fine-tuning, our planner drops into existing VLN pipelines with minimal overhead. Three-Step Nav achieves state-of-the-art zero-shot performance on the R2R-CE and RxR-CE dataset.

Submission Number: 2087