StepNav: Structured Trajectory Priors for Efficient and Multimodal Visual Navigation

TL;DR

StepNav introduces a structured, multimodal trajectory prior framework that improves the safety, efficiency, and robustness of visual navigation in complex environments by leveraging geometry-aware success probability fields and optimal control refinement.

Contribution

It presents a novel structured prior approach for trajectory generation that outperforms unstructured generative models in autonomous navigation tasks.

Findings

Safer and more efficient plans generated in fewer steps

Improved robustness and safety over state-of-the-art methods

Validated in both simulation and real-world benchmarks

Abstract

Visual navigation is fundamental to autonomous systems, yet generating reliable trajectories in cluttered and uncertain environments remains a core challenge. Recent generative models promise end-to-end synthesis, but their reliance on unstructured noise priors often yields unsafe, inefficient, or unimodal plans that cannot meet real-time requirements. We propose StepNav, a novel framework that bridges this gap by introducing structured, multimodal trajectory priors derived from variational principles. StepNav first learns a geometry-aware success probability field to identify all feasible navigation corridors. These corridors are then used to construct an explicit, multi-modal mixture prior that initializes a conditional flow-matching process. This refinement is formulated as an optimal control problem with explicit smoothness and safety regularization. By replacing unstructured noise with physically-grounded candidates, StepNav generates safer and more efficient plans in significantly fewer steps. Experiments in both simulation and real-world benchmarks demonstrate consistent improvements in robustness, efficiency, and safety over state-of-the-art generative planners, advancing reliable trajectory generation for practical autonomous navigation. The code has been released at https://github.com/LuoXubo/StepNav.