Guiding Vector Field Generation via Score-based Diffusion Model

TL;DR

This paper introduces SGVF, a novel framework that uses score-based diffusion models to generate guiding vector fields directly from data, enabling robust robotic path following on complex, multi-branch paths.

Contribution

The paper presents a unified, data-driven approach to generate guiding vector fields for complex paths, overcoming limitations of classical methods that require smooth, ordered curves.

Findings

SGVF effectively handles multi-branch and probabilistic paths.

It achieves reliable path following where classical GVFs fail.

Code and experiments are available at the provided GitHub link.

Abstract

Guiding Vector Fields (GVFs) are a powerful tool for robotic path following. However, classical methods assume smooth, ordered curves and fail when paths are unordered, multi-branch, or generated by probabilistic models. We propose a unified framework, termed the Score-Induced Guiding Vector Field (SGVF), which leverages score-based generative modeling to construct vector fields directly from data distributions. SGVF learns tangent fields from point clouds with unit-norm, orthogonality, and directional-consistency losses, ensuring geometric fidelity and control feasibility. This approach removes the reliance on ad-hoc path segmentation and enables guidance along complex topologies such as branching and pseudo-manifolds. The study establishes a correspondence between score vanishing in diffusion models and GVF singularities and highlights representational capacity near sharp path curvatures. Experiments on robotic navigation in planar environments demonstrate that SGVF achieves reliable path following in scenarios where classical GVFs fail, underscoring its potential as a bridge between generative modeling and geometric control. Code and experiment video are available at https://github.com/czr-gif/Guiding-Vector-Field-Generation-via-Score-based-Diffusion-Model.