Saved in:
Bibliographic Details
Main Authors: Mizuta, Kazuki, Leung, Karen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.01192
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918400686555136
author Mizuta, Kazuki
Leung, Karen
author_facet Mizuta, Kazuki
Leung, Karen
contents Robust robot planning in dynamic, human-centric environments remains challenging due to multimodal uncertainty, the need for real-time adaptation, and safety requirements. Optimization-based planners enable explicit constraint handling but can be sensitive to initialization and struggle in dynamic settings. Learning-based planners capture multimodal solution spaces more naturally, but often lack reliable constraint satisfaction. In this paper, we introduce a unified generation-refinement framework that combines reward-guided conditional flow matching (CFM) with model predictive path integral (MPPI) control. Our key idea is a bidirectional information exchange between generation and optimization: reward-guided CFM produces diverse, informed trajectory priors for MPPI refinement, while the optimized MPPI trajectory warm-starts the next CFM generation step. Using autonomous social navigation as a motivating application, we demonstrate that the proposed approach improves the trade-off between safety, task performance, and computation time, while adapting to dynamic environments in real-time. The source code is publicly available at https://cfm-mppi.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01192
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unified Generation-Refinement Planning: Bridging Guided Flow Matching and Sampling-Based MPC for Social Navigation
Mizuta, Kazuki
Leung, Karen
Robotics
Robust robot planning in dynamic, human-centric environments remains challenging due to multimodal uncertainty, the need for real-time adaptation, and safety requirements. Optimization-based planners enable explicit constraint handling but can be sensitive to initialization and struggle in dynamic settings. Learning-based planners capture multimodal solution spaces more naturally, but often lack reliable constraint satisfaction. In this paper, we introduce a unified generation-refinement framework that combines reward-guided conditional flow matching (CFM) with model predictive path integral (MPPI) control. Our key idea is a bidirectional information exchange between generation and optimization: reward-guided CFM produces diverse, informed trajectory priors for MPPI refinement, while the optimized MPPI trajectory warm-starts the next CFM generation step. Using autonomous social navigation as a motivating application, we demonstrate that the proposed approach improves the trade-off between safety, task performance, and computation time, while adapting to dynamic environments in real-time. The source code is publicly available at https://cfm-mppi.github.io.
title Unified Generation-Refinement Planning: Bridging Guided Flow Matching and Sampling-Based MPC for Social Navigation
topic Robotics
url https://arxiv.org/abs/2508.01192