Unified Generation-Refinement Planning: Bridging Guided Flow Matching and Sampling-Based MPC for Social Navigation
This work addresses the problem of real-time adaptation and safety in social navigation for robotics, presenting an incremental improvement by integrating learning-based and optimization-based methods.
The paper tackles robust robot planning in dynamic human-centric environments by introducing a unified generation-refinement framework that combines reward-guided conditional flow matching with model predictive path integral control, demonstrating improved trade-offs in safety, task performance, and computation time for social navigation.
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.