Research Analyzer
← Back ICRA 2026

Generative Predictive Control: Flow Matching Policies for Dynamic, Difficult-To-Demonstrate Tasks

Vincent Kurtz, Joel Burdick

PDF

AI summary

Key figure (auto-extracted from paper)
Generative predictive control leverages flow-matching policies to bootstrap sampling-based control, enabling stable, high-frequency feedback for fast, hard-to-demonstrate robotic tasks.
Generative control Flow matching Predictive control Robotics Domain randomization Supervised learning

Problem

Existing generative control methods rely on costly expert demonstrations and struggle with fast, nonlinear dynamics, limiting them to slow, quasi-static tasks.

Approach

The authors propose GPC, a supervised learning framework that alternates between generating training data via sampling-based predictive control and training a flow-matching policy, which is then used to warm-start control at inference.

Key results

  • Outperforms PPO across multiple dynamic simulation tasks
  • Novel warm-start scheme enables smooth high-frequency feedback
  • Integrates risk-aware domain randomization for robust training
  • Identifies scalability limits on complex humanoid tasks

Why it matters

Offers a scalable, supervised alternative to behavior cloning and reinforcement learning for fast, dynamic robotics applications.

Abstract

Generative control policies have recently unlocked major progress in robotics. These methods produce action sequences via diffusion or flow matching, with training data provided by demonstrations. But existing methods come with two key limitations: they require expert demonstrations, which can be difficult or costly to obtain, and they are limited to relatively slow, quasi-static tasks. In this paper, we leverage a tight connection between sampling-based predictive control and generative modeling to address these issues. In particular, we introduce generative predictive control, a supervised learning framework for tasks with fast dynamics that are easy to simulate but difficult to demonstrate. We show how trained flow-matching policies can be warm-started at inference time, maintaining temporal consistency and enabling high-frequency feedback. We believe that generative predictive control offers a complementary approach to existing behavior cloning methods, and hope that it will pave the way toward generalist policies that extend beyond quasi-static demonstration-oriented tasks.

Index terms

Machine Learning for Robot Control Simulation and Animation Optimization and Optimal Control

Related papers