Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jiang, Sunshine, Fang, Xiaolin, Roy, Nicholas, Lozano-Pérez, Tomás, Kaelbling, Leslie Pack, Ancha, Siddharth
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908557628145664
author Jiang, Sunshine
Fang, Xiaolin
Roy, Nicholas
Lozano-Pérez, Tomás
Kaelbling, Leslie Pack
Ancha, Siddharth
author_facet Jiang, Sunshine
Fang, Xiaolin
Roy, Nicholas
Lozano-Pérez, Tomás
Kaelbling, Leslie Pack
Ancha, Siddharth
contents Recent advances in diffusion$/$flow-matching policies have enabled imitation learning of complex, multi-modal action trajectories. However, they are computationally expensive because they sample a trajectory of trajectories: a diffusion$/$flow trajectory of action trajectories. They discard intermediate action trajectories, and must wait for the sampling process to complete before any actions can be executed on the robot. We simplify diffusion$/$flow policies by treating action trajectories as flow trajectories. Instead of starting from pure noise, our algorithm samples from a narrow Gaussian around the last action. Then, it incrementally integrates a velocity field learned via flow matching to produce a sequence of actions that constitute a single trajectory. This enables actions to be streamed to the robot on-the-fly during the flow sampling process, and is well-suited for receding horizon policy execution. Despite streaming, our method retains the ability to model multi-modal behavior. We train flows that stabilize around demonstration trajectories to reduce distribution shift and improve imitation learning performance. Streaming flow policy outperforms prior methods while enabling faster policy execution and tighter sensorimotor loops for learning-based robot control. Project website: https://streaming-flow-policy.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2505_21851
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories
Jiang, Sunshine
Fang, Xiaolin
Roy, Nicholas
Lozano-Pérez, Tomás
Kaelbling, Leslie Pack
Ancha, Siddharth
Robotics
Artificial Intelligence
Machine Learning
Recent advances in diffusion$/$flow-matching policies have enabled imitation learning of complex, multi-modal action trajectories. However, they are computationally expensive because they sample a trajectory of trajectories: a diffusion$/$flow trajectory of action trajectories. They discard intermediate action trajectories, and must wait for the sampling process to complete before any actions can be executed on the robot. We simplify diffusion$/$flow policies by treating action trajectories as flow trajectories. Instead of starting from pure noise, our algorithm samples from a narrow Gaussian around the last action. Then, it incrementally integrates a velocity field learned via flow matching to produce a sequence of actions that constitute a single trajectory. This enables actions to be streamed to the robot on-the-fly during the flow sampling process, and is well-suited for receding horizon policy execution. Despite streaming, our method retains the ability to model multi-modal behavior. We train flows that stabilize around demonstration trajectories to reduce distribution shift and improve imitation learning performance. Streaming flow policy outperforms prior methods while enabling faster policy execution and tighter sensorimotor loops for learning-based robot control. Project website: https://streaming-flow-policy.github.io/
title Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.21851