mlsanityData to 14 Oct 2026

FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation

arXiv 2412.04987 ↗First posted 6 Dec 2024cs.ROcited by 104

On the map: Diffusion models → Diffusion and flow policies for robotics

also in 1 more
Abstract (arXiv)

Robots can acquire complex manipulation skills by learning policies from expert demonstrations, which is often known as vision-based imitation learning. Generating policies based on diffusion and flow matching models has been shown to be effective, particularly in robotic manipulation tasks. However, recursion-based approaches are inference inefficient in working from noise distributions to policy distributions, posing a challenging trade-off between efficiency and quality. This motivates us to propose FlowPolicy, a novel framework for fast policy generation based on consistency flow matching and 3D vision. Our approach refines the flow dynamics by normalizing the self-consistency of the velocity field, enabling the model to derive task execution policies in a single inference step. Specifically, FlowPolicy conditions on the observed 3D point cloud, where consistency flow matching directly defines straight-line flows from different time states to the same action space, while simultaneously constraining their velocity values, that is, we approximate the trajectories from noise to robot actions by normalizing the self-consistency of the velocity field within the action space, thus improving the inference efficiency. We validate the effectiveness of FlowPolicy in Adroit and Metaworld, demonstrating a 7× increase in inference speed while maintaining competitive average success rates compared to state-of-the-art methods. Code is available at https://github.com/zql-kk/FlowPolicy.

Key facts. Cited by 104 papers in the map (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 23 of its 42 references that are in the map. First posted on arXiv 6 Dec 2024.

Builds on

23 of 42 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation3 Jun
  2. 2024Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation13 May
  3. 2023Boosting Continuous Control with Consistency Policy10 Oct
  4. 2023Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning29 Sep
  5. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policies5 Apr
  6. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar
  7. 2023Imitating Human Behaviour with Diffusion Models25 Jan
  8. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning12 Aug

Other references · 15

  1. 2020Denoising Diffusion Implicit Modelscited by 9,781
  2. 2022Flow Matching for Generative Modelingcited by 5,702
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2023Consistency Modelscited by 1,822
  5. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  6. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 846
  7. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
  8. 2021Conditional Image Generation with Score-Based Diffusion Modelscited by 197
  9. 2023Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generationcited by 133
  10. 2024Consistency Flow Matching: Defining Straight Flows with Velocity Consistencycited by 104
  11. 2024AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policiescited by 50
  12. 2024RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effectivecited by 41
3 more
  1. 2024Flow Matching Imitation Learning for Multi-Support Manipulationcited by 29
  2. 2022IL-flOw: Imitation Learning from Observation using Normalizing Flowscited by 12
  3. 2023Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 37; 2026: 66.

104 papers.

Sort:

By area:

  1. 2025RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learningcited by 59
  2. 2025Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policiescited by 52
  3. 2025Leave No Observation Behind: Real-time Correction for VLA Action Chunkscited by 46
  4. 2025CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decodingcited by 38
  5. 2025Much Ado About Noising: Dispelling the Myths of Generative Robotic Controlcited by 36
  6. 2025VITA: Vision-to-Action Flow Matching Policycited by 25
  7. 2026FASTER: Rethinking Real-Time Flow VLAscited by 21
  8. 20253D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulationcited by 20
  9. 2025One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlowcited by 18
  10. 2025AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Modelscited by 17
  11. 2026Action-to-Action Flow Matchingcited by 16
  12. 2024Score and Distribution Matching Policy: Advanced Accelerated Visuomotor Policies via Matched Distillationcited by 13
38 more
  1. 2025FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistencycited by 13
  2. 2025Multi-agent Coordination via Flow Matchingcited by 10
  3. 2026TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAMcited by 10
  4. 2025TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matchingcited by 9
  5. 2025Conditioning Matters: Training Diffusion Policies is Faster Than You Thinkcited by 9
  6. 2025VFP: Variational Flow-Matching Policy for Multi-Modal Robot Manipulationcited by 9
  7. 2025DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulationcited by 8
  8. 2025Mirror Flow Matching with Heavy-Tailed Priors for Generative Modeling on Convex Domainscited by 8
  9. 2026Abstracting Robot Manipulation Skills via Mixture-of-Experts Diffusion Policiescited by 8
  10. 2026STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Predictioncited by 7
  11. 2026One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policiescited by 7
  12. 2025EgoTraj-Bench: Towards Robust Trajectory Prediction Under Ego-view Noisy Observationscited by 6
  13. 2026VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memorycited by 6
  14. 2026Multi-Camera View Scaling for Data-Efficient Robot Imitation Learningcited by 6
  15. 2025UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planningcited by 5
  16. 2025Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulationcited by 5
  17. 2026Action Hallucination in Generative Vision-Language-Action Modelscited by 5
  18. 2026Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulationcited by 5
  19. 2026Drift-Based Policy Optimization: Native One-Step Policy Learning for Online Robot Controlcited by 5
  20. 2025EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AIcited by 4
  21. 2025OMP: One-step Meanflow Policy with Directional Alignmentcited by 4
  22. 2025Coordinated Humanoid Manipulation with Choice Policiescited by 4
  23. 2026RAW-Flow: Advancing RGB-to-RAW Image Reconstruction with Deterministic Latent Flow Matchingcited by 4
  24. 2026SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulationcited by 4
  25. 2026Lifelong Language-Conditioned Robotic Manipulation Learningcited by 4
  26. 2026From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillationcited by 4
  27. 2026Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matchingcited by 4
  28. 2026Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulationcited by 4
  29. 2026πR2: Reactive Real-time Flow Policiescited by 4
  30. 2025FlowHFT: Imitation Learning via Flow Matching Policy for Optimal High-Frequency Trading under Diverse Market Conditionscited by 3
  31. 2025Extremum Flow Matching for Offline Goal Conditioned Reinforcement Learningcited by 3
  32. 2025RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environmentscited by 3
  33. 2025Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysiscited by 3
  34. 2025Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Datacited by 3
  35. 2025Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equationcited by 3
  36. 2025Masked Generative Policy for Robotic Controlcited by 3
  37. 2026HeRO: Hierarchical 3D Semantic Representation for Pose-aware Object Manipulationcited by 3
  38. 2026Dreaming the Unseen: World Model-regularized Diffusion Policy for Out-of-Distribution Robustnesscited by 3

50 most cited of 104 All 104 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation
  2. 2024Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching
  3. 2026FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation
  4. 2025MP1: MeanFlow Tames Policy Learning in 1-step for Robotic Manipulation
  5. 2025ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training
  6. 2026FlowDPG: Deterministic Policy Gradient on Flow Matching Policies for Real-World Manipulation
  7. 20253D Flow Diffusion Policy: Visuomotor Policy Learning via Generating Flow in 3D Space
  8. 2025FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation