mlsanityData to 7 Oct 2026

Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation

arXiv 2405.07503 ↗First posted 13 May 2024cs.RO cs.AIcited by 159

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

Abstract (arXiv)

Many robotic systems, such as mobile manipulators or quadrotors, cannot be equipped with high-end GPUs due to space, weight, and power constraints. These constraints prevent these systems from leveraging recent developments in visuomotor policy architectures that require high-end GPUs to achieve fast policy inference. In this paper, we propose Consistency Policy, a faster and similarly powerful alternative to Diffusion Policy for learning visuomotor robot control. By virtue of its fast inference speed, Consistency Policy can enable low latency decision making in resource-constrained robotic setups. A Consistency Policy is distilled from a pretrained Diffusion Policy by enforcing self-consistency along the Diffusion Policy's learned trajectories. We compare Consistency Policy with Diffusion Policy and other related speed-up methods across 6 simulation tasks as well as three real-world tasks where we demonstrate inference on a laptop GPU. For all these tasks, Consistency Policy speeds up inference by an order of magnitude compared to the fastest alternative method and maintains competitive success rates. We also show that the Conistency Policy training procedure is robust to the pretrained Diffusion Policy's quality, a useful result that helps practioners avoid extensive testing of the pretrained model. Key design decisions that enabled this performance are the choice of consistency objective, reduced initial sample variance, and the choice of preset chaining steps.

Key facts. Cited by 159 papers in the map (data through 7 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 30 of its 34 references that are in the map. First posted on arXiv 13 May 2024.

Builds on

30 of 34 references.

Closest ancestors · 6

Same direction, newest first

  1. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations6 Mar
  2. 2023Boosting Continuous Control with Consistency Policy10 Oct
  3. 2023Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning29 Sep
  4. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policies5 Apr
  5. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar
  6. 2023Imitating Human Behaviour with Diffusion Models25 Jan

Other references · 24

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  7. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  8. 2023Consistency Modelscited by 1,778
  9. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  10. 2023Large Language Modelscited by 774
  11. 2022On Distillation of Guided Diffusion Modelscited by 721
  12. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
12 more
  1. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 450
  2. 2021Implicit Behavioral Cloningcited by 442
  3. 2023Improved Techniques for Training Consistency Modelscited by 430
  4. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  5. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learningcited by 380
  6. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 344
  7. 2023Emu Edit: Precise Image Editing via Recognition and Generation Taskscited by 321
  8. 2022Perception Prioritized Training of Diffusion Modelscited by 301
  9. 2022Behavior Transformers: Cloning k modes with one stonecited by 299
  10. 2023Efficient Diffusion Training via Min-SNR Weighting Strategycited by 242
  11. 2022MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generationcited by 225
  12. 2023Large Language Models for Robotics: A Surveycited by 132

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 22; 2025: 59; 2026: 78.

159 papers.

Sort:

By area:

  1. 2025Cosmos World Foundation Model Platform for Physical AIcited by 833
  2. 2025Real-Time Execution of Action Chunking Flow Policiescited by 199
  3. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Controlcited by 191
  4. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 176
  5. 2025ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policycited by 139
  6. 2025ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Modelcited by 112
  7. 2024FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulationcited by 99
  8. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decodingcited by 88
  9. 2024One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillationcited by 83
  10. 2024The Ingredients for Robotic Diffusion Transformerscited by 72
  11. 2024Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulationcited by 71
  12. 2024ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulationcited by 57
38 more
  1. 2024Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoningcited by 57
  2. 2024Affordance-based Robot Manipulation with Flow Matchingcited by 54
  3. 2024Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Modelscited by 51
  4. 2025ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledgecited by 49
  5. 2024Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Samplingcited by 46
  6. 2025NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidancecited by 46
  7. 2025ManiFlow: A General Robot Manipulation Policy via Consistency Flow Trainingcited by 43
  8. 2025Diffusion Models for Robotic Manipulation: A Surveycited by 39
  9. 2024Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulationcited by 38
  10. 2025CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decodingcited by 38
  11. 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrationscited by 35
  12. 2025Much Ado About Noising: Dispelling the Myths of Generative Robotic Controlcited by 35
  13. 2024ARCap: Collecting High-quality Human Demonstrations for Robot Learning with Augmented Reality Feedbackcited by 31
  14. 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalizationcited by 29
  15. 2024CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Predictioncited by 26
  16. 2025MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attentioncited by 26
  17. 2024TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learningcited by 21
  18. 2024Fast and Robust Visuomotor Riemannian Flow Matching Policycited by 18
  19. 2025One-Step Flow Policy Mirror Descentcited by 18
  20. 2024Discrete Policy: Learning Disentangled Action Space for Multi-Task Robotic Manipulationcited by 17
  21. 2026Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imaginationcited by 17
  22. 2025One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlowcited by 16
  23. 2024Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignmentcited by 14
  24. 2024Variational Distillation of Diffusion Policies into Mixture of Expertscited by 14
  25. 2025Generative Models in Decision Making: A Surveycited by 14
  26. 2025Falcon: Fast Visuomotor Policies via Partial Denoisingcited by 14
  27. 2025IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimationcited by 13
  28. 2025Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Controlcited by 13
  29. 2025H3DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learningcited by 13
  30. 2025FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistencycited by 13
  31. 2024Score and Distribution Matching Policy: Advanced Accelerated Visuomotor Policies via Matched Distillationcited by 12
  32. 2025RationalVLA: A Rational Vision-Language-Action Model with Dual Systemcited by 12
  33. 2025A Survey on Imitation Learning for Contact-Rich Tasks in Roboticscited by 12
  34. 2026SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillationcited by 12
  35. 2025D3P: Dynamic Denoising Diffusion Policy via Reinforcement Learningcited by 10
  36. 2025TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matchingcited by 9
  37. 2025Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplingscited by 8
  38. 2025Real-Time Iteration Scheme for Diffusion Policycited by 8

50 most cited of 159 All 159 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Hybrid Consistency Policy: Decoupling Multi-Modal Diversity and Real-Time Efficiency in Robotic Manipulation
  2. 2024How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation
  3. 2026FLASH: Efficient Visuomotor Policy via Sparse Sampling
  4. 2025FALCON: Actively Decoupled Visuomotor Policies for Loco-Manipulation with Foundation-Model-Based Coordination
  5. 2025Inference-stage Adaptation-projection Strategy Adapts Diffusion Policy to Cross-manipulators Scenarios
  6. 2025Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution
  7. 2025CDP: Towards Robust Autoregressive Visuomotor Policy Learning via Causal Diffusion
  8. 2026VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memory