Pith. sign in

REVIEW 13 cited by

Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.07503 v2 pith:JW23WX3T submitted 2024-05-13 cs.RO cs.AI

classification cs.ROcs.AI
keywords policyconsistencydiffusioninferencepretrainedtasksvisuomotoralternative
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Spatial Attention: Adapting Execution Horizons for Diffusion Policies via Observation Sensitivity

    cs.RO 2026-07 conditional novelty 6.5 of 10

    Under a fixed sampling budget, execution horizons that minimize disturbance-induced likelihood drop should shorten as Spatial Attention rises; forecasting it yields higher success rates than fixed horizons.

  2. FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulation

    cs.RO 2026-07 conditional novelty 6.0 of 10

    A shared visual-force diffusion policy with a multimodality indicator and manifold consistency distillation raises contact-rich task success to 81.7% while keeping diverse pre-contact modes.

  3. SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation

    cs.RO 2026-07 conditional novelty 6.0 of 10

    SegDiff predicts continuous trajectories anchored to the next keypose and uses DDIM inversion for dynamic temporal ensembling, outperforming continuous and keypose baselines on RLBench, RoboMimic, and five real tasks.

  4. High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matching

    cs.RO 2026-07 conditional novelty 6.0 of 10

    One-step flow-matching visuomotor policy with recursive correction, dual-timestep spectral consistency, and contrastive mode separation matches or exceeds 10-step baselines at 1 NFE.

  5. SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation

    cs.RO 2026-03 conditional novelty 6.0 of 10

    SeedPolicy introduces self-evolving gated attention to extend the temporal horizon of diffusion policies, yielding 36.8% and 169% relative gains over standard DP on clean and randomized RoboTwin 2.0 tasks.

  6. TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control

    cs.RO 2026-01 conditional novelty 6.0 of 10

    TIDAL raises VLA control feedback from ~2.4 Hz to ~9 Hz by caching semantic intent and interleaving one-step flow generation with execution, doubling dynamic interception success in simulation.

  7. DASIP: Dynamic Test-Time Compute Scaling for Robot Control with Stochastic Interpolant Policies

    cs.RO 2025-11 reject novelty 6.0 of 10

    A difficulty classifier adaptively selects step count, solver, and ODE/SDE mode for stochastic-interpolant robot policies, reporting 2.6–4.4x compute savings with roughly unchanged success rates.

  8. RwoR: Generating Robot Demonstrations from Human Hand Collection for Policy Learning without Robot

    cs.RO 2025-07 conditional novelty 6.0 of 10

    A generative model and wrist camera turn human hand videos into robot gripper demonstrations that train manipulation policies at success rates close to those trained on real gripper data.

  9. DemoSpeedup: Accelerating Visuomotor Policies via Entropy-Guided Demonstration Acceleration

    cs.RO 2025-06 conditional novelty 6.0 of 10

    DemoSpeedup accelerates visuomotor policies by downsampling high-entropy segments of demonstrations, achieving roughly 2x faster execution with maintained or improved success rates.

  10. SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment

    cs.RO 2025-11 conditional novelty 5.0 of 10

    Selective Flow Alignment replaces reflow-generated actions with nearby expert actions during training, yielding a one-step flow policy that beats diffusion baselines on 66 simulated and 7 real tasks.

  11. 3D-CovDiffusion: 3D-Aware Diffusion Policy for Coverage Path Planning

    cs.RO 2025-10 reject novelty 4.0 of 10

    A diffusion policy generates ordered spray-painting trajectories from point clouds, but its claimed coverage advantage reverses against the paper's own strongest baseline on three of four categories.

  12. Detecting Reading-Induced Confusion Using EEG and Eye Tracking

    cs.HC 2025-08 unverdicted novelty 4.0 of 10

    Multimodal EEG plus eye tracking classifies reading-induced confusion at 77.3% average weighted accuracy, beating unimodal models by 4-22%, in an 11-participant study.

  13. Retrieve-Augmented Generation for Speeding up Diffusion Policy without Additional Training

    cs.LG 2025-07 conditional novelty 4.0 of 10

    RAGDP accelerates pretrained diffusion policies by initializing denoising from the nearest retrieved expert demonstration action, improving accuracy-versus-speed trade-offs without extra training.

Pith tools