One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation
read the original abstract
Diffusion models, praised for their success in generative tasks, are increasingly being applied to robotics, demonstrating exceptional performance in behavior cloning. However, their slow generation process stemming from iterative denoising steps poses a challenge for real-time applications in resource-constrained robotics setups and dynamically changing environments. In this paper, we introduce the One-Step Diffusion Policy (OneDP), a novel approach that distills knowledge from pre-trained diffusion policies into a single-step action generator, significantly accelerating response times for robotic control tasks. We ensure the distilled generator closely aligns with the original policy distribution by minimizing the Kullback-Leibler (KL) divergence along the diffusion chain, requiring only $2\%$-$10\%$ additional pre-training cost for convergence. We evaluated OneDP on 6 challenging simulation tasks as well as 4 self-designed real-world tasks using the Franka robot. The results demonstrate that OneDP not only achieves state-of-the-art success rates but also delivers an order-of-magnitude improvement in inference speed, boosting action prediction frequency from 1.5 Hz to 62 Hz, establishing its potential for dynamic and computationally constrained robotic applications. We share the project page at https://research.nvidia.com/labs/dir/onedp/.
This paper has not been read by Pith yet.
Forward citations
Cited by 21 Pith papers
-
Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies
TAKO demonstrates real-time adversarial takeover of robotic diffusion policies via reusable universal patches on visual inputs, achieving 100% success in steering attacker-chosen trajectories across multiple tasks, en...
-
The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks
TISED framework reveals paradoxical effects where inference optimizations can lengthen task completion time on static tasks or raise success rates on dynamic tasks in embodied AI.
-
Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
A new speculative inference system speeds up diffusion VLAs to 19.1 ms average latency (3.04x faster) on LIBERO by replacing most full 58 ms inferences with 7.8 ms draft rounds while preserving task performance.
-
Test-time Sparsity for Extreme Fast Action Diffusion
Test-time sparsity with a parallel pipeline and omnidirectional feature reuse accelerates action diffusion by 5x to 47.5 Hz while cutting FLOPs 92% with no performance loss.
-
Muninn: Your Trajectory Diffusion Model But Faster
Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.
-
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
Frequency analysis of smooth robot actions bounds denoising error to low-frequency modes, enabling a sub-1% parameter 3D diffusion policy with two-step inference that reaches SOTA on manipulation benchmarks.
-
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
HDP3 is a pocket-scale 3D diffusion policy with a Diffusion Mixer decoder that achieves state-of-the-art visuomotor control using two-step DDIM inference and under 1% of the parameters of prior 3D diffusion policies.
-
You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector
Optimizing a single constant initial noise vector for frozen generative robot policies improves success rates on 38 of 43 tasks by up to 58% relative improvement.
-
Information Filtering via Variational Regularization for Robot Manipulation
Variational Regularization imposes an adaptive information bottleneck on noisy intermediate features in DP3-UNet and DP3-DiT policies, consistently raising task success rates on RoboTwin2.0, Adroit, and MetaWorld whil...
-
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
VLA-Corrector adds a detect-and-correct inference layer using a latent vision monitor and online gradient guidance to enable adaptive action horizons in chunked VLA policies.
-
The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks
TISED decomposes inference optimization effects on embodied tasks and identifies paradoxical outcomes where faster per-step inference can increase task completion time on static tasks or raise success rates on dynamic tasks.
-
ARP: Enhancing Quantized Skill Abstractions via Visual Alignment and Iterative Refinement for Robotic Manipulation
ARP enhances quantized skill abstractions in imitation learning by coupling visual grounding via contrastive alignment with execution refinement via IRH, reporting SOTA results on LIBERO, Meta-World, and real-robot tasks.
-
Vesta: A Generalist Embodied Reasoning Model
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
-
Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
IDP generates one-step robot actions by adaptively weighting a scalar potential objective using conditional expert geometry derived from local variations of observation-similar expert actions, combined with expert-pro...
-
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
Hydra-DP3 achieves SOTA visuomotor performance with under 1% of prior 3D diffusion policy parameters by using frequency analysis to justify a lightweight decoder and two-step DDIM inference.
-
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
Hydra-DP3 is a lightweight 3D diffusion policy that uses frequency analysis of smooth action trajectories to enable two-step DDIM inference and achieves state-of-the-art results with under 1% of prior parameters.
-
FASTER: Value-Guided Sampling for Fast RL
FASTER models multi-candidate denoising as an MDP and trains a value function to filter actions early, delivering the performance of full sampling at lower cost in diffusion RL policies.
-
VADF: Vision-Adaptive Diffusion Policy Framework for Efficient Robotic Manipulation
VADF adds an Adaptive Loss Network for hard-negative training sampling and a Hierarchical Vision Task Segmenter for adaptive noise scheduling during inference to speed convergence and reduce timeouts in diffusion robo...
-
RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation
RoamFlow applies MeanFlow to predict average velocity fields for one-step action policies in image-goal navigation, trained via expert imitation followed by RL refinement.
-
Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning
Sparse ActionGen accelerates diffusion policies up to 4x for robot control via rollout-adaptive pruning and zig-zag activation reuse without performance loss.
-
Cosmos World Foundation Model Platform for Physical AI
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.