RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution

Tao Wang; Wei Wang; Jianhui Wang; ZhengYang Ye; Qi Wang; Weidi Huang; Bing Xu

cs.ROAug 16, 2026

RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution

Authors: Tao Wang, Wei Wang, Jianhui Wang, ZhengYang Ye, Qi Wang, Weidi Huang, Bing Xu

Organizations: Zhejiang University, Hangzhou, Zhejiang, China. · State Key Laboratory of High-end Heavy-load Robots, Midea Group, Foshan, Guangdong, China.

Abstract

Cloud-side inference expands the computational resources available to imitation-learning policies, but communication and inference latencies create a mismatch between prediction and execution. We propose RAPAC-DP, a response-aligned pending-action compensation framework for diffusion- and flow-based action generators. By conditioning on actions committed during inference, RAPAC-DP generates a full-horizon action chunk aligned with the scheduled handover time. A lightweight pending-action encoder and LoRA adapters learn this compensation while keeping the pretrained base policy frozen. We construct delay-conditioned training samples from delay-free demonstrations, requiring neither an explicit dynamics model nor additional data collected under delayed execution. In simulation benchmarks at the largest evaluated delays, RAPAC-DP retains 81.4% of its overall delay-free performance on Kinetix and achieves a mean success rate of 63.3% across three RoboMimic tasks. Across 450 physical trials on a Franka Panda manipulator, RAPAC-DP increases the high-delay mean success rate from 28.9% for RTC to 60.0% across static and conveyor-based pick-and-place tasks.

Figures & tables

Fig. 1: Schematic of observation–execution alignment under execution delay. (a) Naive inserts the complete request-aligned chunk at

t+d

, beginning with

\hat{\mathbf{a}}_{t}^{(t)}

. The pending actions

\mathbf{P}_{t,d}

change the robot state during inference, producing an observation–execution mismatch. (b) RAPAC-DP conditions on

\mathbf{P}_{t,d}

and generates a complete action chunk beginning at the scheduled handover

t+d

Fig. 2: Overview of the RAPAC-DP framework. (a) Response-aligned training on a diffusion policy. Delay-free demonstrations provide pending-action conditions and full-horizon targets beginning at the sampled delay step. Only the pending-action encoder and LoRA adapters are updated while the base policy remains frozen. (b) Asynchronous online execution. During remote inference, the local controller executes committed pending actions and inserts the newly received action chunk into the execution queue at the scheduled handover time.

Fig. 3: Success rates under increasing execution delay on 12 Kinetix tasks. (a) Representative environments. (b) Overall performance, obtained by averaging the 12 environments equally within each seed before computing the across-seed mean. (c) Per-environment performance. RAPAC-DP keeps the compensation pathway enabled at every delay level, including $d=0$ . For RAPAC-DP, A2C2, and RTC, thick curves show the mean, shaded bands show the standard deviation across three seeds, and pale curves show individual seeds. Naive is evaluated with one seed and therefore has no uncertainty band.

Fig. 4: Success rates under increasing execution delay on RoboMimic: (a) Can, (b) Square, and (c) Transport. Ours denotes RAPAC-DP. For RAPAC-DP, A2C2, and Naive, thick curves and shaded bands denote the mean and sample standard deviation across three random seeds, while pale curves show individual runs. RTC reflects the success rate from 50 rollouts per condition.

	Delay-range averages			Representative delays
Method	Low ( $0$ – $3$ )	High ( $4$ – $7$ )	Overall ( $0$ – $7$ )	$d=0$	$d=3$	$d=7$
Naive	$77.4\pm 2.4$	$28.2\pm 1.5$	$52.8\pm 1.9$	$89.1\pm 2.7$	$62.9\pm 3.9$	$13.6\pm 0.8$
+ LoRA	$78.2\pm 1.3$	$27.4\pm 0.8$	$52.8\pm 1.0$	$85.6\pm 0.4$	$63.8\pm 2.8$	$12.4\pm 2.0$
+ response-aligned target	$61.6\pm 2.5$	$\mathbf{70.2\pm 1.2}$	$65.9\pm 1.2$	$87.1\pm 1.0$	$68.0\pm 2.0$	$55.8\pm 1.4$
+ pending-action sequence	$\mathbf{87.8\pm 1.4}$	$\mathbf{70.2\pm 1.8}$	$\mathbf{79.0\pm 1.6}$	$\mathbf{89.3\pm 1.3}$	$\mathbf{87.3\pm 1.3}$	$\mathbf{63.3\pm 2.3}$

TABLE I: RoboMimic ablation results. Rows are cumulative; values are mean success rates

\pm

standard deviation over three seeds (%).

Fig. 5: Simulation environments and physical execution sequences. (a) RoboMimic simulation tasks: Can, Square, and Transport. (b) Physical pick-and-place tasks: Cube Grasping, Vegetable Grasping with a plastic eggplant, and Dynamic Grasping on a conveyor belt. Each row displays six chronological snapshots from an illustrative trial, with time progressing from left to right.

Fig. 6: Physical pick-and-place success rates across Cube Grasping, Vegetable Grasping, and Dynamic Grasping. RAPAC-DP (Ours) and RTC are evaluated under nominal execution latencies of 200 and 450 ms obtained through latency injection and mapped to discrete delays of

d=3

and

d=7

, respectively. Sync is evaluated under natural latency as a synchronous reference. Each bar summarizes 30 physical trials for a total of 450 trials; labels indicate success percentages, and error bars denote 95% confidence intervals.

Robotic Control

Robotic control studies how machines use sensing and computation to produce reliable movement and interaction in changing environments.

See all 584 papers

Training-Free Imitation Learning with Closed-Form Diffusion Policies
May 31, 2026Raghav Mishra, Ian R. ManchesterDiffusion Model Guidance Visuomotor Policy Learning
Australian Center for Robotics, ARIAM Hub, and School of Aerospace, Mechanical and Mechatronic Engineering University of Sydney
Diffusion-Guided Uncertainty-Aware Delayed Policy Optimization
Jul 6, 2026Junqi Tu, Zejiao Liu, Fangfei Li +1Reinforcement Learning Robotic RL
The Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, China · The School of Mathematics, East China University of Science and Technology, Shanghai, China
TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration
Dec 13, 2025Ye Li, Jiahe Feng, Yuan Meng +9Diffusion Policy Adaptive Computation for Diffusion Models
Tsinghua University

May 31, 2026J/K move · Enter open · S save

Training-Free Imitation Learning with Closed-Form Diffusion Policies

Raghav Mishra, Ian R. Manchester

Australian Center for Robotics, ARIAM Hub, and School of Aerospace, Mechanical and Mechatronic Engineering University of Sydney

Diffusion Model Guidance Visuomotor Policy Learning Diffusion Policy Imitation Learning Policy Learning

Open paper AskPDF arXiv

While diffusion-based policies have impressive performance and expressivity, their long offline training slows down the data collection and policy deployment loop. We introduce Closed-Form Diffusion Policies, a class of training-free diffusion-based policies for imitation learning using the closed-form score derived from the demonstration dataset. We deploy CFDP with real-time inference with a mobile CPU in hardware experiments, showing it can successfully perform imitation directly from the dataset in milliseconds and with faster inference than neural diffusion policies. In experiments on imitation learning benchmarks, we show that CFDP is competitive against neural baselines that require hours of training, providing a favorable tradeoff between training time and performance. Finally, we show how closed-form diffusion policies act as a composable primitive that enables data-driven inference-time editing of pre-trained neural diffusion policies, including policy guidance and novel demonstration augmentation.

Abstract

Robotic Control

Explore similar work

Training-Free Imitation Learning with Closed-Form Diffusion Policies

Diffusion-Guided Uncertainty-Aware Delayed Policy Optimization

TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration