|国家预印本平台
首页|Efficient Task-specific Conditional Diffusion Policies: Shortcut Model Acceleration and SO(3) Optimization

Efficient Task-specific Conditional Diffusion Policies: Shortcut Model Acceleration and SO(3) Optimization

Efficient Task-specific Conditional Diffusion Policies: Shortcut Model Acceleration and SO(3) Optimization

来源:Arxiv_logoArxiv
英文摘要

Imitation learning, particularly Diffusion Policies based methods, has recently gained significant traction in embodied AI as a powerful approach to action policy generation. These models efficiently generate action policies by learning to predict noise. However, conventional Diffusion Policy methods rely on iterative denoising, leading to inefficient inference and slow response times, which hinder real-time robot control. To address these limitations, we propose a Classifier-Free Shortcut Diffusion Policy (CF-SDP) that integrates classifier-free guidance with shortcut-based acceleration, enabling efficient task-specific action generation while significantly improving inference speed. Furthermore, we extend diffusion modeling to the SO(3) manifold in shortcut model, defining the forward and reverse processes in its tangent space with an isotropic Gaussian distribution. This ensures stable and accurate rotational estimation, enhancing the effectiveness of diffusion-based control. Our approach achieves nearly 5x acceleration in diffusion inference compared to DDIM-based Diffusion Policy while maintaining task performance. Evaluations both on the RoboTwin simulation platform and real-world scenarios across various tasks demonstrate the superiority of our method.

Haiyong Yu、Yanqiong Jin、Yonghao He、Wei Sui

计算技术、计算机技术自动化技术、自动化技术设备

Haiyong Yu,Yanqiong Jin,Yonghao He,Wei Sui.Efficient Task-specific Conditional Diffusion Policies: Shortcut Model Acceleration and SO(3) Optimization[EB/OL].(2025-04-14)[2025-07-16].https://arxiv.org/abs/2504.09927.点此复制

评论