Diffusion-based policies have achieved remarkable results in robotic manipulation but often struggle to adapt rapidly in dynamic scenarios, leading to delayed responses or task failures. We present DCDP, a Dynamic Closed-Loop Diffusion Policy framework that integrates chunk-based action generation with real-time correction. DCDP integrates a self-supervised dynamic feature encoder, cross-attention fusion, and an asymmetric action encoder-decoder to inject environmental dynamics before action execution, achieving real-time closed-loop action correction and enhancing the system's adaptability in dynamic scenarios. In dynamic PushT simulations, DCDP improves adaptability by 19\% without retraining while requiring only 5\% additional computation. Its modular design enables plug-and-play integration, achieving both temporal coherence and real-time responsiveness in dynamic robotic scenarios, including real-world manipulation tasks. The project page is at: https://github.com/wupengyuan/dcdp
@article{arxiv.2603.01953,
title = {Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy},
author = {Pengyuan Wu and Pingrui Zhang and Zhigang Wang and Dong Wang and Bin Zhao and Xuelong Li},
journal= {arXiv preprint arXiv:2603.01953},
year = {2026}
}