无需重训练，实时动态修正动作，提升机器人适应力
Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policy
- 分块生成动作+实时环境反馈，动态调整执行策略
- 动态场景下适应性提升19%，计算量仅增加5%
- 模块化设计，可直接用于真实机械臂操作
基于扩散模型的策略在机器人操作中表现优异，但在动态环境中常因响应迟缓或任务失败而受限。本文提出DCDP——一种动态闭环扩散策略框架，通过分块动作生成与实时校正结合，引入自监督动态特征编码器、交叉注意力融合和非对称编解码结构，在动作执行前注入环境动态信息，实现真正意义上的实时闭环修正，显著增强系统在动态场景中的适应能力。在动态PushT仿真中，不需重训练即可提升适应性19%，额外计算仅增加5%。其模块化设计支持即插即用，在真实世界操作任务中同时保证时间连贯性与实时响应。项目主页：https://github.com/wupengyuan/dcdp
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。