Streaming Diffusion Policy：基于可变噪声扩散模型的快速策略合成
Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models
AI总结：
提出 SDP（Streaming Diffusion Policy），通过生成部分去噪动作轨迹并利用可变噪声实现快速策略合成，在模拟和真实环境中大幅加速同时保持性能。
摘要：
扩散模型在机器人模仿学习中得到了快速应用，实现了复杂灵巧任务的自主执行。然而，动作合成通常很慢，需要多步迭代去噪，这限制了模型在需要快速反应策略的任务中的应用。为了规避这一点，近期的研究探索了如何利用扩散过程的蒸馏来加速策略合成。然而，蒸馏在计算上代价高昂，并且可能损害合成动作的准确性和多样性。我们提出了 SDP（Streaming Diffusion Policy），这是一种加速策略合成的替代方法，其利用了以下见解：生成部分去噪的动作轨迹比生成完整输出动作轨迹快得多。在每次观测时，我们的方法输出具有可变噪声损坏水平的部分去噪动作轨迹，其中要执行的即时动作是无噪声的，随后的动作则具有越来越高的噪声和不确定性。通过对先前预测的噪声动作轨迹（向前滚动一个时间步）应用几步去噪，即可快速生成新观测的部分去噪动作轨迹。我们展示了该方法的有效性，在模拟和真实世界环境中均大幅加速了策略合成，同时保持了性能。
英文摘要：
Diffusion models have seen rapid adoption in robotic imitation learning, enabling autonomous execution of complex dexterous tasks. However, action synthesis is often slow, requiring many steps of iterative denoising, limiting the extent to which models can be used in tasks that require fast reactive policies. To sidestep this, recent works have explored how the distillation of the diffusion process can be used to accelerate policy synthesis. However, distillation is computationally expensive and can hurt both the accuracy and diversity of synthesized actions. We propose SDP (Streaming Diffusion Policy), an alternative method to accelerate policy synthesis, leveraging the insight that generating a partially denoised action trajectory is substantially faster than a full output action trajectory. At each observation, our approach outputs a partially denoised action trajectory with variable levels of noise corruption, where the immediate action to execute is noise-free, with subsequent actions having increasing levels of noise and uncertainty. The partially denoised action trajectory for a new observation can then be quickly generated by applying a few steps of denoising to the previously predicted noisy action trajectory (rolled over by one timestep). We illustrate the efficacy of this approach, dramatically speeding up policy synthesis while preserving performance across both simulated and real-world settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
