自引导动作扩散
Self-Guided Action Diffusion
AI总结：
本文提出自引导动作扩散方法，通过在扩散步骤中利用先前决策引导提议分布，以极低推理成本实现接近最优性能，并在动态任务上比现有方法提升高达70%的成功率。
摘要：
近期工作已表明，在推理时对动作样本进行搜索对于改进生成式机器人策略具有前景。特别是，通过双向解码优化跨块一致性已被证明能有效提升扩散策略的一致性和反应性。然而，随着采样动作多样性的增加，该方法在计算上仍然昂贵。在本文中，我们提出了自引导动作扩散，这是一种针对基于扩散的策略量身定制的更高效的双向解码变体。我们方法的核心是在每个扩散步骤中基于先前的决策来引导提议分布。在仿真任务中的实验表明，所提出的自引导方法能够以可忽略的推理成本实现接近最优的性能。值得注意的是，在紧张的采样预算下，我们的方法在具有挑战性的动态任务上比现有方法实现了高达70%的成功率提升。项目网站见 https://rhea-mal.github.io/selfgad.github.io。
英文摘要：
Recent works have shown the promise of inference-time search over action samples for improving generative robot policies. In particular, optimizing cross-chunk coherence via bidirectional decoding has proven effective in boosting the consistency and reactivity of diffusion policies. However, this approach remains computationally expensive as the diversity of sampled actions grows. In this paper, we introduce self-guided action diffusion, a more efficient variant of bidirectional decoding tailored for diffusion-based policies. At the core of our method is to guide the proposal distribution at each diffusion step based on the prior decision. Experiments in simulation tasks show that the proposed self-guidance enables near-optimal performance at negligible inference cost. Notably, under a tight sampling budget, our method achieves up to 70% higher success rates than existing counterparts on challenging dynamic tasks. See project website at https://rhea-mal.github.io/selfgad.github.io.
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。
