用自引导提升机器人扩散策略的效率与成功率
Self-Guided Action Diffusion
- 每步扩散过程根据已有决策引导动作采样分布
- 在有限采样预算下，动态任务成功率最高提升70%
- 适合追求高效推理的机器人策略研究者
近期工作表明，推理阶段对动作样本的搜索能提升生成式机器人策略的性能。特别是通过双向解码优化跨片段一致性，显著提升了扩散策略的一致性与响应能力。然而，随着动作采样多样性增加，该方法计算开销巨大。本文提出自引导动作扩散（Self-Guided Action Diffusion），一种面向扩散策略的更高效双向解码变体。核心思想是在每一步扩散过程中，基于先前决策引导提议分布。仿真任务实验表明，所提自引导机制可在几乎无额外推理成本下实现接近最优性能。尤其在严格采样预算下，其在复杂动态任务上的成功率比现有方法最高提升70%。项目主页见 https://rhea-mal.github.io/selfgad.github.io。
原文摘要 · Abstract (English)
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.
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。