将复杂规划算法蒸馏为高效策略，实现长时序抓取与非抓取操作的零样本迁移。
$\texttt{SPIN}$: distilling $\texttt{Skill-RRT}$ for long-horizon prehensile and non-prehensile manipulation
- 用技能感知的RRT算法生成高质量演示，支持长序列动作规划。
- 通过连接器策略减少技能切换时物体扰动，提升动作连贯性。
- 纯仿真训练的策略在真实机器人上零样本成功率达80%以上。
当前机器人在需要长序列抓取与非抓取技能、接触丰富交互及长期推理的长时序操作任务中表现不佳。本文提出SPIN（Skill Planning to INference），一种将计算密集型规划算法通过模仿学习蒸馏为策略的框架。我们设计了Skill-RRT，是RRT的扩展，引入技能适用性检测与中间物体位姿采样以解决此类长时序问题。为串联独立训练的技能，提出连接器——目标条件策略，用于最小化技能切换时的物体扰动。利用Skill-RRT生成高质量演示，并通过带噪声的重放机制进行蒸馏，以降低在线计算时间。最终策略完全在仿真中训练，实现零样本迁移到真实世界，在三个挑战性长时序操作任务中成功率超过80%，优于现有最先进分层强化学习与规划方法。
原文摘要 · Abstract (English)
Current robots struggle with long-horizon manipulation tasks requiring sequences of prehensile and non-prehensile skills, contact-rich interactions, and long-term reasoning. We present $\texttt{SPIN}$ ($\textbf{S}$kill $\textbf{P}$lanning to $\textbf{IN}$ference), a framework that distills a computationally intensive planning algorithm into a policy via imitation learning. We propose $\texttt{Skill-RRT}$, an extension of RRT that incorporates skill applicability checks and intermediate object pose sampling for solving such long-horizon problems. To chain independently trained skills, we introduce $\textit{connectors}$, goal-conditioned policies trained to minimize object disturbance during transitions. High-quality demonstrations are generated with $\texttt{Skill-RRT}$ and distilled through noise-based replay in order to reduce online computation time. The resulting policy, trained entirely in simulation, transfers zero-shot to the real world and achieves over 80% success across three challenging long-horizon manipulation tasks and outperforms state-of-the-art hierarchical RL and planning methods.
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。