发表机构
Australian Centre for Robotics, The University of Sydney; College of Connected Computing, Vanderbilt University（悉尼大学澳大利亚机器人中心; 范德堡大学互联计算学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
NestDex 是一种嵌套策略学习框架，借助 Copilot 辅助遥操作减轻灵巧操作演示收集负担，提升演示可靠性与效率，助力自主策略学习。
AI 中文摘要
灵巧操作可实现机器人与物理世界更丰富的交互，但这类行为的学习受限于收集一致、完整任务演示的难度。与平行爪操作不同，灵巧任务要求操作者在整个任务中协调机械臂运动与精确、接触密集的手指行为。我们提出 NestDex，这是一种嵌套策略学习框架，通过利用学习到的手部技能辅助演示收集来减轻该负担。操作者通过单自由度离合器控制机械臂并调节激活的手部技能，而非直接指定完整的手指轨迹。内部手部策略根据最新的本体感受历史调整其运动，而视觉-语言选择器则为每个任务阶段激活适当的技能。由此产生的演示用于训练一个独立的外部视觉运动策略，该策略在部署时可控制机械臂和手部，无需内部策略。手部动作变分自动编码器提供紧凑的手部动作目标，同时在关节空间中保留机械臂指令。在真实世界的灵巧操作实验中，NestDex 提高了演示的可靠性和效率，所得的实证评估支持有效的自主策略学习。视频演示可在项目网站获取：this https URL
英文摘要
Dexterous manipulation promises substantially richer robot interaction with the physical world, but learning these behaviours remains constrained by the difficulty of collecting consistent, complete-task demonstrations. Unlike parallel-jaw manipulation, dexterous tasks require the operator to coordinate arm motion with precise, contact-rich finger behaviour throughout the task. We introduce NestDex, a nested policy-learning framework that reduces this burden by using learned hand skills to assist demonstration collection. The operator controls the arm and regulates the active hand skill through a single-DoF clutch, rather than directly specifying the full finger trajectory. The inner hand policy adapts its motion from the latest proprioceptive history, while a vision-language selector activates the appropriate skill for each task stage. The resulting demonstrations train a separate outer visuomotor policy that controls both the arm and hand without the inner policies at deployment. A hand-action variational autoencoder provides compact hand-action targets while retaining arm commands in joint space. Across real-world dexterous manipulation experiments, NestDex improves demonstration reliability and efficiency, and the resulting empirical evaluations support effective autonomous policy learning. Video Demo are available at project website https://aus.bot/research/nestdex.
Comments9 pages, 11 figures, 3 tables. Project website: https://aus.bot/research/nestdex
