发表机构
Nanyang Technological University; Tongji University; Shanghai Institute of Intelligent Science and Technology; NTU–VinUni Joint Research Laboratory for Embodied AI and Robotics; VinUniversity（南洋理工大学; 同济大学; 上海智能科学与技术研究院; 南洋理工大学-维纳大学具身智能与机器人联合研究实验室; 维纳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对空中抓取提升任务，提出循环教师-学生框架，通过关键状态课程和闭合目标，在仿真中训练单一策略，实现部分观测下的全身协调，成功率高达99.97%。
AI 中文摘要
空中抓取与提升任务需要在目标部分观测条件下，协调进近、抓取和提升的全身动作。训练中，早期进近失败可能限制对后续任务阶段的接触，而可见性的变化在执行过程中使对齐和闭合时机的确定变得复杂。我们提出了一种循环教师-学生框架，在仿真中学习单一策略，以联合控制飞行、手臂运动和夹爪闭合，无需显式的任务阶段输入。一个特权教师通过强化学习，结合关键状态课程进行训练，该课程先暴露抓取和提升状态，再将其与正常进近轨迹连接。其行为被蒸馏到一个循环视觉学生模型中，该模型用双视角点云和本体感觉替代特权目标状态，并整合观测历史以实现闭环控制。一个专门的闭合目标函数根据模型定义的持续就绪序列来监督闭合时机。训练和主要评估使用一个模拟的抓取-载荷模型，该模型具有条件触发的锁存、虚拟连接和基于力矩的载荷加载，用于短距离提升。在该模型下完成的8,996个仿真回合中，冻结的学生模型在标称、物理/控制随机化和额外相机随机化条件下的完整任务成功率分别为99.97%、97.14%和95.84%。标称条件下，按锁存次数加权的每个种子第90百分位对齐误差均值为8.12毫米。
英文摘要
Aerial grasp-and-lift tasks require whole-body coordination across approach, acquisition, and lifting under partial target observations. Early approach failures can limit exposure to later task stages during training, while changing visibility complicates alignment and closure timing during execution. We present a recurrent teacher-student framework that learns a single policy in simulation to jointly command flight, arm motion, and gripper closure without an explicit task-phase input. A privileged teacher learns through reinforcement learning with a critical-state curriculum that exposes acquisition and lifting states before connecting them to normal approach trajectories. Its behavior is distilled into a recurrent visual student that replaces privileged target states with dual-view point clouds and proprioception, integrating observation history for closed-loop control. A dedicated closure objective supervises closure timing from sustained model-defined readiness sequences. Training and primary evaluation use a simulated acquisition-and-payload model with condition-triggered latching, virtual attachment, and wrench-based payload loading for short-distance lifting. Across 8,996 completed simulation episodes under this model, the frozen student achieves full-task success rates of 99.97%, 97.14%, and 95.84% under nominal, physics/control-randomized, and additional camera-randomized conditions, respectively. The nominal latch-count-weighted mean of per-seed 90th-percentile alignment errors at acquisition is 8.12 mm.
