发表机构
Indian Institute of Technology Bombay; Rutgers University（印度理工学院孟买分校; 罗格斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对密集杂乱场景中自遮挡下的物体抓取，提出基于计划条件模仿的TRACE框架，利用数字孪生和教师-学生机制，在模拟和真实机器人上均取得高成功率并显著减少执行时间。
AI 中文摘要
从密集杂乱场景中抓取物体需要进行重新排列，在此过程中，机械臂在移动物体时可能会遮挡其他物体。反复收回机械臂以恢复可见性会中断执行过程。我们提出了TRACE，一个用于自遮挡条件下抓取的计划条件模仿框架。单个无遮挡观测初始化一个数字孪生，其中特权教师生成一个固定的标称滚动。一个循环学生结合局部滚动上下文、部分物体观测和本体感觉来选择能够纠正与预测偏差的动作。行为克隆初始化学生；DAgger使用教师标签在学生访问的状态上进行细化。滚动在整个执行过程中保持固定，因此部署的学生在推动过程中既不需要在线教师查询，也不需要额外的模拟器滚动。在511个模拟测试场景中，TRACE达到了90.7%的成功率，而标称重放为43.4%，特权闭环教师为96.7%。在匹配的26,373个标签预算下，学生状态监督达到87.8%，而仅专家克隆为66.7%，证明了超越额外标签的收益。在UR5e上，TRACE达到了90.0%的成功率，而闭环教师为95.0%，同时将总执行时间从192.7秒减少到67.3秒。它避免了教师在推动过程中每次试验平均16.8次与感知相关的机械臂收回，同时保留最终一次收回以进行可抓取性评估。代码和数据将在以下网址发布：此https URL。
英文摘要
Retrieving objects from dense clutter requires rearrangement during which the manipulator can occlude objects while moving them. Repeated arm withdrawals to restore visibility interrupt execution. We introduce TRACE, a plan-conditioned imitation framework for retrieval under self-occlusion. A single unoccluded observation initializes a digital twin, where a privileged teacher generates a fixed nominal rollout. A recurrent student combines local rollout context, partial object observations, and proprioception to select actions that can correct deviations from the prediction. Behavior cloning initializes the student; DAgger refines it with teacher labels on student-visited states. The rollout remains fixed throughout execution, so the deployed student needs neither online teacher queries nor additional simulator rollouts during pushing. On 511 simulation test scenes, TRACE achieves 90.7% success versus 43.4% for nominal replay and 96.7% for the privileged closed-loop teacher. At a matched 26,373-label budget, student-state supervision achieves 87.8% versus 66.7% for expert-only cloning, demonstrating gains beyond additional labels. On a UR5e, TRACE achieves 90.0% success versus 95.0% for the closed-loop teacher, while reducing total execution time from 192.7 s to 67.3 s. It avoids the teacher's 16.8 sensing-related arm retractions per trial during pushing, retaining a final withdrawal for graspability evaluation. Code and data will be released at: https://trace-retrieval.github.io.
Comments8 pages, 5 figures
