模仿学习能否保持灵巧操作中的时间鲁棒性？跨任务执行速度的专家-学习者对比

摘要

通过模仿学习的灵巧操作策略通常针对场景、物体或指令的变化进行鲁棒性评估，但较少考察其在不同任务执行速度下的表现。这使得我们仍不清楚学习者相对于其模仿的专家保留了多大的时间鲁棒性。我们在相同的任务条件、初始条件采样和加速倍数下对专家和学习者进行了比较。我们将该评估实例化为 ParcelStow——一项接触丰富的任务，机器人需要抓取、重新定向并插入一个包裹。演示涵盖了包裹获取之后各操作阶段的加速范围。一个脚本化专家和基于该专家演示训练的 Action Chunking with Transformers（ACT）策略在标称速度下均达到100%的任务成功率。然而，两者的成功率在演示速度范围内出现分化：在最大演示速度下，专家成功率为84%，ACT成功率为53%。两个采用不同参数初始化的ACT策略表现出相似的性能下降，从标称速度到最大演示速度分别下降34和48个百分点，而专家仅下降16个百分点。阶段级分析表明，ACT在最大演示速度下的47次失败中，有35次是由于插入错位所致。在相对运动交接方式下，每一次由ACT完成的抓取都能在自由空间中的重新定向与传递阶段保持对包裹的把持，但完成整体任务的比例仅为64%，而在专家抓取后这一比例为95%。在所有被评估的策略和速度条件下，414次未形成力闭合的抓取均未完成任务。因此，标称任务成功率相同并不意味着专家性能在不同执行速度下得到保持。代码、数据和评估脚本可在 https://github.com/coenwerem/parcelstow 获取。

English

Dexterous manipulation policies learned by imitation are typically evaluated for robustness to variation in scenes, objects, or instructions, but their performance across task execution speeds is less often examined. This leaves open how much temporal robustness a learner retains relative to the expert it imitates. We compare an expert and learner under the same task conditions, initial-condition draws, and speedup factors. We instantiate the evaluation in ParcelStow, a contact-rich task in which the robot acquires, reorients, and inserts a parcel. The demonstrations span the speedup range for the manipulation phases after parcel acquisition. A scripted expert and an Action Chunking with Transformers (ACT) policy trained from the expert's demonstrations both achieve 100 percent task success at nominal speed. Their success rates diverge within the demonstrated range: at its maximum, expert success is 84 percent and ACT success is 53 percent. Two ACT policies with different parameter initializations show similar degradation, decreasing by 34 and 48 percentage points from nominal speed to the maximum demonstrated speed, compared with 16 points for the expert. Stage-level analysis shows that 35 of ACT's 47 failures at the maximum demonstrated speed are insertion misalignments. Under the relative-motion handoff, every ACT acquisition retains the parcel through reorientation and transfer in free space, but only 64 percent complete the overall task, compared with 95 percent after expert acquisition. Across all evaluated policies and speeds, none of the 414 acquisitions without force closure completes the task. Equal nominal task success therefore does not imply preservation of expert performance across execution speeds. Code, data, and evaluation scripts are available at https://github.com/coenwerem/parcelstow.