自动化可变形密封圈装配
Automating Deformable Gasket Assembly
AI总结：
本文针对长周期高精度的可变形密封圈装配任务，提出并对比了4种方法（1种深度模仿学习策略和3种程序化算法），通过100次物理试验发现Binary+算法在直通道装配中成功率达10/10且优于学习策略。
摘要：
在密封圈装配中，必须将可变形密封圈对齐并压入狭窄通道。该任务常见于汽车、电器、电子产品及其他产品的密封表面制造过程。密封圈装配是一项长周期、高精度任务，密封圈必须与通道对齐并被完全压入以实现牢固贴合。为比较不同方法，我们提出了4种密封圈装配方法：一种来自深度模仿学习的策略和三种程序化算法。我们用100次物理试验评估这些方法。结果表明，Binary+算法在直通道上10/10成功，而基于250次人类遥操作演示的学习策略在10次试验中8次成功，且明显更慢。代码、CAD模型、视频和数据可在https://berkeleyautomation.github.io/robot-gasket/找到。
英文摘要：
In Gasket Assembly, a deformable gasket must be aligned and pressed into a narrow channel. This task is common for sealing surfaces in the manufacturing of automobiles, appliances, electronics, and other products. Gasket Assembly is a long-horizon, high-precision task and the gasket must align with the channel and be fully pressed in to achieve a secure fit. To compare approaches, we present 4 methods for Gasket Assembly: one policy from deep imitation learning and three procedural algorithms. We evaluate these methods with 100 physical trials. Results suggest that the Binary+ algorithm succeeds in 10/10 on the straight channel whereas the learned policy based on 250 human teleoperated demonstrations succeeds in 8/10 trials and is significantly slower. Code, CAD models, videos, and data can be found at https://berkeleyautomation.github.io/robot-gasket/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
