利用低成本硬件学习精细双手操作
Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
AI总结：
本文提出低成本遥操作与端到端模仿系统，并通过 ACT 建模动作序列，使不精确硬件仅凭少量演示完成多项精细双手任务。
摘要：
精细操作任务，例如穿扎带或插入电池，对机器人而言众所周知地困难，因为它们需要高精度、对接触力的谨慎协调以及闭环视觉反馈。执行这些任务通常需要高端机器人、精确传感器或细致校准，而这些设备可能价格昂贵且难以搭建。学习能否让低成本且不精确的硬件执行这些精细操作任务？我们提出了一种低成本系统，可直接根据通过定制遥操作接口采集的真实演示进行端到端模仿学习。然而，模仿学习本身也带来挑战，尤其是在高精度领域：策略中的误差会随时间累积，而且人类演示可能具有非平稳性。为应对这些挑战，我们开发了一种简单而新颖的算法——基于 Transformer 的动作组块（Action Chunking with Transformers，ACT），它学习动作序列上的生成式模型。ACT 使机器人能够在真实世界中学习 6 项困难任务，例如打开半透明调料杯和插入电池，成功率达到 80–90%，且仅需相当于 10 分钟的演示数据。项目网站：https://tonyzhaozh.github.io/aloha/
英文摘要：
Fine manipulation tasks, such as threading cable ties or slotting a battery, are notoriously difficult for robots because they require precision, careful coordination of contact forces, and closed-loop visual feedback. Performing these tasks typically requires high-end robots, accurate sensors, or careful calibration, which can be expensive and difficult to set up. Can learning enable low-cost and imprecise hardware to perform these fine manipulation tasks? We present a low-cost system that performs end-to-end imitation learning directly from real demonstrations, collected with a custom teleoperation interface. Imitation learning, however, presents its own challenges, particularly in high-precision domains: errors in the policy can compound over time, and human demonstrations can be non-stationary. To address these challenges, we develop a simple yet novel algorithm, Action Chunking with Transformers (ACT), which learns a generative model over action sequences. ACT allows the robot to learn 6 difficult tasks in the real world, such as opening a translucent condiment cup and slotting a battery with 80-90% success, with only 10 minutes worth of demonstrations. Project website: https://tonyzhaozh.github.io/aloha/
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。
