ARCADE：通过增强现实实现可扩展的演示收集与生成以用于模仿学习
ARCADE: Scalable Demonstration Collection and Generation via Augmented Reality for Imitation Learning
AI总结：
本文提出 ARCADE 框架，利用增强现实简化机器人演示收集，并从单个人类演示自动生成合成演示，在 Fetch 机器人多个操作任务及真实倒水任务中验证了其可扩展性和有效性。
摘要：
机器人模仿学习（IL）是机器人学习中的一项关键技术，智能体通过模仿人类演示来学习。然而，IL 面临可扩展性挑战，这些挑战源于不够用户友好的演示收集方法，以及为有效训练而积累足够数量演示所需的大量时间。为此，我们提出了增强现实演示收集与生成（ARCADE）框架，旨在扩大机器人操作任务的演示收集规模。我们的框架结合了两项关键能力：1）利用 AR 使演示收集变得像用户用手执行日常任务一样简单；2）能够从单个人类演示自动生成额外的合成演示，从而显著减少用户的工作量和时间。我们在真实的 Fetch 机器人上评估了 ARCADE 在三个机器人任务上的表现：3-Waypoints-Reach、Push 和 Pick-And-Place。使用我们的框架，我们能够利用经典 IL 算法——普通行为克隆（BC）快速训练出一个策略，该策略在这三个任务上均表现优异。我们还将 ARCADE 部署到一个真实家庭任务 Pouring-Water 上，取得了 80% 的成功率。
英文摘要：
Robot Imitation Learning (IL) is a crucial technique in robot learning, where agents learn by mimicking human demonstrations. However, IL encounters scalability challenges stemming from both non-user-friendly demonstration collection methods and the extensive time required to amass a sufficient number of demonstrations for effective training. In response, we introduce the Augmented Reality for Collection and generAtion of DEmonstrations (ARCADE) framework, designed to scale up demonstration collection for robot manipulation tasks. Our framework combines two key capabilities: 1) it leverages AR to make demonstration collection as simple as users performing daily tasks using their hands, and 2) it enables the automatic generation of additional synthetic demonstrations from a single human-derived demonstration, significantly reducing user effort and time. We assess ARCADE's performance on a real Fetch robot across three robotics tasks: 3-Waypoints-Reach, Push, and Pick-And-Place. Using our framework, we were able to rapidly train a policy using vanilla Behavioral Cloning (BC), a classic IL algorithm, which excelled across these three tasks. We also deploy ARCADE on a real household task, Pouring-Water, achieving an 80% success rate.
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。
