Imitating manipulation skills through observing human demonstrations in everyday life is promising in allowing service robots to be programed quickly, as well as to perform human-like behaviors. Such a Learning by demonstration (LbD) problem is challenging because robots are expected to adapt their learned behaviors to the changes of task parameters and the environment, rather than simply cloning the human teacher's motion. In this paper, we propose a hierarchical and parameterized LbD framework that combines symbolic and trajectory learning of pick-and-place manipulation tasks. We have extended the two-step parameterized learning method with error compensation for learning Environment-adaptive Action Primitives (EaAPs), which is capable of adapting robot's reproduced trajectories to new task instances as well as environmental changes. To arrive at refined plans in situations of under-specified human demonstrations, we propose to model the semantics of demonstrated activities with PDDL-based skill scripts. Therefore, latent motion primitives that are impossible to be learned directly from observing human demonstration in noisy video data can be inferred. The proposed method is implemented as a hierarchical LbD framework and has been evaluated on real robot hardware to illustrate the effectiveness of the proposed approach. GRAPHICAL ABSTRACT

中文翻译：

---

从未指定的人类演示中进行拾取和放置操作的分层和参数化学习

通过观察日常生活中的人类演示来模仿操作技能，有望让服务机器人快速编程，并执行类似人类的行为。这种示范学习 (LbD) 问题具有挑战性，因为机器人需要根据任务参数和环境的变化调整其学习行为，而不是简单地克隆人类教师的动作。在本文中，我们提出了一种分层和参数化的 LbD 框架，该框架结合了拾放操作任务的符号和轨迹学习。我们扩展了两步参数化学习方法，用于学习环境自适应动作原语（EaAP）的误差补偿，该方法能够使机器人的再现轨迹适应新的任务实例以及环境变化。为了在未指定人类演示的情况下制定完善的计划，我们建议使用基于 PDDL 的技能脚本对演示活动的语义进行建模。因此，可以推断出无法通过观察嘈杂视频数据中的人类演示直接学习的潜在运动原语。所提出的方法作为分层 LbD 框架实施，并已在真实机器人硬件上进行了评估，以说明所提出方法的有效性。图形概要 所提出的方法作为分层 LbD 框架实施，并已在真实机器人硬件上进行了评估，以说明所提出方法的有效性。图形概要 所提出的方法作为分层 LbD 框架实施，并已在真实机器人硬件上进行了评估，以说明所提出方法的有效性。图形概要