Learning from Demonstration (LfD) aims to encode versatile skills from human demonstrations. The field has been gaining popularity since it facilitates knowledge transfer to robots without requiring expert knowledge in robotics. During task executions, the robot motion is usually influenced by constraints imposed by environments. In light of this, task-parameterized LfD (TP-LfD) encodes relevant contextual information in reference frames, enabling better skill generalization to new situations. However, most TP-LfD algorithms require multiple demonstrations in various environment conditions to ensure sufficient statistics for a meaningful model. It is not a trivial task for robot users to create different situations and perform demonstrations under all of them. Therefore, this paper presents a novel concept for learning motion policies from few demonstrations by finding the reference frame weights which capture frame importance/relevance during task executions. Experimental results in both simulation and real robotic environments validate our approach.

翻译：从示范中学习旨在从人类示范中编码通用技能。该领域因无需机器人专业知识即可实现向机器人知识迁移而日益受到关注。在任务执行过程中，机器人运动通常受环境约束影响。鉴于此，任务参数化示范学习通过参考帧编码相关上下文信息，有利于技能向新场景的泛化。然而，多数TP-LfD算法需要在不同环境条件下进行多次示范以获取足够统计量来构建有效模型。对机器人用户而言，创建不同情境并在所有情境下执行示范并非易事。因此，本文提出一种新概念：通过寻找能反映任务执行过程中参考帧重要性的帧权重，从少量示范中学习运动策略。仿真及真实机器人环境的实验结果验证了本方法的有效性。