arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2111.07447cs.ROcs.LG
收藏

通过自我重放一次演示学习多阶段任务

Learning Multi-Stage Tasks with One Demonstration via Self-Replay

Imperial College London(帝国理工学院)

Norman Di Palo, Edward Johns

摘要:

在这项工作中,我们介绍了一种新的方法,从一个单一的人类演示学习日常的多阶段任务,而不需要任何先验的对象知识。受最近的粗到精模仿学习方法的启发,我们将模仿学习建模为一个学习对象到达阶段,然后是演示者动作的开环重放。我们在此基础上构建了多阶段任务,在人类演示之后,机器人可以自动收集整个多阶段任务的图像数据,通过到达序列中的下一个对象,然后重播演示,然后在任务的所有阶段循环重复。我们评估与现实世界的一组日常的多阶段的任务,我们表明,我们的方法可以解决从一个单一的演示实验。视频和补充材料可以在https://www.robot-learning.uk/self-replay上找到。

英文摘要:

In this work, we introduce a novel method to learn everyday-like multi-stage tasks from a single human demonstration, without requiring any prior object knowledge. Inspired by the recent Coarse-to-Fine Imitation Learning method, we model imitation learning as a learned object reaching phase followed by an open-loop replay of the demonstrator's actions. We build upon this for multi-stage tasks where, following the human demonstration, the robot can autonomously collect image data for the entire multi-stage task, by reaching the next object in the sequence and then replaying the demonstration, and then repeating in a loop for all stages of the task. We evaluate with real-world experiments on a set of everyday-like multi-stage tasks, which we show that our method can solve from a single demonstration. Videos and supplementary material can be found at https://www.robot-learning.uk/self-replay.

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。

↑