.png){kind=icon}
返回
Simultaneously learning actions and goals from demonstration
.png){kind=icon}
PRE
AI
DOI：10.1007/s10514-015-9448-x.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Our research aim is to develop interactions and algorithms for learning from na < ve human teachers through demonstration. We introduce a novel approach to leverage the goal-oriented nature of human teachers by learning an action model and a goal model simultaneously from the same set of demonstrations. We use robot motion data to learn an action model for executing the skill. We use a generic set of perceptual features to learn a goal model and use it to monitor the executed action model. We evaluate our approach with data from 8 na < ve teachers demonstrating two skills to the robot. We show that the goal models in the perceptual feature space are consistent across users and correctly recognize demonstrations in cross-validation tests. We additionally observe that a subset of users were not able to teach a successful action model whereas all of them were able to teach a mostly successful goal model. When the learned action models are executed on the robot, the success was on average 66.25 %. Whereas the goal models were on average 90 % correct at deciding on success/failure of the executed action, which we call monitoring.
Keyword:
Learning from demonstration
Goal learning
Human-robot interaction
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.3
论文数:
1.7K
被引数:
5.0K
机构
引用论文
.png){kind=icon}
查看更多内容