Scholarlink

<p>Learning from Demonstration (LfD) algorithms seek to enable end-users to teach robots new skills through human demonstration of a task. Previous studies have analyzed how robot failure affects human trust, but not in the context of the human teaching the robot. In this paper, we investigate how human teachers react to robot failure in an LfD setting. We conduct a study in which participants teach a robot how to complete three tasks, using one of three instruction methods, while the robot is pre-programmed to either succeed or fail at the task. We find that when the robot fails, people trust the robot less (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(p&lt;.001\)</EquationSource> </InlineEquation>) and themselves less (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(p=.003\)</EquationSource> </InlineEquation>) and they believe that others will trust them less (<InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(p&lt;.001\)</EquationSource> </InlineEquation>). Human teachers also have a lower impression of the robot and themselves (<InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(p&lt;.001\)</EquationSource> </InlineEquation>) and found the task more difficult when the robot fails (<InlineEquation ID="IEq5"> <EquationSource Format="TEX">\(p&lt;.001\)</EquationSource> </InlineEquation>). Motion capture was found to be a less difficult instruction method than teleoperation (<InlineEquation ID="IEq6"> <EquationSource Format="TEX">\(p=.012\)</EquationSource> </InlineEquation>), while kinesthetic teaching gave the teachers the lowest impression of themselves compared to teleoperation (<InlineEquation ID="IEq7"> <EquationSource Format="TEX">\(p=.035\)</EquationSource> </InlineEquation>) and motion capture (<InlineEquation ID="IEq8"> <EquationSource Format="TEX">\(p=.001\)</EquationSource> </InlineEquation>). Importantly, a mediation analysis showed that people’s trust in themselves is heavily mediated by what they think that others—including the robot—think of them (<InlineEquation ID="IEq9"> <EquationSource Format="TEX">\(p&lt;.001\)</EquationSource> </InlineEquation>). These results provide valuable insights to improving the human–robot relationship for LfD.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

The effects of robot learning on human teachers for learning from demonstration

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月23日

查看全文
  • Erin Hedlund-Botti,
  • Julianna Schalkwyk,
  • Michael Johnson,
  • Matthew Gombolay

摘要

Learning from Demonstration (LfD) algorithms seek to enable end-users to teach robots new skills through human demonstration of a task. Previous studies have analyzed how robot failure affects human trust, but not in the context of the human teaching the robot. In this paper, we investigate how human teachers react to robot failure in an LfD setting. We conduct a study in which participants teach a robot how to complete three tasks, using one of three instruction methods, while the robot is pre-programmed to either succeed or fail at the task. We find that when the robot fails, people trust the robot less ( \(p<.001\) ) and themselves less ( \(p=.003\) ) and they believe that others will trust them less ( \(p<.001\) ). Human teachers also have a lower impression of the robot and themselves ( \(p<.001\) ) and found the task more difficult when the robot fails ( \(p<.001\) ). Motion capture was found to be a less difficult instruction method than teleoperation ( \(p=.012\) ), while kinesthetic teaching gave the teachers the lowest impression of themselves compared to teleoperation ( \(p=.035\) ) and motion capture ( \(p=.001\) ). Importantly, a mediation analysis showed that people’s trust in themselves is heavily mediated by what they think that others—including the robot—think of them ( \(p<.001\) ). These results provide valuable insights to improving the human–robot relationship for LfD.