Human Perceptions of a Curious Robot that Performs Off-Task Actions

Human Perceptions of a Curious Robot that Performs Off-Task Actions
复制标题

人类对执行任务外行为的好奇机器人的看法

DOI：
--
复制
发表时间：
2020
期刊：
IEEE/ACM International Conference on Human-Robot Interaction
影响因子：
--
通讯作者：
M. Cakmak
M. Cakmak
中科院分区：
--
文献类型：
--
作者：
Nick Walker;K. Weatherwax;Julian Allchin;L. Takayama;M. Cakmak

文献摘要

被引文献

相似文献

研究人员提出了好奇心模型，作为驱动机器人学习和适应环境的一种手段。虽然这些模型在数学原则的庄园中平衡目标和探索导向的动作，但不了解用户如何看待追求任务外动作的机器人。受基于内在奖励的好奇心模型的激励，我们进行了三次在线视频调查，共有264名参与者，评估了各种好奇行为。我们的研究结果表明，一个机器人的任务外的行动被认为是好奇心的表达，但这些行动会导致对机器人的能力的看法产生负面影响。当机器人解释或承认其偏离主要任务时，这可以部分减轻任务外行为的负面影响。CCS概念·应用计算$ ightarrow$心理学; ·以人为本的计算$ ightarrow$交互设计的实证研究。ACM参考格式：Nick步行者、Kevin Weatherwax、Julian Allchin、Leila Takayama和Maya Cakmak。2020.人类对一个好奇的机器人执行任务外动作的感知。在2020年ACM/IEEE人机交互国际会议（HRI '20）的会议记录中，2020年3月23日至26日，英国剑桥。ACM，纽约，NY，美国，10页。https://doi.org/10.1145/3319502.3374821
Researchers have proposed models of curiosity as a means to drive robots to learn and adapt to their environments. While these models balance goal- and exploration-oriented actions in a mathematically principled manor, it is not understood how users perceive a robot that pursues off-task actions. Motivated by a model of curiosity based on intrinsic rewards, we conducted three online video-surveys with a total of 264 participants, evaluating a variety of curious behaviors. Our results indicate that a robot’s off-task actions are perceived as expressions of curiosity, but that these actions lead to a negative impact on perceptions of the robot’s competence. When the robot explains or acknowledges its deviation from the primary task, this can partially mitigate the negative effects of off-task actions. CCS CONCEPTS • Applied computing $ ightarrow$Psychology; • Human-centered computing $ ightarrow$Empirical studies in interaction design. ACM Reference Format: Nick Walker, Kevin Weatherwax, Julian Allchin, Leila Takayama, and Maya Cakmak. 2020. Human Perceptions of a Curious Robot that Performs Off- Task Actions. In Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction (HRI ’20), March 23–26, 2020, Cambridge, United Kingdom. ACM, New York, NY, USA, 10 pages. https://doi.org/10.1145/3319502.3374821