Modeling the Timing and Duration of Grip Behavior to Express Emotions for a Social Robot
Modeling the Timing and Duration of Grip Behavior to Express Emotions for a Social Robot
复制标题
DOI：
10.1109/lra.2020.3036372
复制
发表时间：
2021-01
影响因子：
5.2
通讯作者：
Xiqian Zheng;M. Shiomi;T. Minato;H. Ishiguro
中科院分区：
文献类型：
--
作者：
Xiqian Zheng;M. Shiomi;T. Minato;H. Ishiguro
这封信讨论的是当人们一起观看刺激视频时，抓取时机对机器人表达情感的影响。过去对人机触摸交互的研究主要集中在表达机器人情感的触摸行为类型上，而对时间因素的关注较少。在这封信中，我们进行了数据收集，以调查适当的抓握时间来表达温暖和恐怖的情绪。参与者在观看视频刺激时，通过使用机器人来识别触摸（抓握）的时间和持续时间。一般来说，他们更喜欢在恐怖视频高潮前抓拍，而在暖心视频高潮后抓拍。我们通过概率分布的拟合方法来模拟时间和持续时间，以重现类似人类的触摸行为，并将模型应用于机器人。
This letter addresses the effects of grip timing to express a robot's emotions to people while they are watching a video stimulus together. Past studies on human-robot touch interaction focused on the types of touch behaviors for expressing a robot's emotion, but timing factors have received less attention. In this letter, we conducted data collection to investigate the appropriate grip timing to express heartwarming and horror emotions. Participants identified touch (grip) timing and durations by using a robot while they are watching video stimuli. Typically, they preferred a grip timing before a climax for horror videos but after a climax for heartwarming videos. We modeled the timing and durations by a fitting approach to probabilistic distribution to reproduce human-like touch behaviors, and also we implemented the models to an android robot.