Tanevska Ana, Rea Francesco, Sandini Giulio, Cañamero Lola, Sciutti Alessandra
Department of Robotics, Brain and Cognitive Science, Italian Institute of Technology (IIT), Genova, Italy.
EECAiA Lab, School of Computer Science, University of Hertfordshire, Hatfield, United Kingdom.
Front Robot AI. 2020 Oct 19;7:121. doi: 10.3389/frobt.2020.00121. eCollection 2020.
In our everyday lives we regularly engage in complex, personalized, and adaptive interactions with our peers. To recreate the same kind of rich, human-like interactions, a social robot should be aware of our needs and affective states and continuously adapt its behavior to them. Our proposed solution is to have the robot learn how to select the behaviors that would maximize the pleasantness of the interaction for its peers. To make the robot autonomous in its decision making, this process could be guided by an internal motivation system. We wish to investigate how an adaptive robotic framework of this kind would function and personalize to different users. We also wish to explore whether the adaptability and personalization would bring any additional richness to the human-robot interaction (HRI), or whether it would instead bring uncertainty and unpredictability that would not be accepted by the robot's human peers. To this end, we designed a socially adaptive framework for the humanoid robot iCub. As a result, the robot perceives and reuses the affective and interactive signals from the person as input for the adaptation based on internal social motivation. We strive to investigate the value of the generated adaptation in our framework in the context of HRI. In particular, we compare how users will experience interaction with an adaptive versus a non-adaptive social robot. To address these questions, we propose a comparative interaction study with iCub whereby users act as the robot's caretaker, and iCub's social adaptation is guided by an internal comfort level that varies with the stimuli that iCub receives from its caretaker. We investigate and compare how iCub's internal dynamics would be perceived by people, both in a condition when iCub does not personalize its behavior to the person, and in a condition where it is instead adaptive. Finally, we establish the potential benefits that an adaptive framework could bring to the context of repeated interactions with a humanoid robot.
在日常生活中，我们经常与同龄人进行复杂、个性化且适应性强的互动。为了重现同样丰富、类似人类的互动，社交机器人应该了解我们的需求和情感状态，并不断根据这些来调整其行为。我们提出的解决方案是让机器人学习如何选择能使与同龄人互动的愉悦感最大化的行为。为了使机器人在决策中具有自主性，这个过程可以由内部动机系统来引导。我们希望研究这种自适应机器人框架将如何运作并针对不同用户进行个性化定制。我们还希望探索这种适应性和个性化是否会给人机交互（HRI）带来任何额外的丰富性，或者它是否反而会带来人类同伴无法接受的不确定性和不可预测性。为此，我们为仿人机器人iCub设计了一个社交自适应框架。结果，机器人感知并重新利用来自人的情感和交互信号，作为基于内部社会动机进行适应的输入。我们努力在人机交互的背景下研究我们框架中产生的适应性的价值。特别是，我们比较用户与自适应社交机器人和非自适应社交机器人互动时的体验。为了解决这些问题，我们提出了一项与iCub的比较互动研究，在该研究中用户充当机器人的照料者，iCub的社交适应由一个内部舒适水平引导，该水平会随着iCub从其照料者那里接收到的刺激而变化。我们研究并比较在iCub不对人的行为进行个性化定制的情况下以及在其具有适应性的情况下，人们会如何感知iCub的内部动态。最后，我们确定自适应框架在与仿人机器人反复互动的背景下可能带来的潜在好处。
