Researchers from the RIKEN Guardian Robot Project in Japan have created an android child that can convey six basic emotions. The name of the android is Nikola, and the research behind its development tested how well people could identify the six facial expressions of sadness, happiness, fear, anger, surprise, and disgust.
The research was published in Frontiers in Psychology.
Artificial Muscles and Emotions
The emotions were generated by “muscles” that could move in Nikola’s face, and it was the first time that the quality of android-expressed emotion has been tested and verified for the specific emotions.
Nikola’s face contains 29 pneumatic actuators that control the movements of artificial muscles. Six additional actuators control head and eyeball movements. Because pneumatic actuators are controlled by air pressure, the movements are smooth and silent.
The actuators were based on the Facial Action Coding System (FACS), which is often used to study facial expressions. Traditional studies of emotions, as well as how people react to them, often face several limitations. One of the biggest difficulties in conducting a controlled experiment with live people interacting. An experiment that involves individuals looking at photos or videos of people is less natural and doesn’t result in the same reactions.
The new study was led by Wataru Sato from the RIKEN Guardian Robot Project.
“The hope is that with androids like Nikola, we can have our cake and eat it too,” says Sato. “We can control every aspect of Nikola’s behavior, and at the same time study live interactions.”
Identifying Nikola’s Facial Expressions
To achieve this, the team had to first see if Nikola’s facial expressions were understandable.
The result showed that a person certified in FACS scoring was able to identify each facial action unit, which meant that Nikola’s facial movements accurately resembled a real human’s. It also demonstrated that everyday people could recognize the six emotions in Nikola’s face. With that said, some emotions like disgust proved more difficult to identify due to Nikola’s silicone skin being less elastic than real human skin. This meant that the android couldn’t form wrinkles very well.
“In the short term, androids like Nikola can be important research tools for social psychology or even social neuroscience,” says Sato. “Compared with human confederates, androids are good at controlling behaviors and can facilitate rigorous empirical investigation of human social interactions.”
While Nikola still doesn’t have a body, the team wants to build a full android that can assist people.
“Androids that can emotionally communicate with us will be useful in a wide range of real-life situations, such as caring for older people, and can promote human wellbeing,” says Sato.
- Removing Objects From Video More Efficiently With Machine Learning
- AI Hardware Technology Imitates Changes in Neural Network Topology
- Stealing Machine Learning Models Through API Output
- NeRF: The Challenge of Editing the Content of Neural Radiance Fields
- Researchers Create Self-Propelled Artificial Cilia