Mini robots assess children’s mental health

According to a 2020 survey by NHS Digital, one in six children aged between 5 to 16 years old have a probable mental disorder. That statistic is a third higher compared to 2017.

A 2022 study carried out by roboticists, computer scientists and psychiatrists from the University of Cambridge found, from a study of a small pool of children (28) aged between 8 to 13 years old, that they opened-up and shared ‘secrets’ with a small humanoid robot, offering it information that they hadn’t felt comfortable sharing via standard methods.

These robots, referred to as ‘Socially Assistive Robots’ (SARs) have the potential to help children during therapeutic and clinical interventions. The full extent of their ability to assess a child’s mental wellbeing is not yet fully known. However, the early indications are positive that they could be used as an additional aid, alongside professional support.

How does a robotic assessment work?

The study consisted of a 45-minute one-to-one session with a 60cm tall robot. During the session the robot performed different tasks, it:

• Asked open ended questions about happy and sad memories over the last week
• Administered the Short Mood and Feelings Questionnaire
• Administered a picture task inspired by the Children’s Apperception Test
• Administered the Revised Children’s Anxiety and Depression Scale for generalised anxiety, panic disorder and low mood.

The feedback revealed that the children enjoyed talking to the robot, and they felt able to share more than they could using a standard assessment or questionnaire. This, the researchers believe, is because of the robots small and unintimidating size. The children also see it as a confidante, something they feel they can safely share their secrets with without getting into trouble.

Interacting with a mini robot

During the 45 minutes the children interacted with the robot, it administered the Short Mood and Feelings questionnaire and a Revised Child Anxiety and Depression Scale. The team found that when compared to standard methods of analysis, the robotised version was the most suitable for identifying wellbeing related anomalies in children.

It was also noted that children exhibited different response patterns depending on if their level of wellbeing was decreasing. Those with the lowest feelings of wellbeing demonstrated a more negative response to the robot, compared to those who were not experiencing wellbeing problems, and thus, their responses were more positive.

The study, by Professor Hatice Gunes, Leader of the Affective Intelligence and Robotics Laboratory in Cambridges Department of Computer Science and Technology, was initially devised to explore how SARs could be used as wellbeing coaches for adults. But after she became a mother, she became interested in how children express themselves.

“After I became a mother, I was much more interested in how children express themselves as they grow, and how that might overlap with my work in robotics. Children are quite tactile, and they’re drawn to technology. If they’re using a screen-based tool, they’re withdrawn from the physical world. But robots are perfect because they’re in the physical world – they’re more interactive, so the children are more engaged.”

Noticing the small things

Some changes within a child’s mental wellbeing can be so subtle that traditional methods of assessment may not catch these micro differences. But the use of robots is a possible way to pick-up these reactions before they become a bigger concern.

SARs are not a means to replace people with machines, but if they can catch micro reactions earlier, it could be to the benefit of everyone – especially the children.

With mental health and wellbeing plummeting over recent years, it is positive to think that the younger generations can get the help exactly when they need it.