Skip to main content
Move the World.
robot's thought process

Lead Image Courtesy of SoftBank

Italian researchers have given one of SoftBank's robots, called Pepper, the ability to share its internal monologue with humans while completing tasks.

Trusting the bots: AI systems can do a lot — drive cars, cool cities, and even save lives — but the systems usually can't explain exactly how they do those things. Sometimes, their developers don't even know the answer.

This is known as AI's black box problem, and it's holding back the mainstream adoption of AI.

"Trust is a major issue with artificial intelligence because people are the end-users, and they can never have full trust in it if they do not know how AI processes information," Sambit Bhattacharya, a professor of computer science at Fayetteville State University, told the Economic Times in 2019.

The idea: University of Palermo researchers thought it might be easier for people to trust an AI bot if they knew the robot's thought process during interactions.

"The robots will be easier to understand for laypeople, and you don't need to be a technician or engineer," study co-author Antonio Chella said in a press release. "In a sense, we can communicate and collaborate with the robot better."

For a study published in iScience, Chella and first author Arianna Pipitone, trained a Pepper robot in table setting etiquette. They then gave it the ability to say, in plain English, what it was "thinking" when executing a task.

Inside a robot's head: In a recorded demo, when asked to hand over a napkin, the robot starts talking in what sounds like a stream of consciousness: "Where is the napkin? The object is in the box....I am using my right arm to get the object."

This gave the person working with Pepper an understanding of the robot's thought process.

"The robot is no longer a black box, but it is possible to look at what happens inside it and why some decisions are (made)," the researchers wrote in their study.

robot's thought process

Pepper could share its internal monologue during the table setting experiment. Credit: Antonio Chella & Arianna Pipotone

The cold water: Equipping collaborative AI robots like Pepper with the ability to "think out loud" could make them more trustworthy — but it's still only possible if the bot's designer knows what's going on inside the AI's brain, or can program the system to figure it out.

Every explanation Pepper gave during the demo was something the researchers trained it to be able to say — they didn't learn anything new about the robot's thought process, though the rest of us would.

"The robot is no longer a black box."

Antonio Chella & Arianna Pipitone

Bonus round: The experiment did yield one surprise, though: Pepper was better at solving problems — such as what to do when a command goes against the established rules — when it could think through them out loud with a human partner, who could then provide feedback.

When faced with 30 of these dilemmas, the Pepper that could share its thought process completed 26, while the one that couldn't talk it out finished only 18 (a task was considered incomplete when the robot ran out of possible actions).

"Inner speech enables alternative solutions for the robots and humans to collaborate and get out of stalemate situations," Pipitone said in the press release.

We'd love to hear from you! If you have a comment about this article or if you have a tip for a future Freethink story, please email us at [email protected].

Up Next

Uprising
Can Humans Figure Out How Deep Learning AI Thinks?
deep learning ai
Uprising
Can Humans Figure Out How Deep Learning AI Thinks?
Deep learning AI is becoming more complex, capable, and impenetrable, but these scientists are attempting to break the black box.

Deep learning AI is becoming more complex, capable, and impenetrable, but these scientists are attempting to break the black box.

Artificial Intelligence
Deep Learning vs. Machine Learning: Explained
deep learning vs machine learning
Artificial Intelligence
Deep Learning vs. Machine Learning: Explained
Deep learning vs. machine learning AI: what’s the difference?

Deep learning vs. machine learning AI: what’s the difference?

Robotics
This AI Robot Could Become Your Favorite Coworker
AI Robot
Robotics
This AI Robot Could Become Your Favorite Coworker
European researchers have developed an AI robot to safely work alongside humans, anticipating their needs and providing a strong pair of extra hands.

European researchers have developed an AI robot to safely work alongside humans, anticipating their needs and providing a strong pair of extra hands.

The Future Explored
Robots Can Read Your P-P-P-Poker Face
emotion ai
The Future Explored
Robots Can Read Your P-P-P-Poker Face
Emotion-detecting technology could be the next frontier of personalization. But what does this mean for privacy?

Emotion-detecting technology could be the next frontier of personalization. But what does this mean for privacy?

Robotics
If You Train Robots Like Dogs, They Learn Faster
reinforcement learning robots
Robotics
If You Train Robots Like Dogs, They Learn Faster
The dog-inspired SPOT framework effectively trains an AI robot more quickly than other reinforcement learning methods.

The dog-inspired SPOT framework effectively trains an AI robot more quickly than other reinforcement learning methods.

Dispatches
AI Will Make You Smarter
AI Will Make You Smarter
Dispatches
AI Will Make You Smarter
Artificial intelligence will multiply your own intelligence, in ways that will surprise you.
By Terrence Sejnowski

Artificial intelligence will multiply your own intelligence, in ways that will surprise you.

Future of Fertility
For Childhood Cancer Survivors, Adult Fertility Isn’t a Given
For Childhood Cancer Survivors, Adult Fertility Isn’t a Given
Future of Fertility
For Childhood Cancer Survivors, Adult Fertility Isn’t a Given
Experimental procedures offer beta solutions for girls, and more time to figure it out for boys.
By Julia Sklar

Experimental procedures offer beta solutions for girls, and more time to figure it out for boys.

Outer Space
Meet the Amateur Astronomer Who Found a Lost NASA Satellite
Meet the Amateur Astronomer Who Found a Lost NASA Satellite
Watch Now
Outer Space
Meet the Amateur Astronomer Who Found a Lost NASA Satellite
A $130 million satellite vanished. Over a decade later, a blogger/astronomer found it.
Watch Now

Amateur astronomer Scott Tilley made international headlines when he rediscovered NASA’s IMAGE satellite, 13 years after it mysteriously disappeared. In this interview with Freethink, Scott discusses his role in the satellite’s recovery, why he enjoys amateur astronomy, and how citizen scientists like him have contributed to our knowledge of space from the space race to the present day.

Dispatches
Does CRISPR Cause Cancer?
Does CRISPR Cause Cancer?
Dispatches
Does CRISPR Cause Cancer?
Two studies find that CRISPR'd cells tend to become cancerous. Here's what that means for biotech medicine.

Two studies find that CRISPR'd cells tend to become cancerous. Here's what that means for biotech medicine.