The generation of robot social behavior involves assigning the next robot behavior in order to respond to the current user behavior while maintaining continuity with the current robot behavior.
To provide effective and enjoyable human-robot interaction, it is important for social robots to exhibit nonverbal behaviors, such as a handshake or a hug.
However, the traditional approach of reproducing pre-coded motions allows users to easily predict the reaction of the robot, giving the impression that the robot is a machine rather than a real agent. Therefore, we propose a neural network architecture based on the Seq2Seq model that learns social behaviors from human-human interactions in an end-to-end manner.
We adopted a generative adversarial network to prevent invalid pose sequences from occurring when generating long-term behavior. To verify the proposed method, experiments were performed using the humanoid robot Pepper in a simulated environment. Because it is difficult to determine success or failure in social behavior generation, we propose new metrics to calculate the difference between the generated behavior and the ground-truth behavior.
We used these metrics to show how different network architectural choices affect the performance of behavior generation, and we compared the performance of learning multiple behaviors and that of learning a single behavior. We expect that our proposed method can be used not only with home service robots, but also for guide robots, delivery robots, educational robots, and virtual robots, enabling the users to enjoy and effectively interact with the robots.
Original Article: Nonverbal Social Behavior Generation for Social Robots Using End-to-End Learning
The Latest Updates from Bing News
Go deeper with Bing News on:
Human-robot interaction
- Astribot S1 AI Humanoid robot unveiled demonstrating its agility, dexterity and accuracy
This week the Astribot S1 humanoid robot was unveiled in Shenzhen, China, marking another significant leap forward in autonomous robotics ...
- Europe taps deep learning to make industrial robots safer colleagues
European researchers have launched the RoboSAPIENS project to make adaptive industrial robots more efficient and safer to work with humans.
- Robots with weapons? Bill would make that illegal in Massachusetts
"We are creating robots to be friendly and useful, not harm or hurt people or animals," says an executive at Boston Dynamics, which supports the bill.
- Robot uses AI to mimic human facial expressions
A robot capable of mimicking human facial expressions has been developed by engineers at Columbia University in the US.
- Smiling robot face uses AI to mimic a person’s smile
Smiling robot face uses AI to mimic a person’s smile ...
Go deeper with Bing News on:
Social behavior generation
- From Gen Alpha to boomers, we asked 6 therapists what each generation is talking about in therapy
Baby boomers inherited a thriving economy and ruined it for the rest of us. Millennials are anxious avocado-eaters who'll never own property, while Gen Zers are depressed snowflakes who take liberties ...
- Opinion: Does social media rewire kids’ brains? Here’s what the science really says
Jonathan Haidt's "The Anxious Generation" feeds the latest technology panic. But the research says something different.
- The Gen Z mob is not as revolutionary as it thinks
Perhaps figures such as West and Stein praise extremism because they’ve never fully grown up. But approval is no proof that protests are morally right. First Amendment protections don’t disqualify ...
- Gen Z New Yorkers Don't Care About Donald Trump's Trial
While young voters in New York are less interested in the trial, they believe it is "legitimate," according to a new poll.
- ‘Entitled behaviour’: Growing Gen Z work trend leaving bosses fed up
A new trend is sweeping Aussie workplaces and one boss has claimed it’s proof of Gen Z’s “entitlement” and shows they want everything “now”. Generation Z are young, hungry and champing at the bit to ...