Published: 24th November 2023
IIIT Bangalore Researchers use psychology to build more ‘human-like bots’
The work on the possible game-changer tech was started in 2021 and the pipeline was trained on human-to-human interaction and human-robot interaction, in total 36 sessions
As the relationship between humans and technology gets more diverse and complex, young researchers at the International Institute of Information Technology (IIIT) Bangalore have developed a technology for modelling engagement in human-robot interactions.
This innovative technology will provide deeper insights into a person's personality, attitude, and emotions including adopting the Big Five personality traits, the Interpersonal Circumplex (IPC), and the Triandis Theory of Interpersonal Behavior (TIB), stated a report in The New Indian Express.
The interpretable and ready-to-use pipeline was developed by graduate students Soham Joshi and Arpitha Malavalli. The research was published in One Journal of the Public Library Of Science (PLOS).
"Automated systems of today are very static and standard in their response, and the quality of interaction is not up to the mark. However, when we humans have an interaction with each other, we analyse their mood, personality, hand gestures and expressions and alter our responses accordingly. That's what this pipeline aims to do - be more cognitive and human-like," said Shrisha Rao, Professor at IIIT-Bangalore, and the senior researcher of the study ‘A pipeline to model engagement in human-robot interactions’.
The applications of this pipeline can be found in domains like online learning platforms, assistive robotics, and intelligent conversational agents. If there is low engagement in customers using chatbots the pipeline may show that there needs to be a change in the interaction style.
Similarly for online learning, if students are not engaged in the topic, the pipeline could predict disinterest, and introduce gamification and incentives to engage the students. For control systems, if a pilot or driver falls asleep, a trigger can be sent by the pipeline to be put on auto-mode.
"We wanted to leverage psychology theories that already exist and are well-defined. We tried to mirror the same in human-robot interaction. Given that if the robot can see your head movement or hear your voice modulation, then it can derive some inferences on your personality, and the end goal is to analyse if you're engaged in the conversation, and suggest ways on how a human would go about it," shared Arpitha with The New Indian Express.
The work on the possible game-changer tech was started in 2021 and the pipeline was trained on human-to-human interaction and human-robot interaction over 36 sessions. Speaking on the accuracy of the model, Arpitha and Rao added that any psychology-related study cannot be 100 percent accurate, however they were able to derive better correlations and is explainable.
The team will take the study forward and further establish the use of psychology for robots and also partner with industries to bring the application of the pipeline into products.