Robohub.org
 

TERESA project adds a vital component to human-robot interaction: social intelligence


by
02 February 2017



share this:
Source: TERESA project

TERESA project. Photo credit: Claire Cocano

TERESA is a 3-year research project funded by the European Union and carried out by six institutions from four European countries. Its goal is to develop a new socially intelligent semi-autonomous telepresence system.

A telepresence system consists of an internet-connected mobile robot equipped with a video screen, speakers, and microphones.  A remotely located pilot sitting at a computer can control the robot and use it to interact with people at the robot’s location.

Telepresence systems offer a number of advantages over traditional teleconferencing solutions such as Skype. The robot acts as an avatar for the pilot, allowing the pilot to appear much more present to people around the robot. In addition, because a telepresence robot is mobile, it enables spontaneous interaction, such as mingling at a cocktail party, that would not be possible with Skype.

Source: TERESA project

TERESA project. Photo credit: Claire Cocano

However, existing telepresence systems suffer from a key limitation. They require the pilot to manually execute many behaviours that would happen automatically and effortlessly if the pilot was physically present.  These include navigating through groups of people in a socially appropriate way, maintaining a socially appropriate distance and orientation to others, and maintaining socially appropriate eye contact.

The need to manually execute these low-level behaviours at the same time as selecting high-level behaviours, such as whom to talk to and what to say, can afflict the pilot with cognitive overload, which in turns leads to poor quality social interaction.

In the TERESA project, we have created a new semi-autonomous telepresence system that automates low-level decision making, thereby freeing the pilot to focus on the social interaction itself. TERESA can autonomously navigate through groups of people in a socially intelligent way and approach a specific person selected by the pilot. During conversation, TERESA can also maintain a socially appropriate distance from those around the robot and set the height, orientation, and tilt of its video screen so as to facilitate that conversation.

TERESA is not just intelligent but socially intelligent, thanks to advances in multi-modal perception, machine learning, and robotics developed in the project by an interdisciplinary team of computer scientists, engineers, sociologists, and experts in human-robot interaction.

Working with an elderly day centre in France, we have repeatedly validated TERESA with dozens of elderly subjects. Our results show that semi-autonomous telepresence systems can play a key role in improving the quality of remote interaction. Although TERESA is just a proof of concept, it illustrates the potential of social intelligence to transform telepresence systems and other robots as well.


If you enjoyed this article, you may want to read more about telepresence robotics:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.



tags: , , , ,


Shimon Whiteson research focuses on artificial intelligence.
Shimon Whiteson research focuses on artificial intelligence.





Related posts :



Robot Talk Episode 119 – Robotics for small manufacturers, with Will Kinghorn

  02 May 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Will Kinghorn from Made Smarter about how to increase adoption of new tech by small manufacturers.

Multi-agent path finding in continuous environments

  01 May 2025
How can a group of agents minimise their journey length whilst avoiding collisions?

Interview with Yuki Mitsufuji: Improving AI image generation

  29 Apr 2025
Find out about two pieces of research tackling different aspects of image generation.

Robot Talk Episode 118 – Soft robotics and electronic skin, with Miranda Lowther

  25 Apr 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Miranda Lowther from the University of Bristol about soft, sensitive electronic skin for prosthetic limbs.

Interview with Amina Mević: Machine learning applied to semiconductor manufacturing

  17 Apr 2025
Find out how Amina is using machine learning to develop an explainable multi-output virtual metrology system.

Robot Talk Episode 117 – Robots in orbit, with Jeremy Hadall

  11 Apr 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Jeremy Hadall from the Satellite Applications Catapult about robotic systems for in-orbit servicing, assembly, and manufacturing.

Robot Talk Episode 116 – Evolved behaviour for robot teams, with Tanja Kaiser

  04 Apr 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Tanja Katharina Kaiser from the University of Technology Nuremberg about how applying evolutionary principles can help robot teams make better decisions.

AI can be a powerful tool for scientists. But it can also fuel research misconduct

  31 Mar 2025
While AI is allowing scientists to make technological breakthroughs, there’s also a darker side to the use of AI in science: scientific misconduct is on the rise.



 

Robohub is supported by:




Would you like to learn how to tell impactful stories about your robot or AI system?


scicomm
training the next generation of science communicators in robotics & AI


©2025.05 - Association for the Understanding of Artificial Intelligence


 












©2025.05 - Association for the Understanding of Artificial Intelligence