AI and robotics experts from the National Robotarium based at Heriot-Watt University in Scotland have started work on what they believe is the world’s first multi-user conversational robots for healthcare.

Part of a multi million-pound collaborative project involving experts from eight European and Asian institutions, SPRING (Socially Pertinent Robots in Gerontological Healthcare) is the first research project to be announced by the National Robotarium, which opens its doors Heriot-Watt’s Edinburgh campus next year.

SPRING, a four-year project funded by the EU’s €80bn (£72.5bn) Horizon2020 R&D programme, will develop socially assistive robots (not pictured) with the capacity to perform multi-person interactions and “open social conversation” for the first time in a healthcare setting.

The work builds on the success of Heriot-Watt University’s Amazon Alexa Prize conversational AI system, Alana.

The project will focus on supporting elderly patients by carefully coupling scientific findings and user-focused technological developments to bring social robots into gerontological healthcare.

Professor Oliver Lemon, Heriot-Watt University, suggested that social robots could assist clinicians by helping to explain complex concepts to patients with limited medical knowledge.

Professor Lemon said: “Social robot technology is of interest for elderly care because robot companionship has the long-term potential to better connect people with each other.

“Research shows that the careful use of robots in group settings can have a positive impact on health, such as decreased stress and loneliness, and improved mood and sociability.

“Social robots could improve both psychological well-being and the relationship between patients and hospital professionals.”

Robot roll-out

Over the past five years, social robots have been introduced into many public spaces ranging from museums and malls to hospitals and retirement homes.

A recent example is North Bristol NHS Trust and the Bristol Robotics Laboratory at the UWE Bristol, which are currently collaborating on a partnership that will explore how emerging technologies such as AI, machine learning and assistive robots can support patients at home or in hospital.

Yet the technology has faced challenges: hardware and supporting software is often designed for reactive, single-user interactions, leading to limited one-on-one conversations, are among the main limitations to date.

This means that robots typically wait for commands or questions based on a limited set of scripted actions.

“While overcoming the limitations of current social robots raises numerous scientific and technological challenges, it has the potential to create tremendous social impact and economic value,” said Lemon.

“The National Robotarium’s focus on creating societal benefits is ideally aligned to addressing such challenges. This type of technology is touch-free and hands-free so will be in great demand in the future as it will reduce the risk and spread of infection.”

SPRING will develop new research into conversational AI, computer vision, machine learning and human-robot interaction, alongside human behaviour analysis and ‘sensorimotor’ robot control.

The work will focus on helping social robots to understand various individuals and group situations and take appropriate decisions such as identifying patients that have been waiting alone for a long time or who might be anxious. The social robots will ultimately engage in face-to-face conversation with patients, their family members, staff members, and with whole groups of people.