The team used adaptive control and Nash equilibrium game theory to programme a robot that can understand its human user’s behaviour, while it was interracting with the human, in order to better anticipate the human’s movements and respond to them.

“Game theory has had important impacts in economics during the last century and lead to several Nobel prizes such as Nash’s one,” said Imperial College’s Professor Etienne Burdet. “To apply it for human-robot interaction, it was necessary to understand how the robot can identify the human user’s control goals simultaneously to smoothly.”

“It is still very early days in the development of robots and at present, those that are used in a working capacity are not intuitive enough to work closely and safely with human users,” said Sussex engineer Dr Yanan Li, claiming: “By enabling the robot to identify human users’ behaviour and exploiting game theory to let the robot optimally react to them, we have developed a system where robots can work along humans as humans do.”

The resulting reactive robotic programming system, according to Sussex, enables a robot to continuously learn the human user’s control and adapt its own control correspondingly. “The robot is able to understand the human user’s action and then respond to and assist them to perform tasks successfully and with minimal effort.”

The work is published in Nature Machine Intelligence in the paper ‘Differential game theory for versatile physical human–robot interaction‘ which describes a robot inteneded to help an impaired stroke survivor retrain their motor control. The full paper is available free.

According to the paper “the controller of equations will induce both a stable interaction with the human user (as it adapts its control gain to compensate for the human bounded but possibly unstable control gain), and an interactive behaviour corresponding to a desired control strategy.”