An Augmented Cognition approach in prediction of human behaviour for control in applications in HRI

Abstract

Ever increasing autonomy of machines and the need to interact with them creates challenges to ensure safe operation. Recent technical and commercial interest in increasing autonomy of vehicles has lead to the integration of more sensors and actuators inside the vehicle, making them more like robots. To consider the synthesis of safe and compliant controllers, the idea of integrating a model of the human in order to estimate and predict it’s behaviour by the means of using different measurements like heart rate seems useful. This talk presents initial results around this work, studying and applying different physiological measurements to predict (and maybe in the future to influence) human behaviour, in this case manoeuvres in a simulated driving environment, using data-driven techniques.

During my holidays in Colombia, I was fortunate enough to be invited and give a talk in my alma mater, Universidad Nacional de Colombia ❤️.

It was a shortened version of a previous talk I had for the DC Seminar in University of Bristol. I was lucky enough to get a full room of students and lecturers to share some ideas about HRI and its importance for the future of autonomous vehicles.

The talk was even mentioned on their social media 😄. Overall, a great experience that can hopefully be replicated very soon.

Erwin Lopez

Research Associate in Perception, Decision and Actions for HRI

My research interests include control, robotics, HRI and embedded systems.