Research Theme: Robotics

SARAS - Smart Autonomous Robotic Assistant Surgeon
Autonomous Driving
AVATAR - Towards emotional robot surrogates
The goal of SARAS is to develop a next-generation surgical robotic platform that allows a single surgeon (i.e., without the need for an expert assistant surgeon) to execute robotic minimally invasive surgery (R-MIS), thereby increasing the social and economic efficiency of a hospital while guaranteeing the same level of safety for patients. This platform is called solo-surgeon system.
Autonomous cars need to be able to understand complex, human centred environments. This requires, in particular, to recognise significant events taking place in the road scene in real time. It also requires smart cars to understand people's behavioural patterns, in order to make prompt predictions about their future behaviour and react as needed.

We are annotating a significant fraction of the Oxford RobotCar Dataset with actions and activity labels, together with bounding boxes indicating where the action/event is taking place in the image plane.
In partnership with Cognitive Robotics group and the University of Malta, we seek to work towards designing 'emotional' robotic avatars able to both enhance remote personal presence experience, and provide realistic body surrogates for people with disabilities. The emotional state of an individual is detected and recognised in real-time in their natural environment, and communicated by the robot through appropriate facial expressions and bodily gestures enacted by the robot’s head, face, limbs and torso.