Social robots are an exciting and emerging field of study that will have a significant impact on people’s lives in the future.  In order for social robots to be truly accepted they must be able to interact with the public in a human-like manner.  As with human-to-human interactions, such interactions will require the robot to recognise the emotional state of the user, produce responses based on their emotions and predict the impact of the robots responses. 

This PhD project will contribute to on-going research in the development of social robots. In particular, this project will investigate neural network models for simulating emotional interaction. An example application of these robots is to encourage users to make beneficial lifestyle changes by interacting with a companion robot.  Such lifestyle changes could involve following a healthier lifestyle, learning a musical instrument or practical skill, taking medication at the appropriate time or giving up smoking.

The main objectives of this PhD project would include the following:

• Development of novel associative neural network models to perform emotion recognition and prediction from speech.  These neural models are likely to make use of the mirror neuron system theory related to empathy and the temporal nature of speech.
• Identify the most appropriate subset of features from the speech signal to perform real-time emotion recognition.
• Explore the development of an integration memory architecture. For the social robot to engage in personalised long-term interactions, it will incorporate an integration architecture based on neuroscience evidence from human-memory processing.
• Develop empathic communication based on the emotional state of the person for inclusion in a social robot. This will involve producing emotional outputs that encourage lifestyle change in the user, and a feeling of companionship through the robot’s sounds, simple body language, and speech for reminders, encouragement and feedback.
• Create associative neural memory models to identify relationships between emotional cues by the robot and the response of the user to aid interactions between robots and humans.

Candidate Specification

• A minimum of a 2:1 first degree in a relevant discipline/subject area with a minimum 60% mark in the Project element or equivalent with a minimum 60% overall module average.
• Or in the event of a first degree classification of less than 2:1, a Masters Degree in a relevant subject area will be considered as an equivalent. The Masters must have been attained with overall marks at merit level (60%). In addition, the dissertation or equivalent element in the Masters must also have been attained with a mark at merit level (60%).the potential to engage in innovative research and to complete the PhD within a three-year period of study
• A minimum of English language proficiency (IELTS overall minimum score of 7.0 with a minimum of 6.5 in each component)