COMPGI17 - Affective Computing and Human-Robot Interaction

This database contains 2016-17 versions of the syllabuses. For current versions please see here.

Code COMPGI17 (Also taught as: COMPM082)
Year MSc
Prerequisites Fundamentals of calculus, probability, statistics or have taken either COMPGI01 (Supervised Learning) or COMPGI20 (Introduction to Supervised Learning) in term 1. (GI02 Unsupervised Learning is a plus).
Term 2
Taught By Nadia Berthouze (100%)
Aims The module targets students who have no previous knowledge in cognitive science and emotion theory and therefore the aim of Part 1 of the module is to give a basic introduction to the theory of emotion from psychology and neuroscience viewpoints and to understand its importance in human decision and communication processes. Part 2 will concentrate on the application of machine learning techniques to emotion recognition by looking at current applications in entertainment, education, and health. Part 3 will focus on the challenges in designing robots that are capable of socially interacting with humans. Examples of current applications in entertainment, education, health, therapy, rehabilitation, service robotics, rescue robots will be used to identify problems and discuss machine learning solutions for the topics taught in Parts 2 and 3.
Learning Outcomes To have a basic knowledge of emotion models and of how technology (e.g., robot) can be endowed with the ability to affectively and socially interact with its user. To understand the challenges that affective computing and HRI pose to the machine learning field and identify the advantages and disadvantages of different machine learning techniques to address those issues. To understand how traditional HCI methods need to be modified to be applied to the HRI field.


Emotion theory:
What is affect, emotion, mood?
Why do we have emotions? Neurological and psychological perspectives.
How do humans express and recognise emotions?
Emotion expression models, appraisal and causal theories.
Affective and social interaction.


Affective computing:
Affective computing, definition and aims.

Emotion Recognition:
Application of machine learning techniques for adaptive emotion recognition from single modality (e.g. facial expressions, biosignals).
Adaptive multimodal emotion recognition: signal fusion.

Human-Robot Interaction (HRI):
Social robotics: motivation and emotions in robots.
Emotion based architecture.
Evaluation methods for HRI research.
Ethical issues in Affective Computing and HRI research.

Method of Instruction:

Lecture presentations, programming assignments.


The course has the following assessment components:

  • Coursework Section (1 piece, 40%)
  • Written Examination (2.5 hours, 60%)

To pass this course, students must:


  • Obtain an overall pass mark of 50% for all sections combined.



course website