Period/time: Summer 2015
Computer programming, and basic knowledge in at least one of the
following areas: signal processing, human-computer interaction and
The course gives a comprehensive introduction to human interaction with
social robots. The research and development of social robots has
recently gained significant momentum due to the advances in computing
and sensing technologies. Socially assistive robots have many
applications ranging from social care, entertainment to education, just
to name a few. A central capability that a social robot must have is to
be able to interact with its users naturally, e.g., through speech and
vision, and in a social setup. The purpose of this course is to
introduce the theory and technologies for natural interaction with
social robots and train students with practical skills of developing
social robot applications.
In the end of the study the students will carry out joint project work
with the support of supervisors. The projects involve programming and
testing social robots that we have (http://socialrobot.dk
iSocioBot and Nao.
Students who complete the course will gain knowledge, skills and competences as follows:
- Must have knowledge about sensing technologies including audio, speech, and vision.
- Must have knowledge about human-robot interaction and user modeling.
- Must be able to apply the taught multimodal sensing methods to solve concrete engineering problems.
- Must be able to evaluate and compare the human-robot interaction methods for a specific application.
- Must have competencies in programming social robots for a targeted application.
- Must have competencies in testing human-robot interaction methods and systems.
Course slides will be made available prior to the course, in addition to a list of literature (included in the slides).
Course Introduction (slides
Introduction to Robot Operating Systems (ROS) (slides)
Introduction to iSocioBot and NAO robot, and demos (slides)
Social Robots and Applications (Slides)
Machine Learning and Pattern Recognition (slides)
Speech Processing I: Acquisition of Speech, Feature Extraction and Speaker Localization (slides)
Speech Processing II: Speaker Identification and Speech Recognition (slides)
Image Processing I: Image Acquisition, Pre-processing and Feature Extraction (slides)
Image Processing II: Face Detection and Face Recognition (slides)
- User Modelling (slides)
Multimodal Human-Robot Interaction (slides)