Coordinating teacher: CASTILLO MONTOYA, JOSE CARLOS
Department assigned to the subject: Department of Systems Engineering and Automation
ECTS Credits: 3.0 ECTS
Students are expected to have completed
Programming (C, C++, Python, Matlab, etc...).
Competences and skills that will be acquired and learning results.
The main goal of this course is to introduce the main techniques and applications of machine learning in robotics. We will study the main areas in which machine learning is employed nowadays, paying also attention to recent approaches such as Deep Learning.
Description of contents: programme
- Why is Machine Learning useful in robotics?
- Supervised learning
- Unsupervised learning
2. Techniques for data classification
- Support Vector Machines
- K-nearest neighbours
- Naïve Bayes
3. Regression techniques for data prediction
- Decision trees
- Linear and non-linear models
- Neural networks
4. Clustering techniques for grouping data and detecting patterns
- Markov hidden models
- Gaussian mixture models
5. New trends: Deep Learning
6. Machine learning applications in robotics
- Human-Robot Interaction
- Autonomous vehicles
Learning activities and methodology
Magistral classes, laboratory practical sessions, individual tutorials, and personal work from the students
% end-of-term-examination 40
% of continuous assessment (assigments, laboratory, practicals...) 60
Alpaydin, Ethem . Introduction to machine learning. MIT Press. 2010
John Paul Mueller and Luca Massaron. Machine Learning For Dummies. John Wiley & Sons. 2016
Sonia Chernova, Andrea L. Thomaz. Robot Learning from Human Teachers. Morgan & Claypool Publishers. 2014
Vishnu Nath, Stephen E. Levinson. Autonomous Robotics and Deep Learning. Springer Science & Business Media. 2014
Yasser Mohammad and Toyoaki Nishida. Data Mining for Social Robotics: Toward Autonomously Social Robots. Springer. 2016
The course syllabus and the academic weekly planning may change due academic events or other reasons.