Intelligent Robotics

Recommended Prerequisites

Machine Learning; Intelligent Agents.

Teaching Methods

Lecture classes with detailed presentation of the topics of the syllabus using audiovisual means.

Laboratory classes in which students execute small projects on intelligent robot algorithms, either in a ROS-based simulator or in real mobile robots.

Learning Outcomes

Intelligent robots are autonomous robotic systems endowed with intelligent behaviors. These systems have to process sensory information in order to perceive the environment in which they operate and build representations of that environment and a knowledge base that allows them to reason, plan actions, make decisions, and eventually learn from the outcome of those actions in order to achieve goals that enable them to complete the missions for which they were designed. These perception and reasoning skills are achieved through the use of artificial intelligence techniques.

The main objective of this course is to provide the student with the fundamental knowledge to design, implement and test algorithms to deploy systems based on intelligent robots in real world applications.

Work Placement(s)

No

Syllabus

1. Introduction to cognitive robotics

Perceive-reason-act cycle

Robot Operating System (ROS), mobile robot simulators

 

2. Sensing and perception

Abstracting raw sensor data: feature extraction for semantic perception

Probabilistic estimation and tracking of static and dynamic features

 

3. Environment representation, localization and SLAM

Probabilistic maps: grid, topological and semantic mapping

Monte Carlo-based localization

Grid and graph-based SLAM algorithms

 

4. Planning, reasoning, and decision making under uncertainty

Sampling-based motion planning

Information-theoretic path planning and exploration

Introduction to reasoning using formal logic

Partially Observable Markov Decision Processes

 

5. Human-robot interaction

Interaction modalities

Principles and theories of human-robot interaction

Collaboration and group interaction

 

6. Application case studies

Service robots

Field robots

Assessment Methods

Assessment
Laboratory work or Field work: 50.0%
Exam: 50.0%

Bibliography

Alonzo Kelly. "Mobile robotics: mathematics, models, and methods", Cambridge University Press, 2014. ISBN: 978-1107031159

 

Sebastian Thrun, Wolfram Burgard, Dieter Fox, "Probabilistic Robotics", The MIT Press, 2005. ISBN: 978-0-262-20162-9

 

Howie Choset, Kevin M. Lynch, Seth Hutchinson, George A. Kantor, Wolfram Burgard, Lydia E. Kavraki, Sebastian Thrun, "Principles of Robot Motion Theory, Algorithms, and Implementations", The MIT Press, 2005. ISBN 978-0-262-03327-5

 

Steven M. LaValle. "Planning Algorithms", Cambridge University Press, 2006. ISBN: 978-0-521-86205-9

 

Stuart J. Russell, and Peter Norvig. “Artificial intelligence: a modern approach”, Fourth edition, Pearson, 2020. ISBN: 978-0134610993