Cognitive Robotics

Faculteit Science and Engineering
Jaar 2019/20
Vakcode WMAI19001
Vaknaam Cognitive Robotics
Niveau(s) master
Voertaal Engels
Periode semester I a

Uitgebreide vaknaam Cognitive Robotics
Leerdoelen After successful completion of this course, students will be able to:
1. Explain the main theories of open-ended learning and cognitive robotics.
2. Explain meaning of different concepts often used in the field of 3D computer vision and
Human Robot Interaction and their application in robotics.
3. Exploit deep transfer learning algorithms for open-ended object category recognition.
4. Implement and experiment deep learning architectures for object grasping.
5. Create a tight coupling between object perception and manipulation and perform experiment using real Kinect data and a simulated Panda robotic arm.
6. Design a cognitive robotic system capable of dealing with unseen object categories and performing manipulation tasks in open-ended environments.
7. Use RACE cognitive robotic system, ROS, and Gazebo in practical projects.

Remark: The course unit prepares students to do their graduation project if they choose to do it in robotics.
Omschrijving Cognitive robots are expected to be more autonomous and work effectively in human-centric environments. This implies that robots should have special capabilities, such as learning from past experiences and real-time object perception. A cognitive robot should process very different types of information in varying time scales. Two different modes of processing, generally
labelled as System 1 and System 2, are commonly accepted theories in cognitive psychology. The operations of System 1 (i.e. perception and action) are typically fast, automatic, reactive and intuitive. The operations of System 2 (i.e. semantic) are slow, deliberative and

This year theme of the course is “Towards lifelong assistive robotics: a tight coupling between object perception and manipulation”. This course will present and examine several algorithms for a cognitive robot mainly with the distinctive characteristics of System 1. Topics include Introduction to Cognitive Robotics, 3D Object Perception, Object Grasping and Manipulation, Planning, Human Robot Interaction, Open-Ended Learning, Deep Transfer Learning, Evaluations, and Application to Assistive Robots.
Uren per week
Onderwijsvorm Bijeenkomst (S), Hoorcollege (LC), Practisch werk (PRC)
Toetsvorm Opdracht (AST), Practisch werk (PR), Verslag (R)
(Essay assignments (20%), Practical assignments and reports (30%), Final project and report (50%))
Vaksoort master
Coördinator S.H. Mohades Kasaei, PhD.
Docent(en) S.H. Mohades Kasaei, PhD.
Entreevoorwaarden Prior knowledge of basic linear algebra and matrix calculation would be useful but is not required. For programming throughout the course, we mainly use C++/Python based ROSLunar. For your final project, you are free to choose MATLAB, Python, or C++ as your coding language.
Opmerkingen Please note that this course has limited lab capacity. If you sign up for this course and are not an AI/HMC-student, we cannot guarantee you a spot.
Opgenomen in
Opleiding Jaar Periode Type
MSc Artificial Intelligence  (B - Mandatory Course Units Computational Intelligence and Robotics) - semester I a verplicht CI&R
MSc Artificial Intelligence  (C - Elective Course Units) - semester I a keuzevak MAS
MSc Human-Machine Communication  (C - Elective Course Units) - semester I a keuze