URL study guide

https://studiegids.vu.nl/en/courses/2024-2025/XB_0120

Course Objective

Knowledge and insight: At the end of the course the student will be familiar with the basics of robotics and robot learning, such as kinematics, motor control and how to apply machine learning algorithms to tasks in robotics. Applying knowledge and insight & Learning skills: The student will be able to understand how to solve standard control problems with mathematical tools, such as forward and inverse kinematics/dynamics and end-effector-control. The student will be able to solve such problems in simulated and in real-world robots. Judgment: Furthermore, the student will understand when to use AI-driven robot learning methodologies and when to use analytical and closed-form solutions for robot control. Communication: The student will be capable of explaining the benefits and drawbacks of the use of AI and analytical solutions to non-experts.

Course Content

The first half of the course will cover the basics of robotics and robot control. Topics will include forward/inverse kinematics, modeling of robots, Denavit-Hartenberg, the basics of dynamics, trajectory planning and optimization and control algorithms. In the second half, the course will give an introduction into robot learning and embodied AI, i.e., the combination of artificial intelligence & machine learning with robotics. This will include the discussion of model-free and model-learning approaches for robotic tasks, their disadvantages and advantages over control methods.

Teaching Methods

Two Lectures & one Practical session per week. Attendance of lectures is not mandatory but highly recommended: While lecture slides will be made available, the lecture may also make use of black
- and/or white-boards. The course will also include practical (programming) assignments in Python/ROS.

Method of Assessment

The grade will be determined 70% through the final exam, and 30% through practical assignments. A resit will only be offered for the exam, but not for the practical assignments.

Literature

Recommended to supplement the course: Mark W. Spong, Seth Hutchinson, M. Vidyasagar, “Robot Modeling and Control”, Wiley B. Siciliano, L. Sciavicco. Robotics: Modelling, Planning and Control, Springer C.M. Bishop. Pattern Recognition and Machine Learning, Springer R. Sutton, A. Barto. Reinforcement Learning
- An Introduction, MIT Press

Recommended background knowledge

It is recommended to take the ‘Reinforcement Learning’ course of the Situated AI minor in parallel or prior to this course. Good knowledge and command of topics taught in the courses ‘Statistical Methods for AI’ and ‘Linear Algebra for AI’ is recommended. Good command of Python is necessary for the practicals
Academic year1/09/2431/08/25
Course level6.00 EC

Language of Tuition

  • English

Study type

  • Bachelor