Course syllabus

Course-PM

EEN095 Artificial intelligence and autonomous systems lp1 HT20 (7.5 hp)

The course is offered by the Department of Electrical Engineering

Contact details

Examiner:

Dr. Emmanuel Dean (deane@chalmers.se)

Lecturer:

• Dr. Emmanuel Dean (deane@chalmers.se)
• Dr. Karinne Ramirez (karinne@chalmers.se)

TA:

• M.Sc. Maximilian Diehl (diehlm@chalmers.se) 
• M.Sc. Ivan Torres (toivan@chalmers.se)

Student Representatives:

• Marcus Alvefelt (marcbor@student.chalmers.se)
• Joel Brofors (brofors@student.chalmers.se)
• Tommy Gelotte (t.gelotte@gmail.com)
• Robert Lundstrm (alfsulf@hotmail.com)
• Nils Twedmark (nilstw@student.chalmers.se)

Course purpose

The course aims to provide a basic introduction to artificial intelligence both in terms of planning and machine learning. Special emphasis is placed on applications in robotics and self-driving vehicles.

Schedule

Schedule

Course literature

The following list provides suggested literature for this course. This literature is not mandatory. It is intended to provide additional support for the course. Participants may use it to acquire more detailed information about the topics covered in this course.

• [1] Introduction to Machine Learning, E. Alpaydin, F. Bach, The MIT Press Cambridge, Massachusetts.
• [2] Machine Learning. T. M. Mitchell, McGraw-Hill.
• [3] Artificial Intelligence: A Modern Approach, S. Jonathan Russell, P. Norvig, Pearson.
• [4] Modelling and Control of Robot Manipulators, L. Sciavicco, and B. Siciliano, Springer.
• Additional material will be provided via Canvas for the course.

Course design

The course is goal-oriented, where a common autonomous robot problem will be described. This problem will be subdivided into topics that aim to tackle them. This lecture provides theoretical and practical information to solve these sub-problems. The topics range from AI planning, system identification, modeling, and control of robot systems. At the end of assignment 7, we will have a general Q&A session where the participants will be able to revise their acquired knowledge to prepare for the final written exam. Each assignment session will cover implementations in the form of practical and programming exercises in Matlab (m-files) and Simulink models.

Course hours:

Lectures:                                      24 hrs

Assignments:                               110 hrs

Reading:                                       20 hrs

The main communication will be through the Q&A sessions (see schedule below), the Canvas - Inbox, and the course email account (een095.ai@gmail.com).

The assignments will be elaborated using Matlab/Simulink, therefore the participants will require access to this software. Support for each assignment will be offered in the Q&A sessions. 

 

Learning objectives and syllabus

Learning objectives:

• describe the basic principles in artificial intelligence (AI), including both learning and decision making.
• apply learning methods on autonomous systems, especially for robot path planning.
• analyze and apply learning techniques based on system identification.
• combine learning and decision making for both continuous and discrete systems

Link to the syllabus on Studieportalen.

Study plan

Examination form

The examination will be divided into two parts, one for the Laboratory module, and the other for the lecture:

1. Compulsory laboratory Assignments (7 Assignments): The goal of these assignments is to provide practical experience on implementations of AI algorithms and robot control. The assignments will be delivered in teams. Each team has to deliver original material for the assignments in the form of m-files and/or Simulink models, depending on the assignment. The code must be accompanied by a short report that describes the delivered solution and how to run it (in the case the delivered material requires custom initialization).  Each assignment will have a set of tasks, which in total can accumulate 10 points. An assignment will be considered as "pass" when it completes at least 6 out of those 10 points. The assignments should be strictly delivered on time according to the course schedule (see below). Any assignment submitted after the deadline will be considered as not delivered (it will be marked as fail). The laboratory will be passed when the participant delivers at least 4 correct assignments. Additionally, each assignment will have a task with bonus points, which will be used to improve the final grade of the written exam.  
2. Compulsory Written Exam: The goal of the written exam is to allow the participants to demonstrate the acquired skills to understand and develop integrated AI solutions for autonomous robot problems. The final written exam will be based on the information given in the lectures and acquired from the assignments.  The exam will have a total of 100 points. The requirements for passing the exam is:

   Number of Points	Exam Grade
   80-100	5
   60-79	4
   40-59	3
   less than 40	fail

   During the exam, the participants are allowed to bring their calculators. Another additional material is not allowed.
3. Bonus Points: The bonus points are obtained by solving additional selected tasks in the assignments. These bonus points will only be used to improve the final written exam grade. Therefore, the bonus points will be accounted for only when the participant passes both the written exam (>=40 points) and the laboratory (4/7 assignments). 

Since this lecture is goal-oriented, the assignments have an important impact on the final grade. First, the written exam will be based on the theory behind the solutions for the tasks in the assignments. Second, the assignments can be used to accumulate bonus points and improve the final grade of the course.

Further details and information will be given in the first lecture of this course.