Autonomous robotics – B(E)3M33ARO

Course overview

The Autonomous robotics course will explain the principles needed to develop algorithms for mobile robots. In particular, the main focus is on:

  • Mapping the world (e.g. 3D semantic map) from measurements of exteroceptive sensors such as camera or lidar
    (see lectures on sensor calibration, SLAM and deep learning on images).
  • Planning in the map (see lectures Planning I-IV).
  • Performing the plan in the world (Planning II and Reinforcement Learning).

It is assumed that students of this course have a working knowledge of mathematical analysis, linear algebra, probability theory, and statistics. In addition, basic programming skills in python are expected.

Distant teaching

In order to minimize the risk of spreading the coronavirus, contact (classroom) teaching has been replaced by web-based distance learning, see regularly updated list of coronavirus news for more details. The course consists of lectures and labs, both taught online using BBB client which runs directly in the web browser. The time-slot corresponds to the officialrozvrh/timetable. All students will receive an email invitation with the link to the conference room not later than 1 hour before the their lecture/lab.

  • Lectures: Each lecture consists of (i) online lecture taught in BBB client, (ii) PDF worksheet with numerical problems to be solved by students (we do not check if students do so, however the individual solution of provided problems is highly recommended in order to pass the exam test). See lectures webpage for more details.
  • Labs: The first 8 weeks will be focused on regular labs, the second half is devoted to solving the semestral work. Most of the regular labs contains homework to be solved before the start of the following labs.
  • Semestral work is scheduled for the second half of the term, however students are encouraged to play with the robots from the very beginning of the course. Since the work with the real robots seems unlikely due to the quarantine, students will solve the semestral work in the Gazebo simulator. In case that the epidemiological conditions allow physical presence of students in RoboLab (KN:E-130), students will be given opportunity to demonstrate their solution on the real robot. Any successful demonstration will be rewarded by bonus points. The consultation of semestral work will be provided during the consultation labs in the second half of the semester. In case of any problems which need to be solved immediately, please contact Bedrich Himmel.

Points, credit requirements and final grade

Maximum number of points is 100. Points are structured as follows:

  • homework (4×7 = 28),
  • semestral work (22),
  • exam test (50).

Minimum credit requirements:

  • Upload own solution of the semestral work and all homework (which satisfy minimum requirements) before the beginning of the labs in the thirteenth week.
  • Active participation on all regular labs. The active participation means that students are able to demonstrate progress on the lab assignment and answer questions of the lab tutor).

The final grade will be determined by the total number of points according to the following table

No of points Exam assessment
0-49 F
50- 59 E
60-69 D
70-79 C
80-89 B
90-100 A
  1. [KZ] Goodfellow et al. Deep Learning, 2016 http://www.deeplearningbook.org
  2. [KZ] Hartley, Zisserman Multipleview Geometry, 2004, https://www.robots.ox.ac.uk/~vgg/hzbook
  3. [VV] Steven M. LaValle. Planning Algorithms, Cambridge University Press, 2006. (volně na internetu, http://planning.cs.uiuc.edu/)
  4. [VH] B. Siciliano, O. Khatib (editoři). Handbook of Robotics, Springer-Verlag, Berlin 2008.

Plagiarism

We want students to work individually, therefore any plagiarism in codes, homework or reports will be mercilessly punished ;-). We strongly urge each student to read what is/isnot a plagiarism - we believe that many students will be surprised. In any case, it is not permitted to use the work of your colleagues or predecessors. Each student is responsible for ensuring that his work does not get into the hands of other colleagues. In the case of multiple submission of the same work, all involved students will be penalized, including those who gave the work available to others

courses/aro/start.txt · Last modified: 2021/02/15 13:48 by zimmerk