Mobile and Collective Robotics

During a review of study plans, the course B3M33MKR can be substituted for the course BE3M33MKR.

It is not possible to register for the course BE3M33MKR if the student is concurrently registered for or has already completed the course B3M33MKR (mutually exclusive courses).

It is not possible to register for the course BE3M33MKR if the student is concurrently registered for or has already completed the course A3M33MKR (mutually exclusive courses).

In order to register for the course BE3M33MKR, the student must have registered for the required number of courses in the group BEZBM no later than in the same semester.

It is not possible to register for the course BE3M33MKR if the student is concurrently registered for or has previously completed the course B3M33MKR (mutually exclusive courses).

Garant předmětu:

Lecturer:

Tutor:

Supervisor:

Department of Cybernetics

Synopsis:

The course introduces a basic mobile robot structure design together with control methods aimed to achieve autonomous and collective behaviors for robots. Methods and tool s for data acquisition and processing are presented herein with the overall goal to resolve the task of autonomous navigation for mobile robots comprising the tasks of sensor fusion, environmental modeling including Simultaneous Localization And Mapping (SLAM) approaches. Besides sensor-processing related tasks, methods for robot trajectory planning will be introduced. The central topic of the course stands in specific usage of the afore methods capable of execution with groups of robots and taking the advantage of their cooperation and coordination in groups. Labs and seminars are organized in a form of an Open Laboratory whereas the students will implement some fundamental algorithms and study their properties on real data.

Requirements:

B3M33ARO/BE3M33ARO (Autonomous Robotics)

Syllabus of lectures:

1. Taxonomy of the localization problem. Continuous localization.

2. Probabilistic methods of localization 1 - Bayes filter

3. Probabilistic methods of localization 2 - KF, EKF, particle filter

4. Simultaneous localization and mapping (SLAM): EKF, PF, Rao-Blackwell

5. Graph SLAM.

6. Sensors used in mobile robotics.

7. Environment representation and modeling for mobile robotics (fundamental approaches, space decomposition, graph-based and hierarchical representations, occupancy grids)

8. Environment representation and path planning (overview, selection of an appropriate model and planning method, hierarchical planning, configuration space)

9. Probabilistic and special planning approaches (RRT, potential fields)

10. Planning under uncertainty (MDP, POMDP)

11. Multi-robot systems, aspects of their design, cooperation, coordination, communication.

12. Localization in multi-robot teams.

13. Processing of 3D information.

14. Current problems and challenges in mobile robotics.

Syllabus of tutorials:

1. Labs organization, transformations

2. Iterative Closest Point (ICP)

3. Individual work (ICP) and consultation.

4. Individual work (ICP) and consultation.

5. Kalman filter (KF+EKF)

6. Individual work (KF+EKF) and consultation.

7. Particle filter (PF) and consultation

8. Individual work (PF) and consultation.

9. Individual work (PF) and consultation.

10. Individual work (PF) and consultation.

11. Rapidly Exploring Random Trees (RRT)

12. Individual work (RRT) and consultation.

13. Individual work (RRT) and consultation.

14. Individual work (RRT), grading.

Study Objective:

The aim of the course is to introduce an elementary structure of intelligent mobile robots. Moreover, fundamental problems of robot control and realization of autonomous behavior of one robot as well as a group of several robots are introduced.

Study materials:

R. Siegwart, I.R.Nourbakhsh, D.scaramuzza: Introduction to Autonomous Mobile Robots, MIT press, 2011.

S. Thrun, W.Burgard, D. Fox: Probabilistic Robotics. MIT press, 2005.

S.M.LaValle: Planning Algorithms. Cambridge University Press, 2006.

A. Kelly: Mobile Robotics: Mathematics, Models, and Methods. Cambridge University Press, 2013.

H. Choset, K. M. Lynch, S. Hutchinson, G. A. Kantor, W. Burgard, L. E. Kavraki, S. Thrun: Principles of Robot Motion: Theory, Algorithms, and Implementations (Intelligent Robotics and Autonomous Agents series), MIT Press, 2005.

Note:

Further information:

https://cw.fel.cvut.cz/wiki/courses/BE3M33MKR

No time-table has been prepared for this course

The course is a part of the following study plans: