Aim of the course

The aim of the course is to consolidate the theoretical knowledge (of modeling and identification / estimation of mobile robots and artificial intelligence, including genetic algorithms, evolutionary and multi-stage decision-making processes), and gaining practical skills in solving problems related to the construction of single mobile robots and teams of them.
Laboratory resources enable the design of an own mobile robot performing the task posed by the teacher, and the creation of a group of robots who can work together to solve a given more complex problem.
Posed tasks relate to simple commands associated with moving robots and terrain mapping, as well as the implementation of simple algorithms of cooperation between  robots. This kind of algorithms are usually implemented in virtual environments (eg. on the platforms of Java or Robocod), which -  despite many advantages - are not tailored to the needs of an automatic-control engineer, who programs microcomputers and computer-controlled robots.
Therefore, it is appropriate to develop engineering skills tailored to specific robotic platforms (such as the NAO humanoid robot, developed teams of the Q-fix robots, and other land rovers or vehicles on tracks).

Methodology of work in the laboratory

Work in the laboratory involves the implementation of given problem tasks formulated for each group of (2 or 3) students. 

Sample topics of laboratory exercises:

1. ROB: Introduction to a mobile robotic platform (actuators, sensors, operating system, API)
2. MEMS: Working with standard sensors (distance/IR gauges, accelerometers, encoders)
3. SLAM: Creating a map in the SLAM mode with the use of sensors
4. KF: Filtering data from the sensors, based on implementation of the (extended) Kalman filter
5. STAT: Avoidance of static obstacles (eg. by the algorithm of potential field)
6. DYN: Avoidance of dynamic obstacles
7. A*: Traversing a known maze (from point A to B - algorithms Dijkstra, A *, etc.)
8. A+: Going through a dynamic maze
9. MAP: Collaborative mapping
10. TEAM: Team strategies.