Course detail
Mobile Robots
FSI-0MR Acad. year: 2025/2026 Summer semester
The course focuses on mastering modern methods for developing mobile robots, including design, simulation, and implementation of autonomous robotic systems. Students will explore advanced technologies such as quadruped robots, humanoid robots utilized in logistics and industry, and autonomous warehouse robots (AGV) capable of real-time operational optimization. The curriculum includes understanding the fundamentals of algorithm design and solving engineering problems through programming in Python and C. In teams, students work on their own projects, integrating theoretical knowledge with practical skills. The course emphasizes an intuitive approach to solving problems in mobile robotics, ranging from simple constructions to systems powered by artificial intelligence.
Supervisor
Learning outcomes of the course unit
Prerequisites
The course is intended for enthusiastic students with interests in mobile robotics. Some programming skills are welcomed as well as any knowlege about microcontrollers, sensors etc ... however, not required.
Planned learning activities and teaching methods
Assesment methods and criteria linked to learning outcomes
Credit requirements: active participation in laboratories and successful implementation of a group project in cooperation with the teacher. The project is defended by presenting in front of other students and ended with a practical demonstration of the implemented project. The evaluation is fully in competence of a tutor according to the valid directives of BUT.
Participation in laboratories is desirable in the case to fulfill the credits requirements. Teaching is divided according to weekly schedules. The form of compensation for missed seminars is fully at the discretion of the teacher.
Language of instruction
Czech
Aims
The course is designed to provide in-depth knowledge of methods for navigation, localization, path planning, and simultaneous localization and mapping (SLAM) in modern autonomous ground vehicles (AGVs), as well as techniques for developing walking platforms, including:
- Understanding the principles of programming using Python and embedded C.
- Applying AI algorithms to mobile robotic systems for tasks like navigation, obstacle detection, and walking pattern generation.
- Implementing these principles into simulation models or real-world devices.
Practical experiments are conducted using commonly used hardware in mobile robotics (embedded systems, simulation tools, sensors, etc.). The course is primarily aimed at students interested in mobile robotics.
Specification of controlled education, way of implementation and compensation for absences
The study programmes with the given course
Programme N-MET-P: Mechatronics, Master's
branch ---: no specialisation, 5 credits, compulsory-optional
Programme B-STR-P: Engineering, Bachelor's
branch AIŘ: Applied Computer Science and Control, 5 credits, elective
Programme BIT: Information Technology, Bachelor's
branch BITP: Information Technology, 5 credits, elective
Type of course unit
Laboratory exercise
39 hours, compulsory
Syllabus
- Learn about the current challenges and solutions in mobile robotics.
- Understand the platforms, tools, and integration of simulation models for robot development.
- Study the design of robots, integration of hardware peripherals, and sensor models.
- Explore how machine learning and reinforcement learning can be applied to robotic systems.
- Learn methods for localization, path planning, and navigation in known environments.
- Study how machine learning can be used to generate walking patterns for robots.
- Get familiar with ROS and its applications in robotics.
- Apply your knowledge to design and build custom robots.
- Use tools like PyBullet, Gymnasium, and Stable Baselines to develop and test robots.
- Implement the concepts learned into real-world robotic systems.
- Test the robot performance in real-world conditions.
- Verification of the robotics system performance.
- Finalize and present your robotic project with all implemented features.