460-4133/01 – Autonomous Driving (AJ)
Gurantor department | Department of Computer Science | Credits | 5 |
Subject guarantor | Ing. Jan Gaura, Ph.D. | Subject version guarantor | Ing. Jan Gaura, Ph.D. |
Study level | undergraduate or graduate | Requirement | Compulsory |
Year | 2 | Semester | winter |
| | Study language | Czech |
Year of introduction | 2019/2020 | Year of cancellation | 2022/2023 |
Intended for the faculties | FEI | Intended for study types | Follow-up Master |
Subject aims expressed by acquired skills and competences
The subject familiarizes students with the techniques used in the autonomous driving of vehicles. By passing the course students will get an overview of modern methods of environment mapping, navigation and decision making in self-driving vehicles.
Teaching methods
Lectures
Tutorials
Project work
Summary
In particular, the following topics will be discussed: Methods and concepts of autonomous vehicle control using different sensors. This includes acquaintance with LIDAR sensors, camera systems, their use in vehicle environment analysis, interest detection and environmental prediction and space mapping. The surrounding area information is then used to plan further steps of an autonomous vehicle.
Compulsory literature:
Recommended literature:
Way of continuous check of knowledge in the course of semester
Hand in tasks completed during exercises. Hand in of a project. Pass of final exam.
E-learning
Other requirements
No additional demands are required.
Prerequisities
Subject has no prerequisities.
Co-requisities
Subject has no co-requisities.
Subject syllabus:
Lectures:
1. Car navigation using GPS, RDS-TMC.
2. Introduction to autonomous driving, definition of basic concepts.
3. Sensors for autonomous driving, cameras, LIDAR, ultrasound.
4. Sensor data fusion.
5. Machine learning tools in autonomous driving.
6. Detecting objects around the vehicle.
7. Space mapping around the vehicle.
8. Methods of localization in known environment - particle filter.
9. Methods of localization in unknown environment - SLAM.
10. Motion models of other objects around vehicles.
11. Route planning, shortest path algorithms.
12. Search for possible route paths.
13. Predicting the route of other objects.
14. Behavioral planning, trajectory generation.
Exercises:
1. Working with the GPS geolocation system and radio transmission of traffic information using RDS-TMC.
2. Working with cameras, setting parameters and storing data.
3. Work with LIDAR sensor and ultrasonic sensors.
4. Processing of sensor data and their fusion into subsequent analysis.
5. Introduction to the software framework of machine learning.
6. Detection of interest objects around a vehicle using machine learning.
7. Creating map data based on sensor data.
8. Use of particle filter to locate a vehicle in a known environment.
9. SLAM techniques to locate a vehicle in an unknown environment.
10. Motion models of other objects around a vehicle.
11. Implement algorithms for finding the shortest path.
12. Methods of searching space of possible routes and their visualization.
13. Methods of predicting the route of other objects and their visualization.
14. Behavioral planning, trajectory generation.
Project:
In the project, students will implement the selected problem of autonomous vehicle driving using available data.
Conditions for subject completion
Occurrence in study plans
Occurrence in special blocks
Assessment of instruction