Vision-Based Mobile Robots Control Along a Given Trajectory

The paper presents the application of a computer vision approach to tracking the mobile robot's state. As an exemplary environment, we use a feedback control system for the trajectory planning and control. The system in the feedback loop use images taken from a centrally placed camera and, based on this, calculates the robots states, i.e. position and angle of rotation. The solution is adopted for indoor experiments. The experimental part shows the application of trajectory planning for multiple robots to cover a given area. The robot state is calculated using the YOLO model. We show that current machine learning techniques are fast and accurate for such applications and do not require image preprocessing or camera calibration.