Abstract: A cleaning system includes a self-driving cleaning robot and a charging station with a reference marker. The cleaning robot has an optical detection unit by way of which it detects the reference marker. The cleaning robot has a computing unit that is connected for communication purposes to the detection unit and a control unit for controlling the cleaning robot. The computing unit controls the approach of the cleaning robot to the charging station in a distance-dependent and in a detection-dependent manner using a histogram of oriented gradients and using the reference marker. A HOG method and a reference marker method can thus be used in combination for improved navigation.

Abstract: A method for bypassing impassable objects by a robot through the use of artificial intelligence. A reliable and low-cost bypassing of obstacles taking account of data privacy aspects is achieved in that in the event of a collision of the robot with an obstacle, an optical original recording of the obstacle is produced, artificial duplicates being generated from the original recording, the duplicates being used to train the artificial intelligence. A system has a robot and an IT infrastructure configured to execute the method.