The present invention proposes a profound user-mower interaction, which enables the user to teach a robotic lawn mower (1) for improving its visual obstacle detection. The main idea of the invention is that the user can show some typical obstacles (6) from his garden to the mower (1). This will increases the performance of the visual obstacle detection. In the simplest scenario the user just places the mower (1) in front of an obstacle 6, and activates the learning mechanism of the classification means (module) (3) of the mower (1). The increasing use of smart devices (8) such as smart phones or tablets enables also more elaborated learning. For example, the mower can send the input image (9) to the smart device (8), and the user can provide a detailed annotation of the image. This will drastically improve the learning, because the mower (1) is provided with ground truth information.
