Abstract: Apparatuses, methods and storage media associated with an environment recognition system using SLAM pipeline with semantic segmentation are described herein. In some instances, the system is mounted on the body of the robotic apparatus, and includes one or more light sources, to illuminate a portion of an environment that surrounds the apparatus; a camera, to capture one or more images of the illuminated portion of the environment; and a processing device coupled with the camera and the light sources, to process the captured images, using semantic segmentation of the images applied in a SLAM pipeline. The processing is used to identify a position of the body of the apparatus, and/or a position of one or more objects disposed in the illuminated portion of the environment, based at least in part on a result of the processing of the one or more images. Other embodiments may be described and claimed.