At present time there is no sensor that gives a robot the capability to perceive and recognize the environment in which it is located. This paper presents a system based on machine learning methods, that allows a mobile robot to recognize and identify objects found in internal environments, by using a low cost LIDAR sensor.For this purpose, a multi-layer data acquisition system was built from the single-layer LIDAR sensor "hokuyo urg-04lx-ug01". Where thanks to different methods of point cloud processing, it was possible to segment and identify different objects in a scene and then implement deep learning techniques like support vector machines and multilayer perceptron neural networks which allowed the object recognition.The final result was an integrated system, where the processing of point clouds and correct extraction of characteristics contributed to the performance of the implemented classification methods.