DESIGN OF AUTONOMOUS ROBOTIC PLATFORMS BASED ON MODEL DATA

Abstract

The article presents a method for selecting the configuration of the shooting equipment of a robotic platform, associated with the use of virtual digital models of sensors and a scene. The topic is really actual, since a number of complex technical and interesting scientific problems of computer vision are currently associated with the use of autonomous mobile systems. Technical difficulties are determined, first of all, by the fact that such complexes are equipped with many different sensors, the data from which must be processed in a single coordinate system with high accuracy. To do this, it is necessary to calibrate the system using an object with a special markup, the use of which allows you to effectively use computer vision algorithms and make the process fully automatic. The accuracy of the relative orientation of the sensors, which can be achieved in this case, can be considered a quality criterion when choosing survey equipment. In the process of designing a platform, it is rather difficult to determine in advance how many sensors and their placement is optimal in terms of the result - obtaining a high quality digital scene model. In this situation, it is natural to compare different hardware configurations and choose from them. However, to obtain the required amount of real data, a significant amount of time is required to work with complex expensive equipment. The key to solving the problem may be the use of virtual data - a realistic digital model of the sensors and the scene, synthesized using the graphics engine. This paper presents the process of designing a promising vehicle, including the selection and placement of shooting equipment on the platform – cameras and lidars. The best configuration is selected from the three proposed according to the criterion of the accuracy of restoring the positions of the sensors during the calibration process. The application software was developed on the basis of the Unreal Engine 4 graphics engine. Digital models of the vehicle, sensors and scene were created in accordance with the parameters of the real prototype. Taking into account the technical characteristics of the sensors, three options for their placement have been created. For each variant, s