Sensor design and integration into small sized autonomous vehicle

Abstract

Autonomous vehicles use several different kinds of sensors to get information about the surrounding area. With sensors and artificial intelligence, the autonomous vehicle tries to find the optimal decision as close as possible to the appropriate behavior. Because of the huge amount of data, the usage of modern machine learning and data-driven approaches is necessary. Although computing big data is not easily handled especially onboard a vehicle, the critical mass of the diverse data generated from different sources is essential. In the field of autonomous vehicles, there have not been standards yet, but the range of applied sensors is well-known. Most systems use a combination of cameras, radar, and LIDAR (Light Detection and Ranging) sensors that transmit data to a central computer that detects the environment around the car. Self-driving development could be supported with model-sized self-driving vehicles because of the complexity of the area. The development of autonomous vehicles consists of security, communication, and data processing issues. Mistakes are increasing the risks of potential accidents. The realistic environment which can be simulated or built makes it possible that the learned behavior can be carried across the platforms while the differences in the sizes are not playing an important role in the matter of learning. The previous reason causes the model-size self-driving development to be more cost-effective. In our work, we developed a self-driving model car with different types of sensors. Measurement data from them can be used to improve the self-driving capabilities of the vehicle.