A Study on the Obstacle Recognition for Autonomous Driving RC Car Using LiDAR and Thermal Infrared Camera

In this paper, we propose a new obstacle recognition method by using infrared camera that can detect the heat and LiDAR sensors, so that the front car and the pedestrian are recognized without error. Collision avoidance from obstacle recognition is the most important feature in ADAS (Advanced Driver Assistance System), aimed at providing correct, timely and reliable warnings before an imminent collision. Conventional obstacle recognition technologies using LiDAR and radar have caused serious accidents, because they fail to recognize objects accurately in bad weather and at night. In this paper, an infrared camera that can detect the heat is additionally introduced, so that the front car and the pedestrian are recognized in advance. In the future, if the AEB (Automatic Emergency Brake) through the proposed method is supplied to elderly drivers at low prices, it is expected that the mortality rate due to traffic accidents of the elderly will be significantly reduced.