Deep learning based visual perception and decision-making technology for autonomous vehicles

Abstract

Along with the social fast developing and the scientific and technological advancement day by day, the automatic driving system has been widely used in many areas, so it has been a hotspot. Because of the constant progress of the deep learning technique, the vision environmental sensor technique and the behavior decision technique have obtained some inspiration. The paper introduces a new method for detecting target with human body, which is based on recurrent convolution neural networks. In recent years, we have seen a number of developments in the field of decision making, such as reinforcement learning, and the development of deep neural networks. This thesis mainly focuses on the research of VMI and decision algorithms, and gives a brief introduction to their further application in ATS. In this paper, some key techniques of vision sensing and behavior decision are discussed in detail. This paper analyses the merits and deficiencies of current study on environment sensing technique and behavior decision technique. Finally, this paper summarizes and forecasts the vision environmental awareness and behavior decision techniques.