Summarizing vehicle driving decision-making methods on vulnerable road user collision avoidance

Abstract

With the development of intelligent vehicles and autonomous driving technology, the safety of vulnerable road user (VRU) in traffic has been more guaranteed, and many research achievements have been made in the key area of collision avoidance decision-making methods. In this paper, the knowledge mapping method is used to mine the available literature in depth, and it is found that the research focus has shifted from the traditional accident cause analysis to emerging deep learning and virtual reality technology. This paper summarizes research on the three core dimensions of environmental perception, behavior cognition and collision avoidance decision-making in intelligent vehicle systems. In terms of perception, accurate identification of pedestrians and cyclists in complex environments is a major demand for VRU perception; in terms of behavior cognition, the coupling of VRU intention identification and motion trajectory prediction and other multiple factors needs further research; in terms of decision-making, the intention identification and trajectory prediction of collision objects are not included in the risk assessment model, and there is a lack of exploration specifically for cyclists' collision risk. On this basis, this paper provides guidance for the improvement of traffic safety of contemporary VRU under the conditions of intelligent and connected transportation.