Development of Risk Predictive Collision Avoidance System and Its Impact on Traffic and Vehicular Safety

Abstract

Various collision avoidance systems (CASs) have been developed and employed in human-operated vehicles as well as more recently in autonomous vehicles. Most of the existing CASs perform an override function to actuate automatic emergency braking in a critical situation based on the current traffic information obtained from in-vehicle sensors or short-range vehicular communications. These CASs focus on the critical situation in the vicinity of the subject vehicle, which means they may have negative influences on the subject vehicle and its following vehicles, particularly when the leader vehicle of a platoon with short headway applies harsh braking to mitigate an impending collision risk. This study proposes a risk predictive CAS (RPCAS) which executes predictive deceleration with mild braking in advance to prevent a potential rear-end collision by predicting the collision risk arising from a downstream site. To evaluate the performance of the RPCAS, the proposed system is compared with several existing CASs in various car-following cases based on a microscopic traffic simulation. The simulation results show that the RPCAS can effectively reduce the rear-end collision risk with less harsh braking compared with the existing CASs. Furthermore, the RPCAS enables vehicles arriving from upstream to anticipate a potential crash, which provides them with sufficient time to reduce their current speeds proactively. The research findings suggest that the proposed system can attenuate the negative impacts of the previous CASs in relation to traffic and vehicular safety.

Safety Monitoring System of CAVs Considering the Trade-Off between Sampling Interval and Data Reliability

“…Therefore, when communication messages for the safety monitoring of CADs are designed, the reduction in the efficiency and the characteristics of the indicator should be considered. In the future, the characteristics of more diverse safety indicators will be analyzed by expanding the results of this study for various applications, such as evaluation of the collision risk and control of the automated vehicle, and for other execution strategies such as execution time and calculation of the safety indicator of an in-vehicle device [ 60 , 61 , 62 ]. Furthermore, although this study assumed the same sampling interval and data transmission interval, the follow-up paper will also analyze the optimal method for data transmission from connected and automated vehicles when different sampling intervals and transmission intervals, depending on their urgency, are applied.…”

RETRACTED CHAPTER: Optimization of Driving Efficiency for Pre-determined Routes: Proactive Vehicle Traffic Control

“…Machine Learning is a term used to encompass a wide variety of techniques applied to discover patterns and relationships in data sets. The primary objective of any Machine Learning algorithm is to discover significant relationships in training data sets and to produce a generalization of these relationships that can be used to interpret new unknown data [ 11 ].…”