Vehicle Collision Prediction under Reduced Visibility Conditions

Abstract

Rear-end collisions often cause serious traffic accidents. Conventionally, in intelligent transportation systems (ITS), radar collision warning methods are highly accurate in determining the inter-vehicle distance via detecting the rear-end of a vehicle; however, in poor weather conditions such as fog, rain, or snow, the accuracy is significantly affected. In recent years, the advent of Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) communication systems has introduced new methods for solving the rear-end collision problem. Nevertheless, there is still much left for improvement. For instance, weather conditions have an impact on human-related factors such as response time. To address the issue of collision detection under low visibility conditions, we propose a Visibility-based Collision Warning System (ViCoWS) design that includes four models for prediction horizon estimation, velocity prediction, headway distance prediction, and rear-end collision warning. Based on the history of velocity data, future velocity volumes are predicted. Then, the prediction horizon (number of future time slots to consider) is estimated corresponding to different weather conditions. ViCoWs can respond in real-time to weather conditions with correct collision avoidance warnings. Experiment results show that the mean absolute percentage error of our velocity prediction model is less than 11%. For non-congested traffic under heavy fog (very low visibility of 120 m), ViCoWS warns a driver by as much as 4.5 s prior to a possible future collision. If the fog is medium with a low visibility of 160 m, ViCoWs can give warnings by about 2.1 s prior to a possible future collision. In contrast, the Forward Collision Probability Index (FCPI) method gives warnings by only about 0.6 s before a future collision. For congested traffic under low visibility conditions, ViCoWS can warn a driver by about 1.9 s prior to a possible future collision. In this case, the FCPI method gives 1.2 s for the driver to react before collision.

Vehicle safety analysis at non‐signalised intersections at different penetration rates of collision warning systems

“…The collision probability of a vehicle at non‐signalised intersections can be calculated as (19) based on the very commonly‐used evaluation index TTC according to Chen and Hsiung [42] where is the collision probability of vehicle i , denotes the set of all conflicted vehicles of vehicle i , is the minimum TTC during the conflict between vehicle i and vehicle j , and the parameters a and b are set as 0.5 and 2.5, respectively, according to Chen and Hsiung [42].…”

Low-Cost Urban Test Scenario Generation Using Microscopic Traffic Simulation

“…TTC is a commonly used criticality metric [30]- [32]. According to Chen [33]- [34], the relationship between TTC and the probability of collision can be calculated quantitatively by using (2) xb…”

Lateral Motion Prediction of On-Road Preceding Vehicles: A Data-Driven Approach

“…Sekizawa et al, in 2007 developed a stochastic switched autoregressive exogenous (SS-ARX) model to predict the collision avoidance behavior of drivers using simulated driving data in a virtual reality system [8]. Chen et al, in 2018, designed a visibility-based collision warning system to use the neural network to reach four models to predict vehicle rear-end collision under a low visibility environment [9]. Specifically, Shan et al, in 2013, proposed a long-term vehicle position tracking and prediction model that incorporates vehicle behaviors and physical features of the driving environment (i.e., road segments, and intersections and areas).…”