Vehicle Collision Prediction under Reduced Visibility Conditions

IET intell. transp. syst

Chen

et al. 2020

The market penetration of intelligent vehicles is a long‐term process. In recent years, significant attention has been paid to the influence of technology market penetration rate (MPR) on efficiency at signalised intersections, but little attention has been given to such an influence on safety at non‐signalised intersections. In this study, the influence of the intersection collision warning (ICW) system MPR on safety at non‐signalised intersections is investigated. The authors built a Matlab‐based simulation platform where an ICW algorithm was implemented. The simulation was firstly conducted to verify their models. Then the simulation results of different MPRs were obtained and compared statistically. Collision probability, conflict index, and collision rate were analysed for safety evaluation. The overall results showed that vehicle safety at non‐signalised intersections improves with the increase of the ICW system MPR. Without considerations of inappropriateness and otherness of driver reaction to warnings, when the MPR is 20% and all vehicles are connected by vehicle‐to‐everything, the collision probability, conflict index, and collision rate can be reduced by around 20, 20, and 35%, respectively. The simulation method can establish a mapping relation between the ICW system MPRs and vehicle safety indices at non‐signalised intersections.

“…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]

P^{i} = ({, \begin{matrix} right leftthickmathspace.5em \\ 1, normalif x \leq a \\ 1 - 2 {()(, \frac{min_{j \in M_{i}} {TTC}_{\min}^{i, j} - a}{b - a})}^{2}, normalif a \leq x \leq \frac{a + b}{2} \\ 2 {()(, \frac{min_{j \in M_{i}} {TTC}_{\min}^{i, j} - b}{b - a})}^{2}, normalif \frac{a + b}{2} \leq x \leq b \\ 0, normalif x \geq b \end{matrix}),

where

P^{i}

is the collision probability of vehicle i ,

M_{i}

denotes the set of all conflicted vehicles of vehicle i ,

{TTC}_{\min}^{i, j}

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].…”

Section: Simulation Methodology and Designmentioning

confidence: 99%

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

Liu

IET intell. transp. syst

Chen

et al. 2020

“…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…”

Section: Risk Probability Lossmentioning

confidence: 99%

Low-Cost Urban Test Scenario Generation Using Microscopic Traffic Simulation

et al. 2020

Scenario-based testing is already a well-known test approach to the automotive industry for the Validation, Verification and Testing of Connected and Automated Vehicles. How to construct the scenarios of complex traffic environment is a major challenge to this method. A common approach for generating scenarios is collecting and post-processing natural traffic data with a lot of time and money costs. In order to reduce the cost of scenario collection, we propose a low-cost method based on Microscopic Traffic Simulation to obtain a large number of urban traffic scenarios. Based on public data, we establish a microscopic traffic model for a specific area within the Shenzhen urban. Through a simulation, the 24-hour traffic behavior of vehicles for this area is simulated. About 189,752 scenarios covering the entire travel process are generated, which is equivalent to the data collected by a well-equipped car traveling 254,480 kms or 8,288 h. Our scenarios include not only typical urban scenarios such as U-turn and Parallel-driving (two vehicles driving in parallel on a single lane), but also collision accident scenarios of various forms. In addition, in order to evaluate the risks faced by Connected and Automated Vehicles in different scenarios, we design a new criticality metric, Scenario Risk Index, based on the risk assessment principle. The Scenario Risk Index has nothing to do with a certain function, and can quantitatively comprehensively evaluate the criticality and loss of potential accidents. INDEX TERMS Test scenario, microscopic traffic simulation, traffic conflict technique, risk assessment.

“…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).…”

Section: Literature Reviewmentioning

confidence: 99%

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

Delport²,

2019

Sensors

Drivers’ behaviors and decision making on the road directly affect the safety of themselves, other drivers, and pedestrians. However, as distinct entities, people cannot predict the motions of surrounding vehicles and they have difficulty in performing safe reactionary driving maneuvers in a short time period. To overcome the limitations of making an immediate prediction, in this work, we propose a two-stage data-driven approach: classifying driving patterns of on-road surrounding vehicles using the Gaussian mixture models (GMM); and predicting vehicles’ short-term lateral motions (i.e., left/right turn and left/right lane change) based on real-world vehicle mobility data, provided by the U.S. Department of Transportation, with different ensemble decision trees. We considered several important kinetic features and higher order kinematic variables. The research results of our proposed approach demonstrate the effectiveness of pattern classification and on-road lateral motion prediction. This methodology framework has the potential to be incorporated into current data-driven collision warning systems, to enable more practical on-road preprocessing in intelligent vehicles, and to be applied in autopilot-driving scenarios.