Innovative countermeasures for red light running prevention at signalized intersections: A driving simulator study

Eco-approach and departure is a complex control problem wherein a driver’s actions are guided over a period of time or distance so as to optimize fuel consumption. Reinforcement learning (RL) is a machine learning paradigm that mimics human learning behavior, in which an agent attempts to solve a given control problem by interacting with the environment and developing an optimal policy. Unlike the methods implemented in previous studies for solving the eco-driving problem, RL does not require prior knowledge of the environment to be learned and processed. This paper develops a deep reinforcement learning (DRL) agent for solving the eco-approach and departure problem in the vicinity of signalized intersections for minimization of fuel consumption. The DRL algorithm utilizes a deep neural network for the RL. Novel strategies such as varying actions, prioritized experience replay, target network, and double learning were implemented to overcome the expected instabilities during the training process. The results revealed the significance of the DRL algorithm in reducing fuel consumption. Interestingly, the DRL algorithm was able to successfully learn the environment and guide vehicles through the intersection without red light running violation. On average, the DRL provided fuel savings of about 13.02% with no red light running violations.

Download Full-text

Discrimination of Effects between Directional and Nondirectional Information of Auditory Warning on Driving Behavior

Discrete Dynamics in Nature and Society ◽

10.1155/2015/980281 ◽

2015 ◽

Vol 2015 ◽

pp. 1-7 ◽

Cited By ~ 6

Author(s):

Yuting Zhang ◽

Xuedong Yan ◽

Zhuo Yang

Keyword(s):

Reference Group ◽

Red Light ◽

Warning System ◽

Driving Behavior ◽

Signalized Intersections ◽

Directional Information ◽

Red Light Running ◽

Collision Warning ◽

The Relationship ◽

Auditory Warning

This study examines the impacts of directional and nondirectional auditory warning information in a collision warning system (CWS) on driving behavior. The data on driving behavior is collected through experiment, with scenarios containing unexpected hazard events that include different warning content. As drivers approached the collision event, either a CWS auditory warning was given or no warning was given for a reference group. Discriminant analysis was used to investigate the relationship between directional auditory warning information and driving behavior. In the experiment, the CWS warnings significantly reduced brake reaction time and prompted drivers to press the brake pedal more heavily, demonstrating the effectiveness of CWS warnings in alerting drivers to avoid red-light running (RLR) vehicles when approaching a signalized intersection. Providing a clear warning with directional information about an urgent hazard event could give drivers adequate time to prepare for the potential collision. In terms of deceleration, a directional information warning was shown to greatly help drivers react to critical events at signalized intersections with more moderate braking. From these results, requirements can be derived for the design of effective warning strategies for critical intersections.

Download Full-text

Investigating Different Types of Red-Light Running Behaviors among Urban e-Bike Rider Mixed Groups

Journal of Advanced Transportation ◽

10.1155/2021/1977388 ◽

2021 ◽

Vol 2021 ◽

pp. 1-9

Author(s):

Fan Zhang ◽

Chenchen Kuai ◽

Huitao Lv ◽

Wenhao Li

Keyword(s):

Traffic Safety ◽

Traffic Accidents ◽

Unobserved Heterogeneity ◽

Red Light ◽

Multinomial Logit Model ◽

Time Of Day ◽

Signalized Intersections ◽

Traffic Light ◽

Safety Level ◽

Red Light Running

The red-light running (RLR) behaviors of urban mixed e-bike groups (delivery and ordinary e-bike) have become the main cause of traffic accidents at signalized intersections. The primary purpose of this study is to identify influencing factors of e-bike riders’ RLR behaviors, focusing on the role of delivery e-bike riders in mixed e-bike rider groups. Crossing behaviors of 4,180 e-bike samples (2006 delivery e-bikes and 2174 ordinary e-bikes) at signalized intersections are observed in Xi’an, China. The random parameter multinomial logit model is employed to capture the unobserved heterogeneous effects, and the effects of interaction terms are also considered. The results indicate that delivery e-bike riders are more likely to run red lights than ordinary e-bike riders. E-bike type, riders’ age, waiting position, traffic volume, traffic light type, and time of day are associated with crossing behaviors in urban mixed e-bike groups. In addition, the variable of traffic light status is found to account for unobserved heterogeneity. Findings are indicative to the development of effective implications in improving e-bikes’ traffic safety level at signalized intersections.

Download Full-text