How does intersection field of view influence driving safety in an emergent situation?

Predicting collision cases at unsignalized intersections using EEG metrics and driving simulator platform

Unsignalized intersection collision has been one of the most dangerous accidents in the world. How to identify road hazards and predict the potential intersection collision ahead are challenging problems in traffic safety. This paper studies the feasibility of EEG metrics to forecast road hazards and presents an improved neural network model to predict intersection collision based on EEG metrics and driving behavior. It is demonstrated that EEG metrics show significant differences between collision and non-collision cases. It indicates that EEG metrics can serve as effective indicators to predict the collision probability. The drivers with higher relative power in fast frequency band (alpha and beta), lower relative power in slow frequency band (delta and theta) are more likely to have conflicts. The prediction using three machine learning models (Multi-layer perceptron (MLP), Logistic regression (LR) and Random forest (RF)) based on three input datasets (only EEG metrics, only driving behavior and combined EEG metrics with driving behavior) are compared. The results show that for single time point prediction, MLP model has the highest accuracy among three machine learning models. The model solely based on EEG metrics datasets has higher accuracy than driving behavior as well as combined datasets. However, for multi-time point prediction, the accuracy of MLP is only 73.9%, worse than LR and RF. We improved the MLP model by adding attention mechanism layer and using random forest model to select important features. As a consequence, the accuracy is greatly improved and reaches 88%. This study demonstrates the importance and feasibility of EEG signals to identify unsafe drivers ahead. The improved neural network model can be helpful to reduce intersection accidents and improve traffic safety.

Using a V2V- and V2I-based collision warning system to improve vehicle interaction at unsignalized intersections

INTRODUCTION

Unsignalized intersections are critical components of the road network where traffic collisions occur frequently.

METHOD

This study aims to design a Vehicle-to-Vehicle (V2V)- and Vehicle-to-Infrastructure (V2I)-based unsignalized intersection collision warning system (UICWS) to improve driver performance and enhance driver safety at unsignalized intersections. A multi-user driving simulator experiment was conducted with 48 participants divided into 24 pairs. The dynamic interaction of each participant pair as they approached the intersection from straight-crossing directions was examined under different warning conditions (i.e., with vs without UICWS) and intersection field of view (IFOV) conditions (i.e., standard vs improved IFOV).

RESULTS AND CONCLUSIONS

The experimental results showed that the UICWS could effectively help drivers make appropriate operation decisions and reduce the number of right-angle collisions and near-collisions at unsignalized intersections. In the condition without UICWS, improved IFOV could prompt drivers to make crossing decisions in advance and adjust speed smoothly. Moreover, drivers' crossing maneuvers changed with the relative distance between the subject and conflict vehicles and the intersection. The risks of collisions and near-collisions increased significantly when the two vehicles were at a similar distance to the intersection before they initiated any actions.

PRACTICAL APPLICATIONS

The findings show that the proposed UICWS can effectively reduce collisions or near-collisions at unsignalized intersections in a connected vehicle environment. On this basis, some active intervention strategies, such as specific speed guidance depending on the dynamics of the conflict vehicle, can be developed to ensure vehicles passing through unsignalised intersections safely.

Driving With Hemianopia X: Effects of Cross Traffic on Gaze Behaviors and Pedestrian Responses at Intersections

Purpose

We conducted a driving simulator study to investigate the effects of monitoring intersection cross traffic on gaze behaviors and responses to pedestrians by drivers with hemianopic field loss (HFL).

Methods

Sixteen HFL and sixteen normal vision (NV) participants completed two drives in an urban environment. At 30 intersections, a pedestrian ran across the road when the participant entered the intersection, requiring a braking response to avoid a collision. Intersections with these pedestrian events had either (1) no cross traffic, (2) one approaching car from the side opposite the pedestrian location, or (3) two approaching cars, one from each side at the same time.

Results

Overall, HFL drivers made more (p < 0.001) and larger (p = 0.016) blind- than seeing-side scans and looked at the majority (>80%) of cross-traffic on both the blind and seeing sides. They made more numerous and larger gaze scans (p < 0.001) when they fixated cars on both sides (compared to one or no cars) and had lower rates of unsafe responses to blind- but not seeing-side pedestrians (interaction, p = 0.037). They were more likely to demonstrate compensatory blind-side fixation behaviors (faster time to fixate and longer fixation durations) when there was no car on the seeing side. Fixation behaviors and unsafe response rates were most similar to those of NV drivers when cars were fixated on both sides.

Conclusion

For HFL participants, making more scans, larger scans and safer responses to pedestrians crossing from the blind side were associated with looking at cross traffic from both directions. Thus, cross traffic might serve as a reminder to scan and provide a reference point to guide blind-side scanning of drivers with HFL. Proactively checking for cross-traffic cars from both sides could be an important safety practice for drivers with HFL.

Vision impairment and traffic safety outcomes in low-income and middle-income countries: a systematic review and meta-analysis

BACKGROUND

Road traffic injuries are a major public health concern and their prevention requires concerted efforts. We aimed to systematically analyse the current evidence to establish whether any aspects of vision, and particularly interventions to improve vision function, are associated with traffic safety outcomes in low-income and middle-income countries (LMICs).

METHODS

We did a systematic review and meta-analysis to assess the association between poor vision and traffic safety outcomes. We searched MEDLINE, Embase, PsycINFO, CINAHL, Web of Science, Cochrane Database of Systematic Reviews, and the Cochrane Central Register of Controlled Trials in the Cochrane Library from database inception to April 2, 2020. We included any interventional or observational studies assessing whether vision is associated with traffic safety outcomes, studies describing prevalence of poor vision among drivers, and adherence to licensure regulations. We excluded studies done in high-income countries. We did a meta-analysis to explore the associations between vision function and traffic safety outcomes and a narrative synthesis to describe the prevalence of vision disorders and adherence to licensure requirements. We used random-effects models with residual maximum likelihood method. The systematic review protocol was registered on PROSPERO, CRD-42020180505.

FINDINGS

We identified 49 (1·8%) eligible articles of 2653 assessed and included 29 (59·2%) in the various data syntheses. 15 394 participants (mean sample size n=530 [SD 824]; mean age of 39·3 years [SD 9·65]; 1167 [7·6%] of 15 279 female) were included. The prevalence of vision impairment among road users ranged from 1·2% to 26·4% (26 studies), colour vision defects from 0·5% to 17·1% (15 studies), and visual field defects from 2·0% to 37·3% (ten studies). A substantial proportion (range 10·6-85·4%) received licences without undergoing mandatory vision testing. The meta-analysis revealed a 46% greater risk of having a road traffic crash among those with central acuity visual impairment (risk ratio [RR] 1·46 [95% CI 1·20-1·78]; p=0·0002, 13 studies) and a greater risk among those with defects in colour vision (RR 1·36 [1·01-1·82]; p=0·041, seven studies) or the visual field (RR 1·36 [1·25-1·48]; p<0·0001, seven studies). The I2 value for overall statistical heterogeneity was 63·4%.

INTERPRETATION

This systematic review shows a positive association between vision impairment and traffic crashes in LMICs. Our findings provide support for mandatory vision function assessment before issuing a driving licence.

FUNDING

None.

Research on intervention methods for children's street-crossing behaviour: Application and expansion of the theory of "behaviour spectrums"

Due to immaturity in their physical and cognitive development, children are particularly vulnerable to road traffic injuries as pedestrians. Child pedestrian injury primarily occurs in urban areas, with a significant share at crosswalks. The aim of this study is to explore whether an intervention programme based on the theory of "behaviour spectrums" can improve the street-crossing skills of primary school children. Children were recruited near a local primary school through invitation letters and were randomly divided into two groups: a control group (n = 10, no intervention) and an experimental group (n = 10, intervention). The children in the experimental group received 30-45 min of training. The child participants were asked to wear an eye tracker and performed a crossing test in a real-world street environment; in this test, they were required to successively pass through an unsignalised intersection, an unsignalised T-intersection and a signalised intersection on a designated test route. A high-definition camera was used to record the children's crossing behaviour, and the Tobii Pro Glasses 2 eye tracker was used to derive indicators of the children's visual behaviour in the areas of interest (AOIs) in the street. The evaluation was conducted on children's crossing behaviour in the control group (which received no intervention) and the experimental group (tested at two time points after the intervention: children tested immediately after the intervention and children retested one month after the intervention). The results showed that compared with the control group, the children in the experimental group no longer focused on the small area around the body (e.g., the zebra crossing area) and the area in front of the eyes (e.g., the sidewalk area), which increased their visual attention to the traffic areas on the left and right sides of the zebra crossing; thus, unsafe crossing behaviour was reduced in the experimental group. Compared with the experimental group immediately after the intervention, the intervention effect on some indicators showed a significant weakening trend in the retest of the experimental group one month later. Overall, the results show that an intervention programme based on the theory of "behaviour spectrums" can improve children's crossing skills. This study provides valuable information for the development and evaluation of intervention programmes to improve children's street-crossing skills.

Auditory Messages for Intersection Movement Assist (IMA) Systems: Effects of Speech- and Nonspeech-Based Cues

OBJECTIVE

The objective of this study was to assess the effects of different warning messages for an Intersection Movement Assist (IMA) based on drivers' ability to avoid a potential safety hazard.

BACKGROUND

An IMA system can detect hazards and warn drivers when it is unsafe to enter an intersection. The effects of different warning information conveyed by these systems are still unknown.

METHOD

A driving simulator study with 80 participants was conducted with a red light running (RLR) scenario using a 5 (warnings) x 2 (training) between-subject design. IMA warnings included the messages "Danger," "Brake now," "Vehicle on your left," a beep, and no IMA warning. Training was provided to half of the participants. Analysis of variance and logistic regression models were used to examine differences in drivers' avoidance behavior.

RESULTS

The analyses showed that all tested warning messages can significantly enhance drivers' avoidance performance. Significant differences were observed in crash occurrence, avoidance behavior (i.e., reaction time and speed change), and eye movements (i.e., fixation pattern and time to first fixation). The effects of training also differed given the warning message provided.

CONCLUSION

The "Brake now" message performed best in reducing crash involvement and prompted better avoidance performance. The "Danger" and "Vehicle on your left" messages improved drivers' hazard detection ability. The training showed a potential to enhance the effectiveness of nonspeech warning messages.

APPLICATION

The findings of this study can help designers and engineers better design IMA warning messages for RLR scenarios.

Analysis of drivers' deceleration behavior based on naturalistic driving data

Objective: As one of the bases for designing a humanlike brake control system for the intelligent vehicle, drivers' deceleration behavior needs to be understood. There are two modes for drivers' deceleration behavior: (i) brake pedal input, by applying brake system to reduce the speed; (ii) no pedal input, by releasing the accelerator pedal without pressing the brake pedal, thus decelerating by naturalistic driving resistance. The deceleration behavior that drivers choose to press the brake pedal has been investigated in previous studies. However, releasing the accelerator pedal behavior has not received much attention. The objective of this study is to investigate factors that influence drivers' choice of the two deceleration modes using naturalistic driving data, which provide a theoretical foundation for the design of the brake control system.Methods: A logistic model was constructed to model drivers' deceleration mode, valued as "no pedal input" or "brake pedal input" for dependent variables. Factors such as Light condition, Intersection mode, Road alignment, Traffic flow, Traffic light, Ego-vehicle motion state, Lead vehicle motion state, Time headway (THW), and Ego-vehicle speed were considered in the model as independent variables.Results: 393 deceleration events were selected from the naturalistic driving data, which used as the database for the regression model. As a result, 6 remarkable factors were found to influence drivers' deceleration model, which include Traffic flow, Intersection mode, Lead vehicle motion state, Ego-vehicle motion state, Ego-vehicle speed and THW. Specifically, (1) the possibility of drivers choosing "no pedal input" is gradually increasing with the increase of THW and speed; (2) The drivers prefer to choose "no pedal input" when the lead vehicle is decelerating compared to it's stationary. This probability is relatively high when the lead vehicle is traveling along the road; (3) the possibility of choosing "no pedal input" at intersection is higher than roads without intersection; (4) the possibility of choosing "no pedal input" is higher when traveling with more traffic flow.Conclusion: The drivers' deceleration behavior can be divided into "no pedal input" and "brake pedal input." The following six factors significantly affect drivers' choice of deceleration mode: Traffic flow, Intersection mode, Lead vehicle motion state, Ego-vehicle motion state, Ego-vehicle speed and THW. The logistic regression model can quantify the influence of these six factors on drivers' deceleration behavior. This study provides a theoretical basis for the braking system design of ADAS (Advanced Driving Assistant System) and intelligent control system.