Pedestrian-vehicle Interactions Research Articles

Analysis of the Interaction between Humans and Autonomous Vehicles Equipped with External Human–Machine Interfaces: The Effect of an Experimental Reward Mechanism on Pedestrian Crossing Behavior in a Virtual Environment

The advent of autonomous vehicles (AVs) has sparked many concerns about pedestrian safety, prompting manufacturers and researchers to integrate external Human–Machine Interfaces (eHMIs) into AVs as communication tools between vehicles and pedestrians. The evolving dynamics of vehicle–pedestrian interactions make eHMIs a compelling strategy for enhancing safety. This study aimed to examine the contribution of eHMIs to safety while exploring the impact of an incentive system on pedestrian risk behavior. Participants interacted with AVs equipped with eHMIs in an immersive environment featuring two distinct scenarios, each highlighting a sense of urgency to reach their destination. In the first scenario, participants behaved naturally without specific instructions, while in the second scenario, they were informed of an incentive aimed at motivating them to cross the road promptly. This innovative experimental approach explored whether motivated participants could maintain focus and accurately perceive genuine risk within virtual environments. The introduction of a reward system significantly increased road-crossings, particularly when the vehicle was approaching at higher speeds, indicating that incentives encouraged participants to take more risks while crossing. Additionally, eHMIs notably impacted pedestrian risk behavior, with participants more likely to cross when the vehicle signaled it would not stop.

Enhanced microsimulation framework for right-turning vehicle-pedestrian interactions at signalized intersection

The unclear understanding of right-turning vehicle behavior at signalized intersections complicates the interaction with pedestrians. Current micro-dynamic modeling research falls short of effectively simulating this complexity. Specifically, the existing models fail to adequately capture the three states that right-turning vehicles may undergo: car-following, free right-turn, and avoidance of conflicting pedestrians. Moreover, pedestrian behavior is typically influenced by encountering conflicting vehicles and surrounding pedestrians, as well as traffic signals. To simulate these behaviors, the right-turning and yielding intelligent driver model (RTYIDM), the modified social force model (MSFM) considering green light pressure, and the yielding decision model between pedestrians and vehicles have been established. Model calibration is performed using detailed behavioral data collected and extracted from field observations. Furthermore, a microsimulation platform with 3D visualization and playback features has been developed to facilitate testing and demonstration. Model validation is performed by comparing it with actual trajectories in three representative scenarios of pedestrian crossing with conflict between pedestrians and vehicles. Meanwhile, the calibrated model's ability to predict pedestrian-interaction events and estimate vehicle yielding rates is also assessed. The well-established simulation performance of the proposed model makes it a useful tool for evaluating existing traffic operations.

Understanding distracted pedestrians’ risky behaviour: The role of walking and visual characteristics through a field study

Use of mobile phones while crossing the road has become a growing safety concern among pedestrians. Though recently, some studies have attempted to understand risky behaviour of distracted pedestrians by analyzing impacts of distraction on pedestrians’ walking and visual characteristics, the impacts were measured individually. Moreover, most of the existing findings are based on lab-based experiments, whereas the real-world conditions are quite dynamic in nature. Hence, to overcome these gaps, the current study aims to understand to what extent different potential factors (such as distraction, walking characteristics, visual behaviour, etc.) affect the risk of unsafe pedestrian-vehicle interactions in real-world settings. For this purpose, a field experiment was designed to understand the impact of distraction on pedestrians’ risky behaviour using an eye-tracker at an unsignalized intersection in Delhi. The risk assessment was done using Post-Encroachment Time (PET) measure. The results indicate that the use of mobile phone while crossing the road increased the chances of unsafe (PET < 1.5 s) pedestrian-vehicle interactions by approximately eight folds. Surprisingly, pedestrians who crossed the intersection at high speed had higher chances of unsafe interactions, whereas their increased crossing initiation time reduced the probability of unsafe interactions. Moreover, increased pupil diameter and fixating more on vehicles approaching from the right side resulted in a reduced probability of unsafe interactions. However, the high frequency of saccades and higher fixations on the crosswalk's right side negatively affected unsafe interactions. This study highlights that it is important to consider visual characteristics along with demographic and walking and traffic characteristics as they can provide in-depth insights into pedestrians’ road crossing behaviour that are required to design and implement effective countermeasures and policies.

Safety assessment of pedestrian-vehicle interaction at signalized intersections: An observational study

Road safety is a crucial aspect of global policies and management. Surrogate Safety Measures (SSMs) have gained attention in the study of pedestrian safety. This study aims to establish an effective SSM methodology to analyze driver-pedestrian interactions. The analysis relies on SSM indicators, without the need for an initial classification of driver-pedestrian interactions into specific interaction patterns. The proposed methodology offers several advantages, including the accurate identification of conflicts through an affordable approach making it easily accessible for public administrations and authorities to assess pedestrian safety at road intersections. A dataset comprising 270 driver-pedestrian interactions, observed at three road intersections in Rome, Italy, was examined. The severity level of each event was assessed through a preliminary classification of each interaction into three patterns: high, low, and none. Subsequently, the severity levels were evaluated using three methods, employing Time-to-Collision (TTC), Post-Encroachment Time (PET), and a combination of TTC and PET. A comparison between the severity levels identified by the two approaches was conducted. The findings reveal that Method 2, utilizing PET, consistently identifies conflicts. Additionally, a binomial logistic regression analysis was performed to identify the variables that influence the likelihood of an interaction escalating into a conflict. The results demonstrate that the probability of conflict increases with the duration of a red signal, particularly for younger pedestrians.

Pedestrians’ road-crossing decisions: Comparing different drift-diffusion models

The decision of whether to cross a road or wait for a car to pass, humans make frequently and effortlessly. Recently, the application of drift-diffusion models (DDMs) on pedestrians’ decision-making has proven useful in modelling crossing behaviour in pedestrian–vehicle interactions. These models consider binary decision-making as an incremental accumulation of noisy evidence over time until one of two choice thresholds (to cross or not) is reached. One open question is whether the assumption of a kinematics-dependent drift-diffusion process, which was made in previous pedestrian crossing DDMs, is justified, with DDM-parameters varying over time according to the developing traffic situation. It is currently unknown whether kinematics-dependent DDMs provide a better model fit than conventional DDMs, which are fitted per condition. Furthermore, previous DDMs have not considered reaction times for the not-crossing option. We address these issues by a novel experimental design combined with modelling. Experimentally, we use a 2-alternative-forced-choice paradigm, where participants view videos of approaching cars from a pedestrian’s perspective and respond whether they want to cross before the car or to wait until the car has passed. Using these data, we perform thorough model comparison between kinematics-dependent and condition-wise fitted DDMs. Our results demonstrate that condition-wise fitted DDMs can show better model fits than kinematics-dependent DDMs as reflected in the mean-squared-errors. The condition-wise fitted models need considerably more parameters, but in some cases still outperform kinematics-dependent DDMs in measures that penalize the parameter number (e.g., Akaike information criterion). Introducing a starting point bias provides support for the novel hypothesis of rapid early evidence build-up from the initial view of the vehicle distance. The drift rates obtained for the condition-wise fitted models align with the assumptions in the kinematics-dependent models, confirming that pedestrians’ decision processes are kinematics-dependent. However, the partial preference for condition-wise fitted models in the model selection suggests that the correct form of kinematics-dependence has not yet been identified for all DDM-parameters, indicating room for improvement of current pedestrian crossing DDMs. Developing more accurate models of human cognitive processes will likely facilitate autonomous vehicles to understand pedestrians’ intentions as well as to show unambiguous human-like behaviour in future traffic interactions with humans.

A Coordinated Allocation Method for Right-Turn Strategy at Signalized Intersections with Optimal Pedestrian and Vehicle Delays

With strict enforcement of pedestrian right of way at all intersections, the inappropriate right-turn resource allocation from a spatial and temporal perspective will lead to a reduction in the operational efficiency of the intersection. In this paper, three spatiotemporal resource allocation schemes for right-turning vehicles are proposed, considering the vehicle and pedestrian traffic efficiency in all directions of the intersection. To minimize vehicle and pedestrian delay at the intersection individually, an optimization model is established with the effective green time of each phase and three schemes as decision variables. A right-turn vehicle and pedestrian conflict delay model is developed based on the pedestrian-vehicle interaction behavior as the constraints of the optimization model. The NSGA-II algorithm is used to solve the model, and the quantitative criteria for the exclusive right-turn lane and phase are obtained by sensitivity analysis. The results of this paper can be used as a guide for traffic design and for planning and controlling the operation of right-turning vehicles at intersections.

A Computer Vision-Based Algorithm for Detecting Vehicle Yielding to Pedestrians

Computer vision has made remarkable progress in traffic surveillance, but determining whether a motor vehicle yields to pedestrians still requires considerable human effort. This study proposes an automated method for detecting whether a vehicle yields to pedestrians in intelligent transportation systems. The method employs a target-tracking algorithm that uses feature maps and license plate IDs to track the motion of relevant elements in the camera’s field of view. By analyzing the positions of motor vehicles and pedestrians over time, we predict the warning points of pedestrians and hazardous areas in front of vehicles to determine whether the vehicles yield to pedestrians. Extensive experiments are conducted on the MOT16 dataset, real traffic street scene video dataset, and a Unity3D virtual simulation scene dataset combined with SUMO, which demonstrating the superiority of this tracking algorithms. Compared to the current state-of-the-art methods, this method demonstrates significant improvements in processing speed without compromising accuracy. Specifically, this approach substantially outperforms in operational efficiency, thus catering aptly to real-time recognition requirements. This meticulous experimentation and evaluations reveal a commendable reduction in ID switches, enhancing the reliability of violation attributions to the correct vehicles. Such enhancement is crucial in practical urban settings characterized by dynamic interactions and variable conditions. This approach can be applied in various weather, time, and road conditions, achieving high predictive accuracy and interpretability in detecting vehicle–pedestrian interactions. This advanced algorithm illuminates the viable pathways for integrating technological innovation and sustainability, paving the way for more resilient and intelligent urban ecosystems.

Resource Optimization for Task Offloading With Real-Time Location Prediction in Pedestrian-Vehicle Interaction Scenarios

With the development of autonomous driving, task offloading of Internet of vehicles has become a hot research issue. In pedestrian-vehicle interaction scenarios, characteristics of tasks are constantly changing due to the influence of pedestrians and road conditions. Real-time offloading optimization and signaling are time-consuming, which may not meet the low delay requirement of task offloading. Therefore, this paper proposes a location prediction-based resource optimization scheme for task offloading in these scenarios. Firstly, the locations of pedestrians are predicted by the social force model based on their movement rules, and the locations of vehicles are predicted by the car-following model on the basis of ensuring pedestrian safety. The characteristics of tasks are obtained based on the predicted locations of vehicles. Then a neural network trained beforehand based on deep Q-learning is used to obtain a task offloading strategy. Since the tasks are obtained by prediction in advance, this strategy decision can be processed before vehicles arriving the predicted locations, which saves the time consumption of optimization and signaling. Besides, simulation results show that the proposed scheme still guarantees an acceptably low task offloading delay compared with the other methods, especially in congested areas.

Development and validation of a video-based assessment tool for children's street-crossing safety

BackgroundThe alarming rate of child pedestrian fatalities highlights an urgent imperative for comprehensive test on children's street-crossing safety. Various methods in children's street-crossing studies were reviewed, and the advantages of the video-based experimental real-walk methods were introduced. AimThe present study aimed to develop a reliable assessment tool to evaluate children's crossing safety, assess its validity, and identify developmental characteristics of children's crossing abilities. MethodsWe recorded scenarios of vehicle-pedestrian interactions with varying distances and speeds at multiple suburban zebra crossings without traffic lights, and projected the videos to guide participants through a realistic crossing experience indoors. Sixty children, with 20 in each age group of 6, 8, and 11 years old (with equal numbers of boys and girls), were recruited. The children's crossing safety was measured using the dangerous crossing (DC), safe crossing rate (SCR) and time to contact (TTC), and they were also asked to complete the Chinese version of the Pedestrian Behavior Scale (CPBS). Their eye movements were also recorded with a portable eye tracker. ResultsThe correlation analysis of the simulated street-crossing video test revealed significant associations between behavioral indicators (DC, TTC), CPBS, and eye movement indicators, indicating strong empirical validity. Difficulty analysis confirmed the relatively high SCR among child pedestrians across all three age groups. Discriminant validity analysis demonstrated that age significantly predicted children's crossing safety, with 6-year-olds exhibiting lower safety in both behavioral and attentional dimensions compared to 8-year-olds and 11-year-olds. Finally, predictive validity results indicated varying effects of TTC on CPBS scores across different age groups, with a more significant predictive effect for younger children possessing lower street-crossing abilities. ConclusionThe video test effectively verified the critical period and developmental trend of children's crossing ability and demonstrated high validity. Overall, the developed video test is an effective tool for assessing school-aged children's crossing safety.

A comparison of pedestrian behavior in interactions with autonomous and human-driven vehicles: An extreme value theory approach

Autonomous Vehicle (AV) technologies are expected to result in significant safety and mobility benefits to the road system. However, one of the most important issues that autonomous vehicle technology faces is ensuring safe interactions with active road users such as pedestrians who can have unpredictable behavior. Moreover, road user behavior varies considerably across different traffic environments, which might represent a challenge to implementing AVs as they lack the intuition common in human-driven vehicles (HDV). This study proposes an approach to evaluate crash risk in vehicle–pedestrian interactions. An Extreme Value Theory (EVT) Peak Over Threshold (POT) model is used to compare the crash risk of AV-pedestrian and HDV-pedestrian interactions in four different cities, namely Boston, Las Vegas, Pittsburgh, and Singapore. A Bayesian hierarchical structure is used to incorporate the effect of several behavioral covariates, which enables estimating the crash risk of each interaction. Results show that the risk varies considerably depending on the type of interaction and the environment. For example, the impact of behavioral covariates (i.e., minimum distance between road users and maximum pedestrian speed) on the risk of AV-pedestrian interactions is greater when compared to the risk of HDV-pedestrian interactions in Boston, Las Vegas, and Singapore. This might indicate that, in busy and congested environments, road users may not be entirely comfortable with the presence of AVs. In addition, Singapore presented a higher percentage of riskier AV-pedestrian interactions when compared to the other cities. Finally, this study offers significant insights into the challenges of introducing AVs in diverse environments as behavior plays a crucial role in traffic and can influence conflict occurrence.

Pedestrian–vehicle interactions at unsignalized mid-block crosswalks: Effects on traffic flow, CO[formula omitted] emissions, and energy dissipation

Unsignalized mid-block crosswalks are adopted to regulate unauthorized crossings by promoting drivers’ yielding to pedestrians. Although pedestrian–vehicle interactions at crosswalks have been widely studied, the effects of such facilities regarding traffic flow and emissions have been overlooked. This paper presents a vehicle–pedestrian cellular automata model to analyze the effects of two types of crosswalk systems: raised and zebra, on traffic characteristics. The model allows microscopically studying the impact of the induced speed heterogeneity in terms of traffic flow, CO2 emissions, and kinetic energy dissipation. Simulation results show that traffic flow experiences four phases in both systems: maximum current, congestion, jamming, and blocking; with second-order transitions among them. The maximum current phase is the only one with free-flow conditions shrinking faster in the system with a raised crosswalk than in the one with zebra. Both systems reach the blocking phase when the pedestrian entrance rate surpasses a critical value. However, raised crosswalk has lesser repercussions in CO2 emission and energy dissipation by eliciting traffic calm. This study enhances the comprehension of the impacts of mid-block crosswalks, depending on the manner in which they are deployed.

Effect of vehicle external acceleration signal light on pedestrian-vehicle interaction

The number of casualties resulting from collisions between pedestrians and motor vehicles continues to rise. A significant factor is the misunderstanding of vehicle behavior intentions by pedestrians. This is especially true with the continuous development of vehicle automation technology, which has reduced direct interaction between drivers and the outside world. Therefore, accurate communication of vehicle behavior intentions is becoming increasingly important. The purpose of this study is to investigate the impact of external vehicle acceleration signal light on the interaction experience between pedestrians and vehicles. The differences between the use and nonuse of acceleration signal light are compared through controlled test track experiments in real scenarios and in videos.The results show that acceleration signal light help pedestrians understand vehicle behavior intentions more quickly and make safer crossing decisions as well as improving their perception of safety when crossing the street and their trust in vehicle behavior.

Interaction-Aware Decision-Making for Autonomous Vehicles

Complex, dynamic, and interactive environment brings huge challenges to autonomous driving technologies. Because of the strong interactions between different traffic participants, autonomous vehicles (AVs) must learn how to interact with other road users. Failure to consider interaction when making decisions may result in safety issues. In this paper, an interaction-aware decision-making approach is proposed for AVs. First, focusing on the interaction at uncontrolled mid-block crosswalks, the game theory is used to model the vehicle-pedestrian interaction (VPI). Then, an interaction inference framework is developed using the interaction model to obtain interaction information with pedestrians. Besides, a collaborative action planning method is proposed to generate collaborative actions. More importantly, interactive decision-making is formulated as an optimization problem by considering the task item and action item. Furthermore, considering pedestrians’ different levels of cooperation, the social force pedestrian model is developed. And then, a highly interactive environment is constructed. Finally, qualitative and quantitative evaluations are carried out against three baseline methods. The result shows that our method can interact with different pedestrians and balance safety and efficiency compared to baseline methods.

Pedestrian delay models for compliant & non-compliant behaviour at signalized midblock crosswalks under mixed traffic conditions

The present study aimed to propose new pedestrian delay models for Signalized Midblock Crosswalks (SMC) for mixed traffic conditions. A detailed study of the literature revealed that most of the existing pedestrian delay models were developed for signalized intersections. Thus, the need for the study was established and data were collected at eight SMC in Hyderabad, one of the most densely populated metropolitan cities in India, using video-graphic technique. Two delay models were developed based on the compliance behaviour and non-compliance behaviour of pedestrians. Both models have two components i.e., waiting delay and crossing delay where the latter has two subset components i.e., frictional delay and pedestrian-vehicle interaction delay. The bidirectional effect (pedestrian-pedestrian interaction while crossing the road) of pedestrians was addressed as frictional delay while the non-compliance behaviour by pedestrians and vehicles was addressed as pedestrian-vehicle interaction delay in the present models. The waiting delay component was defined by modifying the Webster delay model for non-uniform pedestrian arrivals. The proposed delay models yielded an error of 5% and 7% for compliance behaviour model and non-compliance behaviour model respectively. The proposed models can be used for optimizing the signal timings and defining Level of Service (LOS) of facilities.

Holistic Spatio-Temporal Graph Attention for Trajectory Prediction in Vehicle-Pedestrian Interactions.

Ensuring that intelligent vehicles do not cause fatal collisions remains a persistent challenge due to pedestrians' unpredictable movements and behavior. The potential for risky situations or collisions arising from even minor misunderstandings in vehicle-pedestrian interactions is a cause for great concern. Considerable research has been dedicated to the advancement of predictive models for pedestrian behavior through trajectory prediction, as well as the exploration of the intricate dynamics of vehicle-pedestrian interactions. However, it is important to note that these studies have certain limitations. In this paper, we propose a novel graph-based trajectory prediction model for vehicle-pedestrian interactions called Holistic Spatio-Temporal Graph Attention (HSTGA) to address these limitations. HSTGA first extracts vehicle-pedestrian interaction spatial features using a multi-layer perceptron (MLP) sub-network and max pooling. Then, the vehicle-pedestrian interaction features are aggregated with the spatial features of pedestrians and vehicles to be fed into the LSTM. The LSTM is modified to learn the vehicle-pedestrian interactions adaptively. Moreover, HSTGA models temporal interactions using an additional LSTM. Then, it models the spatial interactions among pedestrians and between pedestrians and vehicles using graph attention networks (GATs) to combine the hidden states of the LSTMs. We evaluate the performance of HSTGA on three different scenario datasets, including complex unsignalized roundabouts with no crosswalks and unsignalized intersections. The results show that HSTGA outperforms several state-of-the-art methods in predicting linear, curvilinear, and piece-wise linear trajectories of vehicles and pedestrians. Our approach provides a more comprehensive understanding of social interactions, enabling more accurate trajectory prediction for safe vehicle navigation.

Pedestrian Crossing Intention Prediction Model Considering Social Interaction between Multi-Pedestrians and Multi-Vehicles

Accurate pedestrian crossing intention prediction is critical for autonomous vehicles and advanced driver assistance systems. In multi-pedestrian and multi-vehicle interaction scenes, the social interaction between pedestrians and other traffic participants is ubiquitous, which affects pedestrian crossing decisions and the accuracy of prediction. However, previous studies on pedestrian crossing intention lack comprehensive consideration and mathematical modeling of the social interaction. We propose a “social interaction force” (SIF) to identify and quantify social interaction behaviors and combine the hidden Markov model (HMM) to predict pedestrian crossing intentions 1.0 s ahead. Firstly, a large dataset of pedestrian-vehicle interaction samples is collected from two views, and high-dimensional features are extracted for pedestrian intention prediction. Next, the concept of SIF is proposed to quantitatively characterize the influence of other pedestrians and vehicles on pedestrian crossing decisions, including “pedestrian interaction force” and “pedestrian-vehicle interaction force.” Finally, SIF, pedestrian features, and road structure features are input into HMM. Sliding time windows are applied to the HMM to achieve dynamic prediction of pedestrian intention sequences. Experimental results show that the recognition accuracy of the proposed model is 0.976, and the accuracy of 1.0 s ahead prediction is 0.932 with guaranteed prediction speed. The proposed model performance is superior to that of the most prevalent models developed thus far.

Investigating surrogate safety measures at midblock pedestrian crossings using multivariate models with roadside camera data

This study aims to evaluate and compare Surrogate Safety Measures (SSMs) at five midblock Rectangular Rapid Flashing Beacons (RRFB) and two midblock Pedestrian Hybrid Beacons (PHB) sites in Florida using extensive video data collected over the study period of July to November 2021. Computer vision and data processing resulted in four pedestrian SSMs, namely spatial gap, temporal gap, relative time to collision (RTTC) and Post Encroachment Time (PET). An initial investigation of the SSMs using Mann-Whitney-Wilcoxon tests revealed significant differences in the SSM values across different treatment types and hours of the day. Additionally, univariate regression of spatial gap, and multivariate regression of temporal gap, RTTC and PET revealed significant differences of SSMs across RRFB and PHB sites. The study considered both linear and non-linear (gamma, inverse Gaussian and lognormal) regression models. After considering various traffic and operational parameters, the data were aggregated for each pedestrian-vehicle interaction on each lane to create a total of 395 observations. The SSMs included average spatial gap, temporal gap, RTTC and PET for each interaction of pedestrian and vehicle on each lane. The results indicated that non-linear models performed better than the linear models. Moreover, the presence of the PHB, weekday, signal activation, lane count, pedestrian speed, vehicle speed, land use mix, morning period and pedestrian starting position from the sidewalk have been found to be significant determinants of the SSMs. Results also suggest temporal SSMs increase at the PHB sites compared to the RRFB sites, indicating an improvement of traffic safety at PHB sites. However, the spatial gap decreased for PHB sites compared to the RRFB sites, which suggests that pedestrians tend to start to cross the RRFB sites when they perceive vehicles to be further away than at the PHB sites.

A study on meta-analysis approach for pedestrian-vehicle interaction using LiDAR

To analyse the continuous and intricate interaction between pedestrians and vehicles and to safeguard them, high-resolution micro-traffic data is needed. In comparison to other traditional means of data collection, light detection and ranging (LiDAR) technology is gaining popularity since it can deliver this information with less computing effort and is weather-resistant. This article uses LiDAR technology to analyse qualitative and quantitative data related to pedestrian-vehicle interaction. Based on the study selection criteria, a total of 39 studies were included in the qualitative analysis. Based on the availability of the data, four of these studies were then included in the quantitative meta-analysis. Some of the algorithms developed thus far have a 99 percent accuracy rate. The analysis was carried out using the Fisher r-to-z transformed correlation coefficient as the outcome measure. The amount of heterogeneity was estimated using the restricted maximum-likelihood estimator. A random-effects model was fitted to the data. Q = 51.716, p = 0.0001, and I2 = 92.86 percent were the results of the Q test, demonstrating that there is enough heterogeneity amongst the studies. Neither the rank correlation nor the regression test indicated any funnel plot asymmetry. The findings indicate that LiDAR is a suitable technology for studying pedestrian-vehicle interaction. The study results are useful to explore the new technology of LiDAR and its suitability in pedestrian-vehicle interactions.

Evaluating Right-Turn Flashing Yellow Arrow for Vehicle–Pedestrian Interactions Using a Non-Probabilistic Regression Approach

Using video, interactions between right-turning vehicles and pedestrians were documented for sites with a permissive circular green or a flashing yellow arrow (FYA) permissive right-turn indication. Timestamps associated with key vehicle and pedestrian positions were documented and used to calculate three metrics: time for driver to complete right turn (with and without a pedestrian presence) and the time for the pedestrian to arrive at the theoretical conflict point of vehicle–pedestrian interactions. Using timestamp data, multiple non-probabilistic linear regression models were created to describe the relationship between the position of the pedestrian within the crosswalk and the time for a right-turning vehicle maneuver to be completed. Model results implicitly describe the attitude of drivers toward pedestrian presence on the crosswalk. Larger right-turning maneuver completion times are arguably an indicator of greater respect toward pedestrian presence. Given the nature of the model’s output, a pedestrian respect indicator (PRI) based on the value of model parameters is introduced as a potential indicator of the safety of vehicle–pedestrian interactions. PRI values can be computed for individual sites thus allowing its use as a safety indicator. The higher the PRI, the more “respect” toward pedestrians. Proof-of-concept modeling results based on available timestamp data suggest that interactions controlled by a right-turn FYA indication have a higher PRI than interactions controlled by a circular green. An argument is made that PRI values can be potentially used to proactively evaluate the effectiveness of traffic control devices and other safety countermeasures without the need for crash data.

Deep learning-based pedestrian trajectory prediction and risk assessment at signalized intersections using trajectory data captured through roadside LiDAR

In recent years, rapid advancements in the Autonomous Vehicles (AVs) industry have greatly motivated the research and development in pedestrian trajectory prediction and risk assessment. One of the critical requirements for AVs is to predict the future trajectories of pedestrians and provide collision warnings in an accurate and prompt manner. Nevertheless, accurate prediction of pedestrian trajectories remains a technical challenge, mainly caused by the heterogeneity of pedestrian crossing behavior and uncertainties in vehicle-pedestrian interactions. This paper proposes a deep learning-based method for pedestrian trajectory prediction and risk assessment, using trajectory data extracted from roadside LiDAR data and corresponding signal phasing information at MLK and Georgia Avenue in Chattanooga, TN. Meanwhile, a set of criteria referred to as the risk factor is established to quantitatively evaluate the risk of the pedestrian crossing behavior, which also serves as a learnable feature. A Long Short-Term Memory (LSTM) network is proposed, which takes the following data as the input: the pedestrian trajectory data, signal phasing data, and risk factors from the past 10 steps. Meanwhile, the network predicts the pedestrian trajectory and risk factor at the future time step. In the experimental study, the root-mean-square errors between the predicted and ground truth x and y coordinates are 0.225 meters and 0.377 meters, respectively, and the F1 score value for the risk factor is 99.6%, demonstrating the efficacy of the proposed LSTM-based methodology on pedestrian trajectory prediction and risk assessment.