RESUMO
OBJECTIVE: We investigated how different deceleration intentions (i.e. an automated vehicle either decelerated for leading traffic or yielded for pedestrians) and a novel (Slow Pulsing Light Band - SPLB) or familiar (Flashing Headlights - FH) external Human Machine Interface (eHMI) informed pedestrians' crossing behaviour. BACKGROUND: The introduction of SAE Level 4 Automated Vehicles (AVs) has recently fuelled interest in new forms of explicit communication via eHMIs, to improve the interaction between AVs and surrounding road users. Before implementing these eHMIs, it is necessary to understand how pedestrians use them to inform their crossing decisions. METHOD: Thirty participants took part in the study using a Head-Mounted Display. The independent variables were deceleration intentions and eHMI design. The percentage of crossings, collision frequency and crossing initiation time across trials were measured. RESULTS: Pedestrians were able to identify the intentions of a decelerating vehicle, using implicit cues, with more crossings made when the approaching vehicles were yielding to them. They were also more likely to cross when a familiar eHMI was presented, compared to a novel one or no eHMI, regardless of the vehicle's intention. Finally, participants learned to take a more cautious approach as trials progressed, and not to base their decisions solely on the eHMI. CONCLUSION: A familiar eHMI led to early crossings regardless of the vehicle's intention but also led to a higher collision frequency than a novel eHMI. APPLICATION: To achieve safe and acceptable interactions with AVs, it is important to provide eHMIs that are congruent with road users' expectations.
RESUMO
Evidence accumulation models provide a dominant account of human decision-making, and have been particularly successful at explaining behavioral and neural data in laboratory paradigms using abstract, stationary stimuli. It has been proposed, but with limited in-depth investigation so far, that similar decision-making mechanisms are involved in tasks of a more embodied nature, such as movement and locomotion, by directly accumulating externally measurable sensory quantities of which the precise, typically continuously time-varying, magnitudes are important for successful behavior. Here, we leverage collision threat detection as a task which is ecologically relevant in this sense, but which can also be rigorously observed and modelled in a laboratory setting. Conventionally, it is assumed that humans are limited in this task by a perceptual threshold on the optical expansion rate-the visual looming-of the obstacle. Using concurrent recordings of EEG and behavioral responses, we disprove this conventional assumption, and instead provide strong evidence that humans detect collision threats by accumulating the continuously time-varying visual looming signal. Generalizing existing accumulator model assumptions from stationary to time-varying sensory evidence, we show that our model accounts for previously unexplained empirical observations and full distributions of detection response. We replicate a pre-response centroparietal positivity (CPP) in scalp potentials, which has previously been found to correlate with accumulated decision evidence. In contrast with these existing findings, we show that our model is capable of predicting the onset of the CPP signature rather than its buildup, suggesting that neural evidence accumulation is implemented differently, possibly in distinct brain regions, in collision detection compared to previously studied paradigms.
Assuntos
Encéfalo/fisiologia , Tomada de Decisões/fisiologia , Percepção Espacial/fisiologia , Adulto , Biologia Computacional , Eletroencefalografia , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Modelos Neurológicos , Análise e Desempenho de Tarefas , Fatores de Tempo , Adulto JovemRESUMO
OBJECTIVE: We aim to bridge the gap between naturalistic studies of driver behavior and modern cognitive and neuroscientific accounts of decision making by modeling the cognitive processes underlying left-turn gap acceptance by human drivers. BACKGROUND: Understanding decisions of human drivers is essential for the development of safe and efficient transportation systems. Current models of decision making in drivers provide little insight into the underlying cognitive processes. On the other hand, laboratory studies of abstract, highly controlled tasks point towards noisy evidence accumulation as a key mechanism governing decision making. However, it is unclear whether the cognitive processes implicated in these tasks are as paramount to decisions that are ingrained in more complex behaviors, such as driving. RESULTS: The drivers' probability of accepting the available gap increased with the size of the gap; importantly, response time increased with time gap but not distance gap. The generalized drift-diffusion model explained the observed decision outcomes and response time distributions, as well as substantial individual differences in those. Through cross-validation, we demonstrate that the model not only explains the data, but also generalizes to out-of-sample conditions. CONCLUSION: Our results suggest that dynamic evidence accumulation is an essential mechanism underlying left-turn gap acceptance decisions in human drivers, and exemplify how simple cognitive process models can help to understand human behavior in complex real-world tasks. APPLICATION: Potential applications of our results include real-time prediction of human behavior by automated vehicles and simulating realistic human-like behaviors in virtual environments for automated vehicles.
RESUMO
OBJECTIVE: This paper aims to describe and test novel computational driver models, predicting drivers' brake reaction times (BRTs) to different levels of lead vehicle braking, during driving with cruise control (CC) and during silent failures of adaptive cruise control (ACC). BACKGROUND: Validated computational models predicting BRTs to silent failures of automation are lacking but are important for assessing the safety benefits of automated driving. METHOD: Two alternative models of driver response to silent ACC failures are proposed: a looming prediction model, assuming that drivers embody a generative model of ACC, and a lower gain model, assuming that drivers' arousal decreases due to monitoring of the automated system. Predictions of BRTs issued by the models were tested using a driving simulator study. RESULTS: The driving simulator study confirmed the predictions of the models: (a) BRTs were significantly shorter with an increase in kinematic criticality, both during driving with CC and during driving with ACC; (b) BRTs were significantly delayed when driving with ACC compared with driving with CC. However, the predicted BRTs were longer than the ones observed, entailing a fitting of the models to the data from the study. CONCLUSION: Both the looming prediction model and the lower gain model predict well the BRTs for the ACC driving condition. However, the looming prediction model has the advantage of being able to predict average BRTs using the exact same parameters as the model fitted to the CC driving data. APPLICATION: Knowledge resulting from this research can be helpful for assessing the safety benefits of automated driving.
Assuntos
Condução de Veículo , Acidentes de Trânsito , Automação , Fenômenos Biomecânicos , Humanos , Tempo de ReaçãoRESUMO
OBJECTIVE: To present a structured, narrative review highlighting research into human perceptual-motor coordination that can be applied to automated vehicle (AV)-human transitions. BACKGROUND: Manual control of vehicles is made possible by the coordination of perceptual-motor behaviors (gaze and steering actions), where active feedback loops enable drivers to respond rapidly to ever-changing environments. AVs will change the nature of driving to periods of monitoring followed by the human driver taking over manual control. The impact of this change is currently poorly understood. METHOD: We outline an explanatory framework for understanding control transitions based on models of human steering control. This framework can be summarized as a perceptual-motor loop that requires (a) calibration and (b) gaze and steering coordination. A review of the current experimental literature on transitions is presented in the light of this framework. RESULTS: The success of transitions are often measured using reaction times, however, the perceptual-motor mechanisms underpinning steering quality remain relatively unexplored. CONCLUSION: Modeling the coordination of gaze and steering and the calibration of perceptual-motor control will be crucial to ensure safe and successful transitions out of automated driving. APPLICATION: This conclusion poses a challenge for future research on AV-human transitions. Future studies need to provide an understanding of human behavior that will be sufficient to capture the essential characteristics of drivers reengaging control of their vehicle. The proposed framework can provide a guide for investigating specific components of human control of steering and potential routes to improving manual control recovery.
Assuntos
Automação , Condução de Veículo/psicologia , Desempenho Psicomotor/fisiologia , Ergonomia , Humanos , Tempo de Reação/fisiologiaRESUMO
OBJECTIVE: This article provides a review of empirical studies of automated vehicle takeovers and driver modeling to identify influential factors and their impacts on takeover performance and suggest driver models that can capture them. BACKGROUND: Significant safety issues remain in automated-to-manual transitions of vehicle control. Developing models and computer simulations of automated vehicle control transitions may help designers mitigate these issues, but only if accurate models are used. Selecting accurate models requires estimating the impact of factors that influence takeovers. METHOD: Articles describing automated vehicle takeovers or driver modeling research were identified through a systematic approach. Inclusion criteria were used to identify relevant studies and models of braking, steering, and the complete takeover process for further review. RESULTS: The reviewed studies on automated vehicle takeovers identified several factors that significantly influence takeover time and post-takeover control. Drivers were found to respond similarly between manual emergencies and automated takeovers, albeit with a delay. The findings suggest that existing braking and steering models for manual driving may be applicable to modeling automated vehicle takeovers. CONCLUSION: Time budget, repeated exposure to takeovers, silent failures, and handheld secondary tasks significantly influence takeover time. These factors in addition to takeover request modality, driving environment, non-handheld secondary tasks, level of automation, trust, fatigue, and alcohol significantly impact post-takeover control. Models that capture these effects through evidence accumulation were identified as promising directions for future work. APPLICATION: Stakeholders interested in driver behavior during automated vehicle takeovers may use this article to identify starting points for their work.
Assuntos
Automação , Condução de Veículo , Simulação por Computador , Sistemas Homem-Máquina , Tempo de Reação , Acidentes de Trânsito/prevenção & controle , HumanosRESUMO
A conceptual and computational framework is proposed for modelling of human sensorimotor control and is exemplified for the sensorimotor task of steering a car. The framework emphasises control intermittency and extends on existing models by suggesting that the nervous system implements intermittent control using a combination of (1) motor primitives, (2) prediction of sensory outcomes of motor actions, and (3) evidence accumulation of prediction errors. It is shown that approximate but useful sensory predictions in the intermittent control context can be constructed without detailed forward models, as a superposition of simple prediction primitives, resembling neurobiologically observed corollary discharges. The proposed mathematical framework allows straightforward extension to intermittent behaviour from existing one-dimensional continuous models in the linear control and ecological psychology traditions. Empirical data from a driving simulator are used in model-fitting analyses to test some of the framework's main theoretical predictions: it is shown that human steering control, in routine lane-keeping and in a demanding near-limit task, is better described as a sequence of discrete stepwise control adjustments, than as continuous control. Results on the possible roles of sensory prediction in control adjustment amplitudes, and of evidence accumulation mechanisms in control onset timing, show trends that match the theoretical predictions; these warrant further investigation. The results for the accumulation-based model align with other recent literature, in a possibly converging case against the type of threshold mechanisms that are often assumed in existing models of intermittent control.
Assuntos
Condução de Veículo/psicologia , Simulação por Computador , Tomada de Decisões/fisiologia , Retroalimentação Sensorial/fisiologia , Redes Neurais de Computação , Desempenho Psicomotor/fisiologia , Humanos , Atividade Motora/fisiologia , Valor Preditivo dos TestesRESUMO
OBJECTIVE: The objective of this paper was to outline an explanatory framework for understanding effects of cognitive load on driving performance and to review the existing experimental literature in the light of this framework. BACKGROUND: Although there is general consensus that taking the eyes off the forward roadway significantly impairs most aspects of driving, the effects of primarily cognitively loading tasks on driving performance are not well understood. METHOD: Based on existing models of driver attention, an explanatory framework was outlined. This framework can be summarized in terms of the cognitive control hypothesis: Cognitive load selectively impairs driving subtasks that rely on cognitive control but leaves automatic performance unaffected. An extensive literature review was conducted wherein existing results were reinterpreted based on the proposed framework. RESULTS: It was demonstrated that the general pattern of experimental results reported in the literature aligns well with the cognitive control hypothesis and that several apparent discrepancies between studies can be reconciled based on the proposed framework. More specifically, performance on nonpracticed or inherently variable tasks, relying on cognitive control, is consistently impaired by cognitive load, whereas the performance on automatized (well-practiced and consistently mapped) tasks is unaffected and sometimes even improved. CONCLUSION: Effects of cognitive load on driving are strongly selective and task dependent. APPLICATION: The present results have important implications for the generalization of results obtained from experimental studies to real-world driving. The proposed framework can also serve to guide future research on the potential causal role of cognitive load in real-world crashes.
Assuntos
Atenção/fisiologia , Condução de Veículo , Função Executiva/fisiologia , Memória de Curto Prazo/fisiologia , Desempenho Psicomotor/fisiologia , Adulto , Feminino , Humanos , MasculinoRESUMO
To steer a vehicle, humans must process incoming signals that provide information about their movement through the world. These signals are used to inform motor control responses that are appropriately timed and of the correct magnitude. However, the perceptual mechanisms determining how drivers process visual information remain unclear. Previous research has demonstrated that when steering toward a straight road-line, drivers accumulate perceptual evidence (error) over time to initiate steering action (Accumulator framework), rather than waiting for perceptual evidence to surpass time-independent fixed thresholds (Threshold framework). The more general case of steering around bends (with a requirement that the trajectory is adjusted to match the road curvature ahead) provides richer continuously varying information. The current experiment aims to establish whether the Accumulator framework provides a good description of human responses when steering toward curved road-lines. Using a computer-generated steering correction paradigm, drivers (N = 11) steered toward intermittently appearing curved road-lines that varied in position and radius with respect to the driver's trajectory. The Threshold framework predicted that steering responses would be of fixed magnitude and at fixed absolute errors across conditions regardless of the rate of error development. Conversely, the Accumulator framework predicted that drivers should respond to larger absolute errors when the error signal developed at a faster rate. Results were consistent with an Accumulator framework in a manner that supports previous investigations and the computational modeling literature. We propose that the accumulation of perceptual evidence captures human behavior in a variety of steering contexts that drivers face in the real world. (PsycInfo Database Record (c) 2023 APA, all rights reserved).
Assuntos
Condução de Veículo , Desempenho Psicomotor , Humanos , Desempenho Psicomotor/fisiologia , Movimento , Simulação por ComputadorRESUMO
When humans share space in road traffic, as drivers or as vulnerable road users, they draw on their full range of communicative and interactive capabilities. Much remains unknown about these behaviors, but they need to be captured in models if automated vehicles are to coexist successfully with human road users. Empirical studies of human road user behavior implicate a large number of underlying cognitive mechanisms, which taken together are well beyond the scope of existing computational models. Here, we note that for all of these putative mechanisms, computational theories exist in different subdisciplines of psychology, for more constrained tasks. We demonstrate how these separate theories can be generalized from abstract laboratory paradigms and integrated into a computational framework for modeling human road user interaction, combining Bayesian perception, a theory of mind regarding others' intentions, behavioral game theory, long-term valuation of action alternatives, and evidence accumulation decision-making. We show that a model with these assumptions-but not simpler versions of the same model-can account for a number of previously unexplained phenomena in naturalistic driver-pedestrian road-crossing interactions, and successfully predicts interaction outcomes in an unseen data set. Our modeling results contribute to demonstrating the real-world value of the theories from which we draw, and address calls in psychology for cumulative theory-building, presenting human road use as a suitable setting for work of this nature. Our findings also underscore the formidable complexity of human interaction in road traffic, with strong implications for the requirements to set on development and testing of vehicle automation.
RESUMO
Society greatly expects the widespread deployment of automated vehicles (AVs). However, the absence of a driver role results in unresolved communication issues between pedestrians and AVs. Research has shown the crucial role of implicit communication signals in this context. Nonetheless, it remains unclear how pedestrians subjectively estimate vehicle behaviour and whether they incorporate these estimations as part of their crossing decisions. For the first time, this study explores the impact of implicit communication signals on pedestrians' subjective estimations of approaching vehicle behaviour across a wide range of experimental traffic scenarios and on their crossing decisions in the same scenarios through a comprehensive analysis. Two simulator tasks, namely a natural road crossing task and a vehicle behaviour estimation task, were designed with controlled time to collision, vehicle speed, and deceleration behaviour. A novel finding is that the correlation between crossing decisions and vehicle behaviour estimations depends on the traffic scenario. Pedestrians' recognition of different deceleration behaviour aligned with their crossing decisions, supporting the notion that they actively estimate vehicle behaviour as part of their decision-making process. However, if the traffic gap was long enough, the effects of vehicle speed were the opposite between crossing decisions and estimations, suggesting that vehicle behaviour estimation may not directly impact crossing decisions when the time gap to the vehicle is large. We also found that pedestrians crossed the street earlier and estimated yielding behaviour more accurately in early-onset braking scenarios than in late-onset braking scenarios. Interestingly, vehicle speed significantly affected pedestrians' estimations, with pedestrians tending to perceive low vehicle speed as yielding behaviour regardless of whether the vehicle yielded. Finally, we demonstrated that visual cue τÌ is a practical indicator for controlling the vehicle deceleration evidence in the experiment. In conclusion, these findings reveal in detail the role of deceleration parameters as implicit communication signals between pedestrians and AVs, with implications for road crossing safety and the development of AVs.
Assuntos
Acidentes de Trânsito , Pedestres , Humanos , Acidentes de Trânsito/prevenção & controle , Veículos Autônomos , Desaceleração , Comunicação , Segurança , CaminhadaRESUMO
One of the current challenges of automation is to have highly automated vehicles (HAVs) that communicate effectively with pedestrians and react to changes in pedestrian behaviour, to promote more trustable HAVs. However, the details of how human drivers and pedestrians interact at unsignalised crossings remain poorly understood. We addressed some aspects of this challenge by replicating vehicle-pedestrian interactions in a safe and controlled virtual environment by connecting a high fidelity motion-based driving simulator to a CAVE-based pedestrian lab in which 64 participants (32 pairs of one driver and one pedestrian) interacted with each other under different scenarios. The controlled setting helped us study the causal role of kinematics and priority rules on interaction outcome and behaviour, something that is not possible in naturalistic studies. We also found that kinematic cues played a stronger role than psychological traits like sensation seeking and social value orientation in determining whether the pedestrian or driver passed first at unmarked crossings. One main contribution of this study is our experimental paradigm, which permitted repeated observation of crossing interactions by each driver-pedestrian participant pair, yielding behaviours which were qualitatively in line with observations from naturalistic studies.
Assuntos
Condução de Veículo , Pedestres , Humanos , Acidentes de Trânsito/prevenção & controle , Pedestres/psicologia , Segurança , Condução de Veículo/psicologia , Movimento (Física) , CaminhadaRESUMO
Vehicle control by humans is possible because the central nervous system is capable of using visual information to produce complex sensorimotor actions. Drivers must monitor errors and initiate steering corrections of appropriate magnitude and timing to maintain a safe lane position. The perceptual mechanisms determining how a driver processes visual information and initiates steering corrections remain unclear. Previous research suggests 2 potential alternative mechanisms for responding to errors: (a) perceptual evidence (error) satisficing fixed constant thresholds (Threshold), or (b) the integration of perceptual evidence over time (Accumulator). To distinguish between these mechanisms, an experiment was conducted using a computer-generated steering correction paradigm. Drivers (N = 20) steered toward an intermittently appearing "road-line" that varied in position and orientation with respect to the driver's position and trajectory. One key prediction from a Threshold framework is a fixed absolute error response across conditions regardless of the rate of error development, whereas the Accumulator framework predicts that drivers would respond to larger absolute errors when the error signal develops at a faster rate. Results were consistent with an Accumulator framework; thus we propose that models of steering should integrate perceived control error over time in order to accurately capture human perceptual performance. (PsycInfo Database Record (c) 2022 APA, all rights reserved).
Assuntos
Condução de Veículo , HumanosRESUMO
Distractions have been recognised as one important factor associated with pedestrian injuries, as the increasing use of cell phones and personal devices. However, the situation is less clear regarding the differences in the effects of visual-manual and auditory-cognitive distractions. Here, we investigated distracted pedestrians in a one-lane road with continuous traffic using an immersive CAVE-based simulator. Sixty participants were recruited to complete a crossing task and perform one of two distractions, a visual-manual task and an auditory-cognitive task. Moreover, normal and time pressure crossing conditions were included as a baseline and comparison. For the first time, this study directly compared the impacts of visual-manual, auditory-cognitive distractions, and time pressure on pedestrian crossing behaviour and safety in a controlled environment. The results indicated that although pedestrian safety was compromised under both types of distraction, the effects of the applied distractions were different. When engaged in the visual-manual distraction, participants crossed the road slowly, but there was no significant difference in gap acceptance or initiation time compared to baseline. In contrast, participants walked slowly, crossed earlier, and accepted smaller gaps when performing the auditory-cognitive distraction. This has interesting parallels to existing findings on how these two types of distractions affect driver performance. Moreover, the effects of the visual-manual distraction were found to be dynamic, as these effects were affected by the gap size. Finally, compared to baseline, time pressure resulted in participants accepting smaller time gaps with shorter initiation times and crossing durations, leading to an increase in unsafe decisions and a decrease in near-collisions. These results provide new evidence that two types of distraction and time pressure impair pedestrian safety, but in different ways. Our findings may provide insights for further studies involving pedestrians with different distraction components.
Assuntos
Pedestres , Acidentes de Trânsito/prevenção & controle , Atenção , Cognição , Humanos , Pedestres/psicologia , Segurança , Caminhada/psicologiaRESUMO
INTRODUCTION: In current urban traffic, pedestrians attempting to cross the road at un-signalized locations are thought to mostly use implicit communication, such as deceleration cues, to interpret a vehicle's intention to yield. There is less reliance on explicit driver- or vehicle-based messages, such as hand/head movements, or flashing lights/beeping horns. With the impending deployment of Automated Vehicles (AV), especially those at SAE Level 4 and 5, where the driver is no longer in control of the vehicle, there has been a surge in interest in the value of new forms of communication for AVs, for example, via different types of external Human Machine Interfaces (eHMIs). However, there is still much to be understood about how quickly a novel eHMI affects pedestrian crossing decisions, and whether it provides any additional aid, above and beyond implicit/kinematic information from the vehicle. The aim of this between-participant study, funded by the H2020 interACT project, was to investigate how the combination of kinematic information from a vehicle (e.g., Speed and Deceleration), and eHMI designs, play a role in assisting the crossing decision of pedestrians in a cave-based pedestrian simulator. METHOD: Using an existing, well-recognized, message for yielding (Flashing Headlights - FH) as a benchmark, this study also investigated how quickly a novel eHMI (Slow Pulsing Light Band - SPLB) was learned. To investigate the effect of eHMI visibility on crossing decisions, the distance at which each eHMI was perceivable was also measured. RESULTS: Results showed that, compared to SPLB, the FH led to earlier crossings during vehicle deceleration, especially at lower approaching speeds, and smaller time gaps. However, although FH was visible earlier than SPLB, this visibility does not appear to be the only reason for earlier crossings, with message familiarity thought to play a role. Participants were found to learn the meaning conveyed by FH relatively quickly, crossing around 1 second earlier in its presence (compared to the no eHMI condition), across the three blocks of trials. On the other hand, it took participants at least one block of 12 trials for the new SPLB signal to affect crossing, which only accelerated crossing initiations by around 200â¯ms, compared to the no eHMI condition. The role of comprehension, long-term exposure, and familiarity of novel messages in this context is therefore important, if AVs are to provide safe, trustworthy communication messages, which will enhance traffic flow and efficiency.
Assuntos
Pedestres , Acidentes de Trânsito , Fenômenos Biomecânicos , Comunicação , Humanos , Segurança , CaminhadaRESUMO
When faced with an imminent collision threat, human vehicle drivers respond with braking in a manner which is stereotypical, yet modulated in complex ways by many factors, including the specific traffic situation and past driver eye movements. A computational model capturing these phenomena would have high applied value, for example in virtual vehicle safety testing methods, but existing models are either simplistic or not sufficiently validated. This paper extends an existing quantitative driver model for initiation and modulation of pre-crash brake response, to handle off-road glance behavior. The resulting models are fitted to time-series data from real-world naturalistic rear-end crashes and near-crashes. A stringent parameterization and model selection procedure is presented, based on particle swarm optimization and maximum likelihood estimation. A major contribution of this paper is the resulting first-ever fit of a computational model of human braking to real near-crash and crash behavior data. The model selection results also permit novel conclusions regarding behavior and accident causation: Firstly, the results indicate that drivers have partial visual looming perception during off-road glances; that is, evidence for braking is collected, albeit at a slower pace, while the driver is looking away from the forward roadway. Secondly, the results suggest that an important causation factor in crashes without off-road glances may be a reduced responsiveness to visual looming, possibly associated with cognitive driver state (e.g., drowsiness or erroneous driver expectations). It is also demonstrated that a model parameterized on less-critical data, such as near-crashes, may also accurately reproduce driver behavior in highly critical situations, such as crashes.
Assuntos
Acidentes de Trânsito , Condução de Veículo , Movimentos Oculares , Humanos , Percepção Visual , VigíliaRESUMO
OBJECTIVE: The paper presents a systematic analysis of drivers' crash avoidance response during crashes and near-crashes and developed a machine learning-based predictive model that can determine driver maneuver using pre-incident driver behavior and driving context. METHODS: We analyzed 286 naturalistic rear-end crashes and near-crashes from the SHRP2 naturalistic driving study. All the events were manually reduced using face video (face and forward) and kinematic responses. In this paper, we developed new reduction variables that enhanced the understanding of drivers' gaze behavior and roadway attention behavior during these events. These features reflected how the event criticality, measured using time to collision, related to drivers' pre-incident behavior (secondary behavior, gaze behavior), and drivers' perception of the event (physical reaction and maneuver). The imperative understanding of such relations was validated using a random forest- (RF) based classifier, which efficiently predicted if a driver was going to brake or change the lane as an avoidance maneuver. RESULTS: The RF presented in this paper effectively explored the nonlinear patterns in the data and was highly accurate (â¼96 %) in its prediction. A further analysis of the RF model showed that six features played a pivotal role in the decision logic. These included the drivers' last glance duration before the event, last glance eccentricity, duration of 'eyes on road' immediately before the event, the time instance and criticality when the driver perceives the threat as well as acknowledge the threat, and possibility of an escape path in the adjacent lane. Using partial dependency plots, we also showed how different thresholds of these feature variables determined the drivers' maneuver intention. CONCLUSIONS: In this paper we analyzed driving context, drivers' behavior, event criticality, and drivers' response in a unified structure to predict their avoidance response. To the best of our knowledge, this is the first such effort where large-scale naturalistic data (crashes and near crashes) was analyzed for prediction of drivers' maneuver and determined key behavioral and contextual factors that contribute to this avoidance maneuver.
Assuntos
Acidentes de Trânsito , Condução de Veículo , Acidentes de Trânsito/prevenção & controle , Atenção , Fenômenos Biomecânicos , Árvores de Decisões , HumanosRESUMO
Automated vehicles (AVs) will change the role of the driver, from actively controlling the vehicle to primarily monitoring it. Removing the driver from the control loop could fundamentally change the way that drivers sample visual information from the scene, and in particular, alter the gaze patterns generated when under AV control. To better understand how automation affects gaze patterns this experiment used tightly controlled experimental conditions with a series of transitions from 'Manual' control to 'Automated' vehicle control. Automated trials were produced using either a 'Replay' of the driver's own steering trajectories or standard 'Stock' trials that were identical for all participants. Gaze patterns produced during Manual and Automated conditions were recorded and compared. Overall the gaze patterns across conditions were very similar, but detailed analysis shows that drivers looked slightly further ahead (increased gaze time headway) during Automation with only small differences between Stock and Replay trials. A novel mixture modelling method decomposed gaze patterns into two distinct categories and revealed that the gaze time headway increased during Automation. Further analyses revealed that while there was a general shift to look further ahead (and fixate the bend entry earlier) when under automated vehicle control, similar waypoint-tracking gaze patterns were produced during Manual driving and Automation. The consistency of gaze patterns across driving modes suggests that active-gaze models (developed for manual driving) might be useful for monitoring driver engagement during Automated driving, with deviations in gaze behaviour from what would be expected during manual control potentially indicating that a driver is not closely monitoring the automated system.
RESUMO
Current and foreseeable automated vehicles are not able to respond appropriately in all circumstances and require human monitoring. An experimental examination of steering automation failure shows that response latency, variability and corrective manoeuvring systematically depend on failure severity and the cognitive load of the driver. The results are formalised into a probabilistic predictive model of response latencies that accounts for failure severity, cognitive load and variability within and between drivers. The model predicts high rates of unsafe outcomes in plausible automation failure scenarios. These findings underline that understanding variability in failure responses is crucial for understanding outcomes in automation failures.
Assuntos
Automação , Condução de Veículo , Sistemas Homem-Máquina , Tempo de Reação/fisiologia , Acidentes de Trânsito/prevenção & controle , Adulto , Comportamento/fisiologia , Cromatografia em Camada Fina , Feminino , Humanos , Masculino , Visão Ocular/fisiologiaRESUMO
Driver distraction is one of the main causes of motor-vehicle accidents. However, the impact on traffic safety of tasks that impose cognitive (non-visual) distraction remains debated. One particularly intriguing finding is that cognitive load seems to improve lane keeping performance, most often quantified as reduced standard deviation of lateral position (SDLP). The main competing hypotheses, supported by current empirical evidence, suggest that cognitive load improves lane keeping via either increased physical arousal, or higher gaze concentration toward the road center, but views are mixed regarding if, and how, these possible mediators influence lane keeping performance. Hence, a simulator study was conducted, with participants driving on a straight city road section whilst completing a cognitive task at different levels of difficulty. In line with previous studies, cognitive load led to increased physical arousal, higher gaze concentration toward the road center, and higher levels of micro-steering activity, accompanied by improved lane keeping performance. More importantly, during the high cognitive task, both physical arousal and gaze concentration changed earlier in time than micro-steering activity, which in turn changed earlier than lane keeping performance. In addition, our results did not show a significant correlation between gaze concentration and physical arousal on the level of individual task recordings. Based on these findings, various multilevel models for micro-steering activity and lane keeping performance were conducted and compared, and the results suggest that all of the mechanisms proposed by existing hypotheses could be simultaneously involved. In other words, it is suggested that cognitive load leads to: (i) an increase in arousal, causing increased micro-steering activity, which in turn improves lane keeping performance, and (ii) an increase in gaze concentration, causing lane keeping improvement through both (a) further increased micro-steering activity and (b) a tendency to steer toward the gaze target.