Intention Recognition Process And Its Influencing Factors In Driver-pedestrian Interaction

Pedestrians are the most vulnerable road users,and pedestrian accidents usually occur as a result of unsafe interaction with vehicles.Researchers have conducted lots of studies to understand the development and the consequence of the driver-pedestrian interaction,by analyzing traffic accident statistics,parameterizing traffic conflict,and observing interaction behaviors.Especially for the later one,many factors related to pedestrians,drivers,and road environments have found to influence drivers' behavior during the driver-pedestrian interaction.However,according to the theory of situation awareness,interaction behavior is just the consequence of information processing.Drivers must detect pedestrians,recognize the intentions of pedestrians,and predict the future state of pedestrians before making a behavioral response.Drivers' recognition of pedestrian road crossing intentions is an essential process during driver-pedestrian interaction.However,compared with the rich observational findings on interaction behavior,little is known on drivers' performance in recognizing pedestrian intentions,the underlying cognitive processes,and what information is used to recognize intentions.This research conducted two studies to fill in the gap,to get a deep understanding of intention recognition in driver-pedestrian interaction.The first study evaluated drivers' performance in making judgments of pedestrians'road crossing intentions in recorded natural driving scenes.Experienced and novice drivers identified pedestrians as "will cross" or "will not cross" at some time-to-arrival while their eye movements were recorded.The results showed that experienced drivers were more conservative in discriminating whether a pedestrian would cross or not(preferred a "pedestrian will cross" judgment)and took a higher level of information processing of pedestrian intention.Regardless of driving experience,drivers had a higher detection rate,earlier detection,higher level of information processing and quicker response over pedestrians who intended to cross than those did not intend to cross.A quicker response was also achieved when the time-to-arrival was smaller.Analysis of eye movements showed an attentional bias to the upper body of pedestrians when recognizing intention.The second study aimed to know what information was used by drivers as a cue to pedestrians' road crossing intentions,by utilizing the video recording of driver-pedestrian interaction and drivers intention judgments.At first,a logistic regression model was developed to predict pedestrians' road crossing judgments.The result shows that pedestrians' movement state,looking behavior and lateral distance to the lane could predict pedestrians' road crossing judgment,and could be served as the expression of implicit intentions.After that,a generalized linear mixed model was developed to fit drivers' intention judgments.The result shows that drivers could utilize pedestrians'movement state,looking behavior and lateral distance to the lane,as well as pedestrians'position and group size,to recognize pedestrians' intentions.These findings offer an initial understanding of the intention recognition process during driver-pedestrian interaction,and could help to recognize human errors behind vehicle-pedestrian accidents.