Citation

Hacohen S, Shoval S, Shvalb N. Accid. Anal. Prev. 2020; 142: e105518.

Copyright

(Copyright © 2020, Elsevier Publishing)

DOI

10.1016/j.aap.2020.105518

PMID

unavailable

Abstract

Traffic accidents are becoming a significant cause for unnatural deaths around the world, with more than 1.25 million fatalities in road accidents each year, and over 20 million people severely injured. A large portion of accidents that result in fatalities involve interaction between vehicles and pedestrians. In the literature, researchers speculate on a wide range of reasons for these figures. This paper focuses on the relationship between pedestrians' urgency to cross a busy road and the resulting level of risk for an accident. The probability for an accident is determined by a prediction model for a collision between drivers and pedestrians at congested conflict spots. The model is based on a motion planner called the Probabilistic Navigation Function (PNF), initially designed for robot navigation in dynamic cluttered and uncertain environments. The model predicts pedestrians' trajectories when crossing a busy road in a sub-meter accuracy, based on the risk they are willing to take (a reflection of the level of urgency to cross the road). The paper describes an unexpected and surprising pedestrian behavior in simple road crossings scenarios. When the model is given a loose risk boundary (that reflects a high level of pedestrian urgency to cross), the resulting trajectory exposes the pedestrian to a lower risk compared with a trajectory constructed with a strict risk boundary (that reflects a more conservative pedestrian). This is equivalent to claiming that, paradoxically, pedestrians in some scenarios who are willing to take higher levels of risk, face a decreased probability for an accident while crossing a congested road. The paper introduces the PNF model for crossing pedestrians, analyses their performance in a set of simulations, and explains its rationale. Next, an analytic estimation for the risk level as a function of the crossing angle of the selected trajectory is provided. A series of experiments conclude the paper and support the claim that this phenomenon is frequent among crossing pedestrians. The experimental results suggest that in some common scenarios, more cautious pedestrians may lower the initial risk for an accident at the expense of a total higher risk for an accident during the entire road crossing process, compared with a pedestrian who takes an initial higher level of risk that results in, overall, a decreased probability for an accident. A statistical analysis implies that there are significant differences in this occurrence between adults and children.

Language: en

Keywords

Pedestrian safety; Accident avoidance; Pedestrian behavior; Perception model; Probability Navigation Function; Risk aversion; Robot motion planning