Pedestrian Models for Autonomous Driving Part II: High-Level Models of Human Behavior

Abstract

Autonomous vehicles (AVs) must share space with pedestrians, both in carriageway cases such as cars at pedestrian crossings and off-carriageway cases such as delivery vehicles navigating through crowds on pedestrianized high-streets. Unlike static and kinematic obstacles, pedestrians are active agents with complex, interactive motions. Planning AV actions in the presence of pedestrians thus requires modelling of their probable future behaviour as well as detecting and tracking them. This narrative review article is Part II of a pair, together surveying the current technology stack involved in this process, organising recent research into a hierarchical taxonomy ranging from lowlevel image detection to high-level psychological models. This selfcontained Part II covers the higher levels of this stack, consisting of models of pedestrian behaviour, from prediction of individual pedestrians' likely destinations and paths, to game-theoretic models of interactions between pedestrians and autonomous vehicles. This survey clearly shows that, although there are good models for optimal walking behaviour, high-level psychological and social modelling of pedestrian behaviour still remains an open research question that requires many conceptual issues to be clarified. Early work has been done on descriptive and qualitative models of behaviour, but much work is still needed to translate them into quantitative algorithms for practical AV control.

Variable-drift diffusion models of pedestrian road-crossing decisions

“…In road traffic, the successes or failures of human movement and sharing of space has particularly large societal implications, in terms of mobility, productivity, and human safety, and consequently considerable effort has been invested into understanding and modeling how humans locomote both as vehicle drivers and vulnerable road users [27,38,49]. These efforts have further intensified recently, to support development of increasingly automated vehicles [9,54,63]. By many accounts, successful widespread deployment of automated vehicles will be limited by the extent to which these vehicles can encapsulate a sufficent understanding-typically in the form of computational models-of road user behavior and interaction [6,9,40,58].…”

“…These efforts have further intensified recently, to support development of increasingly automated vehicles [9,54,63]. By many accounts, successful widespread deployment of automated vehicles will be limited by the extent to which these vehicles can encapsulate a sufficent understanding-typically in the form of computational models-of road user behavior and interaction [6,9,40,58].…”

“…However, most of these existing models have either emphasized detailed modeling of individual road user behavior, or more coarse-grained modeling of interactions of larger number of road users, for example to study high-level traffic flow. Computational modeling of the subtler details of local interactions between individuals is still in its infancy [9,40].…”

Space Invaders: Pedestrian Proxemic Utility Functions and Trust Zones for Autonomous Vehicle Interactions

“…A comprehensive review on pedestrian models for autonomous driving is proposed in [9,10], ranging from low-level sensing, detection and tracking models [9] to high-level interaction and game theoretic models [10]. In the context of autonomous vehicles, more work has been focused on pedestrian crossing behaviour [53], trajectory prediction [84] and for eHMI (external Human-Machine Interface) [20,29,50,54].…”

“…Autonomous vehicles (AVs) are claimed by many organisations to be close to commercial reality, but their lack of human behaviour understanding is raising concerns. While robotic localisation and navigation in static environments [76] and pedestrian detection [9] are well understood, AVs do not yet have the social abilities of human drivers-who can read the intentions of other road users, predict their future behaviour and then interact with them [10]. Pedestrians, unlike other road users such as cyclists, do not usually follow specific traffic rules, in particular when crossing the road at unsigned crossing points, making them especially difficult to model, predict, and interact with.…”