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

Abstract

Understanding pedestrian proxemic utility and trust will help autonomous vehicles to plan and control interactions with pedestrians more safely and efficiently. When pedestrians cross the road in front of human-driven vehicles, the two agents use knowledge of each other’s preferences to negotiate and to determine who will yield to the other. Autonomous vehicles will require similar understandings, but previous work has shown a need for them to be provided in the form of continuous proxemic utility functions, which are not available from previous proxemics studies based on Hall’s discrete zones. To fill this gap, a new Bayesian method to infer continuous pedestrian proxemic utility functions is proposed, and related to a new definition of ‘physical trust requirement’ (PTR) for road-crossing scenarios. The method is validated on simulation data then its parameters are inferred empirically from two public datasets. Results show that pedestrian proxemic utility is best described by a hyperbolic function, and that trust by the pedestrian is required in a discrete ‘trust zone’ which emerges naturally from simple physics. The PTR concept is then shown to be capable of generating and explaining the empirically observed zone sizes of Hall’s discrete theory of proxemics.

OpenPodcar: an Open Source Vehicle for Self-Driving Car Research

“…A similar experiment performed in a VR environment showed a more realistic behaviour from the participants [10,11]. An additional model of human proxemics (i.e., interpersonal distances) has been developed and is being combined with the game theory model [13,12]. In future work, the OpenPodcar will be used to extend these human experiments using a real physical platform and demonstrate the operation of game theoretic behaviour on a autonomous vehicle for the first time.…”

Extending Quantitative Proxemics and Trust to HRI

“…This section presents a review of previous work on proxemics and trust for HRI, an extensive review of these topics was introduced in [7].…”

“…Links between proxemics and trust have been proposed via a quantitative model, intended for use in the limited case of an autonomous vehicle, Agent 2 , interacting with a pedestrian, Agent 1 1 , crossing its path [7] as in Fig. 1.…”

“…The present paper briefly reviews proxemics, trust, and the recent PTR model [7] which links them quantitatively in the limited case of pedestrian-autonomous vehicle interactions. It then extends the PTR model to new, generalised cases of human-human and human-robot interactions and presents new results comparing the extended model's predictions to empirical data.…”

Would You Trust Driverless Service? Formation of Pedestrian’s Trust and Attitude Using Non-Verbal Social Cues

“…Spatial characteristics and proxemics are important properties for AV that inevitably encounters pedestrians while driving on the road. In particular, the distance between pedestrians and AV is an important factor for the pedestrian to feel momentarily safe and form trust [ 40 ]. There are few studies, however, dealing with the concept of conversational distance in the context of AV actively trying to establish a social relation with pedestrians as well as studies exploring the interaction effects of other non-verbal signals.…”