Towards trusted autonomous vehicles from vulnerable road users perspective

Abstract

A number of recent research projects in human-vehicle interaction field are addressing the problem of human trust in autonomous vehicles. Almost all of these work are focusing on investigating the attributes and the factors that influence the human drivers' trust of these vehicles. However, a little research has been done on the bystander humans' trust of autonomous vehicles. Bystander humans in the context of autonomous vehicles, are humans that does not explicitly interact with the automated vehicle but still affect how the vehicle accomplishes its task by observing or interfering with the actions of the vehicle. Vulnerable road users (VRU) are considered one example of the bystander humans interfering with the autonomous vehicle. According to a recent research study, intent understanding between vulnerable road users and autonomous vehicles was one of the most critical signs that accounted for a trusted interaction between the two entities. In this paper we are proposing a computation framework for modeling trust between vulnerable road users and autonomous vehicles based on a shared intent understanding between the two of them.