Social behavior for autonomous vehicles

Abstract

SignificanceWe present a framework that integrates social psychology tools into controller design for autonomous vehicles. Our key insight utilizes Social Value Orientation (SVO), quantifying an agent’s degree of selfishness or altruism, which allows us to better predict driver behavior. We model interactions between human and autonomous agents with game theory and the principle of best response. Our unified algorithm estimates driver SVOs and incorporates their predicted trajectories into the autonomous vehicle’s control while respecting safety constraints. We study common-yet-difficult traffic scenarios: highway merging and unprotected left turns. Incorporating SVO reduces error in predictions by 25%, validated on 92 human driving merges. Furthermore, we find that merging drivers are more competitive than nonmerging drivers.

Sharing is Caring: Socially-Compliant Autonomous Intersection Negotiation

“…Human drivers do not communicate their intended direction to the coordinator, and thus effectively reserve all three possible directions. In addition, an SVO preference θ i is assigned to each agent and their utility is computed according to (1). In prosocial and egoistic simulations, all agents are assigned θ i = π/4 and θ i = 0, respectively.…”

“…Their support is gratefully acknowledged. 1 interactions as social dilemmas, where the group interests do not necessarily align with the private interests. For example, at intersections, the group interests are to reduce congestion, while the individual interests are to reduce personal delays.…”

“…An egoistic vehicle will not tolerate any swapping that increases its wait time, while a prosocial car will be more inclined to take a minor increase in wait time if it improves the overall system efficiency. For autonomous vehicles [1], we design the SVO preference of the vehicle to best interact with the human drivers. Our results show that both individual wait times and system-wide average wait times decrease as the percentage of prosocial cars increase in the system.…”

Defining interactions: a conceptual framework for understanding interactive behaviour in human and automated road traffic

“…Failure of a HAV to successfully interact with human road users may lead to congestion and human frustration, as a result of overly cautious behaviour on the part of the HAV (Millard-Ball 2016; Brown and Laurie 2017), or may even lead to crashes, if HAVs behave in ways that are unexpected by human road users (Alambeigi, McDonald, and Tankasala 2020). Improved understanding and models-both qualitative and quantitative-of how humans interact in traffic is a key prerequisite for vehicle manufacturers and software developers to program HAVs to successfully interact with humans (Camara et al 2019;Markkula et al 2018;Sadigh et al 2018;Schwarting et al 2019). This adds urgency to previously existing interaction-related research questions, and also introduces new research questions specific to human-machine interaction, for example whether and how eye contact or other human communicative gestures ought to be replaced with external human-machine interfaces (Merat et al 2018;Clamann 2015;Cefkin et al 2019).…”

Defining interactions: A conceptual framework for understanding interactive behaviour in human and automated road traffic

“…Failure of a HAV to successfully interact with human road users may lead to congestion and human frustration, as a result of overly cautious behaviour on the part of the HAV (Millard-Ball 2016; Brown and Laurie 2017), or may even lead to crashes, if HAVs behave in ways that are unexpected by human road users (Alambeigi, McDonald, and Tankasala 2020). Improved understanding and models-both qualitative and quantitative-of how humans interact in traffic is a key prerequisite for vehicle manufacturers and software developers to program HAVs to successfully interact with humans (Camara et al 2019;Markkula et al 2018;Sadigh et al 2018;Schwarting et al 2019). This adds urgency to previously existing interaction-related research questions, and also introduces new research questions specific to human-machine interaction, for example whether and how eye contact or other human communicative gestures ought to be replaced with external human-machine interfaces Clamann 2015;Cefkin et al 2019).…”