Leveraging Autonomous Vehicles to Tally Cooperative Driving Behavior

Abstract

The number of Autonomous Vehicles (AVs) coexisting with conventional human-driven vehicles is expected to increase significantly in the coming years. This coexistence will last decades before full AV adoption is achieved worldwide. However, the cautious nature of AVs and the aggressive behavior of some human drivers could create unprecedentedly challenging scenarios for AVs, such as being stuck on merge lanes and blocked by human-driven vehicles. On the other hand, the cooperative behavior of other human drivers could assist AVs in avoiding deadlock situations. In this paper, we propose to leverage AVs to tally the cooperative driving behavior of human-driven vehicles. To this end, we model cooperative driving behavior in a “highway merge” scenario, which tends to be challenging for AVs. We vary the percentage of cooperative human-driven vehicles and estimate the percentage of AVs required to tally cooperative acts. Results show that when fifty percent of the human drivers cooperate, cooperation leads to statistically significant reductions of up to 68%, 46%, 38%, and 5% in stop delay, number of stops, vehicle delay, and travel time, respectively. Finally, we demonstrate that a 30% penetration of AVs is sufficient to tally up to 78% of cooperative behavior in highway scenarios. To promote cooperation across the population, our future work revolves around the construction of vehicular profiles based on their cooperative behavior. These profiles will be regularly updated and disseminated among AVs to aid their cooperative decisions toward human-driven vehicles in the upcoming interactions.

Keywords

• Human-driven vehicles (HVs)
• cooperative human-driven vehicles (CHVs)
• autonomous vehicles (AVs)
• highway merge
• modeling