Towards Social Autonomous Vehicles: Efficient Collision Avoidance Scheme Using Richardson's Arms Race Model

TL;DR

This paper introduces a social agent model for autonomous vehicles that uses mentalizing and mirroring inspired by human social behavior, integrated with Richardson's arms race model to improve collision avoidance in congested urban traffic.

Contribution

It presents a novel social agent framework for AVs based on human-like social interactions and integrates Richardson's arms race model for effective collision avoidance in dense traffic.

Findings

Collision rates reduced in simulations with the social agent.

The Richardson's arms race model enhances AV coordination in traffic.

The approach outperforms traditional collision avoidance methods.

Abstract

Background Road collisions and casualties pose a serious threat to commuters around the globe. Autonomous Vehicles (AVs) aim to make the use of technology to reduce the road accidents. However, the most of research work in the context of collision avoidance has been performed to address, separately, the rear end, front end and lateral collisions in less congested and with high inter-vehicular distances. Purpose The goal of this paper is to introduce the concept of a social agent, which interact with other AVs in social manners like humans are social having the capability of predicting intentions, i.e. mentalizing and copying the actions of each other, i.e. mirroring. The proposed social agent is based on a human-brain inspired mentalizing and mirroring capabilities and has been modelled for collision detection and avoidance under congested urban road traffic. Method We designed our social agent having the capabilities of mentalizing and mirroring and for this purpose we utilized Exploratory Agent Based Modeling (EABM) level of Cognitive Agent Based Computing (CABC) framework proposed by Niazi and Hussain. Results Our simulation and practical experiments reveal that by embedding Richardson's arms race model within AVs, collisions can be avoided while travelling on congested urban roads in a flock like topologies. The performance of the proposed social agent has been compared at two different levels.