Designing Autonomous Vehicles: Evaluating the Role of Human Emotions and Social Norms

Designing Autonomous Vehicles: Evaluating the Role of Human Emotions and Social Norms Faisal Riaz1, Muaz Niazi 2,* 1Dept. Of Computing-Iqra University, Islamabad, Pakistan 2Dept. Of Computer Sciences-COMSATS, Islamabad, Pakistan fazi_ajku@yahoo.com *muaz.niazi@gmail.com

Abstract Humans are going to delegate the rights of driving to the autonomous vehicles in near future. However, to fulfill this complicated task, there is a need for a mechanism, which enforces the autonomous vehicles to obey the road and social rules that have been practiced by well-behaved drivers. This task can be achieved by introducing social norms compliance mechanism in the autonomous vehicles. This research paper is proposing an artificial society of autonomous vehicles as an analogy of human social society. Each AV has been assigned a social personality having different social influence. Social norms have been introduced which help the AVs in making the decisions, influenced by emotions, regarding road collision avoidance. Furthermore, social norms compliance mechanism, by artificial social AVs, has been proposed using prospect based emotion i.e. fear, which is conceived from OCC model. Fuzzy logic has been employed to compute the emotions quantitatively. Then, using SimConnect approach, fuzzy values of fear has been provided to the Netlogo simulation environment to simulate artificial society of AVs. Extensive testing has been performed using the behavior space tool to find out the performance of the proposed approach in terms of the number of collisions. For comparison, the random-walk model based artificial society of AVs has been proposed as well. A comparative study with a random walk, prove that proposed approach provides a better option to tailor the autopilots of 2

future AVS, Which will be more socially acceptable and trustworthy by their riders in terms of safe road travel.

Key Word: - Autonomous Vehicles, Social Norms, OCC Model, Prospect Based Emotions, Fuzzy Logic, Netlogo

1. Introduction Autonomous road vehicles (ARVs) have been considered better than human driven vehicles in road safety and traffic management. According to the investigation of Riaz and Niazi [1], autonomous vehicles have been found helpful in decreasing road accidents as compared to the human-driven vehicles. Furthermore, the issue of road jams can be solved by replacing human drivers with fully connected autonomous cars, as noted by Litman [2]. In addition, Mersky and Samaras [3] have illustrated that AVs are very helpful in decreasing the road pollution and making the environment green. From these benefits, it might be possible that the law agencies delegate the driving task to AVs by issuing them the driving license. However, to fulfill this complicated task of driving, there is a need for a mechanism, which enforces the autonomous vehicles, which is a robot, to obey the road and social rules that have been practiced by well- behaved drivers.
   The Role of ethics and social norms have been considered important in making robots social, well behaved and more compatible with humans. According to Malle [4], robots can serve as competent social agents by integrating moral norms in their basic architecture. A. Rakotonirainy et al. [5] have proven that social norms can be utilized to design human compatible social AVs robots. According to Kummer et al. [6], social norms can be used in tailoring crash free AVs robot by operating on roads wisely. From the above discussion, it is implied that social norms with some norms compliance mechanism can be used to tailor the next generation of more trustworthy social AVs. 3

Emotions can be used as norms compliance mechanism as it is already proven that emotions help in sustaining the social norms in human society. According to Elster [7], self-attribution emotions like shame helps the human to avoid the violation due to fear of losing their social status. According to N. Criado [8], prospect based emotions like fear enforce the human to follow the social norms in order to avoid the punishment from the law enforcement agencies. Inspired by the role of emotions in social norm compliance in the human society, researchers have used emotions to enforce the artificial agents’ norm compliance. According to staller et al. [9]emotions act as an important factor in the sustainability of social norms. Hence, it is implied that we can use emotions as the norms compliance mechanism to design social norms enabled AVs. Gerdes and Thornton [10] have suggested the mathematical model of social norms for designing the control algorithms of AVs but still their works lack the simulation or proof of concept of proposed mathematical models.
Problem statement- However, to the best of our knowledge the existing literature has not proposed such procedures that allow AVs to configure their autopilots to make collision avoidance decisions about norm compliance usin

…(Full text truncated)…