[Paper Review] Designing Autonomous Vehicles: Evaluating the Role of Human Emotions and Social Norms

Faisal Riaz, Muaz A. Niazi|arXiv (Cornell University)|Aug 6, 2017

Ethics and Social Impacts of AI5 references3 citations

TL;DR

This paper proposes a social norms compliance mechanism in autonomous vehicles (AVs) using emotion-driven decision-making, specifically fear derived from the OCC model and quantified via fuzzy logic. Simulated in NetLogo using SimConnect, the artificial society of AVs outperformed a random-walk baseline in collision avoidance, demonstrating that emotion-informed social norms enhance safety and social acceptability in AV behavior.

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

Motivation & Objective

• To address the challenge of making autonomous vehicles socially acceptable by integrating human-like emotional and normative behaviors.
• To model how emotions—particularly fear—can guide AV decision-making in collision avoidance scenarios.
• To develop a social norms compliance mechanism that enables AVs to emulate socially responsible driving behavior.
• To evaluate whether emotion-informed AVs outperform non-emotive, random-walk-based AVs in terms of safety and reliability.

Proposed method

• The authors model AVs as artificial agents with distinct social personalities and emotional states, using the OCC model to define fear as a prospect-based emotion.
• Fuzzy logic is applied to quantitatively compute the intensity of fear based on traffic and environmental conditions.
• SimConnect is used to interface the fuzzy emotion values with the NetLogo simulation environment to drive AV behavior.
• A social norms compliance mechanism is implemented, where AVs adjust their behavior based on emotional states and social rules to avoid collisions.
• The artificial society is tested using NetLogo's BehaviorSpace tool to evaluate collision rates across multiple simulation runs.
• A random-walk model is used as a baseline for comparison, representing non-emotive, non-normative AV behavior.

Experimental results

Research questions

• RQ1 How can human emotions such as fear be modeled and integrated into autonomous vehicle decision-making for safer driving?
• RQ2 To what extent do emotion-informed AVs reduce collision rates compared to non-emotive AVs?
• RQ3 Can social norms compliance, driven by emotional states, improve the social acceptability and trustworthiness of autonomous vehicles?
• RQ4 How does the integration of fuzzy logic enhance the quantification and application of emotional responses in AVs?

Key findings

• The proposed emotion-based AV system achieved significantly lower collision rates compared to the random-walk baseline model.
• The use of fuzzy logic enabled effective quantification of fear, allowing nuanced and context-sensitive AV responses.
• The artificial society of AVs demonstrated improved safety performance due to social norms compliance driven by emotional states.
• Simulation results confirmed that AVs guided by emotion and social norms are more reliable and trustworthy than those using random behavior.