Socially Intelligent Path-Planning for Autonomous Vehicles Using Type-2 Fuzzy Estimated Social Psychology Models

Abstract

This paper presents a novel framework for socially aware path-planning in autonomous vehicles, integrating Social Value Orientation (SVO) within Artificial Potential Fields (APF) and employing Type-2 Fuzzy Logic for robust SVO approximation. By incorporating an adaptive gradient descent algorithm and leveraging a Type-2 fuzzy system for dynamic modeling of social psychology in vehicular navigation, we enhance autonomous vehicles’ ability to interpret and react to social cues in real-time traffic scenarios. Our approach significantly improves interaction with human road users, ensuring safer and more efficient navigation. The proposed model addresses the limitations of traditional APFs, such as local minima issues, by incorporating dynamic enhanced firework algorithms and resistance networks. It also considers vehicle dynamics, including nonholonomic constraints and tire forces, using a bicycle model for realistic trajectory planning. We introduce a comprehensive set of social cues for pedestrians and vehicles, operationalized through interval type-2 fuzzy system (IT2FS) approximation, to accurately estimate SVO and adjust AV behavior accordingly. Validation is conducted through extensive simulations in a realistic environment using the CARLA simulator, demonstrating the effectiveness of our socially intelligent path-planning mechanism in diverse driving situations. The results show a significant improvement in AV performance, with a 2.93% more altruistic estimation for the vehicle in the right lane and a 1.85% more altruistic estimation for the immobile vehicle. Additionally, the system demonstrated smoother acceleration and steering profiles, reducing peak longitudinal acceleration from $4.181~m/s^{2}$ to $0.196~m/s^{2}$ and improving overall driving stability. This framework enhances autonomous vehicles’ safety, efficiency, and social acceptability, contributing to their successful integration into urban traffic systems.

Keywords

• Autonomous vehicles
• human-aware navigation
• path-planning
• AI-driven modeling