Social Force Control for Human-Like Autonomous Driving

Abstract

An autonomous driving control system that incorporates notions from human-like social driving could facilitate an efficient integration of hybrid traffic where fully autonomous vehicles (AVs) and human operated vehicles (HOVs) are expected to coexist. This paper aims to develop such an autonomous vehicle control model using the social-force concepts, which was originally formulated for modeling the motion of pedestrians in crowds. In this paper, the social force concept is adapted to vehicular traffic where constituent navigation forces are defined as a target force, object forces, and lane forces. Then, nonlinear model predictive control (NMPC) scheme is formulated to mimic the predictive planning behavior of social human drivers where they are considered to optimize the total social force they perceive. The performance of the proposed social force-based autonomous driving control scheme is demonstrated via simulations of an ego-vehicle in multi-lane road scenarios. From adaptive cruise control (ACC) to smooth lane-changing behaviors, the proposed model provided a flexible yet efficient driving control enabling a safe navigation in various situations while maintaining reasonable vehicle dynamics.

Research on the Behavioral Dynamics Motion Planning Method of the Human-Vehicle Social Force Model

“…However, autonomous vehicles will be sharing urban roads with human tra c participants for a long time in the future. Autonomous vehicles running on urban roads need to be able to autonomously interact with pedestrians and must be able to seize road resources [6][7][8]. Especially at urban intersections with complex tra c, the problem of humanvehicle interaction becomes more serious, making it di cult for autonomous vehicles to land and drive [9][10][11][12].…”