Planning Persuasive Trajectories Based on a Leader-Follower Game Model

TL;DR

This paper introduces a leader-follower game-based framework for autonomous vehicles to proactively influence human driver behavior at intersections, using adaptive role mechanisms and model predictive control to generate persuasive trajectories.

Contribution

It presents a novel leader-follower game model with adaptive roles combined with MPC for trajectory planning to influence human drivers, addressing uncertainties in interactions.

Findings

Effective in simulation for persuading human drivers at intersections

Robust to uncertainties in driver behavior

Outperforms baseline trajectory planning methods

Abstract

We propose a framework that enables autonomous vehicles (AVs) to proactively shape the intentions and behaviors of interacting human drivers. The framework employs a leader-follower game model with an adaptive role mechanism to predict human interaction intentions and behaviors. It then utilizes a branch model predictive control (MPC) algorithm to plan the AV trajectory, persuading the human to adopt the desired intention. The proposed framework is demonstrated in an intersection scenario. Simulation results illustrate the effectiveness of the framework for generating persuasive AV trajectories despite uncertainties.