Personalized Lane Change Decision Algorithm Using Deep Reinforcement Learning Approach

TL;DR

This paper presents a deep reinforcement learning-based lane change decision algorithm that personalizes driving behavior to match individual driver preferences, improving safety and user satisfaction in automated highway driving.

Contribution

It introduces a human-centered, driver-in-the-loop methodology with personalization indicators and a tailored RL approach for more human-like lane change decisions.

Findings

RL agents show higher consistency with driver preferences

Personalization improves decision safety and satisfaction

Benchmark comparisons validate effectiveness

Abstract

To develop driving automation technologies for human, a human-centered methodology should be adopted for ensured safety and satisfactory user experience. Automated lane change decision in dense highway traffic is challenging, especially when considering the personalized preferences of different drivers. To fulfill human driver centered decision algorithm development, we carry out driver-in-the-loop experiments on a 6-Degree-of-Freedom driving simulator. Based on the analysis of the lane change data by drivers of three specific styles,personalization indicators are selected to describe the driver preferences in lane change decision. Then a deep reinforcement learning (RL) approach is applied to design human-like agents for automated lane change decision, with refined reward and loss functions to capture the driver preferences.The trained RL agents and benchmark agents are tested in a two-lane highway driving scenario, and by comparing the agents with the specific drivers at the same initial states of lane change, the statistics show that the proposed algorithm can guarantee higher consistency of lane change decision preferences. The driver personalization indicators and the proposed RL-based lane change decision algorithm are promising to contribute in automated lane change system developing.