End-to-End Automated Lane-Change Maneuvering Considering Driving Style Using a Deep Deterministic Policy Gradient Algorithm.

Hongyu Hu,Chengyuan Zheng,Qi Wang,Ziyang Lu

doi:10.3390/s20185443

Abstract

Changing lanes while driving requires coordinating the lateral and longitudinal controls of a vehicle, considering its running state and the surrounding environment. Although the existing rule-based automated lane-changing method is simple, it is unsuitable for unpredictable scenarios encountered in practice. Therefore, using a deep deterministic policy gradient (DDPG) algorithm, we propose an end-to-end method for automated lane changing based on lidar data. The distance state information of the lane boundary and the surrounding vehicles obtained by the agent in a simulation environment is denoted as the state space for an automated lane-change problem based on reinforcement learning. The steering wheel angle and longitudinal acceleration are used as the action space, and both the state and action spaces are continuous. In terms of the reward function, avoiding collision and setting different expected lane-changing distances that represent different driving styles are considered for security, and the angular velocity of the steering wheel and jerk are considered for comfort. The minimum speed limit for lane changing and the control of the agent for a quick lane change are considered for efficiency. For a one-way two-lane road, a visual simulation environment scene is constructed using Pyglet. By comparing the lane-changing process tracks of two driving styles in a simplified traffic flow scene, we study the influence of driving style on the lane-changing process and lane-changing time. Through the training and adjustment of the combined lateral and longitudinal control of autonomous vehicles with different driving styles in complex traffic scenes, the vehicles could complete a series of driving tasks while considering driving-style differences. The experimental results show that autonomous vehicles can reflect the differences in the driving styles at the time of lane change at the same speed. Under the combined lateral and longitudinal control, the autonomous vehicles exhibit good robustness to different speeds and traffic density in different road sections. Thus, autonomous vehicles trained using the proposed method can learn an automated lane-changing policy while considering safety, comfort, and efficiency.

Highlights

In recent years, with the continuous growth in car ownership, issues such as traffic safety and traffic congestion have become increasingly serious
We present the differences in the lane-changing behaviors of agents under the control of different driving styles, and the lane-changing process tracks of agents with different driving styles are compared by setting an identical scene to determine the differences
We developed an end-to-end reinforcement learning framework for the automated lane-change control of intelligent vehicles based on lidar detection data

Summary

Introduction

With the continuous growth in car ownership, issues such as traffic safety and traffic congestion have become increasingly serious. The lane-changing process requires the driver to pay attention to the vehicles moving in the current lane and in the target lane simultaneously, in order to make decisions and implement comprehensive lateral and longitudinal control This makes the lane-changing decision more complex than other driving behaviors. To deal with more complex scenarios, a decision-making method for intelligent vehicles based on reinforcement learning is a major milestone. This method uses a self-learning intelligent control algorithm that enables the agent to constantly interact with the environment. Deep reinforcement learning has emerged as another feasible scheme for automated lane changing and automatic driving of intelligent vehicles [7]

Methods

Results

Conclusion