Combining Dynamic Movement Primitives and Artificial Potential Fields for Lane Change Obstacle Avoidance Trajectory Planning of Autonomous Vehicles

Author:

Liang Kaichong1,Zhao Zhiguo1,Yan Danshu1,Li Wenchang1

Affiliation:

1. Tongji University

Abstract

<div class="section abstract"><div class="htmlview paragraph">Lane change obstacle avoidance is a common driving scenario for autonomous vehicles. However, existing methods for lane change obstacle avoidance in vehicles decouple path and velocity planning, neglecting the coupling relationship between the path and velocity. Additionally, these methods often do not sufficiently consider the lane change behaviors characteristic of human drivers. In response to these challenges, this paper innovatively applies the Dynamic Movement Primitives (DMPs) algorithm to vehicle trajectory planning and proposes a real-time trajectory planning method that integrates DMPs and Artificial Potential Fields (APFs) algorithm (DMP-Fs) for lane change obstacle avoidance, enabling rapid coordinated planning of both path and velocity. The DMPs algorithm is based on the lane change trajectories of human drivers. Therefore, this paper first collected lane change trajectory samples from on-road vehicle experiments. Second, the DMPs parameters are learned from the lane change trajectories of human drivers and the human-like lane change trajectories are planned. Meanwhile, the artificial potential field, which considers driver characteristics, is utilized to adjust the human-like lane change trajectory, ensuring that the vehicle can dynamically avoid obstacles in real-time during the lane change process. Finally, simulations and vehicle experiments were conducted in challenging scenarios with static and dynamic obstacles. The results indicate that the proposed DMP-Fs method exhibits high computational efficiency, strong generalization capabilities, and trackability of the planned trajectories. Furthermore, the DMP-Fs can actively and dynamically avoid obstacles in real-time built upon generating human-like lane change trajectories. The minimum distance between the vehicle and obstacles has been increased from 0.725 to 1.205 m, ensuring the vehicle's driving safety.</div></div>

Publisher

SAE International

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3