Spatio-Temporal Trajectory Planning Using Search And Optimizing Method for Autonomous Driving

Author:

Zhong Liang1,Lu Changgang1,Wu Jian1

Affiliation:

1. Jilin University

Abstract

<div class="section abstract"><div class="htmlview paragraph">In the field of autonomous driving trajectory planning, it’s virtual to ensure real-time planning while guaranteeing feasibility and robustness. Current widely adopted approaches include decoupling path planning and velocity planning based on optimization method, which can’t always yield optimal solutions, especially in complex dynamic scenarios. Furthermore, search-based and sampling-based solutions encounter limitations due to their low resolution and high computational costs. This paper presents a novel spatio-temporal trajectory planning approach that integrates both search-based planning and optimization-based planning method. This approach retains the advantages of search-based method, allowing for the identification of a global optimal solution through search. To address the challenge posed by the non-convex nature of the original solution space, we introduce a spatio-temporal semantic corridor structure, which constructs a convex feasible set for the problem. Trajectory optimization is then performed through numerical optimization methods, resulting in real-time and robust spatio-temporal trajectory planning. The proposed approach initiates by constructing a 3D spatio- temporal map that incorporates information such as dynamic obstacles. Improved A* algorithm is used to search for a preliminary spatio- temporal trajectory, serving as an initial approximation for the trajectory. Based on this initial approximation, a spatio-temporal corridor is constructed as locally convex feasible driving area, then a quintic monomial polynomial is employed to represent a trajectory, considering vehicle kinematics, continuity, and other constraints, this formulation transforms the problem into a general quadratic programming problem. Ultimately, the generated trajectories are rigorously tested through simulations in scenarios involving overtaking and side car cut-in. The results indicate that the generated trajectories are feasible, reasonable, and exhibit good real-time performance<b>.</b></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