A Greedy-Strategy-Based Iterative Optimization Method for Articulated Vehicle Global Trajectory Optimization in Complex Environments

Bikang Hua, Runqi Chai, Kaiyuan Chen, Hankun Jiang, Senchun Chai, Yuanqing Xia
{"title":"A Greedy-Strategy-Based Iterative Optimization Method for Articulated Vehicle Global Trajectory Optimization in Complex Environments","authors":"Bikang Hua, Runqi Chai, Kaiyuan Chen, Hankun Jiang, Senchun Chai, Yuanqing Xia","doi":"10.1142/s2301385025500244","DOIUrl":null,"url":null,"abstract":"This paper considers the problem of trajectory planning for articulated vehicles in complex environments. We formulate this problem as an optimal control problem (OCP) and propose a greedy-strategy-based planner. This planner consists of three stages. In stage 1, an IAA* algorithm is proposed to identify the homotopy class. In stage 2, the collision-free tunnels are constructed along the guiding trajectory generated in stage 1 to simplify the intractable collision-avoidance constraints. In stage 3, a greedy-strategy-based iterative optimization (GSIO) framework is designed, which contributes to escaping from local optimums, making the optimization process more targeted, and converging to the global optimum solution quickly, especially in complex tasks. One feature of the proposed planner is that it is suitable for any type of articulated vehicle, and the proposed optimization framework can be used as an open framework to optimize any criterion that can be described explicitly by a polynomial. Furthermore, in the set simulation cases, our work shows significant competitiveness, under the premise of ensuring moderate CPU processing time, our algorithm achieves approximately a 40% performance improvement in optimization effects compared to selected comparative algorithms.","PeriodicalId":506327,"journal":{"name":"Unmanned Systems","volume":"144 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Unmanned Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1142/s2301385025500244","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

This paper considers the problem of trajectory planning for articulated vehicles in complex environments. We formulate this problem as an optimal control problem (OCP) and propose a greedy-strategy-based planner. This planner consists of three stages. In stage 1, an IAA* algorithm is proposed to identify the homotopy class. In stage 2, the collision-free tunnels are constructed along the guiding trajectory generated in stage 1 to simplify the intractable collision-avoidance constraints. In stage 3, a greedy-strategy-based iterative optimization (GSIO) framework is designed, which contributes to escaping from local optimums, making the optimization process more targeted, and converging to the global optimum solution quickly, especially in complex tasks. One feature of the proposed planner is that it is suitable for any type of articulated vehicle, and the proposed optimization framework can be used as an open framework to optimize any criterion that can be described explicitly by a polynomial. Furthermore, in the set simulation cases, our work shows significant competitiveness, under the premise of ensuring moderate CPU processing time, our algorithm achieves approximately a 40% performance improvement in optimization effects compared to selected comparative algorithms.
基于贪婪策略的迭代优化方法,用于复杂环境下铰接式车辆的全局轨迹优化
本文探讨了复杂环境中铰接车辆的轨迹规划问题。我们将该问题表述为一个最优控制问题(OCP),并提出了一种基于贪婪策略的规划器。该规划器由三个阶段组成。在第 1 阶段,我们提出了一种 IAA* 算法来识别同构类。在第 2 阶段,沿着第 1 阶段生成的引导轨迹构建无碰撞隧道,以简化难以解决的避免碰撞约束。在第 3 阶段,设计了基于贪婪策略的迭代优化(GSIO)框架,它有助于摆脱局部最优,使优化过程更有针对性,并快速收敛到全局最优解,尤其是在复杂任务中。所提出的规划器的一个特点是适用于任何类型的铰接式车辆,而且所提出的优化框架可以作为一个开放式框架,用于优化任何可以用多项式明确描述的准则。此外,在设定的模拟案例中,我们的工作显示出显著的竞争力,在确保适度 CPU 处理时间的前提下,我们的算法与选定的比较算法相比,在优化效果上实现了约 40% 的性能提升。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信