文章基本信息

标题：Efficient Motion Planning for Autonomous Vehicle Maneuvers Using Duality-Based Decomposition
本地全文：下载
作者：Pavel Anistratov ; Björn Olofsson ; Lars Nielsen 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2019
卷号：52
期号：5
页码：78-84
DOI：10.1016/j.ifacol.2019.09.013
语种：English
出版社：Elsevier
摘要：AbstractA method to decompose a motion-planning problem into several segments is presented. It is based on a modification of the original problem, such that certain variables at the splitting points are considered to be precomputed and thus fixed and the remaining variables are obtained by performing Lagrange relaxation. The resulting dual problem is split into several subproblems, allowing parallel computation. The method is formalized as a computational algorithm and evaluated in a safety critical double lane-change situation. The resulting maneuver has close-to-optimal behavior and, for certain initialization strategies, it is obtained in shorter computational time compared to computing the full maneuver in one step.
关键词：Keywordstrajectorypath planningautonomous vehiclesduality-based decompositionmotion controlsafetyintelligent transportation systems