基于双层启发搜索共轭梯度下降的轨迹规划方法及系统

本发明公开了基于双层启发搜索共轭梯度下降的轨迹规划方法及系统，包括以下步骤，初始化阶段创建保存起点信息的队列；开启列表获得起始点、目标点以及车辆运动模型；从所述开启列表中，选择最小代价值的运动模式作为父节点；基于所述父节点对周围节点进行计算判断，满足预设条件后，记该节点为拓展节点并生成轨迹；使用共轭梯度下降法对生成的所述轨迹进行优化。本发明的有益效果：基于非完整无障碍启发搜索，以解决错误方向的搜索代价消耗，指引轨迹朝着目标点行进；基于完整性有障碍启发搜索，以解决在障碍物或者在死胡同区域，指引轨迹远离这些区域；基于共轭梯度下降法，对生成的轨迹进行优化，解决轨迹震荡问题。 The inventio...

Full description

Saved in:
Bibliographic Details
Format Patent
LanguageChinese
Published 22.09.2023
Subjects
GYROSCOPIC INSTRUMENTS
MEASURING
MEASURING DISTANCES, LEVELS OR BEARINGS
NAVIGATION
PHOTOGRAMMETRY OR VIDEOGRAMMETRY
PHYSICS
SURVEYING
TESTING
Online AccessGet full text

Cover

More Information
Summary:本发明公开了基于双层启发搜索共轭梯度下降的轨迹规划方法及系统，包括以下步骤，初始化阶段创建保存起点信息的队列；开启列表获得起始点、目标点以及车辆运动模型；从所述开启列表中，选择最小代价值的运动模式作为父节点；基于所述父节点对周围节点进行计算判断，满足预设条件后，记该节点为拓展节点并生成轨迹；使用共轭梯度下降法对生成的所述轨迹进行优化。本发明的有益效果：基于非完整无障碍启发搜索，以解决错误方向的搜索代价消耗，指引轨迹朝着目标点行进；基于完整性有障碍启发搜索，以解决在障碍物或者在死胡同区域，指引轨迹远离这些区域；基于共轭梯度下降法，对生成的轨迹进行优化，解决轨迹震荡问题。 The invention discloses a trajectory planning method and system based on double-layer heuristic search conjugate gradient descent. The method comprises the following steps of: building a queue for storing starting point information at an initialization stage; opening a list to obtain a starting point, a target point and a vehicle motion model; selecting a motion mode with the minimum cost value asa father node from the opening list; calculating and judging surrounding nodes based on the father node, and after a preset condition is met, recording the node as an expansion node and generating atrack; and optimizing the generated trajectory by using a conjugate gradient descent method. The trajectory planning method and system hav
Bibliography:Application Number: CN201911192327