Title | 路径规划预测方法、装置、设备和计算机可读存储介质 |
Alternative Title | Path planning prediction method, device and equipment and computer readable storage medium
|
Author | |
First Inventor | 李皈颖
|
Original applicant | 南方科技大学
|
First applicant | 南方科技大学
|
Address of First applicant | 518000 广东省深圳市南山区西丽学苑大道1088号
|
Current applicant | 南方科技大学
|
Address of Current applicant | 518000 广东省深圳市南山区西丽学苑大道1088号 (广东,深圳,南山区)
|
First Current Applicant | 南方科技大学
|
Address of First Current Applicant | 518000 广东省深圳市南山区西丽学苑大道1088号 (广东,深圳,南山区)
|
Application Number | CN201910631663.6
|
Application Date | 2019-07-12
|
Open (Notice) Number | CN110348636A
|
Date Available | 2019-10-18
|
Status of Patent | 实质审查
|
Legal Date | 2019-11-12
|
Subtype | 发明申请
|
SUSTech Authorship | First
|
Abstract | 本发明实施例公开了一种路径规划预测方法、装置、设备和计算机可读存储介质,方法包括:根据任务信息建立第一集合,第一集合中每个元素对应一条任务边或车库;根据任务边或车库的位置关系对第一集合的元素进行预排序得到第一序列;根据第一序列中每个元素对应的图像信息和附加特征生成对应的数值向量,将第一序列中的每个元素替换为对应的数值向量生成第二序列;将第二序列的数值向量输入预先训练好的第一模型以输出第三序列,第三序列中每个元素对应一条任务边或车库;根据任务边或车库的位置关系对第三序列进行后排序得到路径规划预测结果。本发明采用能够在专用硬件上加速的神经网络完成任务路径规划,其求解速度更快达到加速路径规划的效果。 |
Other Abstract | The embodiment of the invention discloses a path planning prediction method, device and equipment and a computer readable storage medium, and the method comprises the steps: building a first set according to task information, and each element in the first set corresponding to one task edge or garage; pre-sequencing the elements of the first set according to the position relationship of the task edge or the garage to obtain a first sequence; generating a corresponding numerical vector according to the image information corresponding to each element in the first sequence and the additional features, and replacing each element in the first sequence with the corresponding numerical vector to generate a second sequence; inputting the value vector of the second sequence into a pre-trained firstmodel to output a third sequence, wherein each element in the third sequence corresponds to one task edge or garage; and performing post-sorting on the third sequence according to the position relationship of the task edge or the garage to obtain a path planning prediction result. According to the method, the neural network capable of accelerating on special hardware is adopted to complete task path planning, the solving speed is higher, and the effect of accelerating path planning is achieved. |
CPC Classification Number | G06Q10/04
; G06Q10/08355
; G06N3/08
; G06N3/045
|
IPC Classification Number | G06Q10/04
; G06Q10/08
; G06N3/04
; G06N3/08
|
INPADOC Legal Status | (ENTRY INTO FORCE OF REQUEST FOR SUBSTANTIVE EXAMINATION)[2019-11-12][CN]
|
INPADOC Patent Family Count | 1
|
Extended Patent Family Count | 1
|
Priority date | 2019-07-12
|
Patent Agent | 孟金喆
|
Agency | 北京品源专利代理有限公司
|
URL | [Source Record] |
Data Source | PatSnap
|
Document Type | Patent |
Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/532336 |
Department | Research Institute of Trustworthy Autonomous Systems 工学院_计算机科学与工程系 |
Recommended Citation GB/T 7714 |
李皈颖,杨鹏,唐珂. 路径规划预测方法、装置、设备和计算机可读存储介质.
|
Files in This Item: | There are no files associated with this item. |
|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment