Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
SYSTEMS AND METHODS FOR ROUTE PLANNING BASED ON DEEP CONVOLUTIONAL NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2018/227374
Kind Code:
A1
Abstract:
A method for route planning is disclosed. At least one device including at least one processor and a storage may implement the method. The method may include one or more of the following steps: obtaining a start location and a destination (610); obtaining a first intersection based on the start location and the destination/ obtaining a current intersection based on the exit of the intersection in the previous iteration (620); determining a target entrance of the intersection (630); determining a target exit of the intersection corresponding to the target entrance based on the road characteristic information (640); determining if the target exit on a same road segment is as the destination (650), if not, go to step 620, if yes, connecting the target entrances and target exits (660); generating a recommended route from the start location and destination (670).

Inventors:
WU ZHENGWEI (CN)
HU TAO (CN)
WANG ZHENG (CN)
Application Number:
PCT/CN2017/088061
Publication Date:
December 20, 2018
Filing Date:
June 13, 2017
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BEIJING DIDI INFINITY TECHNOLOGY & DEV CO LTD (CN)
International Classes:
G01C21/34
Foreign References:
CN106225797A2016-12-14
CN106500713A2017-03-15
CN106548645A2017-03-29
US20160370192A12016-12-22
Other References:
See also references of EP 3635336A4
Attorney, Agent or Firm:
METIS IP (CHENGDU) LLC (CN)
Download PDF: