US 12,146,970 B2
Positioning method, device, and electronic apparatus
Cheng Chen, Beijing (CN); Shuai Zhou, Beijing (CN); and Qiang Xu, Beijing (CN)
Assigned to ALIBABA GROUP HOLDING LIMITED, George Town (KY)
Filed by ALIBABA GROUP HOLDING LIMITED, Grand Cayman (KY)
Filed on May 7, 2021, as Appl. No. 17/314,675.
Application 17/314,675 is a continuation of application No. PCT/CN2019/114961, filed on Nov. 1, 2019.
Claims priority of application No. 201811333871.X (CN), filed on Nov. 9, 2018.
Prior Publication US 2021/0263167 A1, Aug. 26, 2021
Int. Cl. G01S 19/49 (2010.01); G01C 21/16 (2006.01); G01S 19/48 (2010.01); G05D 1/00 (2024.01); G05D 1/02 (2020.01)
CPC G01S 19/49 (2013.01) [G01C 21/16 (2013.01); G01C 21/1652 (2020.08); G01S 19/485 (2020.05); G05D 1/024 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A positioning method, comprising:
obtaining a Global Navigation Satellite System (GNSS) position of a vehicle;
obtaining, based on the GNSS position of the vehicle, standard positioning data around a road where the vehicle is located from preset standard positioning database, wherein the standard positioning data comprises pre-computed and pre-stored laser point data of GNSS-positioned key points of road objects with stable attributes on or by either side of the road;
obtaining laser point cloud data, outputted by a laser sensor of the vehicle, around the road where the vehicle is located;
extracting to-be-matched positioning data around the road where the vehicle is located from the laser point cloud data, wherein the to-be-matched positioning data comprises laser point data of laser-sensor-output key points of at least one road object with a stable attribute on or by either side of the road where the vehicle is located;
obtaining more than one sampling positions corresponding to the vehicle at a previous moment;
combining the more than one sampling positions with a plurality of position points near the more than one sampling positions to form first sampling positions;
forward simulating a motion state of the vehicle based on the first sampling positions, to obtain more than one simulated positions corresponding to the vehicle at a current moment;
converting the to-be-matched positioning data into a coordinate system corresponding to the standard positioning data based on the more than one simulated positions corresponding to the vehicle at the current moment;
matching the to-be-matched positioning data in the coordinate system with the standard positioning data, to obtain a probability that the vehicle is located at each simulated position corresponding to the vehicle at the current moment based on a matching result; and
obtaining a position of the vehicle based on the probability that the vehicle is located at each simulated position corresponding to the vehicle at the current moment.