US 12,352,581 B2
Method for ascertaining an initial pose of a vehicle
Timo Nachstedt, Benningen (DE); Georg Krause, Ludwigsburg (DE); and Renlin Li, Heilbronn (DE)
Assigned to ROBERT BOSCH GMBH, Stuttgart (DE)
Appl. No. 17/997,008
Filed by Robert Bosch GmbH, Stuttgart (DE)
PCT Filed May 4, 2021, PCT No. PCT/EP2021/061645
§ 371(c)(1), (2) Date Oct. 24, 2022,
PCT Pub. No. WO2021/233674, PCT Pub. Date Nov. 25, 2021.
Claims priority of application No. 10 2020 206 356.7 (DE), filed on May 20, 2020.
Prior Publication US 2023/0221125 A1, Jul. 13, 2023
Int. Cl. G01C 21/30 (2006.01)
CPC G01C 21/30 (2013.01) 10 Claims
OG exemplary drawing
 
1. A vehicle positioning method for a vehicle using a control device, the method comprising the following steps:
receiving and evaluating measured data ascertained by a GNSS sensor system and/or an odometry sensor system to ascertain an approximate pose of the vehicle;
based on the ascertained approximate pose, using a trajectory map to identify one or more historical statistically significant prior trajectories of one or more vehicles that are within a predefined margin of uncertainty drawn about a position of the ascertained approximate pose;
based on the identification of the one or more historical statistically significant prior trajectories, positioning test points along the identified one or more historical statistically significant prior trajectories;
performing an optimization that selectively applies an optimization algorithm to only the test points positioned along the identified one or more historical statistically significant prior trajectories, so that the optimization algorithm is not applied to data pertaining to only other positions around the approximate pose that do not coincide with any of the one or more historical statistically significant prior trajectories, wherein the optimization algorithm ascertains poses having corresponding cost functions; and
selecting, as an optimized initial pose of the vehicle, one of the poses ascertained by the optimization algorithm which has a greatest cost function of all of the poses ascertained by the optimization algorithm.