US 12,386,075 B2
Mitigating effects of large-area GNSS spoofing and/or jamming on crowd-sourcing-based map updates
Henri Nurminen, Tampere (FI); Pavel Ivanov, Tampere (FI); Marko Luomi, Tampere (FI); and Lauri Aarne Johannes Wirola, Tampere (FI)
Assigned to HERE GLOBAL B.V., Eindhoven (NL)
Filed by HERE Global B.V., Eindhoven (NL)
Filed on Apr. 26, 2023, as Appl. No. 18/307,236.
Prior Publication US 2024/0361465 A1, Oct. 31, 2024
Int. Cl. G01S 19/01 (2010.01); G01S 19/07 (2010.01)
CPC G01S 19/015 (2013.01) [G01S 19/07 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, by at least one processor, one or more instances of crowd-sourced data corresponding to a first time period, wherein a respective instance of crowd-sourced data of the one or more instances of crowd-sourced data was generated by a respective mobile apparatus during the first time period, and the respective instance of crowd-sourced data comprises (a) a respective first location estimate indicating a location of the respective mobile apparatus when the mobile apparatus generated the instance of crowd-sourced data and (b) respective observation data corresponding to sensor data captured by one or more sensors of the mobile apparatus;
for each of the one or more instances of crowd-sourced data, determining, by the at least one processor, a respective corroboration score based at least in part on map data stored in a memory accessible to the at least one processor and at least one of the respective first location estimate or the observation data of the respective instance of crowd-sourced data;
determining, by the at least one processor, a first representative corroboration score for the first time period based on respective corroboration scores determined for the one or more instances of crowd-sourced data corresponding to the first time period;
comparing, by the at least one processor, the first representative corroboration score for the first time period to a second representative corroboration score corresponding to a second time period, wherein the first time period is different from the second time period; and
based on a result of comparing the first representative corroboration score and the second representative corroboration score, determining, by the at least one processor, whether one or more respective first location estimates of the one or more instances of crowd-sourced data are potentially manipulated; and
responsive to determining that the one or more respective first location estimates of the one or more instances of crowd-sourced data are potentially manipulated, performing, by the at least one processor, at least one of (a) preventing the use of the one or more instances of crowd-sourced data from being used to update the map data or (b) reverting an effect of using the one or more instances of crowd-source data to update the map data.