US 12,392,635 B2
Self-position estimation device, self-driving system including the same, and self-generated map sharing device
Hideyuki Kume, Tokyo (JP); Alex Masuo Kaneko, Tokyo (JP); Toshiharu Sugawara, Tokyo (JP); and Akira Kuriyama, Hitachinaka (JP)
Assigned to HITACHI ASTEMO, LTD., Ibaraki (JP)
Appl. No. 17/437,316
Filed by Hitachi Astemo, Ltd., Ibaraki (JP)
PCT Filed Feb. 7, 2020, PCT No. PCT/JP2020/004729
§ 371(c)(1), (2) Date Sep. 8, 2021,
PCT Pub. No. WO2020/189079, PCT Pub. Date Sep. 24, 2020.
Claims priority of application No. 2019-047903 (JP), filed on Mar. 15, 2019.
Prior Publication US 2022/0178717 A1, Jun. 9, 2022
Int. Cl. G01C 21/00 (2006.01); B60W 60/00 (2020.01); G01C 21/34 (2006.01); G08G 1/0962 (2006.01)
CPC G01C 21/3815 (2020.08) [B60W 60/001 (2020.02); G01C 21/3461 (2013.01); G08G 1/09626 (2013.01); B60W 2556/40 (2020.02); B60W 2556/45 (2020.02); B60W 2710/20 (2013.01); B60W 2720/10 (2013.01); G01C 21/3453 (2013.01); G01C 21/3841 (2020.08)] 16 Claims
OG exemplary drawing
 
1. A self-driving system for improving accuracy in estimating a location of a vehicle in which the self-driving system is located, the self-driving system comprising:
a memory; and
a processor communicatively coupled to the memory,
wherein the processor is configured to:
receive measurement results of a sensor configured to measure objects around the vehicle;
estimate a self-location and attitude on a high-precision map from the measurement results in three-dimensional space, wherein the high-precision map includes a plurality of information regarding at least an environment surrounding the vehicle;
detect a low-precision section indicating low estimation accuracy based on the self-location and attitude, wherein the low-precision section is detected when a distance of the vehicle at two different positions at two different times is greater than or equal to a predetermined threshold;
generate a self-generated map saving a position and type of at least one of the objects on the high-precision map in the low-precision section only,
estimate the location of the vehicle using the self-generated map,
calculate costs of a plurality of routes, including a first route which includes the low-precision section, using a calculation wherein cost increases according to an increase in the distance used to detect the low-precision section, and
schedule a route having a minimum cost from a current position to a target position based on the self-location and attitude, the high-precision map, the target position entered by a user, and the low-precision section.