IP Library Granted Patent US 12686390
Granted Patent B2
US 12686390 · App. 17/933,256 · Granted Jul 21, 2026

Vehicle position estimation device

Inventors: Shunya Kumano (Nisshin-city, JP); Takeshi Shikimachi (Kariya-city, JP)
Assignee: DENSO CORPORATION
B60W30/18163B60W2554/4041B60W2554/80B60W2556/45
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12686390
App. No.
17/933,256
Granted
Jul 21, 2026
Kind
B2
Abstract

A vehicle position estimation device includes an external information acquisition unit, a vehicle parameter acquisition unit, a map data acquisition unit, a lane change determination unit, and a position estimation unit. The external information acquisition unit acquires external information. The vehicle parameter acquisition unit acquires a vehicle parameter related to traveling. The map data acquisition unit acquires map data. The lane change determination unit determines whether the vehicle is changing lanes. The position estimation unit estimates a self-position of the vehicle on a map. When the lane change determination unit determines that the vehicle is changing lanes, the position estimation unit estimates the self-position using dead reckoning. When the lane change determination unit determines that the vehicle is not changing lanes, the position estimation unit estimates the self-position based on the external information and the map data.

Claims (46)

1 . A vehicle position estimation device mounted on a vehicle, comprising

at least one of (i) a circuit and (ii) a processor having a memory storing computer program code executable by the processor, the at least one of the circuit and the processor configured to cause the vehicle position estimation device to perform:

acquiring external information, which includes image data obtained by a camera, regarding objects and road markings around the vehicle, a vehicle parameter, which includes vehicle speed and a traveling direction, related to traveling of the vehicle, and map data including road information about lanes;

determining whether the vehicle is changing lanes based on the external information, the vehicle parameter, and the map data; and

estimating a self-position of the vehicle on a map based on the external information, the vehicle parameter, and the map data, wherein

the estimating includes

estimating, when the vehicle is changing lanes, the self-position using dead reckoning by which the self-position is sequentially updated based on the vehicle parameter without using the external information and the map data, based on determining that the vehicle is changing lanes, and

estimating, when the vehicle is not changing lanes, the self-position based on the external information and the map data without using the dead reckoning, based on determining that the vehicle is not changing lanes,

wherein

the dead reckoning is used for estimating the self-position depending on whether the vehicle is changing lanes, and

autonomous driving of the vehicle is supported using the estimated self-position.

2 . The vehicle position estimation device according to claim 1 , wherein

the estimating includes

estimating the self-position based on the external information, and the map data, based on determining that the vehicle is not changing lanes, and the external information indicating that lanes are being detected, and

estimating the self-position using the dead reckoning based on determining that the vehicle is not changing lanes and the external information not indicating that the lanes are being detected.

3 . The vehicle position estimation device according to claim 1 , wherein

the acquiring includes acquiring distances from the vehicle to road edges located rightward and leftward of the vehicle,

the estimating includes

estimating the self-position based on the external information and the map data, based on determining that the vehicle is not changing lanes and the external information indicates that the distances to the road edges are being detected, and

estimating the self-position using the dead reckoning based on determining that the vehicle is not changing lanes and the external information does not indicate that the distances to the road edges are being detected.

4 . The vehicle position estimation device according to claim 1 , wherein

the acquiring includes acquiring distances from the vehicle to two road edges located rightward and leftward of the vehicle, and

the determining includes determining whether the vehicle is changing lanes toward one of the two road edges by using decrease in distance to the one of the two road edges or increase in distance to an other of the two road edges.

5 . The vehicle position estimation device according to claim 1 , wherein

the at least one of the circuit and the processor is configured to cause the vehicle position estimation device to perform

calculating a reliability of each lane based on the external information and the map data, based on determining that the vehicle is traveling on a road having multiple lanes,

the reliability of each lane indicates a probability of the vehicle being traveling in the lane among the lanes, and

the determining includes determining that the vehicle is not changing lanes and has completed a lane change when a lane having a highest reliability calculated by the calculating among the lanes changes from one lane to another.

6 . The vehicle position estimation device according to claim 5 , wherein

the at least one of the circuit and the processor is configured to cause the vehicle position estimation device to perform

calculating the reliability of a lane, which is specified based on the numbers of lanes located on both sides of the vehicle in the external information, to be higher than the reliabilities of the other lanes when the number of lanes in the map data matches the total number of lanes in the external information.

7 . The vehicle position estimation device according to claim 5 , wherein

the at least one of the circuit and the processor is configured to cause the vehicle position estimation device to perform:

comparing the road markings in the external information with the road markings included in the map data; and

setting the reliability of a lane having a matching road marking to be higher than the reliabilities of the other lanes when an acquired road marking matches a road marking in the map data.

8 . The vehicle position estimation device according to claim 5 , wherein

the at least one of the circuit and the processor is configured to cause the vehicle position estimation device to perform

setting the reliabilities of all lanes to be equal when the number of lanes in the map data does not match the total number of lanes in the external information.

9 . The vehicle position estimation device according to claim 1 , wherein

the acquiring includes the acquiring distances from the vehicle to road edges located rightward and leftward of the vehicle, the road edges being different from a longitudinal marking and being located outside of the longitudinal marking, and

the estimating includes

estimating the self-position based on the external information and the map data, based on determining that the vehicle is not changing lanes, and the external information indicates that the distances to the road edges are being detected, and

estimating the self-position using the dead reckoning based on determining that the vehicle is not changing lanes, and the external information does not indicate that the distances to the road edges are being detected.

10 . The vehicle position estimation device according to claim 1 , wherein

the acquiring includes acquiring distances from the vehicle to road edges located rightward and leftward of the vehicle, the road edges being different from a longitudinal marking and being located outside of the longitudinal marking, and

the determining includes determining whether the vehicle is changing lanes toward one of the road edges by using decrease in distance to the one of the road edges or increase in distance to the other of the road edges.