IP Library Granted Patent US 12664682
Granted Patent B2
US 12664682 · App. 18/703,460 · Granted Jun 23, 2026

Autonomous traveling vehicle, device for controlling autonomous traveling vehicle, and own-position estimating method for autonomous traveling vehicle

Inventor: Takashi Uno (Kariya, JP)
Assignee: KABUSHIKI KAISHA TOYOTA JIDOSHOKKI
G06T7/74B60W60/001B60W2420/403G06T2207/30252
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 12664682
App. No.
18/703,460
Granted
Jun 23, 2026
Kind
B2
Abstract

An autonomous traveling vehicle performs data alignment processing, priority order setting processing, identification processing, image matching processing, and own-position estimation processing. The data alignment processing rearranges a plurality of map data into a prescribed order. The identification processing identifies, as an identified group, a group that includes map image data that is most similar to image data when a prescribed condition is satisfied after the data alignment processing. The priority order setting processing further rearranges the plurality of map data rearranged by the data alignment processing, so that the map data belonging to the identified group is used preferentially in the image matching processing.

Claims (43)

1 . An autonomous vehicle configured to travel while estimating its own position, the autonomous vehicle comprising:

a camera configured to image-capture an imaging subject in predetermined time intervals;

a storage configured to store map datasets including position information associated with map image datasets acquired by image-capturing the imaging subject in advance;

an acquisition circuit configured to acquire image data from the camera;

a position estimation circuit configured to execute, in the predetermined intervals, an image matching process that compares the image data with the map image datasets to specify a map image dataset corresponding to the image data and configured to execute a position estimating process that estimates the position of the autonomous vehicle from a relative positional relationship of the specified map image dataset and the image data and from a relative angle of the specified map image dataset and the image data; and

a processor, wherein

the map datasets are divided into groups in accordance with a state of the imaging subject,

the processor is configured to execute

a dataset arranging process for changing an arrangement order of the map datasets to a predetermined arrangement order,

a specifying process for comparing the image data with the map image datasets included in each of the groups when a predetermined condition is satisfied subsequent to the dataset arranging process to specify a group including a map image dataset that is most similar to the image data as a specified group, and

a priority order setting process for further changing the arrangement order of the map datasets that was changed by the dataset arranging process so that the map datasets belonging to the specified group are given priority for use in the image matching process,

the image matching process includes comparing the image data with only a predetermined number of the map datasets from a head of the arrangement order subsequent to the priority order setting process and in order from the head of the arrangement order, and

the processor autonomously controls a traveling motor driver and a steering motor driver of the autonomous vehicle to move the autonomous vehicle to a target location based on the position of the autonomous vehicle that is estimated.

2 . The autonomous vehicle according to claim 1 , wherein the predetermined arrangement order in the dataset arranging process is an order of the map datasets with the position information that is closer in distance to the position information associated with the map image dataset specified when the image matching process was previously executed.

3 . The autonomous vehicle according to claim 1 , wherein the predetermined condition includes an event indicating that an environment in which the autonomous vehicle is traveling may have changed from when the image matching process was previously executed.

4 . The autonomous vehicle according to claim 1 , wherein the specifying process includes

extracting one or more feature points from the image data, and describing feature amounts of the feature points that are extracted,

extracting one or more feature points from the map image datasets included in each of the groups, and calculating a feature amount of each of the feature points that are extracted,

matching a feature point and a feature amount acquired from the image data with a feature point and a feature amount acquired from the map image datasets to search for a pair of the feature point of the image data and the feature point of the map image dataset having similar feature amounts,

specifying a map image dataset having a greatest number of feature points paired with the feature points of the image data as a map image dataset that is the most similar to the image data, and

specifying a group including the map image dataset that is specified as the specified group.

5 . A controller of an autonomous vehicle, the controller is configured to control the autonomous vehicle that travels while estimating its own position, the controller comprising:

an acquisition circuit configured to acquire image data from a camera that image-captures an imaging subject in predetermined time intervals;

a position estimation circuit configured to execute, in the predetermined intervals, an image matching process that compares the image data with map image datasets, included in map datasets including position information associated with map image datasets acquired by image-capturing the imaging subject in advance, to specify a map image dataset corresponding to the image data and configured to execute a position estimating process that estimates the position of the autonomous vehicle from a relative positional relationship of the specified map image dataset and the image data and from a relative angle of the specified map image dataset and the image data; and

the map datasets are divided into groups in accordance with a state of the imaging subject,

the controller is configured to execute

a dataset arranging process for changing an arrangement order of the map datasets to a predetermined arrangement order,

a specifying process for comparing the image data with the map image datasets included in each of the groups when a predetermined condition is satisfied subsequent to the dataset arranging process to specify a group including a map image dataset that is most similar to the image data as a specified group, and

a priority order setting process for further changing the arrangement order of the map datasets that was changed by the dataset arranging process so that the map datasets belonging to the specified group are given priority for use in the image matching process,

the image matching process includes comparing the image data with only a predetermined number of the map datasets from a head of the arrangement order subsequent to the priority order setting process and in order from the head of the arrangement order, and

the controller autonomously controls a traveling motor driver and a steering motor driver of the autonomous vehicle to move the autonomous vehicle to a target location based on the position of the autonomous vehicle that is estimated.

6 . A method for estimating a position of an autonomous vehicle, the method comprising:

image-capturing an imaging subject in predetermined time intervals;

storing map datasets including position information associated with map image datasets acquired by image-capturing the imaging subject in advance;

acquiring image data from a camera;

executing, in the predetermined intervals, an image matching process for comparing the image data with the map image datasets to specify a map image dataset corresponding to the image data;

executing a position estimating process for estimating the position of the autonomous vehicle from a relative positional relationship of the specified map image dataset and the image data and from a relative angle of the specified map image dataset and the image data, the map datasets are divided into groups in accordance with a state of the imaging subject;

executing a dataset arranging process for changing an arrangement order of the map datasets to a predetermined arrangement order;

executing a specifying process for comparing the image data with the map image datasets included in each of the groups when a predetermined condition is satisfied subsequent to the dataset arranging process to specify a group including a map image dataset that is most similar to the image data as a specified group;

executing a priority order setting process for further changing the arrangement order of the map datasets that has been changed by the dataset arranging process so that the map datasets belonging to the specified group are given priority for use in the image matching process, and

the image matching process includes comparing the image data with only a predetermined number of the map datasets from a head of the arrangement order subsequent to the priority order setting process and in order from the head of the arrangement order; and

autonomously controlling, via a processor, a traveling motor driver and a steering motor driver of the autonomous vehicle to move the autonomous vehicle to a target location based on the position of the autonomous vehicle that is estimated.

7 . The autonomous vehicle according to claim 5 , wherein the predetermined condition is in that the autonomous vehicle and the controller are being activated or in that a matching number in the image matching process executed during a preceding routine was less than or equal to a threshold value.