Patent Application
20210063192
The present disclosure relates to an own location estimation device that estimates an own location of a traveling vehicle on a map.
As a comparison technique, an own location estimation device, for example, is provided. The own location estimation device (AUTONOMOUS NAVIGATION BASED ON SIGNATURES) specifies the current position of the vehicle based on the change in the characteristics of the road, and determines the policy of an automatic steering operation.
An own location estimation device for a vehicle having an in-vehicle camera and a cloud map server, is configured to: recognize an environment around the vehicle based on a state of the vehicle and sensing information by the in-vehicle camera; recognize a camera landmark based on the sensing information of the in-vehicle camera; update a cloud map in the map server; estimate a location of the vehicle based on the camera landmark and the map landmark in the cloud map; and generate a new landmark based on the sensing information of the in-vehicle camera when the map landmark does not exist in the cloud map, or when it is determined that an accuracy of the camera landmark is low.
The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description made with reference to the accompanying drawings. In the drawings:
In a comparison, the road width, the lane width, and the like are used as the characteristics of the road. However, in a driving scene such as an intersection on a farm road, there is a possibility that the road width cannot be correctly determined due to the effect of swaying of plants and trees in the wind, and, in some cases, the accuracy of location estimation may not be sufficiently obtained.
In view of the above point, an own location estimation device is provided to improve the accuracy of own location estimation by generating a new landmark even when road characteristics are difficult to obtain.
Based on an aspect of the present disclosure, an own location estimation device for a vehicle includes an in-vehicle camera and a cloud map server, and further includes an environment recognition unit that recognizes the surrounding environment of an own vehicle based on a state amount of the vehicle and sensing information by the in-vehicle camera. The environment recognition unit, includes: a landmark recognition unit that recognizes a camera landmark based on the sensing information of the in-vehicle camera, a cloud map transmission and reception unit that updates a cloud map in the cloud map server, and an own location estimation unit that estimates a location of an own vehicle based on the camera landmark and the map landmark in the cloud map. The landmark recognition unit includes a landmark generation unit that generates a new landmark based on the sensing information of the in-vehicle camera when the map landmark does not exist in the cloud map or when the accuracy of the camera landmark is determined to be low.
According to the above own location estimation device, when there is no map landmark in the cloud map, or when it is determined that the accuracy of the camera landmark is low, the landmark generation unit creates a new landmark based on the sensing information of the in-vehicle camera. Therefore, even if it is difficult to obtain road characteristics, it is possible to improve the accuracy of own location estimation by generating a new landmark.
According to another aspect of the present disclosure, an own location estimation device having a in-vehicle camera and a cloud map server has a processor and a memory. The processor and the memory recognize the environment around the own vehicle based on the state amount of the own vehicle and the sensing information by the in-vehicle camera, recognize the camera landmark based on the sensing information of the in-vehicle camera, update the cloud map in the map server, estimates the position of the own vehicle based on the camera landmark and the map landmark in the cloud map, and generate a new landmark based on the sensing information of the in-vehicle camera when the map landmark does not exist in the cloud map, or when it is determined that the accuracy of the camera landmark is low.
According to the above own location estimation device, when there is no map landmark in the cloud map, or when it is determined that the accuracy of the camera landmark is low, the landmark generation unit creates a new landmark based on the sensing information of the in-vehicle camera. Therefore, even if it is difficult to obtain road characteristics, it is possible to improve the accuracy of own location estimation by generating a new landmark.
The following describes a plurality of embodiments for carrying out the present disclosure with reference to the drawings. In each embodiment, portions corresponding to the elements described in the preceding embodiments are denoted by the same reference numerals, and redundant explanation may be omitted. When only a part of a configuration is described in an embodiment, another preceding embodiment may be applied to the other parts of the configuration. It may be possible not only to combine parts the combination of which is explicitly described in an embodiment, but also to combine parts of respective embodiments the combination of which is not explicitly described if any obstacle does not especially occur in combining the parts of the respective embodiments.
The own location estimation device 100 of the first embodiment will be described with reference to
As shown in
The in-vehicle camera 110 is arranged, for example, in front of the car roof of the own vehicle 10 to photographs (i.e., senses) an actual environment (i.e., an object) around the own vehicle 10, and acquires an image data for recognizing or generating a landmark (hereinafter referred to as camera landmark) from the actual environment. The in-vehicle camera 110 outputs the acquired image data to the environment recognition unit 140.
The cloud map server 120 is a server formed on the cloud via the Internet and stores a cloud map (i.e., map data). The cloud map server 120 is capable of exchanging the map data with the cloud map transmission/reception unit 142 of the environment recognition unit 140, which will be described later, and updating the stored map data. The map data is, for example, segmented every 1 km, and has a maximum capacity of about 10 kb per 1 km. The map data indicates roads (and lanes) and various map landmarks (such as structures, buildings, traffic signs, traffic marks, etc.).
The sensor unit 130 detects a state quantity, such as a vehicle speed and a yaw rate, of the subject vehicle 10 while traveling, and outputs data of the detected state quantity to the environment recognition unit 140. From the state quantity data detected by the sensor unit 130, the environment recognition unit 140 recognizes, for example, that the subject vehicle 10 is traveling on a straight road, or how much curvature the subject vehicle 10 is travelling on a curved road, or the like.
The environment recognition unit 140 recognizes the environment around the vehicle 10 based on the sensing information (i.e., image data) by the in-vehicle camera 110 and the state quantity (i.e., state quantity data) of the vehicle 10 detected by the sensor unit 130. The environment recognition unit 140 has a landmark recognition unit 141, a cloud map transmission/reception unit 142, an own location estimation unit 143, and the like.
The landmark recognition unit 141 recognizes a camera landmark based on the sensing information (i.e., the image data) of the in-vehicle camera 110. The camera landmark is a characteristic road portion, a structure, a building, a traffic sign, a traffic mark, or the like, which is captured by the in-vehicle camera 110.
The cloud map transmission/reception unit 142 stores the camera landmark recognized by the landmark recognition unit 141 and updates the stored map data with respect to the cloud map server 120.
The own location estimation unit 143 estimates the position of the own vehicle 10 on the cloud map from the camera landmark recognized by the landmark recognition unit 141 and the map landmark on the cloud map. The own location estimation unit 143 outputs the estimated position data of the own vehicle 10 to the alarm/vehicle control unit 150.
The landmark recognition unit 141 is arranged with a landmark generation unit 141a. The landmark generation unit 141a generates a new landmark from the image data obtained based on the sensing information of the in-vehicle camera 110 when there is no map landmark in the cloud map, or when the map landmark and the camera landmark are compared and verified and it is determined that the recognition accuracy of the camera landmark is low (details will be described later).
The alarm/vehicle control unit 150 notifies the driver of the warning, for example, when the traveling direction deviates from the road direction based on the position data of the own vehicle 10 output from the environment recognition unit 140 (i.e., the own location estimation unit 143), or executes a control for autonomous driving to a predetermined destination.
The configuration of the own location estimation device 100 is described above. Hereinafter, the operation and the effect will be described with reference to
In step S110 of the flowchart illustrated in
In step S130, the landmark generation unit 141a generates a new landmark. The procedure for generating a new landmark is executed based on the flowchart shown in
That is, in step S131A, the landmark generation unit 141a detects four corners at the intersection, that is, four points at which the lines corresponding to the road width position intersect, as indicated by the circles in
The condition 3 is such that the map data includes data of the distance between intersections, and the difference between the distance of the adjacent corners of the intersection and the distance of the intersections is equal to or less than a predetermined distance threshold. When a positive determination is made in step S133A, it is determined that the intersection imaged by the in-vehicle camera 110 matches the intersection on the map data, and the landmark generation unit 141a extracts the diagonal cross point in step S134A, and generates the center position of the intersection (i.e., the cross point) as a new landmark.
Returning to
When a positive determination is made in step S140, the cloud map transmission/reception unit 142 updates the cloud map in step S150. That is, a new landmark (i.e., the center position of the intersection) is registered in the cloud map.
On the other hand, when a negative determination is made in step S140, the landmark generation unit 141a determines the priority order for generating a new landmark, based on the reliability of the road feature and the object recognition obtained by the sensing information of the in-vehicle camera 110. The landmark generation unit 141a determines the priority order of generating a new landmark based on the distance from the vehicle 10, the size, and the recognition reliability.
Then, in step S160, the cloud map transmission/reception unit 142 updates the cloud map according to the priority order.
According to the above embodiment, when there is no map landmark in the cloud map, or when it is determined that the accuracy of the camera landmark is low, the landmark generation unit 141a creates a new landmark based on the sensing information of the in-vehicle camera 110. Therefore, even if it is difficult to obtain road characteristics, it is possible to improve the accuracy of own location estimation by generating a new landmark.
Further, for example, the center position of the intersection is extracted and generated as a new landmark. Thereby, a new landmark can be set easily and surely.
Further, the landmark generation unit 141a determines the priority order of generating a new landmark based on the reliability of each of the road features and the object recognition obtained by the sensing information of the in-vehicle camera 110, and also determines the priority order of the new landmark based on the distance from the host vehicle 10, the size, and the recognition reliability. This makes it possible to successively add highly reliable landmarks without unnecessarily increasing the storage capacity of the cloud map server 120.
The landmark generation unit 141a generates a new landmark based on the entrance/exit position of the tunnel obtained by the sensing information of the in-vehicle camera 110. The landmark generation unit 141a calculates the entrance/exit position of the tunnel based on the entrance/exit shape of the tunnel, image brightness change, tunnel name display, and the like.
Specifically, the landmark generation unit 141a recognizes the shape of a tunnel (in
In this embodiment, the tunnel is generated as a new landmark, and the same effect as that of the first embodiment can be obtained.
When generating a new landmark, as shown in
In each of the above-described embodiments, an intersection, a tunnel, trees, poles, and the like have been described as examples when a new landmark is generated, but it is not limited to these, and various objects may be adopted.
The controller and the method described in the present disclosure may be implemented by a special purpose computer which is configured with a memory and a processor programmed to execute one or more particular functions embodied in computer programs of the memory. Alternatively, the controller and the method described in the present disclosure may be implemented by a special purpose computer configured as a processor with one or more special purpose hardware logic circuits. Alternatively, the control unit and the method described in the present disclosure may be implemented by one or more special purpose computer, which is configured as a combination of a processor and a memory, which are programmed to perform one or more functions, and a processor which is configured with one or more hardware logic circuits. The computer programs may be stored, as instructions to be executed by a computer, in a tangible non-transitory computer-readable medium.
Here, the process of the flowchart or the flowchart described in the present disclosure includes multiple sections (or steps), and each section is expressed as, for example, S110. Further, each section may be divided into several subsections, while several sections may be combined into one section. Furthermore, each section thus configured may be referred to as a device, module, or means.
Although the present disclosure has been described in accordance with the embodiments, it is understood that the present disclosure is not limited to such embodiments and configurations. The present disclosure covers various modification examples and equivalent arrangements. In addition, various combinations and forms, and further, other combinations and forms including only one element, or more or less than these elements are also within the scope and the scope of the present disclosure.
| Number | Date | Country | Kind |
|---|---|---|---|
| 2018-095471 | May 2018 | JP | national |
The present application is a continuation application of International Patent Application No. PCT/JP2019/011088 filed on Mar. 18, 2019, which designated the U.S. and claims the benefit of priority from Japanese Patent Application No. 2018-095471 filed on May 17, 2018. The entire disclosures of all of the above applications are incorporated herein by reference.
| Number | Date | Country | |
|---|---|---|---|
| Parent | PCT/JP2019/011088 | Mar 2019 | US |
| Child | 17095077 | US |
