JP7072395B2 - Vehicle controls and systems - Google Patents

Description

The present invention relates to a map data structure.

Conventionally, in a car navigation system, it has been possible to specify a parking lot as a guide destination. In this case, the parking lot information often includes information such as the parking lot name, location, fee, and the number of cars that can be parked (see, for example, Patent Document 1).

Further, Patent Document 2 has data on the position of each parking frame partitioned by a white line or the like in the parking lot, the position of the vehicle passage in which the vehicle travels, and the vehicle passage direction set for the vehicle passage. It is described that the navigation ECU has a parking lot map, and the position of the own vehicle in the parking lot is specified based on the parking lot map and the traveling locus of the own vehicle.

Japanese Unexamined Patent Publication No. 2011-209215 Japanese Unexamined Patent Publication No. 2009-1164

In recent years, vehicles (automated driving vehicles) that autonomously travel while acquiring the situation around the own vehicle by various sensors such as a camera mounted on the vehicle and a lidar (LiDAR: Light Detection And Ranging) have been developed.

In this type of self-driving vehicle, it is required to autonomously drive in the parking lot premises and park in a predetermined parking frame or the like, but the information described in Patent Document 1 indicates that the self-driving vehicle is You cannot drive in the parking lot. Further, with respect to a parking lot map in which the arrangement of parking lots and the like as described in Patent Document 2 is set, there is a problem that the application purpose such as parking in the parking lot of the parking lot is fixed and lacks flexibility. ..

One example of the problem to be solved by the present invention is the provision of a map data structure that can be used for various purposes and uses.

In order to solve the above problems, the invention according to claim 1 is a map data structure of map data having parking lot information indicating a parking lot area, and the parking lot information is about the parking lot area. It is possible to add predetermined information to each section subdivided into a predetermined size, and the predetermined information is characterized in that attribute information about the section is included.

It is a schematic block diagram of the system which has the map data storage device which concerns on embodiment of this invention. It is a functional block diagram of the server apparatus shown in FIG. It is a functional block diagram of the vehicle control device shown in FIG. This is an example of dividing the parking lot site into multiple meshes. It is an enlarged view of a part of the parking lot shown in FIG. It is a table which showed the parking lot information about the mesh of the parking lot shown in FIG. This is an example of how to separate meshes. It is a flowchart of a method of adding or updating dynamic attribute information.

Hereinafter, the map data structure according to the embodiment of the present invention will be described. The map data structure according to the embodiment of the present invention is a map data structure of map data having parking lot information indicating a parking lot area, and the parking lot information has a predetermined size for the parking lot area. Predetermined information can be added to each subdivided section, and the predetermined information includes attribute information about the section. By doing so, it is possible to provide a map data structure corresponding to various purposes and uses.

Further, the attribute information may include at least one of static attribute information and dynamic attribute information. By doing so, the autonomous driving vehicle can travel in the parking lot premises based on the static attribute information predetermined for each section. In addition, it is possible to respond to various purposes and uses based on dynamic attribute information added / updated by information acquired by an autonomous driving vehicle or other vehicle.

Further, the attribute information may include information regarding the movement of the vehicle in the section. By doing so, for example, by including the frequent passage of vehicles as an attribute, it becomes possible to grasp the passages and the like that the vehicles frequently pass.

Further, the attribute information may include information regarding the movement of a person in the section. By doing so, for example, by including the frequent passage of people as an attribute, it is possible to grasp the places where people frequently pass, etc., and prevent the autonomous driving vehicle from causing an accident with people. It will be possible to prevent it.

In addition, the attribute information may include information regarding movement between sections. By doing so, it becomes possible to grasp the direction in which the vehicle or the person moves, and it becomes possible to more accurately predict the danger.

Further, the parking lot information may have a plurality of attribute information added to the same section. By doing so, it is possible to give flexibility and diversity to the parking lot information according to the purpose and use.

Further, the map data storage device according to the embodiment of the present invention stores the map data structure described above. By doing so, it is possible to store map data that can be used for various purposes and uses.

A map data structure and a map data storage device according to an embodiment of the present invention will be described with reference to FIGS. 1 to 8. As shown in FIG. 1, the server device 1 can communicate with the vehicle control device 3 mounted on the autonomous driving vehicle C via a network N such as the Internet.

FIG. 2 shows a functional configuration of the server device 1 as a map data storage device. The server device 1 includes a control unit 11, a communication unit 12, and a storage unit 13.

In the control unit 11, the CPU (Central Processing Unit) of the server device 1 functions, and controls the entire server device 1. The control unit 11 reads out the map data of the required area from the map data 13a stored in the storage unit 13 in response to the request from the vehicle control device 3, and distributes the map data to the vehicle control device 3 via the communication unit 12.

The communication unit 12 functions such as the network interface of the server device 1 and receives the request information and the like output by the vehicle control device 3. Further, the map data read from the map data 13a by the control unit 11 is transmitted to the vehicle control device 3.

In the storage unit 13, a storage device such as a hard disk of the server device 1 functions, and map data 13a is stored. The map data 13a is a map including detailed information to the extent that the autonomous driving vehicle C can autonomously travel. Further, the map data 13a includes data (parking lot data) indicating a parking lot area as parking lot information. This parking lot data does not have to be possessed for all the parking lots included in the map data.

The autonomous driving vehicle C includes a vehicle control device 3 and a sensor 4. The vehicle control device 3 autonomously drives (automatically drives) the autonomous driving vehicle C based on the result detected by the sensor 4 and the map data 33a possessed by the vehicle control device 3.

FIG. 3 shows the functional configuration of the vehicle control device 3. The vehicle control device 3 includes a control unit 31, a communication unit 32, and a storage unit 33.

The control unit 31 estimates the self-position of the autonomous driving vehicle C based on the result detected by the sensor 4 and the map data 33a stored in the storage unit 33. Then, the control unit 31 controls the handle (steering device), accelerator, brake, etc. of the autonomous driving vehicle C to autonomously drive the autonomous driving vehicle C. That is, the control unit 31 acquires the detection result (recognition result) of the sensor 4 as the outside world recognition unit. Further, the control unit 31 requests the server device 1 to distribute the map data of the area serving as the traveling route via the communication unit 32, and the map data distributed from the server device 1 is transmitted to the storage unit 33 as the map data 33a. Remember as.

The communication unit 32 transmits the request information and the like output by the control unit 31 to the server device 1. It also receives the map data distributed from the server device 1.

The storage unit 33 as a map data storage device stores map data 33a. Similar to the map data 13a, the map data 33a is a map including detailed information to the extent that the autonomous driving vehicle C can autonomously travel. Further, the map data 33a includes parking lot data as in the map data 13a.

The sensor 4 is a sensor for recognizing the information of the own vehicle such as the position of the own vehicle and the surrounding environment (features existing in the vicinity, etc.), and includes a camera, a rider, a GPS (Global Positioning System) receiver, and the like. .. In addition to these sensors, an acceleration sensor that detects the acceleration of the vehicle, a speed sensor that detects the speed of the vehicle, or an inertia for recognizing the posture (orientation, etc.) of the vehicle and correcting the acquired data of other sensors. A measuring unit (IMU: Inertial Measurement Unit), a gyro sensor, or the like may be provided.

The camera included in the sensor 4 captures an image showing the situation of the outside world of the autonomous driving vehicle C. The rider included in the sensor 4 measures the distance to an object existing in the outside world discretely, and recognizes the position, shape, and the like of the object as a three-dimensional point group. The information acquired by this rider is output as point cloud information. The GPS receiver included in the sensor 4 generates and outputs latitude and longitude position information indicating the current position of the vehicle.

Next, a map data structure having parking lot data according to this embodiment will be described. As the parking lot data of the parking lot according to this embodiment, as shown in FIG. 4, the site (area) of the parking lot P is subdivided into a plurality of mesh Ms (sections). The parking lot P shown in FIG. 4 faces the road R. The shape of the mesh M is not limited to the square as shown in FIG. 4, but may be a rectangle, or may be a polygon such as a hexagon or an octagon. Further, although the size of the mesh M can be arbitrarily determined, it is desirable that the mesh M has a certain size because it can be identified by each attribute information or the like described later.

Further, mesh numbers, position information, attribute information, and the like are set as predetermined information in each mesh M. The position information may be an absolute position such as latitude and longitude, or may be a relative position (number of rows and columns) from a reference position where the absolute position is set. Attribute information will be described later.

FIG. 5 shows a diagram showing a part of the site of the parking lot P extracted. FIG. 5 shows a part of the parking area F of the parking lot P, the passage PS in the parking lot P premises, and the wall W provided between the parking area F and the passage PS.

The parking area F is divided into areas where vehicles can park by the white line L. The wall W is provided to partition the parking area F at the left end of FIG. 5 and the passage PS, and is an area where vehicles and people cannot pass.

In the example of FIG. 5, for example, the mesh M included in the parking area F is added with attribute information indicating that it is a “parking area”. Further, attribute information indicating that it is a "passage" is added to the mesh M included in the passage PS. Further, attribute information indicating that it is a "wall" is added to the mesh M included in the wall W. An example of attribute information is shown in FIG. FIG. 6 shows the parking lot information 33a1 of the parking lot P. The parking lot information 33a1 has a mesh number (No) 33a2 for identifying each mesh, a position information 33a3, and an attribute information (attribute) 33a4.

The mesh number 33a2 is a unique number assigned to each mesh M. The position information 33a3 is set as, for example, latitude and longitude.

The attribute information 33a4 will be described. As shown in FIG. 6, since the mesh M1 shown in FIG. 5 is provided with the wall W, the “wall” is set as the attribute information 33a4 as shown in FIG. Similarly, since the mesh M2 is included in the parking area F, the “parking area” is set as the attribute information 33a4 as shown in FIG. Similarly, since the mesh M3 is included in the passage PS, the “passage” is set as the attribute information 33a4 as shown in FIG. Although not shown in FIG. 6, an attribute indicating that the mesh M including the white line L may be “white line” may be set.

By adding such attribute information 33a4 to the mesh M, the autonomous driving vehicle C travels in the area of the mesh M having the attribute indicating that it is a passage, and the mesh having the attribute indicating that it is a parking area. The area of the mesh M, which is parked in the area of M and has an attribute indicating that it is a wall, can avoid running. The attribute information 33a4 may not be set in all meshes M. For example, as the initial data, the attribute information 33a4 may be set only for a part of the mesh M, and the other mesh M may be set by the flowchart of addition or update of the dynamic attribute information described later.

Further, as a method of dividing the mesh M, it may be divided based on the direction as shown on the left side of FIG. 7, or as a reference on the side constituting the outer circumference of the parking lot P as shown on the right side of FIG. It may be separated.

It should be noted that attribute information other than the parking area, the passage, and the wall shown in FIGS. 5 and 6 can be added to the mesh M. For example, information such as the presence / absence of a roof and, in the case of a multi-story parking lot, information on the floor (which floor it is located on) may be added as attribute information. Alternatively, information on the condition of the site (pavement, gravel, lawn, etc.) may be added as attribute information. Such information can determine the parking position of the autonomous driving vehicle C according to the weather. Alternatively, the self-driving vehicle C can be parked at a position according to the user's preference.

Further, in the mesh M included in the parking area F, information indicating a priority space (priority parking lot), information indicating a store convenient for use, and information indicating that the parking space is for a visitor such as a specific store are stored in the mesh M. It may be added as attribute information. If the information indicating the priority space is added as the attribute information, the autonomous driving vehicle C using the priority space can park in the space. If information indicating a store convenient for use is added as attribute information, the autonomous driving vehicle C can be parked at a position according to the purpose of the store or the like to be visited. Further, if information indicating that the parking space is for a visitor of a specific store or the like is added as attribute information, it is possible to prevent the autonomous driving vehicle C from being accidentally parked in the parking space for the visitor of another store or the like.

Further, information on the classification of large vehicles, ordinary vehicles, light vehicles, motorcycles, etc., and parking direction information such as forward parking, backward parking, etc. may be added to the mesh M included in the parking area F as attribute information. By adding such information as attribute information, it is possible to prevent the vehicle from being parked by mistake in the classification and orientation.

Further, illuminance information such as a place where a puddle is likely to occur, the brightness of lighting, and the goodness of sunlight in the daytime may be added to the mesh M included in the parking area F as attribute information. By adding such information as attribute information, it is possible to prevent the autonomous driving vehicle C from being parked in a place where a puddle is likely to occur on a rainy day or in a dark place.

Further, information indicating a drive-through lane and information indicating a stop position (ordering place, product receiving place) in the drive-through lane may be added to the mesh M included in the passage PS as attribute information. If such information is added as attribute information, the drive-through lane can be appropriately driven.

In addition, the mesh M included in the passage PS has a speed bump installed in the parking lot, information such as its shape and height, an entrance / exit gate, and a checkout machine. Information indicating that may be added as attribute information. By adding such information as attribute information, the autonomous driving vehicle C can be decelerated before the speed bump, and the vehicle can be appropriately temporarily stopped at the entrance / exit gate or the position of the checkout machine. Further, the mesh M including the equipment installed in such a parking lot premises may also be added with attribute information indicating that a person or a vehicle cannot pass, such as the wall W described above. By adding attribute information indicating that people and vehicles cannot pass to the mesh M including the equipment installed in the parking lot premises, the self-driving vehicle C travels avoiding these equipment like the wall W. be able to.

As described above, a plurality of attribute information can be added to the same mesh M as the attribute information. For example, when the mesh M3 in FIG. 5 is provided with speed bumps, the attribute information indicating that the speed bumps are provided may be added in addition to the attribute information indicating that the mesh M3 is the passage PS.

The above-mentioned attribute information is premised on being added to the mesh M in advance as static attribute information, but these attribute information is not limited to being added as static attribute information. For example, it may be dynamic attribute information that is sequentially added or updated based on the detection result of a sensor such as a rider mounted on a vehicle traveling in the parking lot P premises. For example, the parking area F, the passage PS, and the wall W can be treated as dynamic attribute information because they can be identified from the detection results of sensors such as riders and cameras.

Further, as the dynamic attribute information, information on the movement of the vehicle and information on the movement of the person can be included. The information regarding the movement of the vehicle is, for example, information such as the traffic volume of the vehicle in the mesh M, and it is possible to grasp that the vehicle frequently passes by such information. Similarly, information on movement to a person is also information such as the traffic volume of a person in the mesh M, and such information indicates that the mesh M is a pedestrian passage or the like and people frequently pass through. I can grasp it.

Furthermore, information regarding movement between meshes M may be included as dynamic attribute information. This attribute is information indicating, for example, from which direction of the adjacent mesh M the mesh M3 in FIG. 5 is frequently moved to the mesh M3, or from which direction the mesh M3 is frequently moved to the mesh. By setting it as information, it is possible to identify the moving direction of the passage PS including the mesh M3.

Here, FIG. 8 shows a flowchart for adding or updating dynamic attribute information. The flowchart shown in FIG. 8 is executed by the control unit 31 of the vehicle control device 3. Alternatively, it may be executed by the control unit 11 of the server device 1. When the control unit 11 executes the execution, the server device 1 acquires the detection result (sensor information) acquired by the sensor 4 of the autonomous driving vehicle C via the communication unit 12.

First, in step S1, the result (sensor information) detected by the sensor 4 is acquired. This sensor information is, for example, point cloud information acquired by a rider, image information taken by a camera, or the like.

Next, in step S2, the attribute is analyzed based on the sensor information acquired in step S1. This attribute indicates the parking area F or the like described above, and in this step, it is analyzed which attribute is indicated from the detected result. For example, in the case of a priority space or a parking area for a light vehicle, it can be identified by recognizing a mark indicating the priority space or the character "light". Further, the sensor information does not have to be only the immediately preceding information. For example, by accumulating sensor information, if the wall W is recognized at a predetermined frequency, it can be identified as an obstacle or the like.

Next, in step S3, the mesh M including the attribute analyzed in step S2 is specified. For this identification, for example, the mesh M can be specified from the current position of the vehicle equipped with the sensor 4 and the distance to the feature whose attributes are analyzed.

Then, in step S4, attribute information is added or updated for the mesh M specified in step S3.

According to this embodiment, the map data 33a is a map data structure showing an area of the parking lot P, and the area of the parking lot P is subdivided into mesh Ms of a predetermined size, and each mesh M is predetermined. Information can be added, and the predetermined information includes attribute information about the mesh M. By doing so, by adding the attribute information 33a4 to each mesh M, it is possible to provide a map data structure corresponding to various purposes and uses.

Further, the attribute information 33a4 may include at least one of static attribute information and dynamic attribute information. By doing so, the autonomous driving vehicle C can travel in the parking lot P premises based on the static attribute information predetermined for each mesh M in advance. Further, it is possible to correspond to various purposes and uses based on the dynamic attribute information added / updated by the information acquired by the autonomous driving vehicle C or other vehicles.

Further, the attribute information 33a4 may include information regarding the movement of the vehicle in the mesh. By doing so, for example, by including the frequent passage of vehicles as an attribute, it becomes possible to grasp the passages and the like that the vehicles frequently pass.

Further, the attribute information 33a4 may include information regarding the movement of a person in the mesh. By doing so, for example, by including the frequent passage of people as an attribute, it is possible to grasp the places where people frequently pass, etc., and prevent the autonomous driving vehicle from causing an accident with people. It will be possible to prevent it.

Further, the attribute information 33a4 may include information regarding movement between meshes. By doing so, it becomes possible to grasp the direction in which the vehicle or the person moves, and it becomes possible to more accurately predict the danger.

Further, the parking lot information 33a1 may have a plurality of attribute information 33a4 added to the same parking area F. By doing so, the parking lot information 33a1 can be made flexible and diverse according to the purpose and use.

Further, by storing the map data 33a described above in the storage unit 33, it is possible to store map data that can be used for various purposes and uses. Further, by storing the map data 13a in the server device 1, the map data having the parking lot information can be distributed to a plurality of autonomously driven vehicles. Therefore, it is easy to add or update.

The present invention is not limited to the above examples. That is, those skilled in the art can carry out various modifications according to conventionally known knowledge within a range that does not deviate from the gist of the present invention. Even with such a modification, as long as the map data structure, the feature data storage device, and the self-position estimation device of the present invention are provided, the present invention is, of course, included in the category of the present invention.

1 Server device (map data storage device)
3 Vehicle control device 4 Sensor (rider)
13 Storage unit 13a Map data (map data structure)
31 Control unit 32 Communication unit 33 Storage unit (map data storage device)
33a Map data (map data structure)
33a1 Parking lot information 33a4 Attribute information M mesh (section)

Claims (6)

Map data having parking lot information indicating a parking lot area, and the parking lot information includes attribute information about the parking lot area for each section subdivided into a predetermined size. A storage unit that stores the included map data,
A vehicle control device including a control unit for driving a vehicle based on the map data.
The control unit adds or updates the attribute information included in the map data stored in the storage unit based on the result detected by the sensor included in the vehicle.
The attribute information includes at least one of the traffic volume of a vehicle and the traffic volume of a person in the section.
A vehicle control device characterized by that . The vehicle control device according to claim 1 , wherein the attribute information includes information regarding the frequency of movement between the sections. The vehicle control device according to claim 1 or 2 , wherein the parking lot information has a plurality of attribute information added to the same section. A system equipped with a map data storage device and a vehicle control device.
The map data storage device is
Map data having parking lot information indicating a parking lot area, and the parking lot information includes attribute information about the parking lot area for each section subdivided into a predetermined size. A storage unit that stores the included map data,
A control unit for adding or updating the attribute information included in the map data stored in the storage unit based on the result detected by the sensor of the vehicle controlled by the vehicle control device is provided.
The vehicle control device is a system including a control unit for traveling the vehicle based on the map data.
The attribute information includes at least one of the traffic volume of a vehicle and the traffic volume of a person in the section.
A system characterized by that. The system according to claim 4, wherein the attribute information includes information regarding the frequency of movement between the sections. The system according to claim 4 or 5, wherein a plurality of attribute information is added to the attribute information for the same section.

Images