Information processing device, map data generation device, method, and program

Abstract

To provide map data containing advance information for grasping objects to be used for self-position estimation in advance.SOLUTION: An in-vehicle device 1 estimates the self-position based on measurements of objects measured using a LiDAR 2 mounted on a vehicle and position information of the objects included in a map DB 10. The map DB 10 includes object recommendation information indicative of a recommendation value of each object for the position estimation or voxel recommendation information indicative of a recommendation value of each voxel for the position estimation.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present invention relates to a self-position estimation technique.

Background Art

[0002] Conventionally, there has been known a technique of detecting a ground object installed in the traveling direction of a vehicle using a radar or a camera and correcting the position of the host vehicle based on the detection result. For example, Patent Document 1 discloses a technique of estimating the self-position by comparing the output of a measurement sensor with the position information of a ground object registered in advance on a map. Further, Patent Document 2 discloses a self-position estimation technique using a Kalman filter. Furthermore, Non-Patent Document 1 discloses a specification regarding a data format for collecting data detected by a sensor on the vehicle side by a cloud server.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] When estimating the position of a host vehicle by collating measurement results of objects around the position of the host vehicle by an external sensor such as a lidar with the position information of the objects on a map, if the target object cannot be detected due to occlusion by other vehicles or the influence of rain or snow, the accuracy of the host vehicle position estimation deteriorates. Similarly, when the position or shape of the object itself changes, the collation result is shifted due to the inconsistency with the position of the object on the map, resulting in deterioration of the host vehicle position estimation accuracy.

[0006] The present invention has been made to solve the above problems, and a main object thereof is to provide map data including prior information for grasping in advance an object to be used for self-position estimation.

Means for Solving the Problems

[0007] The invention according to the claim is an information processing apparatus, comprising: a detection unit that detects an object around a moving body; a first acquisition unit that acquires an estimated position of the moving body; a second acquisition unit that acquires map information including position information of an object around the estimated position and recommendation value information indicating a recommendation value for performing the position estimation of the moving body; and a position estimation unit that estimates the position of the moving body based on a detection result of the object detected by the detection unit, the estimated position, and the position information of the object included in the map information, wherein the position estimation unit estimates the position of the moving body by a weighting operation based on the recommendation value information.

[0008] Further, the invention according to the claim is an information processing apparatus having a storage unit that stores map data including information indicating a recommendation value for performing the position estimation of the moving body by using a positional relationship between position information of an object and the object measured by a measurement device mounted on the moving body, the recommendation value information being used for a weighting operation of the position estimation.

[0009] Further, the invention according to the claim is a map data generation device, which is information indicating a recommended value for the position estimation of the moving body using the object, generated based on the identification information of the object and the effectiveness information regarding the improvement of the accuracy of the position estimation of the moving body using the object, and has a generation unit that generates map data by associating the recommended value information used for the weighted calculation of the position estimation with the position information of the object. Further, the invention according to the claim is a method executed by a computer, which includes a detection step of detecting an object around the moving body, a first acquisition step of acquiring the estimated position of the moving body, a second acquisition step of acquiring map information including the position information of the object around the estimated position and the recommended value information indicating the recommended value for performing the position estimation of the moving body, and a position estimation step of estimating the position of the moving body based on the detection result of the object detected in the detection step, the estimated position, and the position information of the object included in the map information. The position estimation step estimates the position of the moving body by performing a weighted calculation based on the recommended value information. Further, the invention according to the claim is a program that causes a computer to function as a position estimation unit that estimates the position of the moving body based on the detection result of the object detected by a detection unit that detects an object around the moving body, a first acquisition unit that acquires the estimated position of the moving body, a second acquisition unit that acquires map information including the position information of the object around the estimated position and the recommended value information indicating the recommended value for performing the position estimation of the moving body, and the detection result of the object, the estimated position, and the position information of the object included in the map information. The position estimation unit estimates the position of the moving body by performing a weighted calculation based on the recommended value information.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Mode for Carrying Out the Invention

[0011] According to a preferred embodiment of the present invention, there is provided a data structure of map data, including position information of an object and recommendation value information indicating a recommended value for performing position estimation of a moving body using a positional relationship between the object and the moving body obtained by a measuring device mounted on the moving body, and the data structure is a data structure of map data used for position estimation of the moving body. By having such a data structure, the map data can preferably include prior information for grasping in advance an object to be used for self-position estimation.

[0012] In one aspect of the above data structure, the recommendation value information includes a recommended value for performing the position estimation in a direction with respect to the moving body as a reference. In a preferred example, the recommendation value information further includes a recommended value for performing the position estimation with respect to the orientation of the moving body. According to this aspect, the degree of recommendation for position estimation with respect to an object used for position estimation can be recorded in the map data for each state variable estimated in the position estimation process.

[0013] In another aspect of the above data structure, for each unit region obtained by partitioning space, the position information of the object and the recommendation value information are provided, and the recommendation value information indicates a recommended value for each unit region when performing position estimation of the moving body by collating the position information of the object and the positional relationship with the object for each unit region. According to this aspect, the map data can preferably include prior information for grasping in advance a unit region to be used for position estimation that collates the position information of an object and the positional relationship with the object for each unit region.

[0014] According to another preferred embodiment of the present invention, an information processing apparatus includes a storage unit that stores map data including position information of an object and recommendation value information indicating a recommended value for performing position estimation of a moving body using a positional relationship between the object and the moving body obtained by a measuring device mounted on the moving body. With this aspect, the information processing apparatus can preferably refer to prior information for grasping in advance an object to be used for self-position estimation to perform position estimation or distribute it to other devices that perform position estimation.

[0015] According to another preferred embodiment of the present invention, a map data generation device includes a generation unit that generates map data by associating recommended value information indicating a recommended value for position estimation of the moving body using the object, which is generated based on identification information of the object and effectiveness information regarding the effectiveness of improving the accuracy of position estimation of the moving body using the object, with the position information of the object. In this manner, the map data generation device can suitably include, in the map data, prior information for grasping in advance the object to be used for self-position estimation.

Example

[0016] Hereinafter, preferred first and second embodiments of the present invention will be described with reference to the drawings. In this specification, for the sake of convenience, a character with a "^" or "-" attached above an arbitrary symbol is represented as "A ^ " or "A - " ("A" is an arbitrary character).

[0017] <First Embodiment> (1-1) Overview of the Driving Support System FIG. 1 shows a schematic configuration of a driving support system according to the first embodiment. The driving support system includes an in-vehicle device 1 that moves together with each vehicle as a moving body, and a server device 6 that communicates with each in-vehicle device 1 via a network. Then, based on the information transmitted from each in-vehicle device 1, the driving support system updates a distribution map DB 20, which is a distribution map held by the server device 6. Hereinafter, the "map" shall include data used for ADAS (Advanced Driver Assistance System) and autonomous driving in addition to the data referred to by a conventional in-vehicle device for route guidance.

[0018] The in-vehicle device 1 is electrically connected to the lidar 2, gyro sensor 3, vehicle speed sensor 4, and GPS receiver 5, and based on their outputs, it performs detection of a predetermined object and estimation of the position of the vehicle on which the in-vehicle device 1 is mounted (also referred to as the "own vehicle position"). Then, based on the estimated result of the own vehicle position, the in-vehicle device 1 performs automatic driving control of the vehicle so as to travel along the set route to the destination. The in-vehicle device 1 stores a map database (DB: DataBase) 10 in which information on road data and objects such as landmarks and lane lines provided near the road is registered. The above-mentioned landmarks are, for example, kilometer posts, 100m posts, delineators, traffic infrastructure facilities (such as signs, direction signs, signals), utility poles, street lights, etc. that are periodically arranged along the road. And the in-vehicle device 1 estimates the own vehicle position by collating with the outputs of the lidar 2 etc. based on this map DB 10. In addition, the in-vehicle device 1 transmits upload information "Iu" including information on the detected object to the server device 6. The in-vehicle device 1 is an example of an information transmission device.

[0019] The lidar 2 discretely measures the distance to an object existing in the external world by emitting a pulsed laser in a predetermined angular range in the horizontal and vertical directions, and generates three-dimensional point cloud information indicating the position of the object. In this case, the lidar 2 has an irradiation unit that irradiates laser light while changing the irradiation direction, a light receiving unit that receives the reflected light (scattered light) of the irradiated laser light by the object, and an output unit that outputs scan data based on the light reception signal output by the light receiving unit. The scan data is point cloud data, and is generated based on the irradiation direction corresponding to the laser light received by the light receiving unit and the distance to the object in that irradiation direction specified based on the above-mentioned light reception signal. Hereinafter, in the own vehicle position estimation process, objects such as lane lines and landmarks such as ground features to be measured by the lidar 2 are also referred to as "landmarks". The lidar 2, gyro sensor 3, vehicle speed sensor 4, and GPS receiver 5 each supply output data to the in-vehicle device 1. The lidar 2 is an example of a "measurement device".

[0020] The server device 6 receives and stores the upload information Iu from each in-vehicle device 1. The server device 6 updates, for example, the distribution map DB20 based on the collected upload information Iu. Further, the server device 6 transmits the download information Id including the update information of the distribution map DB20 to each in-vehicle device 1. The server device 6 is an example of an information processing device and a map data generation device.

[0021] FIG. 2(A) is a block diagram showing the functional configuration of the in-vehicle device 1. The in-vehicle device 1 mainly includes an interface 11, a storage unit 12, a communication unit 13, an input unit 14, a control unit 15, and an information output unit 16. These elements are interconnected via a bus line.

[0022] The interface 11 acquires output data from sensors such as the lidar 2, the gyro sensor 3, the vehicle speed sensor 4, and the GPS receiver 5, and supplies it to the control unit 15.

[0023] The storage unit 12 stores programs executed by the control unit 15 and information necessary for the control unit 15 to execute predetermined processes. In this embodiment, the storage unit 12 stores a map DB10 including attribute information such as the position, size, and shape of an object serving as a landmark and object recommendation information described later. Here, the object recommendation information is information indicating a recommendation value (also referred to as an “object recommendation value”) for performing self-vehicle position estimation using a target object for each object. The data structure of the object recommendation information will be described later.

[0024] The communication unit 13 transmits the upload information Iu and receives the download information Id based on the control of the control unit 15. The input unit 14 is a button, a touch panel, a remote controller, a voice input device, etc. for the user to operate. The information output unit 16 is, for example, a display, a speaker, etc. that perform output based on the control of the control unit 15.

[0025] The control unit 15 includes a CPU that executes programs and the like, and controls the entire in-vehicle device 1. In this embodiment, the control unit 15 has a host vehicle position estimation unit 17 and an upload control unit 18.

[0026] The host vehicle position estimation unit 17 corrects the host vehicle position estimated from the output data of the gyro sensor 3, the vehicle speed sensor 4, and / or the GPS receiver 5 based on the measurement values of the distance and angle by the lidar 2 with respect to the landmark and the position information of the landmark extracted from the map DB 10. In this embodiment, as an example, the host vehicle position estimation unit 17 alternately executes a prediction step of predicting the host vehicle position from the output data of the gyro sensor 3, the vehicle speed sensor 4, etc. based on a state estimation method based on Bayesian estimation, and a measurement update step of correcting the predicted value of the host vehicle position calculated in the previous prediction step. Various state estimation filters developed to perform Bayesian estimation can be used as the state estimation filter used in these steps. For example, an extended Kalman filter, an unscented Kalman filter, a particle filter, etc. are applicable. In the first embodiment, the host vehicle position estimation unit 17 performs host vehicle position estimation using an extended Kalman filter as an example. The host vehicle position estimation using the extended Kalman filter will be described in the section "Position Estimation Based on Extended Kalman Filter".

[0027] When the upload control unit 18 detects a predetermined object based on the output of an external sensor such as the lidar 2, it generates upload information Iu including information about the detected object and transmits the upload information Iu to the server device 6. Further, when the host vehicle position estimation unit 17 performs host vehicle position estimation using the detected object as a landmark, the upload control unit 18 determines the effectiveness of improving the accuracy of the position estimation by the host vehicle position estimation for each state variable, and includes flag information indicating the determination result (also referred to as "valid flag") in the upload information Iu and transmits it to the server device 6. The upload control unit 18 is an example of a "generation unit", a "transmission unit", and a "computer" that executes a program. Also, the valid flag is an example of "validity information".

[0028] FIG. 2(B) is a block diagram showing the functional configuration of the server device 6. The server device 6 mainly includes a communication unit 61, a storage unit 62, and a control unit 65. These elements are interconnected via a bus line.

[0029] The communication unit 61 performs operations such as receiving upload information Iu and transmitting download information Id based on the control of the control unit 65. The storage unit 62 stores programs executed by the control unit 65 and information necessary for the control unit 65 to execute predetermined processes. In this embodiment, the storage unit 62 stores a distribution map DB20 and an upload information DB27 that accumulates upload information Iu received from each in-vehicle device 1. The distribution map DB20 includes object recommendation information generated by the control unit 65 with reference to the upload information DB27.

[0030] The control unit 65 includes a CPU that executes programs and controls the entire server device 6. In this embodiment, the control unit 65 performs processes such as accumulating the upload information Iu received from each in-vehicle device 1 by the communication unit 61 in the upload information DB27, generating object recommendation information based on the upload information DB27, and transmitting map update information such as the generated object recommendation information to each in-vehicle device 1 by the communication unit 61.

[0031] (1-2) Position Estimation Based on the Extended Kalman Filter FIG. 3 is a diagram showing the position of the host vehicle to be estimated in two-dimensional orthogonal coordinates. As shown in FIG. 3, the position of the host vehicle on a plane defined in the two-dimensional orthogonal coordinates of xy is represented by the coordinates "(x, y)" and the azimuth (yaw angle) "ψ" of the host vehicle. Here, the yaw angle ψ is defined as the angle formed by the traveling direction of the vehicle and the x-axis. In this embodiment, in addition to the above-mentioned coordinates (x, y) and yaw angle ψ, the position of the host vehicle is estimated using four variables (x, y, z, ψ) that take into account the coordinates of the z-axis perpendicular to the x-axis and y-axis as state variables of the host vehicle position. Since general roads have a gentle gradient, the pitch angle and roll angle of the vehicle are generally ignored in this embodiment.

[0032] FIG. 4 is a diagram showing a schematic relationship between a prediction step and a measurement update step. FIG. 5 shows an example of the own vehicle position estimation unit 17 which is a functional block of the control unit 15. As shown in FIG. 4, by repeating the prediction step and the measurement update step, the calculation and update of the estimated value of the state variable vector "X" indicating the own vehicle position are sequentially executed. Further, as shown in FIG. 5, the own vehicle position estimation unit 17 includes a position prediction unit 21 that executes the prediction step and a position estimation unit 22 that executes the measurement update step. The position prediction unit 21 includes a dead reckoning block 23 and a position prediction block 24, and the position estimation unit 22 includes a landmark search / extraction block 25 and a position correction block 26. In FIG. 4, the state variable vector at the reference time (i.e., the current time) "k" to be calculated is denoted as "X - (k)" or "X ^ (k)". Here, a tilde " - " is attached above the character representing the predicted value, which is the provisional estimated value (predicted value) estimated in the prediction step, and a caret " ^ " is attached above the character representing the value, which is the more accurate estimated value updated in the measurement update step.

[0033] In the prediction step, the dead reckoning block 23 of the control unit 15 uses the moving speed "v" and the angular velocity "ω" of the vehicle (collectively denoted as "control value u(k)=(v(k), ω(k)) T ") to obtain the moving distance and the azimuth change from the previous time. The position prediction block 24 of the control unit 15 adds the obtained moving distance and azimuth change to the state variable vector X ^ (k - 1) calculated in the immediately preceding measurement update step to calculate the predicted value of the own vehicle position at time k (also referred to as "predicted position") X - (k). At the same time, the covariance matrix "P - (k)" corresponding to the error distribution of the predicted position X - (k) is calculated from the covariance matrix "P ^ (k - 1)" at time k - 1 calculated in the immediately preceding measurement update step.

[0034] In the measurement update step, the landmark search and extraction block 25 of the control unit 15 associates the position vector of the landmark registered in the map DB 10 with the scan data of the lidar 2. Then, when this association is successful, the landmark search and extraction block 25 of the control unit 15 uses the measurement value "Z(k)" of the lidar 2 for the associated landmark, the predicted position X - (k), and the position vector of the landmark registered in the map DB 10 to model the measurement process of the lidar 2 and obtains the measurement value of the landmark (referred to as the "measurement prediction value") "Z - (k)". The measurement value Z(k) is a vector value in the vehicle coordinate system (also referred to as the "vehicle coordinate system") obtained by converting the distance and scan angle of the landmark measured by the lidar 2 at time k into components with the vehicle's traveling direction and lateral direction as axes. Then, the position correction block 26 of the control unit 15 multiplies the difference value between the measurement value Z(k) and the measurement prediction value Z - (k) by the Kalman gain "K(k)", and adds this to the predicted position X - (k) to calculate the updated state variable vector (also referred to as the "estimated position") X ^ (k).

[0035]

Equation

[0036] In this way, the prediction step and the measurement update step are repeatedly executed, and the predicted position X - (k) and the estimated position X ^(k) is calculated sequentially to calculate the most probable own vehicle position.

[0037] Here, whether the accuracy of position estimation has improved can be determined by the values of the diagonal elements of the covariance matrix P. Here, assuming that the covariance matrix calculated based on the measurement value for the landmark at time "k" is P(k), the covariance matrix P(k) is expressed by the following equation (2).

[0038]

Equation

[0039] Note that when the state variables x, y, z are in the global coordinate system adopted on the map, as shown in the following equation (3), the operation using the matrix "C ψ (k)" using the current estimated azimuth angle ψ is used to convert to the vehicle coordinate system (X, Y, Z).

[0040]

Equation

[0041] The matrix C ψ (k) is shown by the following equation (4).

[0042]

Equation

[0043] (1 - 3) Data Structure of Object Recommendation Information Next, the object recommendation information commonly included in the map DB10 and the distribution map DB20 will be described.)

[0044] Figure 6 is an example of the data structure of the object recommendation information. As shown in Figure 6, the object recommendation information is information in which an "object ID", a "position", and an "object recommendation value" are associated. The "object ID" is specified as an object ID, which is an identification number assigned to each object serving as a landmark. The object ID is an example of "identification information of an object". The "position" specifies the latitude, longitude, and altitude of the target landmark, respectively. In the "object recommendation value", the object recommendation value given to the target object is specified for each state variable of the vehicle position estimation (here, the traveling direction (x), lateral direction (y), height direction (z), and direction (ψ)). The object recommendation value is set to a value from 0 to 1, and the closer it is to 1, the higher the effectiveness in improving the estimation accuracy of the vehicle position estimation for the target state variable.)

[0045] In this way, in this embodiment, the map DB10 includes object recommendation information indicating the effectiveness (suitability) of position estimation for each object. Thereby, the in-vehicle device 1 can refer to the object recommendation information and identify an object for improving the vehicle position estimation accuracy. Note that the in-vehicle device 1 may transmit a predetermined request signal including the current position information to the server device 6 and receive download information Id including the object recommendation information regarding the objects around the vehicle position from the server device 6. In this case, the in-vehicle device 1 controls the vehicle so as to improve the vehicle position estimation accuracy based on the object recommendation information included in the received download information Id.)

[0046] Here, a specific example of vehicle control based on object recommendation information will be described.

[0047] For example, when the lateral accuracy of the current vehicle position estimation result of in-vehicle unit 1 is poor (i.e., σ y 2 (k) is high), an object existing within a predetermined distance from the current position is searched from the object recommendation information, and the movement route of the vehicle may be determined based on the position of the object having a high object recommendation value of the target state variable (here, the lateral direction) among the searched objects. In this case, for example, in-vehicle unit 1 moves the vehicle to a lane where the target object can be easily detected (for example, the lane closest to the target object). Further, in addition to or instead of the above-described vehicle control, when in-vehicle unit 1 performs vehicle position estimation using a plurality of objects, the measurement value of the object having a high object recommendation value of the target state variable may be weighted more and a Kalman filter or the like may be calculated. Further, when an object having a high object recommendation value of the target state variable does not exist around the current position, in-vehicle unit 1 may switch the position estimation method (for example, position estimation by dead reckoning or switching to the position estimation method of the second embodiment described later).

[0048] (1-4) Data Structure of Upload Information Next, a specific example of the data structure of the upload information Iu will be described.

[0049] FIG. 7 is a diagram showing an outline of the data structure of the upload information Iu transmitted by in-vehicle unit 1. As shown in FIG. 7, the upload information Iu includes header information, travel route information, event information, and media information.

[0050] The header information includes items such as "Version", "Sender", and "Vehicle Metadata". The in-vehicle unit 1 specifies the version information of the data structure of the upload information Iu used in "Version", and specifies the information of the company name (the OEM name of the vehicle or the system vendor name) that sends the upload information Iu in "Sender". Also, the in-vehicle unit 1 specifies the attribute information of the vehicle (such as vehicle type, vehicle ID, vehicle width, vehicle height, etc.) in "Vehicle Metadata". The driving route information includes the item of "Position Estimation". The in-vehicle unit 1 specifies in this "Position Estimation" not only the timestamp information indicating the position estimation time, but also the information of latitude, longitude, altitude indicating the estimated position of the vehicle, and the information regarding the estimation accuracy of these.

[0051] The event information includes the item of "Object Recognition Event". When the in-vehicle unit 1 detects an object recognition event, it specifies the information resulting from the detection in "Object Recognition Event". The media information is a data type used when transmitting raw data (detection information), which is the output data of an external sensor such as the lidar 2.

[0052] Figure 8 shows the data structure of the "Object Recognition Event" included in the event information. Figure 8 shows, for each element (sub-item) included in the "Object Recognition Event", whether the specification of the information corresponding to each element is mandatory or optional.

[0053] As shown in Figure 8, the "Object Recognition Event" includes elements such as "Timestamp", "Object ID", "Offset Position", "Object Type", "Object Size", "Object Size Accuracy", "Media ID", and "Valid Flag".

[0054] When the control unit 15 of the in-vehicle device 1 detects an object based on the output of an external sensor such as the rider 2, it generates event information of an "object recognition event" having the data structure shown in FIG. 8. Here, the in-vehicle device 1 designates the time at the time of object detection for the "timestamp", and designates the object ID of the detected object for the "object ID".

[0055] In addition, for the "offset position", the in-vehicle device 1 designates information on the relative position of the detected object from the vehicle (for example, latitude difference and longitude difference, etc.). For the "object type", the in-vehicle device 1 designates information indicating the type of the detected object. Further, when the in-vehicle device 1 can generate size information of the detected object and accuracy information of the size, it designates these information to the elements of "object size" and "object size accuracy". Also, when the in-vehicle device 1 needs to transmit raw data such as images, videos, and point cloud data output by the sensor unit 7, it designates the identification information given to the raw data to the "media ID". And, regarding the detailed information of the media (raw data) designated by the element of "media ID", it is separately stored in the item of "media information".

[0056] For the "valid flag", the in-vehicle device 1 designates a valid flag indicating the effectiveness of improving the accuracy of vehicle position estimation when performing vehicle position estimation using the target object, for each state variable estimated in vehicle position estimation. For example, the in-vehicle device 1 is the diagonal element of the covariance matrix P (also referred to as the "pre-estimation diagonal element") σ x 2 、σ y 2 、σ z 2 、σ ψ 2 And the diagonal elements of the covariance matrix P (also referred to as the "post-estimation diagonal elements") σ x 2 、σ y 2 、σ z 2 、σψ 2 Compare them for each state variable. Then, the in-vehicle device 1 sets the valid flag of the state variable whose post-estimation diagonal element is smaller than the pre-estimation diagonal element (i.e., the accuracy has improved) to "1", and sets the valid flag of the state variable whose post-estimation diagonal element is larger than the pre-estimation diagonal element (i.e., the accuracy has deteriorated) to "0".

[0057] Here, specific setting examples of the valid flag will be described with reference to FIGS. 9 to 12.

[0058] FIG. 9 is an overhead view showing the periphery of the vehicle equipped with the in-vehicle device 1. Further, FIG. 10 shows an example of the set value of the valid flag specified by the in-vehicle device 1 in the upload information Iu showing the detection results of the objects with object IDs "1", "2", and "3". Furthermore, FIG. 11 is a graph showing the transition of the diagonal element σ in a predetermined period including the execution periods "Tw1" to "Tw4" of the host vehicle position estimation based on the white line 51 of the object ID "1". y 2 FIG. 13 is a graph showing the transition of the diagonal element σ in a predetermined period including the execution period "Tw5" of the host vehicle position estimation based on the sign 52 of the object ID "2". x 2 is a graph showing the transition.

[0059] First, the in-vehicle device 1 refers to the position information, size information, etc. of the objects registered in the map DB10, and sets prediction windows "Wp1" to "Wp3" for determining the detection range of each object for the areas where it is estimated that the white line 51 of the object ID "1" serving as a landmark, the sign 52 of the object ID "2", and the sign 53 of the object ID "3" exist, as shown in FIG. 9.

[0060] Then, the in-vehicle device 1 detects the white line 51 of the object ID "1" within the prediction window Wp1, and performs host vehicle position estimation based on the white line 51. In this case, as shown in FIG. 11, at the end of each of the execution periods Tw1 to Tw4 of the host vehicle position estimation based on the white line 51, compared with the start period, the diagonal element σ y 2is decreasing. That is, after estimating the position of the host vehicle based on the white line 51, the position estimation accuracy in the lateral direction (y) is improving. Therefore, in this case, as shown in FIG. 10, the in-vehicle device 1 sets the valid flag in the lateral direction (y) to "1". On the other hand, for the other diagonal elements σ x 2 , σ z 2 , σ ψ 2 , if they are not decreasing before and after the execution periods Tw1 to Tw4, the valid flags in the traveling direction, height direction, and azimuth are set to "0". Note that the in-vehicle device 1 may set the valid flag for the target state variable to "1" when the decrease width of the diagonal element after estimation from the diagonal element before estimation for the target state variable is equal to or greater than a predetermined threshold, and set the valid flag for the target state variable to "0" when the above decrease width is less than the predetermined threshold. Then, the in-vehicle device 1 generates upload information Iu including the object ID of the white line 51 and the set valid flag, and transmits it to the server device 6.

[0061] Also, the in-vehicle device 1 detects the sign 52 with the object ID "2" within the prediction window Wp2, and estimates the position of the host vehicle based on the sign 52. In this case, as shown in FIG. 12, at the end of the execution period Tw5 of the host vehicle position estimation based on the sign 52, the diagonal element σ x 2 is decreasing compared to the corresponding start period. That is, after estimating the position of the host vehicle based on the sign 52, the position estimation accuracy in the traveling direction (x) is improving. Therefore, in this case, as shown in FIG. 10, the in-vehicle device 1 sets the valid flag in the traveling direction (x) to "1". Similarly, for the diagonal element σ z 2 and the diagonal element σ ψ 2 , if they are decreasing before and after the execution period Tw5, the valid flags in the height direction and azimuth are set to "1". On the other hand, for the diagonal element σ y 2Regarding [[ID=]], if it has not decreased before and after the execution period Tw5, set the horizontal valid flag to "0". Then, the in-vehicle device 1 generates upload information Iu including the object ID of the sign 52 and the set valid flag, and transmits it to the server device 6.

[0062] On the other hand, regarding the sign 53 with the object ID "3", occlusion has occurred due to the obstacles 54 and 55 and it has not been detected within the prediction window Wp3. In this case, the in-vehicle device 1 sets the valid flag of each state variable of the object ID "3" to "0". Then, the in-vehicle device 1 generates upload information Iu including the object ID of the sign 53 and the set valid flag, and transmits it to the server device 6.

[0063] (1-5) Calculation of Object Recommendation Value Next, the method for calculating the object recommendation value for each object will be described. The server device 6 calculates the object recommendation value for each object and for each state variable based on the valid flag included in the upload information Iu received from each in-vehicle device 1. Award The server device 6 calculates the object recommendation value for each object and for each state variable based on the valid flag included in the upload information Iu received from each in-vehicle device 1. Award value.

[0064] For example, if the server device 6 sets the total count (number of samples) of the valid flag information for each state variable of each object ID as "S1" and the sum of the values (0 or 1) of the valid flag for each state variable of each object ID as "S2", then the object recommendation value for each state variable of each object ID is set to "S2 / S1". For example, if the upload information Iu including the valid flag for the traveling direction of each object ID "1" is received 100 times from each in-vehicle device 1 and the sum of these valid flags is 70, then the in-vehicle device 1 sets the object recommendation value for the traveling direction of the object ID "1" to "0.7" (=70 / 100). The object recommendation values for the horizontal direction, height direction, and azimuth can be calculated in the same way.

[0065] By doing so, the server device 6 can be suitably set so that the object recommendation value for each state variable of each object ID is in the value range from 0 to 1. Also, in this case, the object recommendation value of an object not detected due to occlusion, rainfall, snowfall, etc. becomes small, and the object recommendation value of an object that has been detected but is judged to be ineffective for position estimation also becomes small. On the other hand, the object recommendation value of an object for which the ratio judged to be effective for position estimation is high becomes high.

[0066] Preferably, the server device 6 may calculate the object recommendation value using the valid flag of the upload information Iu received for a predetermined past time (for example, 10 minutes). Thereby, the server device 6 can accurately set or update the object recommendation value based on the latest valid flag collected.

[0067] Also, the larger the traffic volume of the road where the target object can be detected, the more upload information Iu including the valid flag can be collected in a short time. Therefore, the server device 6 may set the predetermined time according to the traffic volume of the road. For example, the server device 6 may set the above-mentioned predetermined time to 10 minutes for an object that can be detected on a road with a large traffic volume, and set the above-mentioned predetermined time to 1 hour for an object that can be detected on a road with a small traffic volume. In another example, the server device 6 may calculate the object recommendation value of the target object based on the valid flags included in the latest predetermined number of upload information Iu acquired in the past for the target object. In this case, since the value S1 is the above-mentioned predetermined number, the in-vehicle device 1 can suitably calculate the object recommendation value based on a certain number of samples.

[0068] (1-6) Processing Flow FIG. 13 is an example of a flowchart showing an outline of processing related to transmission and reception of upload information Iu including a valid flag and download information Id including object recommendation information.

[0069] First, when the in-vehicle unit 1 refers to the map DB10 and there is an object serving as a landmark, it sets a prediction window for detecting the object (step S101). Then, the in-vehicle unit 1 determines whether it has detected the target object (step S102). When the in-vehicle unit 1 has detected the target object (step S102; Yes), it determines whether there is an improvement in the accuracy of position estimation before and after the self-vehicle position estimation based on the object for each state variable, and sets a valid flag for each state variable (step S103). On the other hand, when the in-vehicle unit 1 fails to detect the target object (step S102; No), it sets the valid flag of each state variable for the object to 0 (step S104). Then, the in-vehicle unit 1 transmits upload information Iu including the object ID and the valid flag of the target object to the server device 6 (step S105).

[0070] The server device 6 receives the upload information Iu transmitted in step S105 and accumulates the upload information Iu in the upload information DB27 (step S201). Then, the server device 6 determines whether it is the update timing of the distribution map DB20 (step S202). The above update timing may be determined based on the time duration since the previous update of the distribution map DB20, or may be determined based on the cumulative reception count of the upload information Iu received since the previous update of the distribution map DB20.

[0071] Then, when it is the update timing of the distribution map DB20 (step S202; Yes), the server device 6 refers to the upload information DB27 to generate object recommendation information and the like, and updates the distribution map DB20 using the generated object recommendation information and the like (step S203). Then, the server device 6 transmits the download information Id including the object recommendation information and the like generated in step S203 to each in-vehicle device 1 (step S204). Note that the server device 6 may transmit the download information Id only to the in-vehicle device 1 that has made a transmission request for the download information Id. On the other hand, when it is not the update timing of the distribution map DB20 (step S202; No), the server device 6 continues to execute step S201.

[0072] When the in-vehicle device 1 receives the download information Id (step S106; Yes), it updates the map DB10 using the download information Id (step S107). As a result, the latest object recommendation information is recorded in the map DB10. On the other hand, when the in-vehicle device 1 has not received the download information Id from the server device 6 (step S106; No), the process returns to step S101.

[0073] <Second Embodiment> In the driving support system according to the second embodiment, voxel data in which position information of stationary structures and the like is recorded for each unit region (also referred to as a "voxel") when the three-dimensional space is divided into a plurality of regions is recorded in the map DB10 and the distribution map DB20, and the in-vehicle device 1 estimates its own vehicle position using the voxel data. In this case, instead of the object recommendation information, the map DB10 and the distribution map DB20 include information (also referred to as "voxel recommendation information") in which a recommended value for use in position estimation is shown for each voxel. Hereinafter, the same reference numerals are appropriately given to the same components as those in the driving support system of the first embodiment, and the description thereof is omitted.

[0074] (2-1) Position Estimation Based on Voxel Data The voxel data includes data representing the measured point cloud data of static structures in each voxel by a normal distribution, and is used for scan matching using NDT (Normal Distributions Transform).

[0075] FIG. 14 shows an example of the host vehicle position estimation unit 17 in position estimation based on voxel data. The difference from the host vehicle position estimation unit 17 in position estimation based on the extended Kalman filter shown in FIG. 5 is that, instead of the landmark search / extraction unit 25, a point cloud data association block 27 is provided as a process of associating the point cloud data obtained from the lidar 2 with the voxels acquired from the map DB.

[0076] FIG. 15 shows an example of a schematic data structure of voxel data. The voxel data includes information on parameters when expressing the point cloud in a voxel by a normal distribution. In this embodiment, as shown in FIG. 15, it includes a voxel ID, voxel coordinates, a mean vector, and a covariance matrix. Here, the "voxel coordinates" indicate the absolute three-dimensional coordinates of a reference position such as the center position of each voxel. Each voxel is a cube obtained by dividing the space into a grid, and since its shape and size are determined in advance, it is possible to specify the space of each voxel by the voxel coordinates. The voxel coordinates may be used as the voxel ID. The voxel ID is an example of "identification information of an object".

[0077] The "mean vector" and "covariance matrix" indicate the mean vector and covariance matrix corresponding to the parameters when expressing the point cloud in the target voxel by a normal distribution. Defining the coordinates of an arbitrary point "i" in an arbitrary voxel "n" as X n (i)=[x n (i), y n (i), z n (i)] T and setting the number of point clouds in voxel n as "N n ", the mean vector "μ n " and covariance matrix "V n " in voxel n are represented by the following equations (5) and (6), respectively.

[0078] [Number]

[0079] [Number] Scan matching by NDT assuming a vehicle estimates the estimation parameter P = [t x , t y , t z , t ψ T Here, "t x " indicates the movement amount in the x direction, "t y " indicates the movement amount in the y direction, "t z " indicates the movement amount in the z direction, and "t ψ " indicates the yaw angle. Note that although the pitch angle and roll angle are caused by road gradients and vibrations, they are negligibly small.

[0080] Also, for the point cloud data obtained by the lidar 2, association with the voxel to be matched is performed, and the coordinates of an arbitrary point at the corresponding voxel n are X L (i) = [x n (i), y n (i), z n (i)] T Then, the average value "L´ L " of X n (i) at the voxel n is represented by the following equation (7).

[0081] [Number] And when the average value L´ is subjected to coordinate transformation using the above-mentioned estimation parameter P, the transformed coordinate "L n " is represented by the following equation (8).

[0082] [Number] ​ Then, in this embodiment, the in-vehicle device 1 uses the point cloud after coordinate conversion, the average vector μ n and the covariance matrix V n to calculate the evaluation function value "E n " of the voxel n shown by the following formula (9) and the comprehensive evaluation function value "E(k)" (also referred to as the "comprehensive evaluation function value") for all voxels to be matched shown by the formula (10).

[0083]

Equation

[0084]

Equation

[0085]

Equation

[0086] (2-2) Data Structure Next, the voxel recommendation information commonly included in the map DB 10 and the distribution map DB 20 will be described.

[0087] FIG. 16 shows an example of the data structure of voxel recommendation information. As shown in FIG. 16, the voxel recommendation information is information in which a "voxel ID", a "position", and a "voxel recommendation value" are associated. The "voxel ID" specifies the voxel ID assigned to each voxel. The "position" specifies the voxel coordinates (latitude, longitude, and altitude, or xyz coordinates from a reference point) of the target voxel, respectively. The "voxel recommendation value" specifies a voxel recommendation value that is a recommendation value for using the target voxel for position estimation. Here, the voxel recommendation value is set to a value from 0 to 1, and the closer it is to 1, the higher the effectiveness for improving the position estimation accuracy.

[0088] Thus, in this embodiment, the map DB 10 includes voxel recommendation information indicating the effectiveness (suitability) of position estimation for each voxel. Thereby, in the same manner as when using the object recommendation information of the first embodiment, the in-vehicle device 1 can control the vehicle to improve the own vehicle position estimation accuracy by referring to the voxel recommendation information. For example, when the accuracy of the current own vehicle position estimation is poor (that is, the comprehensive evaluation function value E(k) is low), the in-vehicle device 1 moves the vehicle to a lane where it is easy to detect voxels with a high voxel recommendation value, or increases the weight of voxels with a high voxel recommendation value in the NDT matching. Further, when there are no voxels with a high voxel recommendation value in the vicinity, the in-vehicle device 1 may switch the position estimation method.

[0089] Note that the in-vehicle device 1 may transmit a predetermined request signal including the current position information to the server device 6 and receive download information Id including voxel recommendation information regarding voxels around the own vehicle position from the server device 6. In this case, the in-vehicle device 1 controls the vehicle to improve the own vehicle position estimation accuracy based on the received download information Id.

[0090] Also, in the second embodiment, instead of the valid flag, the in-vehicle device 1 determines a value indicating the effectiveness of the target voxel for improving the own vehicle position estimation accuracy (also referred to as the "effective value"). Hereinafter, the in-vehicle device 1 uses the individual evaluation function value E of the target voxel. nSet it as the above effective value. Then, the in-vehicle device 1 transmits, as the upload information Iu, the upload information Iu including at least the information associating the effective value for each voxel ID to the server device 6. The effective value is an example of "effective information".

[0091] Here, the individual evaluation function value E n approaches 1 as the matching degree is high and approaches 0 as the matching degree is low. And the individual evaluation function value E n The larger the voxel with the larger value, the more it contributes to increasing the comprehensive evaluation function value E(k), so it can be said that the effectiveness is high. Therefore, the individual evaluation function value E n of each voxel is suitable as the effective value of each voxel.

[0092] Here, a specific setting example of the effective value will be described with reference to FIGS. 17 to 20.

[0093] FIG. 17 is an overhead view showing the periphery of the vehicle equipped with the in-vehicle device 1. Here, voxels with voxel IDs "1" to "35" exist within a predetermined distance from the vehicle. Note that the voxels with voxel IDs "1" to "35" are located on the surfaces of the objects 56 to 58. FIG. 18 shows a setting example of the effective value specified by the in-vehicle device 1 in the upload information Iu showing the detection results of the voxel IDs "1" to "35". Further, FIG. 19 is a graph showing the transition of the individual evaluation function value E 4 for the voxel ID "4" in a predetermined period including the detection period "Tw6" of the voxel ID "4", and FIG. 20 is a graph showing the transition of the individual evaluation function value E 12 for the voxel ID "12" in a predetermined period including the detection period "Tw7" of the voxel ID "12".

[0094] First, the in-vehicle unit 1 acquires voxel data with voxel IDs "1" to "35" existing within a predetermined distance from the vehicle from the map DB 10, and performs measurement by the lidar 2. As a result, the in-vehicle unit 1 detects voxels with voxel IDs "4" to "11" located on the surface of the object 56 and voxels with voxel IDs "12" to "19" located on the surface of the object 57 at the same or different timings, and estimates the position of the host vehicle by NDT matching. Then, the in-vehicle unit 1 sets the individual evaluation function value E of each voxel calculated in the host vehicle position estimation by NDT matching as the valid value of the corresponding voxel ID. n to be set as the valid value of the corresponding voxel ID.

[0095] At this time, preferably, the in-vehicle unit 1 sets the valid value corresponding to each voxel ID to the average value of the individual evaluation function values E calculated during the period when the voxels of each voxel ID are detected. For example, in the case of voxel ID "4", as shown in FIG. 19, the in-vehicle unit 1 sets the average value of the individual evaluation function values E calculated during the detection period Tw6 as the valid value for voxel ID "4". Similarly, in the case of voxel ID "12", as shown in FIG. 20, the in-vehicle unit 1 sets the average value of the individual evaluation function values E calculated during the detection period Tw7 as the valid value for voxel ID "12". Note that the above detection period may include all the times when the target voxels are detected, or may include only the times when the target voxels are detected within a predetermined distance range. n For example, in the case of voxel ID "4", as shown in FIG. 19, the in-vehicle unit 1 sets the average value of the individual evaluation function values E calculated during the detection period Tw6 as the valid value for voxel ID "4". 4 Similarly, in the case of voxel ID "12", as shown in FIG. 20, the in-vehicle unit 1 sets the average value of the individual evaluation function values E calculated during the detection period Tw7 as the valid value for voxel ID "12". 12 Note that the above detection period may include all the times when the target voxels are detected, or may include only the times when the target voxels are detected within a predetermined distance range.

[0096] On the other hand, for the voxels with voxel IDs "22" to "31" located on the surface of the object 58 corresponding to the building where the curing sheet is stretched for the outer wall repair, the in-vehicle unit 1 cannot detect them because the measured values are shifted due to the presence of the above-mentioned curing sheet. Therefore, in this case, the in-vehicle unit 1 sets the valid values corresponding to the voxel IDs "22" to "31" to 0. Then, the in-vehicle unit 1 generates upload information Iu showing the combination of the voxel ID and the valid value shown in FIG. 18, for example, and transmits it to the server device 6.

[0097] (2-3)Calculation of Voxel Recommendation Value Next, a method for calculating the voxel recommendation value for each voxel will be described. The server device 6 calculates the voxel recommendation value for each voxel ID based on the valid value for each voxel ID included in the upload information Iu received from each in-vehicle device 1. Award Award

[0098]

[0099] For example, if the server device 6 sets the total count (number of samples) of the valid value information for each voxel ID as "S3" and the sum of the valid values for each voxel ID as "S4", the voxel recommendation value for each voxel ID is set to "S4 / S3". For example, if the upload information Iu including the valid value of each voxel ID "1" is received 100 times from each in-vehicle device 1 and the sum of these valid values is 70.0, the in-vehicle device 1 sets the voxel recommendation value for the voxel ID "1" to "0.7" (=70.0 / 100).

[0099] By doing so, the server device 6 can preferably set the voxel recommendation value for each voxel ID to be in the value range from 0 to 1. Also, in this case, the voxel recommendation value of voxels not detected due to occlusion, rainfall, snowfall, etc. becomes small, and even for detected voxels, the voxel recommendation value of voxels with a statistically low individual evaluation function value E (in other words, not effective for position estimation) also becomes small. On the other hand, the voxel recommendation value of voxels with a statistically high individual evaluation function value E (in other words, effective for position estimation) becomes high. n n n n

[0100] Preferably, the server device 6 may calculate the voxel recommended value using the valid value of the upload information Iu received for a predetermined past time period (for example, 10 minutes). More preferably, the server device 6 may set the predetermined time shorter as the traffic volume of the road where the target voxel can be detected is larger. In another example, the server device 6 may calculate the voxel recommended value of the target voxel based on the valid values included in the latest predetermined number of upload information Iu acquired in the past for the target voxel. In this case, since the value S3 is the above-mentioned predetermined number of minutes, the in-vehicle device 1 can preferably calculate the voxel recommended value with a certain number of samples.

[0101] (2-4) Processing Flow FIG. 21 is an example of a flowchart showing an outline of processing related to transmission and reception of upload information Iu including valid values and download information Id including voxel recommended information.

[0102] First, the in-vehicle device 1 refers to the map DB10 and acquires voxel data of voxels existing at positions detectable by the lidar 2 (step S111). Then, the in-vehicle device 1 sets a valid value for each voxel ID based on the presence or absence of detection of each voxel for which voxel data was acquired in step S111 by the lidar 2 and the individual evaluation function value E n for each voxel. In this case, the in-vehicle device 1 sets the valid value for the voxel ID of a voxel for which point cloud data could not be acquired by the lidar 2 to 0, and sets the valid value for the voxel ID of a voxel for which point cloud data could be acquired by the lidar 2 to the individual evaluation function value E n for the voxel. Then, the in-vehicle device 1 transmits the upload information Iu in which the valid value is associated with each voxel ID to the server device 6 (step S113).

[0103] The server device 6 receives the upload information Iu transmitted in step S113 and stores the upload information Iu in the upload information DB 27 (step S211). Then, when it is the update timing of the distribution map DB 20 (step S212; Yes), the server device 6 refers to the upload information DB 27 to generate voxel recommendation information and the like, and updates the distribution map DB 20 using the generated voxel recommendation information and the like (step S213). Then, the server device 6 transmits the download information Id including the voxel recommendation information and the like generated in step S213 to each in-vehicle device 1 (step S214). Note that the server device 6 may transmit the download information Id only to the in-vehicle device 1 that has requested the transmission of the download information Id. On the other hand, when it is not the update timing of the distribution map DB 20 (step S212; No), the server device 6 continues to execute step S211.

[0104] When the in-vehicle device 1 receives the download information Id (step S114; Yes), the in-vehicle device 1 updates the map DB 10 using the download information Id (step S115). Thereby, the latest voxel recommendation information is recorded in the map DB 10. On the other hand, when the in-vehicle device 1 has not received the download information Id from the server device 6 (step S114; No), the process returns to step S111.

[0105] <Modification Example> Hereinafter, modification examples suitable for the first and second embodiments will be described. The following modification examples may be applied to these embodiments in combination.

[0106] (Modification Example 1) Instead of the in-vehicle device 1 determining the vehicle route (target trajectory) by referring to the map DB 10 including the object recommendation information or the voxel recommendation information, the server device 6 that has received the route search request from the in-vehicle device 1 may refer to the distribution map DB 20 including the object recommendation information or the voxel recommendation information to determine the vehicle route (target trajectory) of the vehicle of the in-vehicle device 1 that is the request source. In this way, the object recommendation information and the voxel recommendation information are also preferably used by the server device 6.

[0107] (Modification 2) The configuration of the driving support system shown in FIG. 1 is an example, and the configuration of the driving support system to which the present invention is applicable is not limited to the configuration shown in FIG. 1. For example, instead of having the in-vehicle device 1, the electronic control unit of the vehicle may execute the processing of the own vehicle position estimation unit 17 and the upload control unit 18 of the in-vehicle device 1. In this case, the map DB 10 is stored, for example, in a storage unit in the vehicle, and the electronic control unit of the vehicle may exchange the upload information Iu and the download information Id with the server device 6 via the in-vehicle device 1 or via a communication unit (not shown).

Explanation of Reference Numerals

[0108] 1 In-vehicle device 2 LiDAR 3 Gyro sensor 4 Vehicle speed sensor 5 GPS receiver 6 Server device 10 Map DB 20 Distribution map DB

Claims

1. A detection unit that detects objects around the moving object; A first acquisition unit that acquires an estimated position of the moving object; a second acquisition unit that acquires map information including position information of objects around the estimated position and recommended value information indicating a recommended value for performing the position estimation of the moving body; a position estimation unit that estimates a position of the moving body based on a detection result of the object detected by the detection unit, the estimated position, and position information of the object included in the map information; Equipped with The information processing device, wherein the position estimation unit estimates a position of the moving object by performing a weighting calculation based on the recommendation value information.

2. the recommendation value information has a recommendation value for each direction in estimating a position of the moving object, The information processing apparatus according to claim 1 , wherein the position estimation unit estimates the position of the moving object by performing a weighting calculation for each direction with the moving object as a reference, based on the recommendation value information for each direction.

3. The recommendation value information further includes a recommendation value of a direction in the position estimation of the moving object, The information processing apparatus according to claim 2 , wherein the position estimation unit estimates the position of the moving body by performing a weighting calculation of the direction based on the recommended value information of the direction, with the moving body as a reference.

4. the map information includes, for each unit area, position information of an object and the recommendation value information; The information processing apparatus according to claim 1 , wherein the position estimation unit estimates the position of the moving object by performing a weighting calculation based on the recommendation value information for each unit area.

5. An information processing device having a memory unit that stores map data including position information of an object and information indicating a recommended value for estimating the position of a moving body using the positional relationship with the object measured by a measuring device mounted on the moving body, the recommended value information being used in a weighting calculation for the position estimation.

6. A map data generation device having a generation unit that generates map data by associating recommended value information used in a weighting calculation for the position estimation, the recommended value information being generated based on identification information of the object and effectiveness information regarding the effectiveness of improving the accuracy of the position estimation of the moving body using the object, with the object's position information.

7. 1. A computer-implemented method comprising: A detection step of detecting an object around the moving body; a first acquisition step of acquiring an estimated position of the moving object; a second acquisition step of acquiring map information including position information of objects around the estimated position and recommended value information indicating a recommended value for performing the position estimation of the moving body; a position estimation step of estimating a position of the moving body based on a detection result of the object detected by the detection step, the estimated position, and position information of the object included in the map information; having The method according to claim 1, wherein the position estimating step estimates the position of the moving object by a weighting calculation based on the recommendation value information.

8. A detection unit that detects objects around the moving object; A first acquisition unit that acquires an estimated position of the moving object; a second acquisition unit that acquires map information including position information of objects around the estimated position and recommended value information indicating a recommended value for performing the position estimation of the moving body; a position estimation unit that estimates a position of the moving body based on a detection result of the object detected by the detection unit, the estimated position, and position information of the object included in the map information; The computer functions as The position estimation unit estimates a position of the moving object by performing a weighting calculation based on the recommendation value information.

Images