Method for generating feature point

The method generates feature points at intersections and curves by extracting straight line components and tangents from travel trajectories, improving map matching accuracy for navigation and autonomous driving.

JP2024164218AInactive Publication Date: 2024-11-26PIONEER IP
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2024145725
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing map data updating technologies fail to generate feature points for intersections and turns in complex driving environments, such as parking lots, which are crucial for navigation and autonomous driving.

Method used

A method and device that generate feature points by extracting straight line components from travel trajectories, determining intersections or tangents, and integrating these points to create nodes suitable for navigation and autonomous driving.

Benefits of technology

Accurately generates feature points at intersections and curves, enhancing map matching accuracy for navigation and autonomous driving systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024164218000001_ABST
    Figure 2024164218000001_ABST
Patent Text Reader

Abstract

To generate a feature point to be a candidate of a node of a travelling road on the basis of the trace of travelling of a mobile body.SOLUTION: A server acquires a travel trace from an in-vehicle machine via a network. The server extracts a straight liner component from the travel trace, determines the intersection between the extension of the extracted straight linear component and the extension of another straight linear component adjacent to the straight linear composition in the travel trace, and generates the intersection as a feature point if the travel trace passes within a predetermined range from the intersection.SELECTED DRAWING: Figure 3
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a feature point generating method. [Background technology]

[0002] When a vehicle travels on a new road that does not exist on a map represented by existing map data, such as a newly opened road, a technology is known that infers the shape of the new road from the vehicle's position information and driving direction and updates the map data (Patent Document 1).

[0003] When using the above technology for roads with many intersections and corners, such as roads in a parking lot, it is essential to use map data for navigation and automated driving to generate not only the shape but also feature points for identifying the intersections, corners, etc. However, one example of the problem with the technology in Patent Document 1 is that it only estimates the shape of a new road and does not generate new feature points. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2014-235510 A Summary of the Invention [Problem to be solved by the invention]

[0005] The present invention has as its object to address such problems. That is, the present invention has an object to provide, for example, a feature point generating method, a feature point generating device, and a feature point generating program that can generate feature points of a road, and a recording medium having the feature point generating program recorded thereon. [Means for solving the problem]

[0006] The feature point generation method described in claim 1, which has been made to solve the above-mentioned problems, is a feature point generation method that generates feature points that are candidates for nodes of a road based on a traveling trajectory of a moving body, and is characterized in that it includes an acquisition step of acquiring the traveling trajectory, an extraction step of extracting a straight line component from the traveling trajectory, and a first generation step of generating, as the feature point, an intersection of an extension line of the extracted straight line component and an extension line of another straight line component adjacent to the straight line component in the traveling trajectory.

[0007] Moreover, the feature point generation device described in claim 5 is a feature point generation device that generates feature points that are candidates for nodes of a road based on a travel trajectory of a moving body, and is characterized in including: an acquisition unit that acquires the travel trajectory; an extraction unit that extracts a straight line component from the travel trajectory; and a first generation unit that generates, as the feature point, an intersection of an extension line of the extracted straight line component and an extension line of another straight line component adjacent to the straight line component in the travel trajectory.

[0008] Furthermore, a feature point generation program described in claim 6 is a feature point generation program that causes a computer to generate feature points that are candidates for nodes of a road based on a travel trajectory of a moving object, and is characterized in that the computer is made to function as an acquisition unit that acquires the travel trajectory, an extraction unit that extracts straight line components from the travel trajectory, and a first generation unit that generates, as the feature point, an intersection between an extension line of the extracted straight line component and an extension line of another straight line component adjacent to the straight line component in the travel trajectory.

[0009] A recording medium according to a seventh aspect of the present invention is characterized in that the feature point generating program according to the seventh aspect of the present invention is recorded thereon. [Brief description of the drawings]

[0010] [Figure 1] 1 shows a system configuration using a feature point generating device and a link information generating device according to an embodiment of the present invention. [Diagram 2] 2 is a flowchart of an operation relating to feature point generation by the feature point generation device shown in FIG. 1. [Diagram 3]FIG. 11 is an explanatory diagram showing a specific example of generating feature points. [Figure 4] FIG. 11 is an explanatory diagram showing a specific example of generating feature points. [Diagram 5] FIG. 11 is an explanatory diagram showing a specific example of generating feature points. [Figure 6] FIG. 13 is an explanatory diagram showing a modified example of feature point generation. [Figure 7] FIG. 11 is an explanatory diagram showing a specific example of feature point integration. [Figure 8] 2 is a flowchart of an operation of the feature point generating device shown in FIG. [Figure 9] (A) shows the integration results when there are few driving trajectories, and (B) shows the integration results when there are many driving trajectories. [Figure 10] FIG. 11 is an explanatory diagram showing a specific example of link information generation. [Figure 11] FIG. 11 is an explanatory diagram showing a specific example of link information generation. [Figure 12] 2 is a flowchart of an operation of the link information generating device shown in FIG. [Figure 13] FIG. 11 is an explanatory diagram showing a specific example of link information generation. [Figure 14] FIG. 11 is an explanatory diagram showing a specific example of link information generation. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] A feature point generating method according to one embodiment of the present invention is a method for generating feature points that are candidates for nodes of a road based on a travel trajectory of a moving object, and is characterized by including an acquisition step of acquiring the travel trajectory, an extraction step of extracting a straight line component from the travel trajectory, and a first generation step of generating an intersection of an extension line of the extracted straight line component and an extension line of another straight line component adjacent to the straight line component in the travel trajectory as the feature point. This makes it possible to generate feature points of a road suitable for use in navigation and automatic driving.

[0012] The method may further include a second generation step of generating, as the feature points, an intersection point between a tangent on the travel trajectory from a point deviating from the straight line component to the other straight line component and an extension of the straight line component, and an intersection point between the tangent and an extension of the other straight line component, when the travel trajectory does not exist within a predetermined range centered on the intersection point, or when the intersection point does not exist, as the feature points. This makes it possible to generate feature points that are even more suitable for use in navigation and automatic driving.

[0013] The tangent may also be a tangent at the center of the locus.

[0014] The method may further include a third generation step of generating points where the change in the inclination angle of the travel trajectory is equal to or greater than a predetermined angle as the feature points. This makes it possible to generate feature points that are more suitable for use in navigation and automated driving.

[0015] A feature point generating device according to an embodiment of the present invention is a feature point generating device that generates feature points that are candidates for nodes of a road based on a travel trajectory of a moving object, and is characterized by including an acquisition unit that acquires the travel trajectory, an extraction unit that extracts straight line components from the travel trajectory, and a first generation unit that generates, as the feature point, an intersection between an extension line of the extracted straight line component and an extension line of another straight line component adjacent to the straight line component in the travel trajectory. This makes it possible to generate feature points for new roads.

[0016] The above-described feature point generation method may be implemented as a feature point generation program executed by a computer. Since the program is executed by a computer in this manner, dedicated hardware or the like is not required, and the program can be installed in a general-purpose information processing device to function.

[0017] The feature point generation program may be stored in a computer-readable recording medium. In this way, the program can be distributed as a standalone program in addition to being incorporated into a device, and version upgrades can be easily performed. EXAMPLES

[0018] A feature point generating device and a link information generating device of the present invention will be described with reference to Fig. 1 to Fig. 14. A server 10 serving as a feature point generating device and a link information generating device according to an embodiment of the present invention includes a communication unit 11, a feature point generating unit 12, a link information generating unit 13, and a storage unit 14.

[0019] The communication unit 11 communicates with the vehicle-mounted device 20 (described later) via a network N such as the Internet. The communication unit 11 receives, for example, the position information (latitude, longitude), traveling direction, tilt angle, and other travel trajectory of the vehicle (mobile body) acquired by the vehicle-mounted device 20. Furthermore, when the vehicle-mounted device 20 is a device that requires map data, such as a navigation device, the communication unit 11 transmits map data stored in a storage unit 14 (described later) in response to a request from the vehicle-mounted device 20.

[0020] The feature point generating unit 12 generates feature points that are candidates for nodes on the road based on the travel trajectory received from the communication unit 11.

[0021] The link information generating unit 13 generates links that connect the feature points generated by the feature point generating unit 12 with each other.

[0022] The storage unit 14 stores the feature points generated by the feature point generation unit 12 and the links generated by the link information generation unit 13. The storage unit 14 also accumulates and stores the travel trajectories received from the multiple vehicle-mounted devices 20. The storage unit 14 also stores existing map data in which the vehicle's travel route is indicated by nodes, links, etc.

[0023] In the above description, the feature point generating unit 12 and the link information generating unit 13 are implemented by a calculation device such as a CPU (Central Processing Unit) of the server 10. The storage unit 14 functions as a network interface of the server 10. The storage unit 14 functions as a storage medium such as a hard disk of the server 10. Therefore, the flowcharts of Fig. 2, 8 and 12, which will be described later and are executed by the feature point generation unit 12 and the link information generation unit 13, can be configured as a computer program executed by a CPU to provide a feature point generation program and a link information generation program. Furthermore, the feature point generation unit 12 and the link information generation unit 13 execute the flowcharts shown in Fig. 2, 8 and 12, so that the server 10 implements the feature point generation method and the link information generation method of the present invention.

[0024] The vehicle-mounted device 20 is mounted on a vehicle and collects and transmits a travel trajectory to the server 10. When the vehicle-mounted device 20 is configured as a navigation device, the vehicle-mounted device 20 requests generated map data from the server 10 as necessary.

[0025] The vehicle-mounted device 20 includes a communication unit 21, a control unit 22, and a vehicle information acquisition unit 23.

[0026] The communication unit 21 communicates with the server 10 via a network N such as the Internet. The communication unit 21 transmits a travel trajectory including the vehicle's position information (latitude, longitude), traveling direction, tilt angle, etc. acquired by the vehicle information acquisition unit 23. In this embodiment, the travel trajectory is composed of point cloud data representing positions (latitude, longitude) on the trajectory traveled by the vehicle, as shown in Fig. 3, for example, and the traveling direction, tilt angle, etc. at the positions are added to the points representing the positions.

[0027] In addition, when the vehicle-mounted device 20 is a device that requires map data, such as a navigation device, the communication unit 21 requests map data from the server 10 under control of the control unit 22, etc., and receives the map data transmitted from the server 10.

[0028] The control unit 22 is responsible for the overall control of the in-vehicle device 20. The control unit 22 causes the communication unit 21 to transmit to the server 10, as a travel trajectory, the vehicle position information (latitude, longitude), traveling direction, tilt angle, and the like, collected by the vehicle information acquisition unit 23.

[0029] The vehicle information acquisition unit 23 includes a GPS (Global Positioning System) receiver and a gyro sensor. Alternatively, it is connected to various sensors such as a vehicle speed pulse sensor and a receiver, etc. The vehicle information acquisition unit 23 collects information such as vehicle position information (latitude, longitude), traveling direction, and tilt angle from the above-mentioned sensors, etc.

[0030] The vehicle-mounted device 20 is not limited to a car navigation system installed on the instrument panel of the vehicle, but may be, for example, a portable device such as a smartphone. That is, the vehicle-mounted device 20 may be detachably installed inside the vehicle.

[0031] In the above description, the control unit 22 functions as a calculation device such as a CPU of the in-vehicle device 20. The communication unit 21 functions as a communication circuit, an antenna, and the like of the in-vehicle device 20. The vehicle information acquisition unit 23 functions as an interface circuit with various sensors, and the like.

[0032] Next, the operation of the server 10 and the vehicle-mounted device 20 configured as described above will be described. The vehicle-mounted device 20 transmits a travel trajectory to the server 10 at a predetermined timing, such as every fixed time or every time a fixed distance is traveled. The server 10 functions as an acquisition unit, and receives (acquires) the travel trajectory from the vehicle-mounted device 20 and stores it in the storage unit 14 in sequence.

[0033] The above-mentioned server 10 (its feature point generating unit 12) executes the feature point generating process shown in Fig. 2 at a predetermined timing, such as every time a travel trajectory is received or at regular intervals. The server 10 reads out one of the multiple travel trajectories stored in the storage unit 14 for which the feature point generating process has not been executed (step S1). Next, the server 10 uses a well-known map matching technique to determine whether the read travel trajectory is a travel trajectory that deviates from the travel route included in the map data (step S2).

[0034] When the server 10 determines that the travel path is a travel route included in the map data (N in step S2), the process ends.

[0035] On the other hand, when the server 10 determines that the travel locus deviates from the travel route included in the map data (Y in step S2), the process proceeds to steps S3 to S13, and generates feature points that are candidates for nodes of the travel route from the travel locus.

[0036] First, the server 10 acts as an extractor and extracts straight line components from the travel trajectory using a known straight line extraction technique (step S3). Next, the server 10 determines an intersection point between an extension line LPn of the extracted straight line component LSn and an extension line LPn+1 of another straight line component LSn+1 adjacent to the straight line component LSn in the travel trajectory, as shown in Fig. 3(A) (step S4). If the server 10 can determine the intersection point in step S4 (Y in step S5), the server 10 sets the intersection point determined in step S4 as a feature point candidate Pcn, as shown in Fig. 3(B) (step S6).

[0037] Next, the server 10 determines whether or not a travel trajectory exists within a predetermined range A1 centered on the feature point candidate Pcn (step S7). In this embodiment, the predetermined range A1 is an area within a circle centered on the feature point candidate Pcn, but is not limited to this. The predetermined range A1 may have any shape as long as it is centered on the feature point candidate Pcn.

[0038] As shown in FIG. 3(B), when a driving trajectory exists within a predetermined range A1 centered on the feature point candidate Pcn (Y in step S7), the server 10 functions as a first generation unit as shown in FIG. 3(C), and confirms the feature point candidate Pcn as the feature point Pfn (step S8), and then proceeds to step S13.

[0039] On the other hand, the server 10 proceeds to step S9 when the traveling locus does not exist within the predetermined range A1 centered on the feature point candidate Pcn (N in step S5), for example, when the radius of curvature of the traveling locus is large as shown in Fig. 4(A).The server 10 also proceeds to step S9 when the extension lines LPn and LPn+1 cannot intersect, for example, when the traveling locus has been cranked as shown in Fig. 5 (N in step S5).

[0040] In step S9, the server 10 obtains a tangent Ltn at the center of the travel trajectory from a point Pn that deviates from the straight line component LSn to a point Pn+1 that is on the other straight line component LSn+1, as shown in Figures 4(B) and 5. Then, the server 10 determines the intersection point between the obtained tangent Ltn and an extension line LPn of the straight line component LSn as a feature point candidate Pcn1, and determines the intersection point between the obtained tangent Ltn and an extension line LPn+1 of the straight line component LSn+1 as a feature point candidate Pcn2 (step S10).

[0041] Thereafter, the server 10 determines whether or not a travel trajectory exists within the predetermined range A1 centered on the feature point candidates Pcn1 and Pcn2, as in step S7 (step S11). If a travel trajectory exists within the predetermined range A1 centered on the feature point candidates Pcn1 and Pcn2 (Y in step S11), the server 10 functions as a second generator and determines the feature point candidates Pcn1 and Pcn2 as feature points Pfn, and then proceeds to step S13. On the other hand, if a travel trajectory does not exist within the predetermined range A1 centered on the feature point candidates Pcn1 and Pcn2 (N in step S11), the server 10 proceeds to step S13 without determining them as feature points Pfn.

[0042] After that, the server 10 judges whether the process of determining the characteristic points of steps S4 to S12 has been executed for all adjacent straight line components on the travel locus (step S13). If the characteristic points have not been determined for all adjacent straight line components (N in step S13), the process returns to step S4 and executes the process of determining the characteristic points of the next adjacent straight line components LSn+1 and LSn+2 on the travel locus.

[0043] According to the above-mentioned feature point generation process, the server 10 extracts straight line components from the travel trajectory, and generates a feature point candidate Pcn, which is an intersection of an extension line LPn of the extracted straight line component LSn and an extension line LPn+1 of another straight line component LSn+1 adjacent to the straight line component LSn on the travel trajectory, as a feature point Pfn. This makes it possible to generate feature points at positions that are candidates for nodes, such as corners and intersections on the travel path, and to generate feature points of travel paths suitable for use in navigation and automatic driving.

[0044] Furthermore, according to the feature point generation process described above, if there is no travel trajectory within a predetermined range A1 centered on feature point candidate Pcn, which is the intersection of extension lines LPn, LPn+1, or if there is no intersection of extension lines LPn, LPn+1, feature point candidates Pcn1, Pcn2, which are the intersections of tangent line Ltn and extension lines LPn, LPn+1, respectively, are generated as feature point Pfn.

[0045] As a result, when the radius of curvature of the travel path is large, the feature point Pfn can be generated near the corner of the road and close to the travel path, as shown in Figure 4. This makes it possible to perform map matching with high accuracy, and to generate feature points of the road that are even more suitable for use in navigation and autonomous driving.

[0046] In the above embodiment, if the traveling locus does not exist within the predetermined range A1 centered on the intersection of the extended lines LPn and LPn+1, the intersection is not generated as a characteristic point Pfn, but this is not limited to the above. If there is an intersection of the extended lines LPn and LPn+1, the intersection may be set as a characteristic point Pfn without determining whether or not the traveling locus exists within the predetermined range A1.

[0047] In addition, if there is no driving trajectory within a specified range A1 centered on the intersection of the extension lines LPn, LPn+1, it is not necessary to newly obtain feature point candidates Pcn1, Pcn2, and it is not necessary to generate feature point Pfn based on the extension lines LPn, LPn+1.

[0048] In the above embodiment, if the traveling trajectory does not exist within the predetermined range A1 centered on the intersection (characteristic point candidate Pcn1, Pcn2) between the tangent line Ltn and the extended lines LPn, LPn+1, the characteristic point Pfn is not generated, but this is not limited to the above. The intersection of the tangent line Ltn and the extended lines LPn, LPn+1 may be generated as the characteristic point Pfn without determining whether or not the traveling trajectory exists within the predetermined range A1 centered on the characteristic point candidates Pcn1, Pcn2.

[0049] In addition, if no travel locus exists within the predetermined range A1 centered on the feature point candidates Pcn1 and Pcn2, tangent lines may be drawn at positions slightly shifted from the center toward the points Pn and Pn+1, respectively, and the intersections of the tangent lines and the extended lines LPn and LPn+1 may be set as new feature point candidates.Then, the tangent lines may be shifted toward the points Pn and Pn+1 until a travel locus exists within the predetermined range A1 centered on the new feature point candidates.

[0050] In the above embodiment, the feature point Pfn is generated from the position (latitude, longitude) of the travel trajectory, but the present invention is not limited to this. For example, as shown in FIG. 6, the server 10 may set the position on the travel trajectory where the change in the inclination angle is equal to or greater than a predetermined angle as the feature point Pfn. In this embodiment, the positions on the travel trajectory where the change in the inclination angle is equal to or greater than 1 degree are set as the feature points Pfn and Pfn+1. This allows the feature points Pfn and Pfn+1 to be generated at the boundaries between each floor of a self-propelled multi-storey car park and the slope connecting each floor. The feature points may be generated using altitude data obtained by GPS, but since the altitude data obtained by GPS is likely to have a large error, more accurate feature points can be obtained by obtaining the feature points from the inclination angle as described above. Therefore, the feature points Pfn and Pfn+1 that are more suitable for use in navigation and automatic driving can be generated.

[0051] Also, a camera is installed in the vehicle, and the image of the camera is transmitted from the vehicle to the server 10. The server 10 may analyze the image of the camera, and if a landmark such as a toll booth can be detected, generate the location as a feature point. Furthermore, the vehicle may be equipped with a narrowband communication device (e.g., DSRC) that communicates with the toll booth or the like, and the fact that communication has been performed may be added to the location information transmitted to the server 10. The server 10 generates the location where communication has been performed as a feature point.

[0052] By executing the above-mentioned feature point generation process, it is possible to generate feature points for each of a plurality of travel trajectories. Therefore, as shown in Fig. 7, a plurality of feature points Pf are generated for an intersection of the same travel route, for example.

[0053] Therefore, each time a feature point Pfn is determined by the above-mentioned feature point generation process (i.e., each time steps S9 and S12 are executed), the server 10 functions as an integrating unit and executes the feature point integration process shown in FIG. 8 to integrate multiple feature points Pfn.

[0054] In the feature point integration process, the server 10 determines whether or not an existing feature point Pfn that was determined before the determined feature point Pfn exists within a predetermined range A2 centered on the determined feature point Pfn (step S21). The predetermined range A2 may be the same as the predetermined range A1 used in the feature point generation process, or it may be different. If an existing feature point Pfn exists within the predetermined range A2 (Y in step S21), the server 10 obtains the average position of the two feature points Pfn that exist within the predetermined range A2 (step S22). Then, the server 10 integrates the feature point into the average position (step S23).

[0055] Thereafter, the server 10 deletes the two feature points Pfn before the integration, stores the integrated feature point Pfn as an existing feature point Pfn in the storage unit 14 (step S24), and ends the process. On the other hand, if there is no existing feature point Pfn within the predetermined range A2 (N in step S21), the server 10 stores the currently determined feature point Pfn as an existing feature point in the storage unit 14 (step S24), and ends the process.

[0056] According to the above-mentioned feature point integration process, when multiple generated feature points Pfn exist within the predetermined range A2, the multiple feature points Pfn can be integrated. This prevents multiple feature points Pfn from being added to a single corner or intersection on a road, and makes it possible to generate feature points suitable for use in navigation and automated driving.

[0057] Furthermore, according to the above-described feature point integration process, the positions (latitude, longitude) of multiple feature points Pfn are integrated into an average feature point, which makes it possible to generate feature points Pfn that are even more suitable for use in navigation and automated driving.

[0058] The result of the feature point integration process described above differs depending on the number of driving trajectories. Fig. 9(A) shows the result of feature point integration when there are few driving trajectories. Fig. 9(B) shows the result of feature point integration when there are many driving trajectories. When there are many driving trajectories, the position of feature point 1 moves slightly lower than when there are few driving trajectories. It is generally considered that the more driving trajectories there are, the closer the feature points are to the average of the driving routes that the actual vehicle travels. By generating feature points that conform to the actual driving routes in this way and using the map data, the accuracy of map matching can be improved.

[0059] In the above-mentioned feature point integration process, each time a feature point is generated by the feature point generation process, the feature points are integrated, but the present invention is not limited to this. After the feature point generation process is executed for a plurality of driving trajectories (i.e., after the feature point generation process is executed a plurality of times), the feature point integration process may be executed. In this case, the latitudes and longitudes of a plurality of feature points existing within the predetermined range A2 are averaged, and the feature points are integrated into the averaged point. Furthermore, if there are feature points existing within the predetermined range A2 that have the same latitude and longitude, the feature points may be integrated into the latitude and longitude with the largest number of them. Furthermore, the feature points may be integrated into the center position of a figure formed by connecting a plurality of feature points existing within the predetermined range A2.

[0060] Furthermore, the above-mentioned feature point integration process integrates feature points generated from the extension lines LPn and LPn+1 of the travel trajectory, but it is also possible to integrate feature points generated from the inclination angle in a similar manner. For feature points generated from the inclination angle, the inclination angle is added to the feature point. If there are multiple feature points with the same inclination angle within the predetermined range A2, the feature points may be integrated by averaging the latitudes and longitudes, for example.

[0061] Next, the server 10 generates links that connect the feature points integrated by the feature point integration process described above. The server 10 (the link information generation unit 13) basically connects the feature points Pf7 and Pf18 to each other in the order of passage of one traveling locus R1 that passes through a predetermined range A3 from each of the multiple feature points Pf7 and Pf18, as shown in FIG. 10. The predetermined range A3 may be the same as the predetermined ranges A1 and A2 used in the feature point generation process and the feature point integration process, or it may be different. At this time, the connection direction of the feature points (the passing direction of the vehicle) may also be added to the link data.

[0062] However, with this link generation method, when a link is generated along the traveling trajectory R2 connecting feature point Pf3 and feature point Pf2 as shown in Figure 11(B), because the traveling trajectory R2 passes within a predetermined range A3 centered on feature point Pf8 generated based on the traveling trajectory R1, a link connecting feature point Pf2 → feature point Pf8 → feature point Pf3 is generated as shown in Figure 11(A).

[0063] Therefore, in this embodiment, a link generation process shown in Fig. 12 is executed. First, the server 10 extracts three feature points that are passed by the same travel trajectory within a predetermined range A3 from each feature point and that are consecutive in the order of passing from each feature point among the multiple feature points generated by the feature point generation process and integrated by the feature point integration process (step S30). For example, in the example shown in Fig. 11, feature points Pf2, Pf8, and Pf3 are extracted as three feature points that are passed by the travel trajectory R2 (one of the multiple travel trajectories) within the predetermined range A3 and that are consecutive in the order of passing.

[0064] Next, the server 10 calculates a first evaluation result by evaluating the distance between a line L1 connecting the extracted three consecutive feature points Pf2, Pf8, and Pf3 and a travel trajectory R2 passing through a predetermined range A3 from each of the three feature points Pf2, Pf8, and Pf3 (step S31). In this embodiment, the server 10 determines the maximum value of the distances from the normal line (indicated by the arrow in the figure) on the travel trajectory R2 to the intersection with the line L1 as the first evaluation result, as shown in FIG. 11(A). In the example shown in FIG. 11(A), the maximum value is the distance from the normal line to the intersection with the feature point Pf8.

[0065] Next, the server 10 calculates a second evaluation result by evaluating the distance between the line L2 connecting the first and last characteristic points Pf2 and Pf3 among the three characteristic points Pf2, Pf8, and Pf3 and the traveling locus R2 (step S32). In this embodiment, the server 10 determines the second evaluation result to be the maximum value of the distances until the normal line on the traveling locus R2 intersects with the line L2, as shown in Fig. 11(B). In the example shown in Fig. 11(B), the maximum value is the distance until the normal line intersects with the characteristic point Pf2.

[0066] Next, the server 10 compares the first evaluation result with the second evaluation result, and if the first evaluation result is greater than the second evaluation result by a certain value or more (Y in step S33), the server 10 does not connect the middle feature point Pf8, but generates a link connecting the previous and next feature points Pf2 and Pf3, and ends the process (step S34).On the other hand, if the first evaluation result is not greater than the second evaluation result by a certain value or more (N in step S33), the server 10 connects the three consecutive feature points Pf2, Pf8, and Pf3, and ends the process (step S35).

[0067] In particular, in the case of driving paths in parking lots, the direction of travel and other factors are often precisely determined, and in the example shown in FIG. 11, a pole cone actually exists between Pf2 and Pf8, making the link between Pf2 and Pf8 an inappropriate link. According to the above-described embodiment, in the example shown in FIG. 11, a link connecting the feature points Pf2 and Pf3 is generated. This improves the accuracy of the link, and makes it possible to generate link information suitable for use in navigation and automated driving.

[0068] The first evaluation result and the second evaluation result are not limited to the above-mentioned embodiment. The first evaluation result may be, for example, an area (shown by diagonal lines in the figure) surrounded by the travel trajectory R2, the line L1, the normal line L3 on the travel trajectory R2 passing through the first characteristic point Pf3, and the normal line L4 on the travel trajectory R2 passing through the last characteristic point Pf2, as shown in FIG. 13(A). The second evaluation result may be, for example, an area (shown by diagonal lines in the figure) surrounded by the travel trajectory R2, the line L2, and the normal lines L3 and L4, as shown in FIG. 13(B).

[0069] Also, as shown in Fig. 14(A), the first evaluation result may be the maximum value among the distances between the normal line on the travel trajectory R2 and each of the three feature points Pf2, Pf8, and Pf3. Also, as shown in Fig. 14(B), the second evaluation result may be the maximum value among the distances between the normal line on the travel trajectory R2 and each of the front and rear feature points Pf2 and Pf3. In this case, as in the embodiment shown in Fig. 11, the distance between the normal line on the travel trajectory R2 and the feature point Pf8 becomes the first evaluation result, and the distance between the normal line on the travel trajectory R2 and the feature point Pf2 becomes the second evaluation result.

[0070] Similarly, by defining the first evaluation result and the second evaluation result in this manner, the accuracy of the link is improved, and link information suitable for use in navigation and automated driving can be generated.

[0071] In the above embodiment, the link is generated based on whether the first evaluation result is greater than the second evaluation result by a certain value or more, that is, whether the difference between the first evaluation result and the second evaluation result is greater than a certain value or more, but the present invention is not limited to this. The link may be generated based on whether the first evaluation result is greater than the second evaluation result. To explain in detail, if the first evaluation result>the second evaluation result, the middle feature point Pf8 is not connected, and a link is generated that connects the previous and next feature points Pf2 and Pf3. On the other hand, if the first evaluation result≦the second evaluation result, a link is generated by connecting the three feature points Pf2, Pf8, and Pf3.

[0072] In addition, in the above-described embodiment, the server 10 extracts three consecutive feature points in the link information generating process, but this is not limited to this. Three or more consecutive feature points may be extracted.

[0073] In addition, according to the above-described embodiment, the server 10 capable of communicating with the vehicle-mounted device 20 via the network N generates the feature point and link information, but the present invention is not limited to this. The travel trajectory may be stored in a memory that is detachable from the vehicle-mounted device 20, and the feature point and link information may be generated using a device that reads the memory removed from the vehicle-mounted device 20. In addition, the vehicle-mounted device 20 may generate feature points from its own travel trajectory and transmit them to the server 10.

[0074] In addition, according to the embodiment described above, the generation and integration of feature points and the generation of link information are performed by one server 10, but the present invention is not limited to this. The generation and integration of feature points and the generation of link information may be performed by separate servers.

[0075] In the above embodiment, the driving path is mainly in a parking lot, but the present invention is not limited to this. The driving path may be a general road or the like.

[0076] It should be noted that the present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the gist of the present invention. [Explanation of symbols]

[0077] 10 Server (feature point generating device, link information generating device, acquisition unit) 12 Feature point generation unit (extraction unit, first generation unit, second generation unit, generation unit, integration unit) 13 Link information generation unit

Claims

[Claim 1] A feature point generating device that generates feature points that are candidates for nodes of a travel path based on a travel trajectory of a moving object, comprising: An acquisition unit that acquires the travel locus; An extraction unit that extracts straight line components from the travel trajectory; a first generation unit that generates, as the feature point, an intersection between an extension line of the extracted straight line component and an extension line of another straight line component adjacent to the straight line component on the traveling trajectory.

Citation Information

Patent Citations

  • On-vehicle navigation apparatus

    JP1992172489A

  • Navigation apparatus

    JP1996271272A

  • Navigation device for vehicle

    JP2011196915A

  • Map information generation system, method, and program

    JP2015184459A

  • Map generation device and map generation method, and navigation management system

    JP2017097088A