Self-location estimation system

Abstract

To reduce the degradation of stability of self-position estimation of a vehicle.SOLUTION: A self-position estimation system 1000 capable of communicating with a plurality of vehicles M includes: an environment recognition unit 210 mounted on each of the plurality of vehicles to acquire environmental information; a map information acquisition unit 240 for acquiring map information; a location estimation unit 250 that estimates a self-position of each of the plurality of vehicles by acquiring environmental information and detection information and using the environmental information, the map information, and the detection information; a state determination unit 111 for determining whether or not an object to be determined is passable by using the estimated self-position and the acquired environmental information for each of the plurality of vehicles; and a condition notification unit 113 for notifying a predetermined destination when the state determination unit determines that the object to be determined is impassable.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a self-location estimation system. [Background technology]

[0002] A conventional technology is known that detects the appearance, change, removal, etc. of features on a road, such as traffic lights and signs, by collecting information about features on a road acquired by information acquisition devices mounted on each of a plurality of vehicles and comparing changes in the information within a predetermined period of time (Patent Document 1).The information processing system described in Patent Document 1 suppresses a decrease in the stability of vehicle position estimation by updating map information in response to the appearance, change, removal, etc. of features. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-164840 Summary of the Invention [Problem to be solved by the invention]

[0004] However, even if a feature is removed from the map information because it has been removed, the feature itself may still exist, but the feature may have simply become impassable due to a malfunction. In such cases, a discrepancy may arise between the map information and the actual state of the feature, which may reduce the reliability of vehicle position estimation. [Means for solving the problem]

[0005] The present disclosure can be realized in the following forms.

[0006] According to one aspect of the present disclosure, a self-location estimation system (1000) is provided. This self-location estimation system is capable of communicating with a plurality of vehicles (M), and includes: an environment recognition unit (210) mounted on each of the plurality of vehicles and configured to acquire environmental information, which is information about the environment surrounding the vehicle; a map information acquisition unit (240) configured to acquire map information; a position estimation unit (250) configured to acquire the environmental information about the vehicle from the environment recognition unit mounted on each of the plurality of vehicles and acquire detection information, which is information about the traveling state and position of the vehicle, from a sensor mounted on each of the plurality of vehicles, and estimate the self-location of each of the plurality of vehicles using the environmental information, the map information, and the detection information; a state determination unit (111) configured to determine whether a determination target feature present on a traveling route of each of the vehicles is passable or not, using the estimated self-location and the acquired environmental information in each of the plurality of vehicles; and a state notification unit (113) configured to notify a predetermined destination when the state determination unit determines that the determination target feature is impassable. The object to be determined is an object that restricts vehicle passage by switching between open and closed states.

[0007] According to this form of self-location estimation system, environmental information and detection information for each of multiple vehicles are used to determine whether a feature to be determined that is located on the driving route of each vehicle is passable or not, and if the status determination unit determines that the feature to be determined is impassable, a predetermined destination is notified, thereby providing an opportunity to repair the feature to be determined and preventing a decrease in the stability of self-location estimation due to a difference between the map information and the actual state of the feature. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is an explanatory diagram showing a schematic configuration of a self-position estimation system according to a first embodiment; [Figure 2] 1 is a block diagram showing a schematic configuration of a vehicle according to a first embodiment. [Figure 3] FIG. 2 is a side view showing an imaging area of ​​a camera mounted on a vehicle. [Figure 4] FIG. 2 is a top view showing an imaging area of ​​a camera mounted on a vehicle. [Figure 5] FIG. 2 is a block diagram showing a schematic configuration of a server according to the first embodiment. [Figure 6] 4 is a flowchart showing the procedure of a self-position estimation process according to the first embodiment. [Figure 7] 5 is a flowchart showing the procedure of a map information update process according to the first embodiment. [Figure 8] 10 is a flowchart showing the procedure of a map information update process according to the second embodiment. [Figure 9] 10 is a flowchart showing the procedure from step S242A to step S248A in the map information update process according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] A. First embodiment: A-1. System Configuration: As shown in FIG. 1 , the self-localization system 1000 of this embodiment includes a plurality of vehicles M and a server 100 that can communicate with the plurality of vehicles M via a network. The self-localization system 1000 uses information acquired from the plurality of vehicles M to determine whether features present on the travel route of each vehicle M are passable or impassable, and updates the map information stored in the server 100 according to the feature's status. The "impassable state of the feature" refers, for example, to a state in which a crossing gate at a railroad crossing remains down due to a malfunction. Furthermore, if the self-localization system 1000 determines that the feature is impassable, it notifies the manager Ad of the feature via the network. For example, if a railroad crossing is impassable, the "manager Ad" corresponds to the railway company that manages the crossing. The recipient of the notification from the self-localization system 1000 is not limited to the manager Ad, but may also be a predetermined destination such as a local government or police station in the area where the feature is located.

[0010] Each of the multiple vehicles M is capable of automatic driving and is configured to be able to switch between automatic driving and manual driving. "Automatic driving" means driving in which engine control, brake control, and steering control are automatically performed on behalf of the driver. "Manual driving" means driving in which the driver performs operations for engine control (pressing the accelerator pedal), brake control (pressing the brake pedal), and steering control (turning the steering wheel). Note that the vehicle M is not limited to a vehicle equipped with an engine, and may also be an electric vehicle (EV) or a fuel cell vehicle (FCV).

[0011] 2, each of the multiple vehicles M includes an environment recognition unit 210, a host vehicle state quantity sensor unit 220, a satellite positioning acquisition unit 230, a map information acquisition unit 240, a position estimation unit 250, and a vehicle control unit 260. In this embodiment, at least some of the environment recognition unit 210, the host vehicle state quantity sensor unit 220, the satellite positioning acquisition unit 230, the map information acquisition unit 240, the position estimation unit 250, and the vehicle control unit 260 are functional units realized by a computer including a CPU, a ROM, and a RAM. An example of such a computer is an ECU (Electronic Control Unit).

[0012] The environment recognition unit 210 detects the positions and states of features around the vehicle M. In this embodiment, the vehicle M is equipped with a camera 211, a lidar device 212, and a millimeter-wave radar 213 as the environment recognition unit 210, as shown in FIGS. 3 and 4. In this embodiment, the camera 211 captures an image of a radial area in front of the vehicle M, indicated by hatching, and acquires image data. The lidar device 212 detects the positions and distances of features by emitting laser light and receiving waves reflected by objects. The millimeter-wave radar 213 detects the positions and distances of features by emitting millimeter waves and receiving waves reflected by features. It is sufficient for the vehicle M to be equipped with at least one of the lidar device 212 and the millimeter-wave radar 213. In the following description, the image data, positions, and distances of features acquired by the environment recognition unit 210 will also be referred to as "environmental information." In other words, the environmental information can be said to be information about the environment around the vehicle M.

[0013] 2 detects host vehicle state quantities, such as vehicle speed and yaw rate, that represent the traveling state of the vehicle M while it is traveling. In this embodiment, the vehicle M is equipped with a vehicle speed sensor and a yaw rate sensor as the host vehicle state quantity sensor unit 220. Note that the host vehicle state quantity sensor unit 220 is not limited to the vehicle speed sensor and yaw rate sensor. The vehicle M may also be equipped with sensors that detect the acceleration, pitch angle, and roll angle of the vehicle M as the host vehicle state quantity sensor unit 220.

[0014] The satellite positioning acquisition unit 230 detects the current position (longitude and latitude) of the vehicle M based on navigation signals received from artificial satellites that constitute the GNSS (Global Navigation Satellite System). The current position of the vehicle M acquired by the satellite positioning acquisition unit 230 and the host vehicle state quantity detected by the above-mentioned host vehicle state quantity sensor unit 220 correspond to the "detection information" in this disclosure.

[0015] The map information acquisition unit 240 acquires map information from the server 100. The map information includes dynamic information such as traffic congestion information in addition to static map information such as road width and the number of lanes. In this embodiment, the map information also includes information indicating whether or not a feature that restricts the passage of the vehicle M by switching between an open and closed state, such as a railroad crossing or an ETC gate, is passable (hereinafter also referred to as "passability information").

[0016] The position estimation unit 250 uses the above-mentioned environmental information, detection information, and map information to estimate the vehicle M's own position on the map and the positions of features existing around the vehicle M. In addition, the position estimation unit 250 transmits the estimated own position and the acquired environmental information to the server 100.

[0017] The vehicle control unit 260 controls the acceleration / deceleration and steering of the vehicle M according to the vehicle's own position estimated by the position estimation unit 250 and the positions of features around the vehicle M recognized by the environment recognition unit 210. Furthermore, if the passability information indicates that a feature through which the vehicle M is scheduled to pass is impassable, the vehicle control unit 260 switches the driving state from automated driving to manual driving, changes the driving route, and notifies the driver. For example, if the ETC gate through which the vehicle M was scheduled to pass is closed, the vehicle control unit 260 changes the driving route to avoid the closed ETC gate and pass through an ETC gate through which the vehicle M is permitted to pass. Furthermore, if all ETC gates are closed and the vehicle M must pass through a general gate, the driver must pay a toll. Therefore, the vehicle control unit 260 notifies the driver that the vehicle will pass through the general gate and switches the driving state from automated driving to manual driving. The vehicle control unit 260 corresponds to the "response processing unit" in this disclosure. Depending on the state of the features, the vehicle control unit 260 may execute one of the following: switching the driving state from automatic driving to manual driving, changing the driving route, and notifying the driver.

[0018] 5, the server 100 is configured as a computer including a CPU 110, a storage device 120, a ROM 130, and a RAM 140. The CPU 110, the storage device 120, the ROM 130, and the RAM 140 are communicatively connected to one another via a bus.

[0019] The CPU 110 loads a program stored in the ROM 130 into the RAM 140 and executes it, thereby functioning as a state determination unit 111, a state update unit 112, and a state notification unit 113. The state determination unit 111 acquires environmental information and its own position from each vehicle M, and determines whether or not features present on the travel route of each vehicle M are passable. The state update unit 112 updates map information according to the result of the determination by the state determination unit 111. When the state notification unit 113 determines that a feature is impassable, it notifies the manager Ad of the feature of that fact. Specific processing in each functional unit will be described in the map information update processing to be described later.

[0020] The storage device 120 stores a map information database 121, which is a database that stores the above-mentioned map information. In this embodiment, the map information stored in the map information database 121 is the map information to be acquired by the above-mentioned map information acquisition unit 240. Hereinafter, the map information stored in the map information database 121 will also be referred to as "master map information."

[0021] A-2. Self-location estimation process: Each vehicle M repeatedly executes the self-position estimation process shown in FIG. 6 while traveling to estimate its own position, and transmits the estimated self-position and the acquired environmental information to the server 100.

[0022] In each vehicle M, the acquisition of environmental information by the environment recognition unit 210 (step S110), the acquisition of detection information by the vehicle state quantity sensor unit 220 and the satellite positioning acquisition unit 230 (step S112), and the acquisition of map information by the map information acquisition unit 240 (step S114) are executed in parallel.

[0023] In step S120, the position estimation unit 250 of each vehicle M estimates the own position of the vehicle using the acquired environmental information, detection information, and map information.

[0024] In each vehicle M, the position estimation unit 250 transmits its own position and environmental information to the server 100 (step S130), and the vehicle control unit 260 controls the driving state of the vehicle in accordance with the own position and environmental information (step S132). After steps S130 and S132 are completed, steps S110, S112, and S114 are executed again in each vehicle M. As described above, steps S110 to S132 are repeatedly executed in each vehicle M.

[0025] A-3. Map information update process: The server 100 repeatedly executes the map information update process shown in Figure 7 while the server 100 is operating, and updates the master map information and notifies the feature manager Ad according to the determination result of the passable status of each feature on the travel route of each vehicle M.

[0026] In step S210, the state determination unit 111 acquires the vehicle position and environmental information transmitted from each vehicle M.

[0027] In step S220, the state determination unit 111 uses the acquired self-position and environmental information of each vehicle M to determine whether a feature (hereinafter also referred to as a "determination target feature") present on the travel route of each vehicle M is in a passable state. If the state determination unit 111 reads information indicating that the determination target feature is in a passable state from the self-position and environmental information of each vehicle M, the state determination unit 111 determines that the determination target feature is in a passable state. For example, in the case of an ETC gate, examples of "information indicating that the determination target feature is in a passable state" include the ETC gate's open / closed bar being down, the presence of an "X" sign indicating road closure, the illumination of a red light, the display of a character string such as "closed," etc. Furthermore, if the state determination unit 111 reads from the travel trajectory information of each vehicle M that multiple vehicles M are avoiding a specific ETC gate, the state determination unit 111 determines that the ETC gate is in a passable state. The travel path information means information indicating the travel path of each vehicle M obtained from the history of the vehicle's own position acquired from each vehicle M.

[0028] If it is determined that the target feature is passable (step S220: Yes), the state determination unit 111 determines whether the determination result in step S220 matches the passability information for the target feature in the master map information (step S230).If it is determined that the determination result matches the passability information (step S230: Yes), the state determination unit 111 executes step S210 again.

[0029] If it is determined that the determination result does not match the passability information (step S230: No), the state determination unit 111 determines whether the number of times that the path is determined to be passable is equal to or greater than a preset threshold (step S240).If it is determined that the number of times that the path is determined to be passable is less than the threshold (step S240: No), the state determination unit 111 executes step S210 again.

[0030] If it is determined that the number of times that the feature is determined to be passable is equal to or greater than the threshold (step S240: Yes), the status update unit 112 updates the master map information by determining that the feature is passable (step S250). More specifically, the status update unit 112 updates the passability information in the master map information so that it matches the determination result made by the status determination unit 111 in step S220. If the number of times that the feature is determined to be passable is still low, the feature may not be in a stable passable state. If the master map information is updated in such a case, the master map information may be updated too frequently, which could cause instability. Therefore, in this embodiment, the status update unit 112 updates the master map information when the number of times that the feature is determined to be passable is equal to or greater than the threshold.

[0031] After step S250 is completed, state determination unit 111 executes step S210 again.

[0032] On the other hand, if it is determined that the target feature is impassable (step S220: No), the state determination unit 111 determines whether the determination result by the state determination unit 111 in step S220 matches the passability information for the target feature in the master map information (step S232).If it is determined that the determination result matches the passability information (step S232: Yes), the state determination unit 111 executes step S210 again.

[0033] If it is determined that the determination result does not match the passability information (step S232: No), the state determination unit 111 determines whether the number of times that it has been determined that the path is impassable is equal to or greater than a preset threshold (step S242). If it is determined that the number of times that it has been determined that the path is impassable is less than the threshold (step S242: No), the state determination unit 111 executes step S210 again. The intention behind executing the determination in step S242 is the same as the intention behind executing the determination in step S240 described above.

[0034] If it is determined that the number of times the feature has been determined to be impassable is equal to or greater than the threshold (step S242: Yes), the status update unit 112 updates the master map information by determining that the feature to be determined is impassable (step S252). Furthermore, in step S262, the status notification unit 113 notifies the administrator Ad that the feature to be determined is impassable. After step S262 is completed, the status determination unit 111 executes step S210 again. As described above, steps S210 to S262 are repeatedly executed in the server 100 for each feature to be determined.

[0035] According to the self-location estimation system 1000 of the first embodiment described above, environmental information and detection information for each of the multiple vehicles M are used to determine whether the feature to be determined is passable or not, and if the state determination unit 111 determines that the feature to be determined is impassable, the manager of the feature to be determined or the like is notified of this, thereby providing an opportunity to repair the feature and preventing a decrease in the stability of self-location estimation due to a difference between the map information and the actual state of the feature.

[0036] Furthermore, when the state determination unit 111 determines that the feature to be determined is impassable, the self-position estimation system 1000 performs at least one of switching the driving state from automatic driving to manual driving, changing the driving route, and notifying the driver, thereby enabling the vehicle to travel while avoiding the feature that is impassable.

[0037] Furthermore, the self-location estimation system 1000 updates the passability information in the master map information when the passability information and the judgment result by the state judgment unit 111 differ from each other, so that the master map information can be corrected to correspond to the actual state of the features, and a decrease in the accuracy of self-location estimation can be suppressed.

[0038] B. Second embodiment: As shown in Fig. 8, the self-location estimation system 1000 of the second embodiment differs from the self-location estimation system 1000 of the first embodiment in that steps S242A to S248A shown in Fig. 9 are executed instead of step S242 of the map information update process shown in Fig. 7. The system configuration of the self-location estimation system 1000 of the second embodiment and other steps in the map information update process are the same as those of the self-location estimation system 1000 of the first embodiment, and therefore the same configurations and steps are denoted by the same reference numerals and detailed description thereof will be omitted.

[0039] 9, the state determination unit 111 acquires the duration of the impassable state for the target feature. The duration of the impassable state can be calculated by calculating the difference between the time when the target feature was first determined to be impassable and the current time.

[0040] In step S244A, the state determination unit 111 counts the number of detours that the vehicle M has made around the determination target feature. The "number of detours" refers to the number of times that the determination target feature was determined to be impassable and the vehicle M has detoured around the determination target feature. The number of detours can be found from the driving trajectory information of each vehicle M described above.

[0041] In step S246A, the state determination unit 111 calculates the impassability probability Pc from the duration and the number of detours. The "impassability probability Pc" is a numerical value that indicates the possibility that the target feature is actually impassable. In this embodiment, the impassability probability Pc is calculated by referring to a pre-created table that indicates the relationship between the duration and the number of detours and the impassability probability Pc. This table is created so that the impassability probability Pc increases as the duration increases and as the number of detours increases. This is because if the duration is long and the number of detours is large, it can be said that there is a high possibility that the target feature is continuously impassable rather than accidentally.

[0042] In step S248A, the state determination unit 111 determines whether the calculated impassability probability Pc is equal to or greater than a preset threshold. If the impassability probability Pc is less than the threshold (step S248A: No), the state determination unit 111 again executes step S210 shown in Fig. 8. On the other hand, if the impassability probability Pc is equal to or greater than the threshold in Fig. 9 (step S248A: Yes), the state update unit 112 executes step S252 shown in Fig. 8. In other words, if the determination result that the determination target feature is in an impassable state remains unchanged even after a preset time has elapsed, or if the determination result that the determination target feature is in an impassable state has been obtained a preset number of times or more, the state update unit 112 executes step S252.

[0043] According to the self-location estimation system 1000 of the second embodiment described above, if the impassable state of the feature to be determined continues for more than a preset time, or if the determination result that the feature to be determined is impassable is obtained more than a preset number of times, the probability of impassability Pc is increased, and if the probability of impassability Pc is equal to or greater than a preset threshold, the passability information in the master map information is updated to indicate that the feature to be determined is impassable, and the manager of the feature to be determined is notified of this, thereby providing an opportunity to repair the feature and preventing a decrease in the accuracy of the passability information.

[0044] C. Other Embodiments: (C1) In the above embodiment, the position estimation unit 250 is provided in each vehicle M, but the present disclosure is not limited to this. The server 100 may be provided with the map information acquisition unit 240 and the position estimation unit 250, and may estimate the self-position of each vehicle M using the map information held by the server 100 and the environmental information and detection information acquired from each vehicle M, and notify each vehicle M of the self-position. Even in this embodiment, the same effects as those of the above embodiment can be achieved.

[0045] (C2) In the above embodiment, the status update unit 112 updates the master map information on the condition that the determination result by the status determination unit 111 does not match the passability information in the master map information, but the present disclosure is not limited to this. The status update unit 112 may update the master map information every time a new determination result is obtained. This configuration achieves the same effects as the above embodiment and prevents the map information update process from becoming complicated.

[0046] (C3) In the above embodiment, the state determination unit 111 calculates the impassability probability Pc using the duration of the impassable state and the number of detours taken by the vehicle M, but the present disclosure is not limited to this. The state determination unit 111 may calculate the impassability probability Pc using only one of the duration and the number of detours. Even in this embodiment, the same effects as those of the above embodiment are achieved.

[0047] The present disclosure is not limited to the above-described embodiments and can be realized in various configurations without departing from the spirit thereof. For example, the technical features in each embodiment corresponding to the technical features in the form described in the Summary of the Invention section can be appropriately replaced or combined to solve some or all of the above-described problems or achieve some or all of the above-described effects. Furthermore, if a technical feature is not described as essential in this specification, it can be appropriately deleted.

[0048] The self-localization system 1000 and the method described herein may be implemented by a special-purpose computer configured with a processor and memory programmed to perform one or more functions embodied in a computer program. Alternatively, the self-localization system 1000 and the method described herein may be implemented by a special-purpose computer configured with a processor configured with one or more dedicated hardware logic circuits. Alternatively, the self-localization system 1000 and the method described herein may be implemented by one or more special-purpose computers configured with a processor and memory programmed to perform one or more functions in combination with a processor configured with one or more hardware logic circuits. Furthermore, the computer program may be stored as instructions executed by a computer on a computer-readable non-transitory tangible storage medium. [Explanation of symbols]

[0049] M... vehicle, 111... state determination unit, 113... state notification unit, 210... environment recognition unit, 240... map information acquisition unit, 250... position estimation unit, 1000... self-position estimation system

Claims

1. A self-location estimation system (1000) capable of communicating with a plurality of vehicles (M), an environment recognition unit (210) mounted on each of the plurality of vehicles and configured to acquire environment information that is information relating to the environment around the vehicle; a map information acquisition unit (240) for acquiring map information; a position estimation unit (250) that acquires the environmental information about each of the plurality of vehicles from the environmental recognition unit mounted on each of the plurality of vehicles, and acquires detection information, which is information about the running state and position of each of the plurality of vehicles, from a sensor mounted on each of the plurality of vehicles, and estimates the self-position of each of the plurality of vehicles using the environmental information, the map information, and the detection information; a state determination unit (111) that determines whether a determination target feature existing on a travel route of each of the plurality of vehicles is in a passable state by using the estimated self-position and the acquired environmental information of each of the plurality of vehicles; a state notification unit (113) that notifies a predetermined destination when the state determination unit determines that the target feature is impassable; Equipped with The target feature is a feature that restricts vehicle passage by switching between an open and closed state. Self-location estimation system.

2. The self-location estimation system according to claim 1 , each of the plurality of vehicles includes the map information acquisition unit and the position estimation unit; The self-location estimation system further includes a status update unit (112) that updates passability information stored as part of master map information, which is the map information to be acquired by the map information acquisition unit of each of the vehicles, and which is information indicating the passability state of a feature; the state update unit, when the passability state indicated by the passability information in the master map information differs from the determination result by the state determination unit, updates the passability information in the master map information so that it matches the determination result; Self-location estimation system.

3. The self-location estimation system according to claim 2, Each of the plurality of vehicles has a corresponding processing unit (260), When the passability information included in the map information acquired by the map information acquisition unit indicates that a feature existing on the vehicle's travel route is impassable, the response processing unit executes at least one of switching the driving state of the vehicle from automatic driving to manual driving, changing the vehicle's travel route, and notifying the driver. Self-location estimation system.

4. 4. The self-location estimation system according to claim 2 or 3, the state determination unit increases a numerical value (Pc) representing the possibility that the target feature is in an impassable state when the determination result of the passability state of the target feature remains impassable even after a preset time has elapsed, the state update unit updates the passability information by determining that the target feature is impassable when the numerical value is equal to or greater than a preset threshold value; When the numerical value is equal to or greater than a preset threshold value, the state notification unit notifies the destination of information indicating that the target feature is in an impassable state. Self-location estimation system.

5. The self-location estimation system according to claim 4, the state determination unit increases the numerical value when the same determination result that the object is impassable is obtained a predetermined number of times or more within a predetermined time period, with respect to the passability state of the object to be determined. Self-location estimation system.

Images