Autonomous driving management system and autonomous driving management method

Abstract

To more accurately determine whether or not an automatic driving condition is satisfied.SOLUTION: An automatic driving management system is applied to a vehicle which performs automatic driving using a recognition sensor recognizing a peripheral situation. First sensor recognition information indicates a result recognized by the recognition sensor. Reference information indicates a correspondence between expected sensor recognition information of first sensor recognition information, which is expected in a case where an automatic driving condition is satisfied, and a vehicle position. The automatic driving management system acquires expected sensor recognition information corresponding to a determination target position based on the reference information. The automatic driving management system compares the first sensor recognition information obtained at the determination target position with the expected sensor recognition information corresponding to the determination target position, thereby determining whether or not the automatic driving condition is satisfied at the determination target position.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to a technology for managing the automatic driving of a vehicle. In particular, the present disclosure relates to a technology for determining whether or not the automatic driving conditions are satisfied.

Background Art

[0002] Patent Document 1 discloses an autonomous driving vehicle equipped with a plurality of sensors. The autonomous driving vehicle evaluates the state of dirt and failure of the sensors. When the sensor performance deteriorates due to dirt or failure, the autonomous driving vehicle operates in a degraded mode with limited speed and steering angle.

[0003] Patent Document 2 discloses an electronic control device mounted on a vehicle. The electronic control device determines a sensor detectable area based on the detection information of the sensors mounted on the vehicle. Then, the electronic control device generates driving control information of the vehicle based on the detection information of the sensors and the sensor detectable area.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] Consider the automatic driving of a vehicle. The automatic driving conditions are the conditions under which the automatic driving of the vehicle is permitted, and are also called ODD (Operational Design Domain). The automatic driving system is designed to operate under predetermined automatic driving conditions (ODD). Therefore, when performing automatic driving, it is important to determine whether or not the automatic driving conditions are satisfied.

[0006] One object of the present disclosure is to provide a technique capable of more accurately determining whether or not the automatic driving conditions are satisfied.

Means for Solving the Problems

[0007] The first aspect is related to an automatic driving management system. The automatic driving management system is applied to a vehicle that performs automatic driving using a recognition sensor that recognizes surrounding situations. The automatic driving management system one or more processors that acquire first sensor recognition information indicating the recognition result by the recognition sensor, one or more storage devices that store reference information indicating the correspondence between the expected sensor recognition information, which is the first sensor recognition information expected when the automatic driving conditions are satisfied, and the vehicle position and includes. One or more processors acquire the expected sensor recognition information associated with the determination target position based on the reference information. One or more processors determine whether or not the automatic driving conditions are satisfied at the determination target position by comparing the first sensor recognition information obtained at the determination target position with the expected sensor recognition information associated with the determination target position.

[0008] The second aspect is related to an automatic driving management method. The automatic driving management method is applied to a vehicle that performs automatic driving using a recognition sensor that recognizes surrounding situations. The first sensor recognition information indicates the recognition result by the recognition sensor. The reference information indicates the correspondence between the expected sensor recognition information, which is the first sensor recognition information expected when the automatic driving conditions are satisfied, and the vehicle position. The automatic driving management method acquires the expected sensor recognition information associated with the determination target position based on the reference information, and By comparing the first sensor recognition information obtained at the determination target position with the expected sensor recognition information associated with the determination target position, it is determined whether the automatic driving conditions are satisfied at the determination target position. It includes.

Effect of the Invention

[0009] According to the present disclosure, reference information indicating the correspondence between the expected sensor recognition information and the vehicle position is prepared. The expected sensor recognition information is the first sensor recognition information (recognition result by the recognition sensor) expected when the automatic driving conditions are satisfied. Therefore, by comparing the first sensor recognition information SEN1 obtained at the determination target position with the expected sensor recognition information associated with the determination target position, it is possible to accurately determine whether the automatic driving conditions are satisfied at the determination target position.

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

Embodiments for Carrying Out the Invention

[0011] Embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0012] 1. Overview 1-1. Vehicle Control System FIG. 1 is a conceptual diagram for explaining the overview of vehicle 1 and vehicle control system 10 according to the present embodiment. The vehicle control system 10 controls the vehicle 1. Typically, the vehicle control system 10 is mounted on the vehicle 1. Alternatively, at least a part of the vehicle control system 10 may be included in a remote system outside the vehicle 1 to remotely control the vehicle 1.

[0013] Vehicle 1 is capable of autonomous driving, and the vehicle control system 10 is configured to control the autonomous driving of Vehicle 1. Here, the autonomous driving is assumed to be one that does not necessarily require the driver to be fully concentrated on driving at all times (so-called autonomous driving at level 3 or higher). The autonomous driving level may be level 4 or higher that does not require a driver.

[0014] In the autonomous driving of Vehicle 1, the recognition sensor 30 mounted on Vehicle 1 is used. The recognition sensor 30 is a sensor for recognizing the situation around Vehicle 1. Examples of the recognition sensor 30 include a lidar (Laser Imaging Detection and Ranging), a camera, a radar, etc. The lidar measures the relative position of the reflection point by irradiating a beam and detecting the reflected beam reflected at the reflection point.

[0015] The vehicle control system 10 recognizes the situation around Vehicle 1 using the recognition sensor 30. For example, the vehicle control system 10 recognizes stationary objects and moving objects around Vehicle 1 using the recognition sensor 30. Examples of stationary objects include the road surface 2, road structures 3 (e.g., walls, guardrails, curbs), white lines, etc. Examples of moving objects include surrounding vehicles 4, pedestrians 5, etc. Then, the vehicle control system 10 executes autonomous driving control regarding Vehicle 1 based on the result of the recognition process using the recognition sensor 30.

[0016] 1-2. Autonomous Driving Conditions The autonomous driving conditions are the conditions under which the autonomous driving of Vehicle 1 is permitted. The autonomous driving conditions are also called the ODD (Operational Design Domain). Generally, the autonomous driving conditions are defined by the maximum vehicle speed, driving area, weather conditions, sunlight conditions, etc. For example, in rainy weather, the accuracy of the recognition process using the recognition sensor 30 may decrease, and the accuracy of the autonomous driving control may decrease. Therefore, conventionally, as one of the autonomous driving conditions regarding the weather, something like "the precipitation per unit time is less than a predetermined value (e.g., 5 mm / h)" has been used.

[0017] The vehicle control system 10 is designed to perform autonomous driving under predetermined autonomous driving conditions (ODD). Therefore, when performing autonomous driving, it is important to determine whether the autonomous driving conditions are satisfied. Hereinafter, the process of determining whether the autonomous driving conditions are satisfied is referred to as "ODD compliance determination process". The inventor of the present application recognized the following problems regarding the ODD compliance determination process.

[0018] As an example, consider the above-mentioned autonomous driving condition regarding the weather, "the precipitation per unit time is less than a predetermined value". The precipitation varies greatly even within a relatively narrow range, and local heavy rain has also been increasing in recent years. Therefore, it is not easy to accurately measure the precipitation at the current position of the vehicle 1 pinpointedly. To improve the measurement accuracy of local precipitation, large-scale infrastructure construction such as arranging a large number of rain gauges is required. This is not preferable from the perspective of cost. Also, after the rain stops and the sun shines on the wet road surface, the reflection of light from the road surface increases. In this case, the recognition accuracy of the road surface and falling objects by the recognition sensor 30 may decrease. That is, even if it is not raining, the environment around the vehicle 1 may become unfavorable for autonomous driving. Therefore, performing the ODD compliance determination process based on a simple comparison between the precipitation and the threshold is not necessarily appropriate from the perspective of the accuracy of autonomous driving control.

[0019] In the case of weather conditions that are difficult to measure, such as fog, the difficulty of the ODD compliance determination process further increases.

[0020] In addition to the natural environment such as the weather, the aging deterioration and performance degradation of the recognition sensor 30 itself also affect the accuracy of autonomous driving control. It is necessary to perform the ODD compliance determination process in consideration of various factors that affect the accuracy of autonomous driving control.

[0021] From the above viewpoints, the present disclosure proposes a new technology that can improve the accuracy of the ODD compliance determination process.

[0022] 1-3. New ODD Conformity Judgment Process First, the technical concept of the new ODD conformity judgment process according to this embodiment will be described.

[0023] As described above, it is not always appropriate to perform the OD conformity judgment process using parameters that specifically define the weather itself, such as precipitation. A human driver does not judge whether it is easy or difficult to drive by looking at a specific parameter such as precipitation. A human driver judges whether it is easy or difficult to drive based on the information recognized by their own vision. For example, after the rain stops and the road surface is wet and the sun shines, the reflection of light from the road surface is dazzling and the road surface does not look the same as usual, so a human driver judges that it is difficult to drive. That is, a human driver judges that it is difficult to drive when the information recognized by their own vision is different from usual.

[0024] The ODD conformity judgment process according to this embodiment is also performed in the same way as the sense of a human driver. The "eye" for the vehicle control system 10 that performs automatic driving control is the recognition sensor 30. Therefore, according to this embodiment, the ODD conformity judgment process is performed based on the recognition result by the recognition sensor 30. That is, the ODD conformity judgment process is performed based on whether the "appearance" seen from the recognition sensor 30 of the vehicle 1 is the same as usual.

[0025] FIG. 2 is a conceptual diagram for explaining the outline of the ODD conformity judgment process according to this embodiment. The "first sensor recognition information SEN1" indicates the recognition result by the recognition sensor 30 mounted on the vehicle 1. That is, the first sensor recognition information SEN1 corresponds to the "appearance" seen from the recognition sensor 30. For example, when the recognition sensor 30 includes a lidar, the first sensor recognition information SEN1 includes information on the point cloud (beam reflection points) measured by the lidar. For example, the first sensor recognition information SEN1 includes the number of beam reflection points on the road surface 2 measured during one frame.

[0026] Typically, the first sensor recognition information SEN1 includes information about stationary objects (e.g., road surface 2, road structures 3) recognized by the recognition sensor 30. On the other hand, information about moving objects (e.g., surrounding vehicles 4, pedestrians 5) recognized by the recognition sensor 30 does not necessarily have to be included in the first sensor recognition information SEN1. For convenience, information about moving objects recognized by the recognition sensor 30 is referred to as "second sensor recognition information". The second sensor recognition information is necessary for the automatic driving control by the vehicle control system 10, but does not necessarily have to be included in the first sensor recognition information SEN1.

[0027] The "expected sensor recognition information ESEN" is the first sensor recognition information SEN1 expected when the automatic driving conditions are satisfied. The automatic driving conditions are predetermined in consideration of various factors that affect the accuracy of the automatic driving control. The expected sensor recognition information ESEN corresponds to the "appearance" as seen from the recognition sensor 30 when automatic driving is permitted.

[0028] The "reference information REF" indicates the correspondence relationship between the vehicle position PV and the expected sensor recognition information ESEN. That is, the reference information REF represents the expected sensor recognition information ESEN as a function of the vehicle position PV. It can also be said that the reference information REF indicates the expected sensor recognition information ESEN when the vehicle 1 exists at the vehicle position PV.

[0029] The vehicle position PV may be set along a general vehicle driving trajectory within the road. The vehicle position PV may be assumed to be located at the center of the lane. The vehicle position PV may be a concept that includes both the position and orientation of the vehicle 1. It may be assumed that the orientation of the vehicle 1 is parallel to the extending direction of the lane (white line).

[0030] The expected sensor recognition information ESEN and the reference information REF are generated and updated based on information obtained when the autonomous driving conditions are satisfied. For example, the expected sensor recognition information ESEN and the reference information REF are generated and updated based on the past autonomous driving performance of one or more vehicles 1. In this case, it can be said that the expected sensor recognition information ESEN and the reference information REF represent "past successful experiences". As another example, the reference information REF may be generated and updated through a simulation based on the configuration information of the autonomous driving area and the design information of the recognition sensor 30.

[0031] Furthermore, it can be said that the reference information REF representing the expected sensor recognition information ESEN as a function of the vehicle position PV is a type of map information. However, it should be noted that the reference information REF is a concept completely different from general map information. General map information shows the arrangement of objects in an absolute coordinate system. That is, general map information shows the correspondence between an absolute position and the objects existing at that absolute position. On the other hand, the reference information REF shows the correspondence between the vehicle position PV and the first sensor recognition information SEN1 (recognition result) when viewed from that vehicle position PV when the autonomous driving conditions are satisfied. The reference information REF does not indicate the objects existing at the vehicle position PV.

[0032] The autonomous driving management system 100 is applied to the vehicle 1 and manages the autonomous driving of the vehicle 1. The autonomous driving management system 100 holds the above-mentioned reference information REF and performs an ODD compliance determination process regarding the vehicle 1 based on the reference information REF. In particular, the autonomous driving management system 100 determines whether the autonomous driving conditions are satisfied regarding the vehicle 1 existing at the determination target position PT. Typically, the determination target position PT is the current position of the vehicle 1. As another example, the determination target position PT may be a past position of the vehicle 1.

[0033] Specifically, the automatic driving management system 100 acquires the first sensor recognition information SEN1 obtained by the vehicle 1 (vehicle control system 10) at the determination target position PT. Further, the automatic driving management system 100 acquires the expected sensor recognition information ESEN associated with the determination target position PT based on the reference information REF. The expected sensor recognition information ESEN associated with the determination target position PT is the first sensor recognition information SEN1 expected at the determination target position PT when the automatic driving conditions are satisfied. Therefore, the automatic driving management system 100 can determine whether the automatic driving conditions are satisfied at the determination target position PT by comparing the first sensor recognition information SEN1 obtained at the determination target position PT with the expected sensor recognition information ESEN associated with the determination target position PT. When the first sensor recognition information SEN1 obtained at the determination target position PT is significantly different from the expected sensor recognition information ESEN associated with the determination target position PT, the automatic driving management system 100 determines that the automatic driving conditions are not satisfied at the determination target position PT.

[0034] FIG. 3 is a diagram for explaining an example of the ODD conformity determination process according to the present embodiment. The horizontal axis in FIG. 3 represents the vehicle position PV, and the vertical axis represents the parameter X. The parameter X is a parameter indicating the recognition result by the recognition sensor 30 and is included in the first sensor recognition information SEN1. For example, the parameter X is the number of beam reflection points on the road surface 2 measured by the lidar.

[0035] The expected sensor recognition information ESEN includes the expected value Xe of the parameter X expected when the automatic driving conditions are satisfied. For example, the expected value Xe is the average value of a number of parameters X obtained when the automatic driving conditions are satisfied. The reference information REF indicates the correspondence relationship between the expected value Xe of the parameter X and the vehicle position PV. That is, the reference information REF represents the expected value Xe of the parameter X as a function of the vehicle position PV.

[0036] The allowable range RNG is the range of parameter X for which automatic driving is permitted. This allowable range RNG includes at least the expected value Xe. The width of the allowable range RNG is predetermined. The width of the allowable range RNG may be set based on the standard deviation (σ) of a number of parameter X values obtained when the automatic driving conditions are satisfied. A set of the expected value Xe and the allowable range RNG may be registered in the reference information REF.

[0037] The automatic driving management system 100 acquires the first sensor recognition information SEN1 obtained by the vehicle 1 (vehicle control system 10) at the determination target position PT. The first sensor recognition information SEN1 includes the actual value Xa of parameter X obtained at the determination target position PT. Also, the automatic driving management system 100 acquires the expected value Xe associated with the determination target position PT based on the reference information REF. Then, the automatic driving management system 100 determines whether the automatic driving conditions are satisfied at the determination target position PT by comparing the actual value Xa of parameter X obtained at the determination target position PT with the allowable range RNG including the expected value Xe associated with the determination target position PT. Specifically, when the actual value Xa obtained at the determination target position PT is within the allowable range RNG, the automatic driving management system 100 determines that the automatic driving conditions are satisfied at the determination target position PT. On the other hand, when the actual value Xa obtained at the determination target position PT deviates from the allowable range RNG, the automatic driving management system 100 determines that the automatic driving conditions are not satisfied at the determination target position PT.

[0038] For example, the parameter X is the number of beam reflection points on the road surface 2 measured by the lidar. The expected value Xe is the expected value of the number of beam reflection points on the road surface 2 when the automatic driving conditions are satisfied. During rainy weather, the number of beam reflection points on the road surface 2 significantly decreases. When the number of beam reflection points on the road surface 2 falls below the allowable range RNG including the expected value Xe, the automatic driving management system 100 determines that the automatic driving conditions are not satisfied at the determination target position PT. That is, when the "appearance" of the road surface 2 seen from the recognition sensor 30 of the vehicle 1 is different from normal, it is determined that the automatic driving conditions are not satisfied.

[0039] When it is determined that the determination target position PT is the current position of the vehicle 1 and the automatic driving conditions are not satisfied at the determination target position PT, the automatic driving management system 100 decelerates or stops the vehicle 1. For example, the automatic driving management system 100 instructs the vehicle control system 10 to decelerate or stop the vehicle 1.

[0040] 1-4. Various forms of the automatic driving management system The automatic driving management system 100 may be included in the vehicle control system 10 of the vehicle 1, or may be provided separately from the vehicle control system 10. The automatic driving management system 100 may be a management server that communicates with the vehicle 1 (vehicle control system 10). The automatic driving management system 100 and the vehicle control system 10 may be partially common.

[0041] FIG. 4 is a conceptual diagram for explaining a management server 1000 that manages automatic driving. The management server 1000 may be composed of a plurality of servers that perform distributed processing. The management server 1000 is communicably connected to a large number of vehicles 1 that perform automatic driving. The management server 1000 collects the vehicle position PV and the first sensor recognition information SEN1 from a large number of vehicles 1. In particular, the management server 1000 collects the vehicle position PV and the first sensor recognition information SEN1 from a large number of vehicles 1 when automatic driving is possible. Then, the management server 1000 generates and updates the above-mentioned reference information REF based on the information collected from a large number of vehicles 1.

[0042] For example, the automatic driving management system 100 is included in the management server 1000. In this case, the management server 1000 communicates with the vehicle 1 to be determined, and acquires information on the determination target position PT and the first sensor recognition information SEN1 obtained at the determination target position PT. Then, the management server 1000 performs the above ODD compliance determination process based on the information acquired from the vehicle 1 to be determined and the reference information REF. When it is determined that the automatic driving conditions are not satisfied at the determination target position PT, the management server 1000 instructs the vehicle control system 10 of the vehicle 1 to be determined to decelerate or stop.

[0043] As another example, the automatic driving management system 100 may be included in the vehicle control system 10. In this case, the vehicle control system 10 communicates with the management server 1000 and acquires the reference information REF from the management server 1000. Also, the vehicle control system 10 acquires the first sensor recognition information SEN1 at the determination target position PT. Then, the vehicle control system 10 performs the above ODD compliance determination process based on the first sensor recognition information SEN1 and the reference information REF. When it is determined that the automatic driving conditions are not satisfied at the determination target position PT, the vehicle control system 10 decelerates or stops the vehicle 1.

[0044] Generally speaking, it is as follows. The automatic driving management system 100 includes one or more processors and one or more storage devices. The one or more processors may be included in the vehicle control system 10, may be included in the management server 1000, or may be distributed between the vehicle control system 10 and the management server 1000. The one or more storage devices may be included in the vehicle control system 10, may be included in the management server 1000, or may be distributed between the vehicle control system 10 and the management server 1000. The one or more storage devices store the reference information REF. The one or more processors acquire the first sensor recognition information SEN1 and perform the ODD compliance determination process based on the first sensor recognition information SEN1 and the reference information REF.

[0045] 1-4. Effects As described above, according to the present embodiment, reference information REF indicating the correspondence between the expected sensor recognition information ESEN and the vehicle position PV is prepared. The expected sensor recognition information ESEN is the first sensor recognition information SEN1 (recognition result by the recognition sensor 30) expected when the automatic driving condition is satisfied. Therefore, by comparing the first sensor recognition information SEN1 obtained at the determination target position PT with the expected sensor recognition information ESEN associated with the determination target position PT, it is possible to accurately determine whether the automatic driving condition is satisfied at the determination target position PT. For example, it is possible to more accurately determine whether the automatic driving condition is satisfied as compared with the case of using a parameter that specifically defines the weather itself, such as precipitation.

[0046] In addition, not only the natural environment such as the weather, but also the aging deterioration and performance degradation of the recognition sensor 30 itself affect the accuracy of the automatic driving control. It is necessary to perform the ODD compliance determination process in consideration of various factors that affect the accuracy of the automatic driving control. The expected sensor recognition information ESEN according to the present embodiment is the first sensor recognition information SEN1 (recognition result by the recognition sensor 30) expected when the automatic driving condition is satisfied. Therefore, various factors that affect the accuracy of the automatic driving control are integrally reflected in the expected sensor recognition information ESEN. By using such expected sensor recognition information ESEN and reference information REF, it is possible to perform the ODD compliance determination process simply and with high accuracy.

[0047] Hereinafter, a specific example of the vehicle control system 10, the automatic driving management system 100, and the ODD compliance determination process according to the present embodiment will be described.

[0048] 2. Example of Vehicle Control System 2-1. Configuration Example FIG. 5 is a block diagram showing a configuration example of the vehicle control system 10 according to the present embodiment. The vehicle control system 10 includes a vehicle state sensor 20, a recognition sensor 30, a position sensor 40, a traveling device 50, a communication device 60, and a control device 70.

[0049] The vehicle state sensor 20 detects the state of the vehicle 1. For example, the vehicle state sensor 20 includes a speed sensor, an acceleration sensor, a yaw rate sensor, a steering angle sensor, and the like.

[0050] The recognition sensor 30 recognizes (detects) the situation around the vehicle 1. The recognition sensor 30 includes a lidar 31, a camera 32, a radar, and the like. The lidar 31 irradiates a beam and measures the relative position of the reflection point by detecting the reflected beam reflected at the reflection point. The camera 32 images the situation around the vehicle 1 and acquires an image.

[0051] The position sensor 40 detects the position and orientation of the vehicle 1. Examples of the position sensor 40 include an IMU (Inertial Measurement Unit), a GNSS (Global Navigation Satellite System) sensor, and the like.

[0052] The traveling device 50 includes a steering device, a driving device, and a braking device. The steering device steers the wheels. For example, the steering device includes an electric power steering (EPS) device. The driving device is a power source that generates a driving force. Examples of the driving device include an engine, an electric motor, an in-wheel motor, and the like. The braking device generates a braking force.

[0053] The communication device 60 communicates with the outside of the vehicle 1. For example, the communication device 60 communicates with a management server 1000 (see FIG. 4).

[0054] The control device 70 is a computer that controls the vehicle 1. The control device 70 includes one or more processors 71 (hereinafter simply referred to as the processor 71) and one or more storage devices 72 (hereinafter simply referred to as the storage device 72). The processor 71 executes various processes. For example, the processor 71 includes a CPU (Central Processing Unit). The storage device 72 stores various information. Examples of the storage device 72 include a volatile memory, a non-volatile memory, an HDD (Hard Disk Drive), an SSD (Solid State Drive), and the like. The control device 70 may include one or more ECUs (Electronic Control Unit). A part of the control device 70 may be an information processing device outside the vehicle 1. In that case, a part of the control device 70 communicates with the vehicle 1 and remotely controls the vehicle 1.

[0055] The vehicle control program 80 is a computer program for controlling the vehicle 1. By the processor 71 executing the vehicle control program 80, various processes by the control device 70 are realized. The vehicle control program 80 is stored in the storage device 72. The vehicle control program 80 may be recorded on a computer-readable recording medium.

[0056] 2-2. Driving environment information The control device 70 acquires driving environment information 200 indicating the driving environment of the vehicle 1. The driving environment information 200 is stored in the storage device 72. FIG. 6 is a block diagram showing an example of the driving environment information 200. The driving environment information 200 includes map information 210, vehicle state information 220, surrounding situation information 230, and vehicle position information 240.

[0057] 2-2-1. Map information The map information 210 includes a general navigation map. The map information 210 may indicate lane arrangements and road shapes. The map information 210 may also include position information of landmarks, traffic lights, signs, etc. The control device 70 acquires the map information 210 of the required area from the map database. The map database may be stored in the storage device 72 or may be managed by the management server 1000. In the latter case, the control device 70 communicates with the management server 1000 via the communication device 60 to acquire the required map information 210.

[0058] The map information 210 may include static object map information 215 indicating the absolute position where static objects exist. Examples of static objects include the road surface 2, road structures 3, etc. Examples of road structures 3 include walls, guardrails, curbs, fences, plantings, etc.

[0059] The static object map information 215 may include terrain map information indicating the absolute position (latitude, longitude, altitude) where the road surface 2 exists. The terrain map information may include an evaluation value set for each absolute position. The evaluation value indicates the "likelihood" that the road surface 2 exists at that absolute position.

[0060] The static object map information 215 may include road structure map information indicating the absolute position where road structures 3 exist. The road structure map information may include an evaluation value set for each absolute position. The evaluation value indicates the "likelihood" that road structures 3 exist at that absolute position.

[0061] 2-2-2. Vehicle state information The vehicle state information 220 is information indicating the state of the vehicle 1 and includes vehicle speed, acceleration, yaw rate, steering angle, etc. The control device 70 acquires the vehicle state information 220 from the vehicle state sensor 20. The vehicle state information 220 may indicate the driving state (automatic driving / manual driving) of the vehicle 1.

[0062] 2-2-3. Surrounding situation information The surrounding situation information 230 is information indicating the situation around the vehicle 1. The control device 70 recognizes the situation around the vehicle 1 using the recognition sensor 30 and acquires the surrounding situation information 230.

[0063] For example, the surrounding situation information 230 includes point cloud information 231 indicating the measurement results by the lidar 31. More specifically, the point cloud information 231 indicates the relative positions (azimuth, distance) of each beam reflection point as seen from the lidar 31.

[0064] The surrounding situation information 230 may include image information 232 captured by the camera 32.

[0065] The surrounding situation information 230 further includes object information 233 regarding the objects around the vehicle 1. Examples of the objects include white lines, road structures 3, surrounding vehicles 4 (preceding vehicles, parked vehicles, etc.), pedestrians 5, traffic lights, landmarks, falling objects, etc. The object information 233 indicates the relative position and relative speed of the object with respect to the vehicle 1. For example, by analyzing the image information 232 obtained by the camera 32, the object can be identified and the relative position of the object can be calculated. For example, the control device 70 uses the image recognition AI obtained by machine learning to identify the objects in the image information 232. Also, based on the point cloud information 231 obtained by the lidar 31, the object can be identified and the relative position and relative speed of the object can be acquired.

[0066] In object recognition, the control device 70 may utilize the above-described static object map information 215. The positions of static objects (e.g., road surface 2, road structures 3) are registered in the static object map information 215. Therefore, by using the static object map information 215, it is possible to distinguish between static objects and others. More specifically, the control device 70 grasps the positions of static objects existing around the vehicle 1 based on the static object map information 215 and the vehicle position information 240. Then, the control device 70 removes (subsamples) static objects from the objects recognized using the recognition sensor 30. Thereby, it is possible to distinguish between static objects and others (e.g., surrounding vehicles 4, pedestrians 5, falling objects, etc.). For example, the control device 70 can detect surrounding vehicles 4, pedestrians 5, falling objects, etc. on the road surface 2 by removing the road surface 2 indicated by the terrain map information from the point cloud information 231.

[0067] 2-2-4. Vehicle Position Information The vehicle position information 240 is information indicating the position and orientation of the vehicle 1. The control device 70 acquires the vehicle position information 240 from the detection results of the position sensor 40. Also, the control device 70 may acquire highly accurate vehicle position information 240 by means of a well-known self-position estimation process (Localization) using the object information 233 and the map information 210.

[0068] FIG. 7 is a conceptual diagram for explaining the self-position estimation process (Localization). Various landmarks (feature objects) exist around the vehicle 1. Examples of landmarks include white lines, curbstones, signboards, poles, etc. The control device 70 recognizes the landmarks around the vehicle 1 using the recognition sensor 30. The object information 233 indicates the relative positions of the recognized landmarks. On the other hand, the absolute positions of the landmarks are registered in the map information 210. The control device 70 corrects the vehicle position information 240 so that the relative positions of the landmarks indicated by the object information 233 and the absolute positions of the landmarks obtained from the map information 210 match. Thereby, highly accurate vehicle position information 240 is obtained.

[0069] 2-3. Vehicle Travel Control The control device 70 executes vehicle driving control for controlling the driving of the vehicle 1. The vehicle driving control includes steering control, acceleration control, and deceleration control. The control device 70 executes vehicle driving control by controlling the driving device 50. Specifically, the control device 70 executes steering control by controlling the steering device. Further, the control device 70 executes acceleration control by controlling the driving device. Further, the control device 70 executes deceleration control by controlling the braking device.

[0070] 2-4. Automatic Driving Control The control device 70 performs automatic driving control based on the driving environment information 200. More specifically, the control device 70 generates a driving plan for the vehicle 1 based on the driving environment information 200. Examples of the driving plan include maintaining the current driving lane, changing lanes, making right or left turns, avoiding obstacles, and the like. Further, the control device 70 generates a target trajectory necessary for the vehicle 1 to drive according to the driving plan based on the driving environment information 200. The target trajectory includes a target position and a target speed. Then, the control device 70 performs vehicle driving control so that the vehicle 1 follows the target trajectory.

[0071] In addition, when it is determined by the automatic driving management system 100 that the automatic driving conditions are not satisfied, the control device 70 generates an emergency plan for decelerating or stopping the vehicle 1. Then, the control device 70 performs vehicle driving control according to the emergency plan to decelerate or stop the vehicle 1.

[0072] 3. Automatic Driving Management System 3-1. Configuration Example FIG. 8 is a block diagram showing a configuration example of the automatic driving management system 100 according to the present embodiment. The automatic driving management system 100 includes communication devices 110, one or more processors 120 (hereinafter simply referred to as the processor 120), and one or more storage devices 130 (hereinafter simply referred to as the storage device 130).

[0073] The communication device 110 communicates with the outside of the automatic driving management system 100. For example, when the automatic driving management system 100 is included in the vehicle control system 10, the communication device 110 communicates with the management server 1000 (see FIG. 4). As another example, when the automatic driving management system 100 is included in the management server 1000, the communication device 110 communicates with the vehicle control system 10.

[0074] The processor 120 executes various processes. For example, the processor 120 includes a CPU. The storage device 130 stores various information. Examples of the storage device 130 include a volatile memory, a non-volatile memory, an HDD, an SSD, and the like. When the automatic driving management system 100 is included in the vehicle control system 10, the processor 120 is the same as the processor 71 of the vehicle control system 10, and the storage device 130 is the same as the storage device 72 of the vehicle control system 10.

[0075] The automatic driving management program 140 is a computer program for managing automatic driving. By the processor 120 executing the automatic driving management program 140, various processes by the processor 120 are realized. The automatic driving management program 140 is stored in the storage device 130. The automatic driving management program 140 may be recorded on a computer-readable recording medium.

[0076] The reference information REF indicates the correspondence between the expected sensor recognition information ESEN and the vehicle position PV. The management server 1000 generates and updates the reference information REF. For example, the reference information REF is generated and updated based on the past automatic driving performance of one or more vehicles 1. As another example, the reference information REF may be generated and updated through a simulation based on the configuration information of the automatic driving area and the design information of the recognition sensor 30. The reference information REF is stored in the storage device 130. When the automatic driving management system 100 is included in the vehicle control system 10, the processor 120 communicates with the management server 1000 via the communication device 110 and acquires the reference information REF.

[0077] The vehicle position information 240 and the first sensor recognition information SEN1 are obtained by the vehicle control system 10. The first sensor recognition information SEN1 indicates the recognition result recognized by the recognition sensor 30 of the vehicle 1. For example, the first sensor recognition information SEN1 includes information regarding stationary objects (e.g., road surface 2, road structure 3) recognized by the recognition sensor 30. When the automatic driving management system 100 is included in the management server 1000, the processor 120 communicates with the vehicle control system 10 via the communication device 110 and acquires the vehicle position information 240 and the first sensor recognition information SEN1. The vehicle position information 240 and the first sensor recognition information SEN1 are stored in the storage device 130.

[0078] 3-2. ODD Conformity Judgment Process FIG. 9 is a flowchart showing an example of processing by the automatic driving management system 100 (processor 120) according to the present embodiment.

[0079] In step S100, the processor 120 acquires the vehicle position information 240 and the first sensor recognition information SEN1. The vehicle position information 240 includes information on the determination target position PT. Typically, the determination target position PT is the current position of the vehicle 1. As another example, the determination target position PT may be a past position of the vehicle 1. The first sensor recognition information SEN1 indicates the recognition result by the recognition sensor 30 mounted on the vehicle 1. For example, the first sensor recognition information SEN1 includes the actual value Xa of the parameter X recognized by the recognition sensor 30. The processor 120 acquires the first sensor recognition information SEN1 obtained at the determination target position PT.

[0080] In step S110, the processor 120 acquires the expected sensor recognition information ESEN associated with the determination target position PT based on the reference information REF. For example, the expected sensor recognition information ESEN includes the expected value Xe of the parameter X expected when the automatic driving condition is satisfied.

[0081] In step S120, the processor 120 compares the first sensor recognition information SEN1 obtained at the determination target position PT with the expected sensor recognition information ESEN associated with the determination target position PT.

[0082] If the first sensor recognition information SEN1 obtained at the determination target position PT does not deviate from the expected sensor recognition information ESEN (step S130; No), the process proceeds to step S140. For example, if the actual value Xa of the parameter X obtained at the determination target position PT is within the allowable range RNG including the expected value Xe (step S130; No), the process proceeds to step S140.

[0083] In step S140, the processor 120 determines that the automatic driving conditions are satisfied at the determination target position PT. In this case, the processor 120 continues the automatic driving of the vehicle 1 (step S150).

[0084] On the other hand, if the first sensor recognition information SEN1 obtained at the determination target position PT deviates from the expected sensor recognition information ESEN (step S130; Yes), the process proceeds to step S160. For example, if the actual value Xa of the parameter X obtained at the determination target position PT deviates from the allowable range RNG including the expected value Xe (step S130; Yes), the process proceeds to step S160.

[0085] In step S160, the processor 120 determines that the automatic driving conditions are not satisfied at the determination target position PT. In this case, the processor 120 decelerates or stops the vehicle 1 (step S170).

[0086] 4. Various Examples of ODD Conformance Determination Processing Hereinafter, various examples of the ODD conformance determination processing according to the present embodiment will be described.

[0087] 4-1. First Example In the first example, the recognition sensor 30 includes the lidar 31, and the first sensor recognition information SEN1 includes the point cloud information 231 indicating the measurement result by the lidar 31. The point cloud information 231 indicates the relative position (azimuth, distance) of each beam reflection point as seen from the lidar 31.

[0088] FIG. 10 is a conceptual diagram for explaining an example of the point cloud information 231. The first reflection point R1 is a reflection point on a stationary object (e.g., road surface 2, road structure 3). The second reflection point R2 is a reflection point on a moving object (e.g., surrounding vehicle 4, pedestrian 5). The noise reflection point R3 is a reflection point caused by raindrops or dust in the air.

[0089] The first reflection point R1 is detected continuously in a certain range spatially. The second reflection point R2 is also detected continuously in a certain range spatially. That is, the spatially continuous point cloud is composed of the first reflection point R1 or the second reflection point R2. Here, the above-described stationary object map information 215 indicates the absolute position where the stationary object exists. By combining the stationary object map information 215 and the vehicle position information 240, the position where it is assumed that a stationary object exists around the vehicle 1 can be grasped. Therefore, the processor 120 can classify the spatially continuous point cloud into the first reflection point R1 and the second reflection point R2 based on the stationary object map information 215 and the vehicle position information 240. That is, the processor 120 can identify the first reflection point R1 related to the stationary object and the second reflection point R2 related to the moving object. Also, when the stationary object map information 215 includes at least one of the topographic map information and the road structure map information, the first reflection point R1 related to the road surface 2 and the first reflection point R1 related to the road structure 3 can also be identified.

[0090] On the other hand, the noise reflection point R3 is not spatially continuous. Typically, the noise reflection point R3 exists alone. Therefore, the processor 120 can identify the noise reflection point R3 based on the continuity of the point cloud. For example, assume that the distances to a plurality of reflection points detected in a certain area are 19.8 m, 20.0 m, 5.5 m, 20.2 m, and 20.1 m. In this case, the reflection point with a distance of 5.5 m is the noise reflection point R3. For example, the processor 120 classifies a discontinuous reflection point whose distance difference from the reflection point for an adjacent beam is equal to or greater than a predetermined threshold as the noise reflection point R3.

[0091] Let the number of beams irradiated from the lidar 31 in one frame be “N”. The number of first reflection points n_t is the number of first reflection points R1 measured in one frame. The number of second reflection points n_s is the number of second reflection points R2 measured in one frame. The number of noise reflection points n_n is the number of noise reflection points R3 measured in one frame. The number of non-reflection points m is the number of beams for which no reflected beam is detected in one frame. In this case, the relationship expressed by the following formula (1) holds.

[0092] Formula (1): N = n_t + n_s + n_n + m

[0093] The first sensor recognition information SEN1 includes at least one of the number of first reflection points n_t, the number of noise reflection points n_n, and the number of non-reflection points m. The first sensor recognition information SEN1 may include at least the number of first reflection points n_t. The first sensor recognition information SEN1 may include all of the number of first reflection points n_t, the number of noise reflection points n_n, and the number of non-reflection points m.

[0094] On the other hand, the first sensor recognition information SEN1 may not include the number of second reflection points n_s regarding the moving object. Generally speaking, the second sensor recognition information is information regarding the moving object recognized by the recognition sensor 30. The second sensor recognition information is necessary for the automatic driving control by the vehicle control system 10, but does not necessarily have to be included in the first sensor recognition information SEN1.

[0095] FIG. 11 is a conceptual diagram for explaining an example of the reference information REF. The reference information REF shows the correspondence between the expected value Xe of the parameter X and the vehicle position PV. That is, the reference information REF represents the expected value Xe of the parameter X as a function of the vehicle position PV. In the example shown in FIG. 11, the parameter X includes the number of first reflection points n_t, the number of noise reflection points n_n, and the number of non-reflection points m.

[0096] As an example, the ODD compliance determination process during rainy weather will be described. The reflected beam at a surface with diffuse reflection has a high probability of returning to the lidar 31, while the reflected beam at a surface with total reflection has a low probability of returning to the lidar 31. Therefore, during rainy weather, the number of first reflection points R1 on the road surface 2 decreases. On the other hand, since the raindrops in the air increase, the number of noise reflection points R3 increases. That is, during rainy weather, the number of first reflection points n_t decreases significantly, and the number of noise reflection points n_n increases significantly. Also, as the number of first reflection points n_t decreases, the number of non-reflection points m increases.

[0097] When the number of first reflection points n_t on the road surface 2 decreases, it becomes difficult to detect falling objects on the road surface 2. Also, when the number of noise reflection points n_n increases, it becomes difficult to detect distant objects. That is, during rainy weather, the object detection performance deteriorates, and the accuracy of the automatic driving control decreases. Therefore, it is desirable to perform the ODD compliance determination process with high accuracy.

[0098] FIG. 12 is a conceptual diagram for explaining the ODD compliance determination process using the number of first reflection points n_t. The vertical axis represents the number of first reflection points n_t, and the horizontal axis represents the vehicle position PV. The reference information REF shows the correspondence between the expected value Xe of the number of first reflection points n_t and the vehicle position PV. That is, the reference information REF represents the expected value Xe of the number of first reflection points n_t as a function of the vehicle position PV.

[0099] In the example shown in FIG. 12, the first threshold TH1 defines the lower limit value of the first number of reflection points n_t that allows the continuation of the automated driving (e.g., level 4 automated driving) without deceleration. The first threshold TH1 is set lower than the expected value Xe. The second threshold TH2 defines the lower limit value of the first number of reflection points n_t that allows the continuation of the automated driving if deceleration is performed. The second threshold TH2 is set even lower than the first threshold TH1. The first threshold TH1 and the second threshold TH2 may be registered in the reference information REF together with the expected value Xe.

[0100] The processor 120 acquires the first sensor recognition information SEN1 obtained at the determination target position PT. The first sensor recognition information SEN1 includes the actual value Xa of the first number of reflection points n_t obtained at the determination target position PT. The processor 120 acquires the expected value Xe associated with the determination target position PT based on the reference information REF. When the actual value Xa of the first number of reflection points n_t is greater than or equal to the first threshold TH1, the processor 120 determines that the automated driving conditions are satisfied and the automated driving is possible. When the actual value Xa of the first number of reflection points n_t is less than the first threshold TH1 and greater than or equal to the second threshold TH2, the processor 120 determines that the automated driving is possible if deceleration is performed. When the actual value Xa of the first number of reflection points n_t is less than the second threshold TH2, the processor 120 determines that the automated driving conditions are not satisfied and the automated driving is impossible.

[0101] FIG. 13 is a conceptual diagram for explaining the ODD compliance determination process using the noise number of reflection points n_n. The vertical axis represents the noise number of reflection points n_n, and the horizontal axis represents the vehicle position PV. The reference information REF shows the correspondence between the expected value Xe of the noise number of reflection points n_n and the vehicle position PV. That is, the reference information REF represents the expected value Xe of the noise number of reflection points n_n as a function of the vehicle position PV.

[0102] In the example shown in FIG. 13, the first threshold TH1 defines the upper limit value of the number of noise reflection points n_n that allows the continuation of the automatic driving (e.g., level 4 automatic driving) without deceleration. The first threshold TH1 is set higher than the expected value Xe. The second threshold TH2 defines the upper limit value of the number of noise reflection points n_n that allows the continuation of the automatic driving if deceleration is performed. The second threshold TH2 is set even higher than the first threshold TH1. The first threshold TH1 and the second threshold TH2 may be registered in the reference information REF together with the expected value Xe.

[0103] The processor 120 acquires the first sensor recognition information SEN1 obtained at the determination target position PT. The first sensor recognition information SEN1 includes the actual value Xa of the number of noise reflection points n_n obtained at the determination target position PT. The processor 120 acquires the expected value Xe associated with the determination target position PT based on the reference information REF. When the actual value Xa of the number of noise reflection points n_n is less than or equal to the first threshold TH1, the processor 120 determines that the automatic driving condition is satisfied and the automatic driving is possible. When the actual value Xa of the number of noise reflection points n_n exceeds the first threshold TH1 and is less than or equal to the second threshold TH2, the processor 120 determines that the automatic driving is possible if deceleration is performed. When the actual value Xa of the number of noise reflection points n_n exceeds the second threshold TH2, the processor 120 determines that the automatic driving condition is not satisfied and the automatic driving is impossible.

[0104] When the first sensor recognition information SEN1 includes the first number of reflection points n_t and the number of noise reflection points n_n, the processor 120 performs both the ODD compliance determination process shown in FIG. 12 and the ODD compliance determination process shown in FIG. 13. Then, the processor 120 adopts the determination result in which the driving of the vehicle 1 is more restricted, that is, the determination result with the lower vehicle speed.

[0105] 4-2. Second Example In the second example, consider fog. In the case of fog, the number of water droplets in the air greatly increases. Therefore, the number of noise reflection points n_n greatly increases. Also, as the number of noise reflection points n_n increases, the number of non-reflection points m decreases. On the other hand, the number of first reflection points n_t does not significantly decrease. Therefore, by using at least one of the number of noise reflection points n_n and the number of non-reflection points m, it is possible to appropriately perform the ODD compliance determination process. The ODD compliance determination process is the same as in the case of the first example described above.

[0106] Note that the tendency of the change in the number of reflection points is different between the case of rain and the case of fog. Therefore, it is also possible to estimate the cause of the failure to satisfy the automatic driving conditions based on the tendency of the change in the number of reflection points.

[0107] 4-3. Third Example In the third example, consider the case where the output of the lidar 31 decreases. The decrease in the output of the lidar 31 occurs due to aging deterioration, failure, heat, etc. When the output of the lidar 31 decreases, the number of reflection points generally decreases. In particular, the number of first reflection points R1 on the distant road surface 2 significantly decreases. Therefore, in the third example, from the perspective of the distance from the vehicle 1, the first reflection points R1 on the road surface 2 are further classified.

[0108] For example, as shown in FIG. 14, the road surface 2 is divided into three types: a short-distance road surface 2a, a medium-distance road surface 2b, and a long-distance road surface 2c. The processor 120 classifies the first reflection points R1 on the road surface 2 into the first reflection points R1a on the road surface 2a, the first reflection points R1b on the road surface 2b, and the first reflection points R1c on the road surface 2c based on the distance to the measured reflection points. The numbers of the first reflection points n_ta, n_tb, n_tc are the numbers of the first reflection points R1a, R1b, R1c, respectively.

[0109] The first sensor recognition information SEN1 includes the first number of reflection points n_ta, n_tb, and n_tc. The reference information REF indicates the expected value Xe of each of the first number of reflection points n_ta, n_tb, and n_tc. The processor 120 performs ODD compliance determination processing using the first number of reflection points n_ta, n_tb, and n_tc. Thereby, even when the output of the lidar 31 decreases, it is possible to appropriately perform the ODD compliance determination processing. Further, it is also possible to estimate that the cause of the non-satisfaction of the automatic driving conditions is the decrease in the output of the lidar 31.

[0110] 4-4. The Fourth Example In the fourth example, consider the case where the calibration of the lidar 31 deteriorates. As described above, by using the road structure map information included in the static object map information 215, the first reflection point R1 on the road structure 3 can be identified. However, when the calibration of the lidar 31 deteriorates, the identification accuracy of the first reflection point R1 using the road structure map information decreases. As a result, the number of first reflection points R1 on the road structure 3 decreases. Therefore, by using the number of first reflection points n_t regarding the road structure 3, it is possible to appropriately perform the ODD compliance determination processing. The ODD compliance determination processing is the same as in the case of the first example described above.

[0111] 4-5. The Fifth Example In the fifth example, consider the number of landmarks recognized in the self-position estimation process (see FIG. 7). Examples of landmarks include white lines, curbs, signboards, poles, etc. The recognition result of the landmark using the recognition sensor 30 is obtained from the object information 233. For example, during rainy days, the number of detections of each landmark decreases. In particular, the white line is detected based on the luminance value, but when the road surface 2 is wet, it becomes particularly difficult to detect the white line. As another example, during snow accumulation, the number of detections of the white line and the curb significantly decreases.

[0112] Therefore, in the fifth example, ODD compliance determination processing is performed using the number of landmarks recognized by the recognition sensor 30. The first sensor recognition information SEN1 includes the number of each landmark recognized by the recognition sensor 30. The reference information REF indicates the expected value Xe of the number of each landmark. The processor 120 performs ODD compliance determination processing using the number of each landmark.

[0113] FIG. 15 is a conceptual diagram for explaining ODD compliance determination processing using the number of white lines n_wl. The vertical axis represents the number of white lines n_wl, and the horizontal axis represents the vehicle position PV. The reference information REF shows the correspondence between the expected value Xe of the number of white lines n_wl and the vehicle position PV. That is, the reference information REF represents the expected value Xe of the number of white lines n_wl as a function of the vehicle position PV.

[0114] In the example shown in FIG. 15, the first threshold TH1 defines the lower limit value of the number of white lines n_wl at which automatic driving (e.g., level 4 automatic driving) can be continued without deceleration. The first threshold TH1 is set lower than the expected value Xe. The second threshold TH2 defines the lower limit value of the number of white lines n_wl at which automatic driving can be continued if deceleration is performed. The second threshold TH2 is set even lower than the first threshold TH1. The first threshold TH1 and the second threshold TH2 may be registered in the reference information REF together with the expected value Xe.

[0115] The processor 120 acquires the first sensor recognition information SEN1 obtained at the determination target position PT. The first sensor recognition information SEN1 includes the actual value Xa of the number of white lines n_wl obtained at the determination target position PT. The processor 120 acquires the expected value Xe associated with the determination target position PT based on the reference information REF. When the actual value Xa of the number of white lines n_wl is greater than or equal to the first threshold TH1, the processor 120 determines that the automatic driving condition is satisfied and automatic driving is possible. When the actual value Xa of the number of white lines n_wl is less than the first threshold TH1 and greater than or equal to the second threshold TH2, the processor 120 determines that automatic driving is possible if deceleration is performed. When the actual value Xa of the number of white lines n_wl is less than the second threshold TH2, the processor 120 determines that the automatic driving condition is not satisfied and automatic driving is impossible.

[0116] 4-6. The Sixth Example FIG. 16 is a conceptual diagram for explaining the sixth example. In the sixth example, consider the image (image information 232) captured by the camera 32. The processor 120 can extract the road surface 2 in the image by analyzing the image obtained by the camera 32. For example, the processor 120 can extract the road surface 2 in the image by applying semantic segmentation to the image. Segmentation (region division) is a technique of grouping regions for each group having similar feature amounts (color, texture, etc.) in the image and dividing the image into a plurality of regions.

[0117] The image quality (visibility) of the image captured by the camera varies greatly depending on the imaging conditions. For example, the image quality deteriorates in rainy weather. As another example, when the lens of the camera 32 is dirty, the image quality deteriorates. As still another example, at night, the image quality deteriorates due to insufficient light. When the image quality of the image deteriorates, the object detection performance based on the image deteriorates, and the accuracy of the automatic driving control deteriorates. Therefore, it is desirable to perform the ODD compliance determination process with high accuracy.

[0118] As described above, the processor 120 extracts the road surface 2 in the image by analyzing the image obtained by the camera 32. However, when the image quality of the image deteriorates, the area of the road surface 2 extracted decreases. Therefore, in the sixth example, the ODD compliance determination process is performed by using the area ratio of the road surface 2 in the image. The first sensor recognition information SEN1 includes the area ratio of the road surface 2 in the image. The reference information REF indicates the expected value Xe of the area ratio of the road surface 2 in the image. The processor 120 performs the ODD compliance determination process using the area ratio of the road surface 2 in the image. The ODD compliance determination process is the same as in the case of the fifth example described above.

Explanation of Signs

[0119] 1 Vehicle 10 Vehicle control system 20 Vehicle state sensor 30 Recognition sensor 31 Lidar 40 Position sensor 50 Travel device 60 Communication device 70 Control device 80 Vehicle control program 100 Automatic driving management system 110 Communication device 120 Processor 130 Storage device 140 Automatic driving management program 200 Driving environment information 210 Map information 215 Static object map information 220 Vehicle state information 230 Surrounding situation information 231 Point cloud information 240 Vehicle position information 1000 Management server ESEN Expected sensor recognition information PT Determination target position PV Vehicle position REF Reference information RNG Allowable range SEN1 First sensor recognition information Xa Actual value Expected value of Xe

Claims

1. An automatic driving management system applied to a vehicle that performs automatic driving using a recognition sensor for recognizing the surrounding situation, one or more processors that acquire first sensor recognition information indicating the recognition result by the recognition sensor, one or more storage devices that store reference information and comprising, The expected sensor recognition information is the first sensor recognition information expected when the automatic driving conditions regarding the environment around the vehicle are satisfied, The reference information indicates the correspondence between the vehicle position and the expected sensor recognition information when the vehicle is present at the vehicle position, The one or more processors further, Based on the reference information, obtain the expected sensor recognition information associated with the determination target position, By comparing the first sensor recognition information obtained by the vehicle present at the determination target position with the expected sensor recognition information associated with the determination target position, it is determined whether the automatic driving conditions regarding the environment around the vehicle at the determination target position are satisfied configured as, The recognition sensor includes a lidar, The first sensor recognition information includes the measurement result by the lidar, The lidar measures the relative position of the reflection point by irradiating a beam and detecting the reflected beam reflected at the reflection point, The first number of reflection points is the number of the reflection points on the stationary object measured in one frame, The number of noise reflection points is the number of the reflection points in the air measured in the one frame, The number of non-reflection points is the number of beams in which the reflected beam is not detected in the one frame, The first sensor recognition information includes at least one of the first number of reflection points, the number of noise reflection points, and the number of non-reflection points An automatic driving management system.

2. The automatic driving management system according to claim 1, The first sensor recognition information includes parameters indicating the recognition result by the recognition sensor, The expected sensor recognition information includes the expected value of the parameter expected when the automatic driving conditions regarding the environment around the vehicle are satisfied, The reference information indicates the correspondence between the expected value of the parameter and the vehicle position, The one or more processors further, Based on the reference information, obtain the expected value associated with the determination target position, Compare the actual value of the parameter obtained by the vehicle existing at the determination target position with the allowable range including the expected value associated with the determination target position. When the actual value of the parameter obtained at the determination target position deviates from the allowable range, determine that the automatic driving conditions regarding the environment around the vehicle at the determination target position are not satisfied. configured as an automatic driving management system.

3. The automatic driving management system according to claim 1, wherein the first sensor recognition information includes information regarding stationary objects recognized by the recognition sensor. an automatic driving management system.

4. The automatic driving management system according to claim 3, wherein the second sensor recognition information is information regarding moving objects recognized by the recognition sensor, and the second sensor recognition information is not included in the first sensor recognition information. an automatic driving management system.

5. The automatic driving management system according to claim 1, wherein the parameter is at least one of the first reflection count, the noise reflection count, and the non - reflection count included in the first sensor recognition information, the expected sensor recognition information includes an expected value of the parameter expected when the automatic driving conditions regarding the environment around the vehicle are satisfied, the reference information indicates the correspondence between the expected value of the parameter and the vehicle position, the one or more processors further acquire the expected value associated with the determination target position based on the reference information, compare the actual value of the parameter obtained by the vehicle existing at the determination target position with the allowable range including the expected value associated with the determination target position, and when the actual value of the parameter obtained at the determination target position deviates from the allowable range, determine that the automatic driving conditions regarding the environment around the vehicle at the determination target position are not satisfied. configured as an automatic driving management system.

6. The automatic driving management system according to any one of claims 1 to 4, wherein the one or more processors further recognize landmarks around the vehicle using the recognition sensor, and estimate the position of the vehicle based on the recognition result of the landmarks and map information indicating the positions of the landmarks. configured as The first sensor recognition information includes the number of the landmarks recognized using the recognition sensor. An automatic driving management system. **Claim 7**: An automatic driving management system applied to a vehicle that performs automatic driving using a recognition sensor that recognizes the surrounding situation, one or more processors that acquire first sensor recognition information indicating a recognition result by the recognition sensor, and one or more storage devices that store reference information and are provided with The expected sensor recognition information is the first sensor recognition information expected when the automatic driving conditions regarding the environment around the vehicle are satisfied. The reference information indicates a correspondence relationship between a vehicle position and the expected sensor recognition information when the vehicle is present at the vehicle position. The one or more processors further acquire the expected sensor recognition information associated with the determination target position based on the reference information, and determine whether or not the automatic driving conditions regarding the environment around the vehicle at the determination target position are satisfied by comparing the first sensor recognition information obtained by the vehicle present at the determination target position with the expected sensor recognition information associated with the determination target position. It is configured as The recognition sensor includes a camera that images the situation around the vehicle. The one or more processors further extract a road surface in the image by analyzing an image obtained by the camera. The first sensor recognition information includes an area ratio of the road surface in the image. An automatic driving management system.

Images