Vehicle recognition system and server

Abstract

To accurately identify and track a pose of each of plural vehicles within an ODD.SOLUTION: When detecting that a dynamic object 7 has reached an arbitrary feature point 4 on a traveling route 3, an infrastructure sensor 5 transmits to a server dynamic object ID information which includes a dynamic object ID for use in identifying the dynamic object 7 and time information obtained when the dynamic object 7 reaches the feature point. When detecting that a vehicle has reached the feature point 4, each of plural vehicles 1 transmits to a server 9 vehicle ID information which includes a vehicle ID for use in identifying an own vehicle and time information obtained when the own vehicle reaches the feature point 4. The server 9 performs matching processing on the dynamic object ID information and vehicle ID information, and thus determines whether a vehicle consistent with the dynamic object 7 exists among the plural vehicles 1.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a technology for raising the level of autonomous driving of autonomous vehicles.

Background Art

[0002] To achieve level 4 autonomous driving, usually, expensive sensors and processors are required. This is a very important issue for owners who own a large number of level 4 autonomous vehicles. This is because as the number of vehicles increases, the maintenance cost and hardware cost increase significantly. To reduce these costs, a predetermined number of sensors can be installed in the infrastructure so that a level 2 vehicle equipped with inexpensive sensors can achieve level 4 autonomous driving within the operational design domain (ODD). These infrastructure sensors constantly monitor the ODD. Here, the ODD refers to the driving environment conditions on which each autonomous driving system operates, such as road conditions, conditions regarding the distance to the vehicles in front and behind, speed conditions, sensor detection conditions, and the like.

[0003] Also, as described in Patent Document 1 and the like, by means of Vehicle-to-Infrastructure (V2I) technology, a vehicle can communicate with infrastructure services to obtain additional information for supporting autonomous driving. For example, sensors installed in the infrastructure can cover the blind spots of the vehicle, reduce the possibility of traffic accidents, and issue warnings to approaching vehicles. In addition, the infrastructure itself can notify the state of traffic lights. These V2I technologies can enhance the autonomous driving function of the vehicle. That is, it becomes possible to raise the level of autonomous driving without installing additional hardware in the vehicle.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

SUMMARY OF THE INVENTION

PROBLEMS TO BE SOLVED BY THE INVENTION

[0005] In order to raise the level of autonomous driving without adding expensive in-vehicle sensors, when multiple vehicles are moving within the ODD, in order to provide useful information, a system that provides V2I technology needs to accurately identify the positions of each of the multiple vehicles within the ODD. Also, an edge server that receives and calculates information from infrastructure sensors requires the initial pose of the vehicle in order to accurately track the pose of the vehicle. Here, in the present invention, the pose of a vehicle refers to the coordinate position (x-y) within the driving route on which the vehicle travels and the azimuth (θ) of the driving direction.

MEANS FOR SOLVING THE PROBLEMS

[0006] To solve the above problems, a vehicle recognition system according to the present invention includes an infrastructure sensor that monitors dynamic objects moving on a driving route, and a server that receives information from a plurality of vehicles traveling on the driving route. The infrastructure sensor, when detecting that a dynamic object has reached an arbitrary feature point on the driving route, transmits dynamic object ID information including a dynamic object ID for identifying the dynamic object and time information when the dynamic object reached the feature point to the server. Each of the plurality of vehicles, when detecting that it has reached a feature point, transmits vehicle ID information including a vehicle ID for identifying itself and time information when it reached the feature point to the server. The server determines whether there is a vehicle that matches the dynamic object among the plurality of vehicles by performing a matching process on the dynamic object ID information and the vehicle ID information.

[0007] In addition, the server according to the present invention receives dynamic object ID information including a dynamic object ID for identifying a dynamic object and time information when the dynamic object reaches an arbitrary feature point on the travel route from an infrastructure sensor that monitors dynamic objects moving on the travel route, and receives vehicle ID information including a vehicle ID for identifying itself and time information when itself reaches the feature point from each of a plurality of vehicles traveling on the travel route. A matching logic unit that determines whether there is a vehicle that matches the dynamic object among the plurality of vehicles by performing a matching process on the dynamic object ID information and the vehicle ID information.

Advantages of the Invention

[0008] According to the present invention, even in a vehicle whose function is restricted to the automatic driving level 2, it can operate completely autonomously within the ODD, that is, in the state of the automatic driving level 4, without installing expensive in-vehicle sensors in each vehicle, by a mechanism based on a predetermined rule. Thus, according to the present invention, it becomes possible to provide a cheaper alternative means for realizing the automatic driving of level 4. Further features related to the present invention will become apparent from the description of this specification and the accompanying drawings. In addition, problems, configurations, and effects other than those described above will be clarified by the description of the following embodiments.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Mode for Carrying Out the Invention

[0010] [Embodiment 1] Hereinafter, embodiments will be described with reference to the drawings. Figure 1 is a diagram showing an overview of a vehicle recognition system according to an embodiment of the present invention. Vehicle 1 is an automobile to be recognized. VID2 is a unique ID that vehicle 1 has. A predetermined driving route 3 is an area where the initial pose of vehicle 1 is calculated and then tracked. Also, the direction and position of traffic within driving route 3 are known. Feature point 4 is a fixed point within driving route 3 detected by an in-vehicle sensor. The position of feature point 4 is also predetermined. Infrastructure sensor 5 is installed on the roadside of driving route 3 and is mounted on an infrastructure that monitors the ODD including driving route 3. Sensor perception area 6 is a virtual space showing the concept of the physical world observed by infrastructure sensor 5. Inside sensor perception area 6, dynamic object 7 is shown as a moving object detected by infrastructure sensor 5. OID8 is a unique ID assigned to dynamic object 7 by infrastructure sensor 5. Edge server 9 is a computer that processes data received from vehicle 1 and infrastructure sensor 5. Infrastructure sensor output 10 is data transmitted from infrastructure sensor 5 to edge server 9 via a wired or wireless network. Vehicle output 0 is data transmitted from vehicle 1 to edge server 9 via a wireless network.

[0011] Figure 2 is an example of a hardware configuration in which the vehicle recognition system according to the present invention is implemented. Vehicle 1 is equipped with an in-vehicle sensor 11, an ECU 12, and an in-vehicle antenna 13. In-vehicle sensor 11 is used to detect feature point 4. ECU (Electronic Control Unit) 12 is an in-vehicle computer that processes data and controls other in-vehicle devices of vehicle 1. In-vehicle antenna 13 is a device for transmitting and receiving data between vehicle 1 and edge server 9.

[0012] In addition, the infrastructure sensor 5 has a sensor 14 and an RSU 15. The sensor 14 is a sensor device installed in the infrastructure to monitor an ODD including a predetermined travel route 3. The RSU (Road Side Unit) 15 is a roadside unit computer that preprocesses the data acquired from the sensor 14.

[0013] In addition, the edge server 9 has an edge server antenna 16 and an edge server computer 17. The edge server antenna 16 is a device for transmitting and receiving data on the edge server 9. The edge server computer 17 is a computer for processing the data received from the vehicle 1 and the infrastructure sensor 5.

[0014] FIG. 3 is a flowchart showing the initial vehicle pose calculation process performed by the vehicle identification system according to the present invention. In step S101, when the vehicle 1 reaches a predetermined travel route 3, it transmits its own VID2 to the edge server 9. Thereafter, processing is performed on each of the vehicle 1 side and the infrastructure sensor 5 side. First, the processing performed on the vehicle 1 side will be described. In step S102, the vehicle 1 starts searching for the feature point 4 using the in-vehicle sensor 11. In step S103, the in-vehicle sensor 11 detects that the vehicle 1 has reached the feature point 4. In step S104, the ECU 12 records the arrival time when the vehicle 1 reaches the feature point 4. In step S105, the vehicle 1 transmits its own VID2 and the arrival time to the edge server antenna 16 of the edge server 9 via the in-vehicle antenna 13.

[0015] Next, the processing performed on the infrastructure sensor 5 side will be described. In step S106, the infrastructure sensor 5 uses the sensor 14 to detect the dynamic object 7 and starts tracking and monitoring. In step S107, the sensor 14 detects that the dynamic object 7 has reached the feature point 4. In step S108, the infrastructure sensor 5 uses the RSU 15 to record the time of the event that the dynamic object 7 has reached the feature point 4. In step S109, the infrastructure sensor 5 transmits the OID 8 associated with the detected dynamic object 7 and the time of the arrival event to the edge server antenna 16 of the edge server 9 via the RSU 15.

[0016] When the edge server 9 receives data from both the vehicle 1 and the infrastructure sensor 5 as described above, it proceeds to step S110, where the edge server 9 collates the VID 2 and the OID 8 using the time data. In step S111, if the matching is successful, it proceeds to step S112, where the edge server 9 calculates the initial vehicle pose of the vehicle 1. If the matching is not successful, it proceeds to step S113 to execute backup processing. Details of the matching process, the initial vehicle pose calculation process, and the backup process will be described later. Thus, it is determined in step S114 that the initial vehicle pose calculation process is complete.

[0017] Details of the matching process will be described with reference to FIG. 4. FIG. 4 is an example of an ID table that can be used in step S110 in FIG. 3. The time stamp 18 is the time data recorded in the infrastructure sensor output 10 and the vehicle output 0. The ID type 19 indicates whether the recorded data belongs to the vehicle 1 or the dynamic object 7. The ID number 20 is the unique ID value for each of the vehicle 1 and the dynamic object. The pair ID 21 indicates the pair of the matched VID 2 and OID 8.

[0018] As shown in FIG. 4, in this embodiment, when the timestamp 18 is 0:25, a VID with an ID number of "01" and an OID with an ID number 20 of "10" are detected. Therefore, it is determined that these are matching pairs, and "100" is assigned as the pair ID 21. Similarly, when the timestamp is 0:56, a VID with an ID number 20 of "02" and an OID with an ID number of "12" are also detected, and the pair ID "101" is assigned to these.

[0019] Also, when the timestamp 18 is 1:12, an OID with an ID number 20 of "11" is detected, but the corresponding VID is not detected. In such a case, it is conceivable that an error occurred in the communication with Vehicle 1, or that something other than a vehicle, such as a person or an animal, was detected as a dynamic object. In the latter case, there is no problem because there is no vehicle to be recognized, but in the former case, although a vehicle exists within the ODD, it cannot be recognized or tracked, resulting in a safety issue.

[0020] To prevent such a situation, when only the OID is received as described above, the edge server 9 extracts the VID that has not yet been successfully matched from the list of VIDs received in step S101 of FIG. 3, identifies the vehicle 1 having that VID, and identifies the vehicle 1 as the vehicle having the VID to be matched with the OID for which the matching did not succeed. This is the backup process performed in step S113 of FIG. 3. Also, when multiple VIDs that have not been successfully matched are extracted, the edge server 9 may issue a command to transmit the location information to each of the vehicles 1 having those VIDs.

[0021] FIG. 5 is a block diagram showing a functional architecture for realizing initial vehicle pose calculation implemented in the vehicle recognition system according to this embodiment. The vehicle 1 is equipped with various ECUs that function as a feature point detection unit 22, a time logger 23, and a data transmission unit 24. The feature point detection unit 22 exhibits a function for finding the feature point 4. The time logger 23 executes a function for recording the time when the vehicle 1 reaches the feature point 4. The data transmission unit 24 executes a function for transmitting the vehicle output 0 to the edge server 9.

[0022] In addition, the infrastructure sensor 5 is equipped with various ECUs that function as a dynamic object detection unit 25, an OID assignment logic unit 26, a feature point detection unit 27, a time logger 28, and a data transmission unit 29. The dynamic object detection unit 25 executes a function for processing sensor data and extracting information regarding the dynamic object 7 therefrom. The OID assignment logic unit 26 executes a function for assigning a unique ID to each detected dynamic object 7. The feature point detection unit 27 executes a function for acquiring a trigger when the dynamic object 7 reaches the feature point 4. The time logger 28 executes a function for recording the detected time when the feature point detection unit 27 detects that the dynamic object 7 has reached the feature point 4. The data transmission unit 29 executes a function for transmitting the infrastructure sensor output 10 to the edge server 9.

[0023] Similarly, various ECUs that function as a matching logic unit 30, an ID database 31, and an initial vehicle pose calculation unit 32 are also mounted on the edge server 9. However, when designing the edge server as a cloud on the network, these functions may be executed by software implemented as a program. The matching logic unit 30 executes a function of pairing the OID 8 and the VID 2 using the timestamp 18. The ID database 31 executes a function of storing the matched ID pair 21 in the storage device of the edge server 9. Also, it executes a function of storing the VID transmitted to the edge server 9 when the vehicle 1 enters the travel route 3 as a list. The initial vehicle pose calculation unit 32 executes a function of calculating the position and orientation of the vehicle 1 based on the observation data transmitted from the infrastructure sensor 5 when the matching between the vehicle 1 and the dynamic object 7 is established.

[0024] FIG. 6 is a diagram for explaining an example of a method for calculating an initial vehicle pose, which is executed in step S112 of FIG. 3. The coordinates 33 are the positions of the predetermined feature points 4. Also, the predetermined direction 34 is the traffic direction set with respect to the travel route 3. When the vehicle 1 reaches the point of the coordinates 33 of the feature point 4, the vehicle 1 and the infrastructure sensor 5 execute the above-described processing and transmit a set of an ID and a timestamp to the edge server 9. Then, the matching logic unit 30 performs a matching process. When the matching is established, the initial vehicle pose calculation unit 32 calculates the position: "coordinates [40.2, 117.9]" and the direction: "driving direction 34" as the initial vehicle pose of the vehicle 1.

[0025] FIG. 7 shows an example related to the detection of feature points using a vehicle as an example. The travel route maintenance camera 35 is an in-vehicle sensor 11 attached to the vehicle 1, and the vehicle 1 can detect and track the lane markers on the travel route 3. In this example, a box-shaped marker 36 formed on the travel route 3 is detected as the feature point 4 using the travel route maintenance camera 35. In FIG. 7, the feature point 4 is shown as a box-shaped marker 36.

[0026] FIG. 8 is a diagram showing the case where the system according to this embodiment is applied at an intersection on a general road. The intersection 37 is an ODD area where the position of the vehicle should be accurately tracked after the initial pose of the vehicle is calculated as a result of the process shown in FIG. 3. In this case, it becomes possible to treat the stop line of the signal as the feature point 4, and it becomes possible to accurately track the position of the vehicle 1 that has entered the intersection.

[0027] As described above, in this embodiment, markers, stop lines, etc. provided on the travel route are set as feature points, and when the vehicle reaches the feature point, the ID information and time stamp of the vehicle 1 and the dynamic object 7 are acquired from each of the vehicle 1 and the infrastructure sensor 5, and a matching process is performed to determine whether the vehicle 1 and the dynamic object 7 match based on those information. When the matching is established, the initial vehicle pose of the vehicle 1 at the feature point 4 is calculated.

[0028] The relationship between the vehicle 1 and the dynamic object 7 each having the VID and OID for which the matching is established is that of the vehicle 1 and the dynamic object 7 which is the result of the vehicle being detected by the infrastructure sensor 5. Therefore, once the matching is established, the observation of the dynamic object 7 by the infrastructure sensor 5 performed later is synonymous with the observation of the vehicle 1. Moreover, when the matching is established, since the initial vehicle pose is calculated, it becomes possible to track the vehicle very accurately both in terms of position and direction after the matching is established. Therefore, the edge server 9 can control the behavior of the vehicle in the ODD very accurately only with the sensor information received from the existing infrastructure sensor 5. That is, it becomes possible to execute a higher level of autonomous driving without mounting an expensive additional device on the vehicle.

[0029] [Embodiment 2] FIG. 9 is a diagram showing a method for detecting feature point 4 according to the example of a vehicle in Example 2. The RFID transmitter 38 is a transmission device for generating the feature point 4 within a predetermined travel route 3. The in-vehicle RFID device 39 is a sensor for detecting the feature point 4 generated by the RFID transmitter 38, corresponding to the in-vehicle sensor 11 in FIG. 2. In this way, by generating the feature point 4 using the RFID transmitter 38 installed on the roadside, it becomes possible to easily generate the feature point 4 on the travel route 3 without the need to apply physical markings or the like. Further, by configuring the RFID transmitter 38 to be portable, it becomes possible to adjust the position where the feature point is generated, the area size, etc. according to the environment such as weather and road conditions.

[0030] FIG. 10 is a diagram showing a situation where the system according to this embodiment is applied to a T-junction 40. The T-junction 40 is an ODD area where the vehicle should be accurately positioned after the initial positioning of the vehicle 1 is completed. Even in an area such as the T-junction 40, since the feature point 4 can be generated by the RFID transmitter 38 (see FIG. 9), it becomes possible to achieve a high level of autonomous driving using existing facilities as in Example 1.

[0031] [Example 3] FIG. 11 shows an example when a communication failure occurs before the initial pose of the vehicle is calculated. The entrance 41 is a location where the vehicle 1 reaches the predetermined travel route 3, and the exit 42 is a location where the vehicle 1 leaves the travel route 3. The ODD 43 is an ODD area where the position of the vehicle 1 should be accurately tracked after the initial pose of the vehicle 1 is calculated. When the vehicle 1 fails to communicate with the edge server 9 when it reaches the feature point near the entrance 41 as shown by S201 in FIG. 11, it maintains the travel as shown by S202 without changing the autonomous driving level and leaves the travel route 3 from the exit 42.

[0032] FIG. 12 shows another example of communication failure. After calculating the initial pose of vehicle 1, as shown in S301, if the connection between vehicle 1 and edge server 9 is lost within the ODD, such as in a parking lot, vehicle 1 is stopped as shown in S302 and waits until the connection with edge server 9 is restored.

[0033] When a communication failure occurs before and after calculating the initial pose of vehicle 1, by adopting the above method, it is possible to prevent the safety level from being endangered. Therefore, the owner of vehicle 1 can safely introduce this system.

[0034] According to the embodiments of the present invention described above, the following operational effects are achieved. (1) The vehicle recognition system according to the present invention is a vehicle recognition system including an infrastructure sensor that monitors dynamic objects moving on a driving route and a server that receives information from a plurality of vehicles driving on the driving route. The infrastructure sensor transmits dynamic object ID information including a dynamic object ID for identifying the dynamic object and time information when the dynamic object reaches a feature point to the server when detecting that the dynamic object has reached an arbitrary feature point on the driving route. Each of the plurality of vehicles transmits vehicle ID information including a vehicle ID for identifying itself and time information when itself reaches the feature point to the server when detecting that it has reached the feature point. The server determines whether there is a vehicle that matches the dynamic object among the plurality of vehicles by performing a matching process on the dynamic object ID information and the vehicle ID information.

[0035] With the above configuration, even for a vehicle whose function is restricted to the automatic driving level 2, based on a mechanism according to a predetermined rule, it can operate completely autonomously within the ODD, that is, in the state of automatic driving level 4, without installing expensive in-vehicle sensors in each vehicle. Thus, according to the present invention, it is possible to provide a cheaper alternative means for realizing level 4 automatic driving.

[0036] (2) The infrastructure sensor observes the position and moving direction of a dynamic object on its travel route, transmits observation data including the observation results to the server, and when the server determines that there is a vehicle that matches the dynamic object, based on the observation data, it calculates the position and moving direction of the vehicle when the vehicle reaches the feature point. Thereby, the vehicle state (position and moving direction) at the time of reaching the feature point can be specified, and since the behavior after reaching the feature point can be tracked by the infrastructure sensor, the behavior of the vehicle within the ODD can be accurately grasped, and level 4 automated driving can be realized with high accuracy.

[0037] (3) Each of a plurality of vehicles transmits its vehicle ID to the server when entering the operation area where the feature points are arranged. The server stores the vehicle IDs received from each of the plurality of vehicles and, when receiving dynamic object ID information and not receiving vehicle ID information that matches the dynamic object ID information, executes a backup process of searching among the stored vehicle IDs to determine whether there is a vehicle ID that should be matched with the dynamic object ID. Thereby, even when a vehicle fails to transmit vehicle ID information due to communication problems or the like, the matching process can be performed again, improving the accuracy of vehicle recognition.

[0038] (4) The feature point is a marker on the travel route, and the vehicle detects the feature point with an in-vehicle camera mounted on the vehicle. Or the feature point is defined by a signal transmitted from an RFID communicator, and the vehicle detects the feature point with an RFID device mounted on the vehicle. Thereby, the feature point can be detected using existing cameras and communication devices without adding expensive equipment, suppressing cost increases.

[0039] (5) Further, the server according to the present invention receives dynamic object ID information including a dynamic object ID for identifying a dynamic object and time information when the dynamic object reaches an arbitrary feature point on the travel route from an infrastructure sensor that monitors the dynamic object moving on the travel route, and receives vehicle ID information including a vehicle ID for identifying itself and time information when itself reaches the feature point from each of a plurality of vehicles traveling on the travel route. A matching logic unit determines whether there is a vehicle that matches the dynamic object among the plurality of vehicles by performing a matching process on the dynamic object ID information and the vehicle ID information. Thus, the same effect as (1) can be expected.

[0040] (6) The server receives observation data including an observation result of the infrastructure sensor observing the position and moving direction of the dynamic object on the travel route of the dynamic object. When it is determined that there is a vehicle that matches the dynamic object, the server further has an initial vehicle pose calculation unit that calculates the position and moving direction of the vehicle at the time when the vehicle reaches the feature point according to the reception of the observation data. Thus, the same effect as (2) can be expected.

[0041] (7) When each of the plurality of vehicles enters an operation area where the feature points are arranged, the server receives and stores the vehicle ID from each of the plurality of vehicles. When the server receives the dynamic object ID information and has not received the vehicle ID information that matches the dynamic object ID information, the server further has a processing unit that executes a backup process of searching whether there is a vehicle ID to be matched with the dynamic object ID among the stored vehicle IDs. Thus, the same effect as (3) can be expected.

[0042] Note that the present invention is not limited to the above embodiments, and various modifications are possible. For example, the above embodiments have been described in detail for easy understanding of the present invention, but the present invention is not necessarily limited to the embodiments having all the configurations described. Also, a part of the configuration of one embodiment can be replaced with the configuration of another embodiment. Further, the configuration of another embodiment can be added to the configuration of one embodiment. Additionally, for a part of the configuration of each embodiment, it is possible to delete it, or add or replace it with other configurations.

Explanation of Reference Numerals

[0043] 1 Vehicle, 2 VID (Vehicle ID), 3 Travel Route, 4 Feature Point, 5 Infrastructure Sensor, 7 Dynamic Object, 8 OID (Dynamic Object ID), 9 Edge Server, 11 On-Vehicle Sensor, 14 Sensor, 16 Edge Server Antenna (Receiving Unit), 17 Edge Server Computer (Processing Unit), 30 Matching Logic Unit, 32 Initial Vehicle Pose Calculation Unit

Claims

1. A vehicle recognition system for recognizing a vehicle traveling on a travel route, comprising: an infrastructure sensor for monitoring a dynamic object moving on the travel route, and a server for receiving information from a plurality of vehicles traveling on the travel route, wherein when the infrastructure sensor detects that the dynamic object has reached an arbitrary feature point on the travel route, the infrastructure sensor transmits dynamic object ID information including a dynamic object ID for specifying the dynamic object and time information when the dynamic object has reached the feature point to the server, each of the plurality of vehicles transmits vehicle ID information including a vehicle ID for specifying itself and time information when itself has reached the feature point to the server when detecting that it has reached the feature point, the server determines whether there is a vehicle that matches the dynamic object among the plurality of vehicles by performing matching processing on the dynamic object ID information and the vehicle ID information, each of the plurality of vehicles transmits the vehicle ID to the server when entering an operation area where the feature point is arranged, the server stores the vehicle ID received from each of the plurality of vehicles, and when receiving the dynamic object ID information and not receiving the vehicle ID information that matches the dynamic object ID information, executes a backup process of searching whether there is a vehicle ID to be matched with the dynamic object ID among the stored vehicle IDs, A vehicle recognition system characterized by the above.

2. The vehicle recognition system according to claim 1, wherein the infrastructure sensor observes a position and a moving direction of the dynamic object on the travel route, and transmits observation data including the observation result to the server, when the server determines that there is a vehicle that matches the dynamic object, the server calculates the position and the moving direction of the vehicle at the time when the vehicle has reached the feature point based on the observation data, A vehicle recognition system characterized by the above.

3. The vehicle recognition system according to claim 1, wherein the feature point is a marker on the travel route, and the vehicle detects the feature point by an in-vehicle camera mounted on the vehicle, A vehicle recognition system characterized by the above.

4. The vehicle recognition system according to claim 1, wherein the feature points are defined by signals transmitted from an RFID communication device, and the vehicle detects the feature points by an RFID device mounted on the vehicle. A vehicle recognition system characterized by the above.

5. A receiving unit that receives dynamic object ID information including a dynamic object ID for identifying the dynamic object and time information when the dynamic object reaches any feature point on the travel route from an infrastructure sensor that monitors the dynamic object moving on the travel route, and receives vehicle ID information including a vehicle ID for identifying itself and time information when itself reaches the feature point from each of a plurality of vehicles traveling on the travel route; A matching logic unit that determines whether there is a vehicle that matches the dynamic object among the plurality of vehicles by performing matching processing on the dynamic object ID information and the vehicle ID information. When each of the plurality of vehicles enters an operation area where the feature points are arranged, the vehicle ID is received and stored from each of the plurality of vehicles. When the server receives the dynamic object ID information and has not received the vehicle ID information that matches the dynamic object ID information, the server further has a processing unit that executes a backup process of searching whether there is a vehicle ID to be matched with the dynamic object ID among the stored vehicle IDs. A server characterized by the above.

6. The server according to claim 5, wherein the infrastructure sensor receives observation data including observation results of the position and moving direction of the dynamic object on the travel route of the dynamic object, when the server determines that there is a vehicle that matches the dynamic object, the server further has an initial vehicle pose calculation unit that calculates the position and moving direction of the vehicle at the time when the vehicle reaches the feature point according to the reception of the observation data. A server characterized by the above.

Images