Vehicle identification system

Abstract

To provide a vehicle identification system that can prevent the occurrence of a situation in which efficient traffic is inhibited in identification of a target vehicle.SOLUTION: A vehicle identification system includes one or more processors. The one or more processors are configured to execute the following first processing to third processing. The first processing is to instruct a first vehicle that execution of a predetermined action to identify a target vehicle is started while the first vehicle travels in a vehicle identification zone. The second processing is to start recognition processing of recognizing an action executed by the first vehicle by using a sensor while the first vehicle travels in the vehicle identification zone. The third processing is to identify the first vehicle executing the predetermined action as the target vehicle.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to a technique for identifying a target vehicle.

Background Art

[0002] Identifying a target vehicle is important in functions that provide control and services to the target vehicle. For example, in automatic valet parking (AVP) in a parking lot, identification of the AVP target vehicle is required from the viewpoints of reliability and safety.

[0003] In Patent Document 1, as a technique related to identification of a target vehicle, a vehicle authentication method in a parking lot is disclosed. The vehicle authentication method disclosed in Patent Document 1 transmits information instructing execution of a predetermined action to the target vehicle, checks whether the vehicle in the parking lot has executed the predetermined action, and authenticates the vehicle that has executed the predetermined action as the target vehicle and performs localization.

[0004] In addition, there are the following Patent Documents 2 or 3 as documents showing the technical level of this technical field.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0006] Patent Document 1 discloses a technology for vehicle identification (authentication) based on vehicle actions. In particular, in Patent Document 1, vehicle identification is performed with the vehicle stopped at the drop-off location. When vehicle identification is performed based on vehicle actions, the vehicle is required to perform an action with a certain duration, so vehicle identification takes a certain amount of time. For this reason, in the technology disclosed in Patent Document 1, the vehicle will remain stopped at the drop-off location for a while from the start to the completion of vehicle identification. A vehicle occupying a space for a long period of time hinders efficient traffic flow and is undesirable.

[0007] One of the purposes of this disclosure is, in light of the above-mentioned issues, to prevent situations in which efficient traffic is disrupted by technologies for identifying target vehicles. [Means for solving the problem]

[0008] One aspect of this disclosure relates to a vehicle identification system for identifying a target vehicle. The vehicle identification system includes one or more processors. The one or more processors are configured to instruct a first vehicle to begin performing a predetermined action for identifying a target vehicle while the first vehicle is traveling through a vehicle identification zone, to begin a recognition process that uses sensors to recognize the action performed by the first vehicle while the first vehicle is traveling through the vehicle identification zone, and to identify the first vehicle performing the predetermined action as a target vehicle. [Effects of the Invention]

[0009] According to this disclosure, while the first vehicle is traveling through a vehicle identification zone, an instruction to start a predetermined action is given, and the recognition process begins. As a result, when the first vehicle stops to receive the function, the identification of the target vehicle can be completed, or part of the action to be performed by the first vehicle can be recognized. Therefore, the time that the target vehicle has to stop for vehicle identification can be reduced. Consequently, the occurrence of situations that hinder efficient traffic can be suppressed. [Brief explanation of the drawing]

[0010] [Figure 1] This is a conceptual diagram illustrating automated valet parking in a parking lot. [Figure 2] This is a conceptual diagram illustrating the overview of the vehicle identification system according to this embodiment. [Figure 3] This is a conceptual diagram illustrating an example of a challenge related to selecting a camera for recognition processing. [Figure 4] This is a conceptual diagram illustrating the overview of camera recognition processing. [Figure 5] This flowchart shows an example of the process performed in the vehicle identification system. [Figure 6] This figure shows an example of the hardware configuration of the vehicle identification system according to this embodiment. [Modes for carrying out the invention]

[0011] 1. Introduction Various functions are being considered to provide control and service to the target vehicles. One such function is Auto Valet Parking (AVP) in parking lots. AVP automatically handles the entry and exit of target vehicles within the parking lot without user intervention. Other functions include the loading, unloading, and organization of target vehicles within the garage using transport equipment.

[0012] Figure 1 is a conceptual diagram illustrating AVP. The management system 100 manages AVP in parking lot 2. Sensors 150 are installed in parking lot 2 to detect the position and status of each vehicle 1 within parking lot 2. The management system 100 manages information about parking lot 2 and each vehicle 1 based on the detection information acquired using the sensors 150. The management system 100 then communicates with the target vehicle in parking lot 2 (for example, via Wi-Fi) and performs AVP for the target vehicle. For example, consider the case where a user wants to park vehicle 1 using AVP. The user parks vehicle 1 (target vehicle) at vehicle stopping position 2b in parking area 2a. After the user gets out of vehicle 1 (target vehicle) at vehicle stopping position 2b, the user makes an AVP request. Based on management data regarding parking lot 2 and each vehicle 1, the management system 100 transmits command information such as parking position and driving route to the target vehicle. The control system of the target vehicle controls the target vehicle according to the received command information, thereby performing AVP related to parking.

[0013] In AVP, from the standpoint of reliability and safety, it is required to identify the target vehicle upon entry (identification can also be rephrased as authentication). This is to confirm that vehicle 1 parked at vehicle stopping position 2b is vehicle 1 (the target vehicle) belonging to a legitimate user. If vehicle identification is successful, vehicle 1 parked at vehicle stopping position 2b is determined to be a legitimate target vehicle, and AVP is started. By identifying the target vehicle in this way, only legitimate target vehicles can be permitted to enter the parking lot. Conversely, if the target vehicle is not identified, there is a risk that unrelated vehicles that are not target vehicles may enter the parking lot. This is problematic from the standpoint of reliability and safety. Similarly, functions that provide control and services to other target vehicles (hereinafter referred to as "AVP and other functions") are also usually required to identify the target vehicle.

[0014] The vehicle identification system according to this embodiment can be configured to identify a target vehicle using functions such as AVP. The vehicle identification system according to this embodiment employs a method (hereinafter referred to as the "action-based identification method") that instructs vehicle 1 to perform an action and identifies the target vehicle based on whether the action recognized using sensor 150 matches an expected action.

[0015] Here, an action can be defined by a combination of a device (means) that performs the action and the operating pattern of that device. Examples of devices that perform an action include lighting devices (headlights, brake lights, fog lights, etc.), interior lighting devices, horns, turn signals, wipers, doors, door windows, engines, electric motors, etc. For example, one action is to flash the headlights in a specified pattern. Another example is to sound the horn in a specified pattern. An action may also include a request for repetition of an operating pattern.

[0016] Action-based identification methods require the detection of actions by vehicle 1 using sensor 150. Therefore, sensor 150 is configured to detect actions that vehicle 1 is to perform. For example, to trigger a visually detectable visible action (such as an action related to the lighting system), sensor 150 is configured as a camera. Alternatively, to trigger an audibly detectable audible action (such as sounding the horn), sensor 150 is configured as a microphone.

[0017] The identification method based on actions can provide freedom in designing the actions used for vehicle identification and has advantages such as high flexibility. On the other hand, in the identification method based on actions, since the vehicle 1 is required to execute an action having a certain duration, a certain amount of time is required for vehicle identification. For this reason, in the prior art (for example, the technology disclosed in Patent Document 1), it is assumed that the vehicle 1 continues to stop at the vehicle stop position 2b for some time from the start to the completion of vehicle identification. However, the fact that the vehicle 1 occupies a certain space for a long time hinders efficient traffic and is not preferable. For example, in AVP, the efficient storage of the vehicle 1 is hindered, and there is a risk of causing congestion of the vehicles 1 waiting for storage.

[0018] In response to the above problems, the vehicle identification system according to the present embodiment can identify the target vehicle while suppressing the occurrence of a situation where efficient traffic is hindered.

[0019] 2 Vehicle Identification System FIG. 2 is a conceptual diagram for explaining the outline of the vehicle identification system according to the present embodiment. The vehicle identification system according to the present embodiment can be composed of a management system 100 that executes processing and a sensor 150 that detects an action executed by the vehicle 1.

[0020] In the vehicle identification system according to the present embodiment, a vehicle identification zone 3 having a certain range is provided in front of the vehicle stop position 2b. The vehicle stop position 2b is a position where the stop of the target vehicle is required in functions such as AVP. It is assumed that the vehicle 1 for which the user wants to receive control / service reaches the vehicle stop position 2b through the vehicle identification zone 3 and stops. The vehicle identification zone 3 may be provided as a virtual range in information processing.

[0021] In the vehicle identification system according to this embodiment, vehicle identification begins when vehicle 1 (first vehicle) travels through vehicle identification zone 3. First, the management system 100 instructs vehicle 1 to begin executing a predetermined action while vehicle 1 is traveling through vehicle identification zone 3. If vehicle 1 is a legitimate target vehicle, vehicle 1 is expected to begin executing the predetermined action in accordance with the instruction. Vehicle 1 may be configured to execute the predetermined action multiple times.

[0022] Next, the management system 100 starts a process (recognition process) to recognize the action that vehicle 1 (first vehicle) will perform using the sensor 150 while vehicle 1 is traveling through the vehicle identification zone 3. The management system 100 then identifies vehicle 1, which is performing a predetermined action, as the target vehicle. For example, if the predetermined action is flashing the headlights, the management system 100 recognizes the flashing pattern from the detection information of the sensor 150 during the recognition process. When the recognized pattern matches the operation pattern of the predetermined action, the management system 100 determines that the predetermined action has been performed and identifies vehicle 1 as the target vehicle. In particular, the vehicle identification system may be configured to complete the identification of the target vehicle before vehicle 1 reaches the vehicle stopping position 2b. For example, the management system 100 is configured to determine a predetermined action to instruct, using the duration of the action as an indicator, according to the state of vehicle 1 (speed, position, etc.).

[0023] After completing the identification of the target vehicle, the management system 100 begins providing control and services to the target vehicle that has stopped at the vehicle stopping position 2b.

[0024] As described above, according to this embodiment, before vehicle 1 reaches vehicle stopping position 2b, an instruction to start executing a predetermined action is given, and the recognition process is initiated. As a result, when vehicle 1 reaches vehicle stopping position 2b, the identification of the target vehicle can be completed, or part of the action to be performed by vehicle 1 can be recognized. Therefore, the time that the target vehicle is stopped at vehicle stopping position 2b can be shortened in relation to vehicle identification. Consequently, the occurrence of situations that hinder efficient traffic can be suppressed.

[0025] 3. Camera selection process In the following, we consider a case in the vehicle identification system according to this embodiment where the predetermined action to be instructed is a visible action, and the sensor 150 used for recognition processing is configured as a camera. In this case, the vehicle identification system needs to use the camera to recognize the visible action performed by the vehicle 1.

[0026] Incidentally, in the AVP and other functions, it is assumed that the sensor 150 includes multiple cameras installed in a predetermined area (for example, parking lot 2). When applying the vehicle identification system according to this embodiment, a camera to be used for recognition processing is selected from among the multiple cameras. Then, while vehicle 1 is driving through the vehicle identification zone 3, recognition processing using the selected camera is started.

[0027] Here, we consider how to select the camera to be used for recognition processing. Depending on its placement and specifications, the camera has a range in which it can accurately detect visible actions (hereinafter referred to as the "effective recognition range"). The effective recognition range does not necessarily coincide with the camera's field of view. The effective recognition range may also depend on the relative distance to the vehicle 1 to be recognized, the relationship between the camera's orientation and the orientation of the vehicle 1 to be recognized, etc. In order to recognize the execution of a predetermined visible action by vehicle 1, it is necessary that vehicle 1 is located within the effective recognition range of the camera used for recognition processing from the start to the end of the predetermined visible action.

[0028] One approach is to pre-select a camera to be used for recognition processing, since the vehicle identification zone 3 is a predetermined range. For example, a camera whose effective recognition range extends to a certain area from the starting position of the vehicle identification zone 3 could be used for recognition processing. However, vehicle 1 will move a certain distance during the time from the start to the end of a predetermined visible action. Therefore, the effective recognition range of a single camera may not be able to capture the entirety of the predetermined visible action from start to finish. For example, this could happen if vehicle 1 is moving at a high speed or if the predetermined visible action starts late.

[0029] Figure 3 is a conceptual diagram illustrating an example of the above problem. In Figure 3, three cameras 151a, 151b, and 151c are shown as sensors 150. The effective recognition ranges 152a, 152b, and 152c of the three cameras 151a, 151b, and 151c are also shown. Camera 151b is positioned to image vehicle 1 after camera 151a. Furthermore, camera 151c is positioned to image vehicle 1 after camera 151b.

[0030] Figure 3 shows the case where camera 151a is used for recognition processing. Figure 3 shows two patterns, pattern A and pattern B, regarding the status of the recognition processing. Pattern A shows the normally expected situation. In pattern A, the interval 4 from the start to the end of a predetermined visible action is included in the effective recognition range 152a of camera 151a. Therefore, the execution of the predetermined visible action by vehicle 1 can be recognized normally. On the other hand, pattern B shows a situation where the start of the predetermined visible action is delayed. For example, this occurs when communication delays or processing delays occur. In pattern B, part of the interval 4 is not included in the effective recognition range 152a. Therefore, the execution of the predetermined visible action by vehicle 1 cannot be recognized, and vehicle identification fails.

[0031] If the default camera fails to successfully recognize the execution of a predetermined visibility action, it is conceivable to switch the camera used for recognition processing and resume the recognition process with the execution of the predetermined visibility action in the next cycle. However, in this case, the recognition processing performed with the default camera becomes wasted. This is undesirable in terms of processing efficiency. Furthermore, if the camera is switched in response to a failure to recognize properly, the start of recognition processing using the switched camera may be delayed. Consequently, there is a risk of repeated failures in vehicle identification. Alternatively, it is conceivable to select multiple cameras to be used for recognition processing in advance to ensure a sufficient effective recognition range. However, in this case, there is a possibility that some cameras will not be used for recognition processing. This is also undesirable in terms of processing efficiency.

[0032] Therefore, the vehicle identification system according to this embodiment can be configured to perform a camera selection process (camera selection process) prior to the start of the recognition process, so as to recognize the period from the start to the end of a predetermined visible action (hereinafter referred to as the "action interval").

[0033] Figure 4 is a conceptual diagram illustrating the overview of the camera selection process. In the camera selection process, a provisional selection of the camera to be used for the recognition process is performed first. The recognition process does not start at the provisional selection stage. The camera initially provisionally selected here may be a predetermined default camera. In Figure 4, camera 151a is provisionally selected.

[0034] Next, in the camera selection process, a process (determination process) is performed to determine whether or not the action section can be recognized using the provisionally selected camera (provisional camera). The determination process can be performed by verifying whether or not the predicted section 4a of the action section is included in the effective recognition range of the provisional camera. The predicted section 4a can be calculated based on the position where a predetermined visible action is started (action start position), the duration of the predetermined visible action, and the speed of vehicle 1. The action start position can be detected using the provisional camera. For example, the rise (first) of the predetermined visible action pattern can be detected using the provisional camera, and the position of vehicle 1 at that time can be obtained as the action start position. The duration of the predetermined visible action is known information in the management system 100. The speed of vehicle 1 can be recognized using the provisional camera. Alternatively, it may be obtained by communication with vehicle 1.

[0035] If the judgment process determines that the action interval can be recognized by the temporary camera, the temporary camera is selected as the camera to be used for the recognition process. On the other hand, if the action interval cannot be recognized by the temporary camera, the temporary selection is redone, and the temporary camera is changed. Then, the judgment process is repeated. This allows the camera that has been previously confirmed to be able to recognize the action interval to be selected as the camera to be used for the recognition process.

[0036] Here are two examples of how to change the temporary camera. In the following examples, the temporary camera that was previously selected will be called the "first camera." Also, one of the cameras installed in the vehicle identification zone 3 that captures vehicle 1 after the first camera will be called the "second camera." For example, in Figure 4, if camera 151a is the first camera, then the second camera is either camera 151b or camera 151c.

[0037] In the first example (see Figure 4), the second camera is tentatively selected as a temporary camera. In Figure 4, assuming camera 151a is the first camera, camera 151b is tentatively selected as a temporary camera. The effective recognition range of the second camera is expected to include all action intervals of subsequent cycles. In other words, when the second camera is selected as the camera to be used for recognition processing, the target of the recognition processing is assumed to be the action intervals of subsequent cycles. Therefore, in the second determination process in the first example, it is verified whether the predicted interval 4a of the subsequent cycles is included in the effective recognition range of the second camera. At this time, the action start position may be predicted from the action start position acquired in the previous step, or it may be detected using the second camera.

[0038] In the second example (see Figure 4), the combination of the first and second cameras is tentatively selected as a provisional camera. In Figure 4, assuming that camera 151a is the first camera, the combination of camera 151a and camera 151b is tentatively selected as a provisional camera. The effective recognition range of the combination of the first and second cameras is an extension of the effective recognition range of the first camera, and is therefore expected to include the prediction interval 4a. The re-determination process in the second example may be performed based on the relationship between the previously calculated prediction interval 4a and the effective recognition range of the combination of the first and second cameras.

[0039] By adopting either the first or second example, the situation where the judgment process is excessively repeated is suppressed, thereby enabling the camera selection process to be executed effectively.

[0040] As explained above, by performing the camera selection process, the vehicle identification system can start the recognition process using cameras that have been previously confirmed to be capable of recognizing the action section. This prevents failures in the vehicle identification process during the recognition process, and consequently improves processing efficiency.

[0041] Figure 5 is a flowchart showing an example of the process performed in the vehicle identification system with respect to the camera selection process described above. The process shown in the flowchart in Figure 5 is started, for example, after vehicle 1 enters the vehicle identification zone 3 and communication is established between the management system 100 and vehicle 1.

[0042] In step S100, the management system 100 instructs vehicle 1 to begin performing a predetermined visible action.

[0043] Next, in step S110, the management system 100 tentatively selects a temporary camera. The tentative selection in step S110 is the first tentative selection (initial selection) in the camera selection process. For example, the management system 100 tentatively selects a predetermined default camera as the temporary camera.

[0044] After step S110, the management system 100 performs a determination process with respect to the provisionally selected provisional camera. The management system 100 uses the provisional camera to obtain the action start position (step S120) and determines whether the provisional camera can recognize the entire sequence of a predetermined visible action performed by vehicle 1, from start to finish (action interval) (step S130).

[0045] If the determination process determines that the action interval cannot be recognized by the temporary camera (step S140; No), the management system 100 changes the temporary camera (step S150) and performs the determination process again. Here, if the previously acquired action start position is referenced, the process related to step S120 can be skipped.

[0046] If the judgment process determines that the action interval can be recognized by the temporary camera (step S140; Yes), the management system 100 selects the temporarily selected temporary camera as the camera to be used for the recognition process (step S160). Then, the management system 100 starts the recognition process using the selected camera (step S170).

[0047] 4 Hardware Configuration Figure 6 shows an example of the hardware configuration of the vehicle identification system 10 according to this embodiment. The vehicle identification system 10 consists of a vehicle 1 and a management system 100 that communicates with the vehicle 1. The vehicle identification system 10 includes a sensor 150 that is communicatively connected to the management system 100.

[0048] The management system 100 includes a processor 110, a storage device 120, and a communication interface 130.

[0049] The processor 110 performs various processes. The processor 110 is composed of components such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), and an FPGA (Field-Programmable Gate Array).

[0050] The storage device 120 is connected to the processor 110 and stores various information necessary for the processing performed by the processor 110. The storage device 120 is composed of recording media such as RAM (Random Access Memory), ROM (Read Only Memory), SSD (Solid State Drive), HDD (Hard Disk Drive), etc.

[0051] The storage device 120 stores a computer program 121 and management data 122.

[0052] The computer program 121 describes the processes to be executed by the processor 110. Information processing by the management system 100 may be realized through the cooperation of the processor 110, which executes the processes related to the computer program 121, and the storage device 120. In particular, information processing related to vehicle identification according to this embodiment may be realized.

[0053] The management data 122 records various management information. For example, the management data 122 records management information related to a predetermined action (device that performs the action, operation pattern, etc.), management information related to the vehicle identification zone 3 (location, range, etc.), management information related to the sensor 150 (placement, specifications, default camera, etc.), etc.

[0054] The communication interface 130 is an interface for communicating with external devices of the management system 100 to send and receive information. For example, the communication interface 130 consists of devices for connecting to surrounding devices via wireless LAN, devices for connecting to a mobile communication network, devices for connecting to the internet, etc. The management system 100 sends and receives information with the vehicle 1 via the communication interface 130.

[0055] Vehicle 1 is equipped with a control processing unit 210, an on-board sensor 220, a communication interface 230, and an on-board device 240.

[0056] The control processing unit 210 is connected to the on-board sensor 220, the communication interface 230, and the on-board device 240 in a communicative manner. The control processing unit 210 is a computer that performs information processing related to the control of the vehicle 1 based on various information. The control processing unit 210 may include a processor and a memory device. The information processing by the control processing unit 210 may be realized through the cooperation of the processor and the memory device.

[0057] For example, the control processing unit 210 is composed of one or more ECUs (Electronic Control Units). Alternatively, for example, the control processing unit 210 is composed of a kit (e.g., an AVP kit) for functions provided by the management system 100. The control processing unit 210 generates and outputs control signals for controlling the vehicle 1 through information processing. In particular, when the vehicle 1 receives an instruction from the management system 100 to start executing a predetermined action, the control processing unit 210 generates and outputs a control signal for executing the predetermined action. The control signal is transmitted to the in-vehicle device 240.

[0058] The on-board sensors 220 detect information about the surrounding environment and driving conditions of vehicle 1. Examples of on-board sensors 220 include cameras, radar, LiDAR, wheel speed sensors, IMU (Inertial Measurement Unit), GNSS (Global Navigation Satellite System) sensors, etc.

[0059] The communication interface 230 is an interface for communicating with external devices of the vehicle 1 to send and receive information. The vehicle 1 sends and receives information with the management system 100 via the communication interface 230.

[0060] The on-board equipment 240 includes lighting equipment, interior lighting equipment, horns, turn signals, wipers, doors, door windows, drive systems, brake systems, steering systems, etc. Each component of the on-board equipment 240 includes an actuator 241 that can be controlled by the control processing unit 210. The on-board equipment 240 receives control signals from the control processing unit 210. The actuators 241 operate according to the received control signals, thereby controlling the on-board equipment 240 by the control processing unit 210. Furthermore, the control of the on-board equipment 240 enables the control of the vehicle 1. [Explanation of Symbols]

[0061] 1 vehicle, 3 vehicle identification zones, 10 vehicle identification systems, 100 management systems, 110 processors, 120 memory devices, 121 computer programs, 122 management data, 150 sensors

Claims

1. A vehicle identification system for identifying target vehicles, Includes one or more processors, The one or more processors described above are: While the first vehicle is traveling through the vehicle identification zone, the first vehicle is instructed to begin performing a predetermined action to identify the target vehicle. While the first vehicle is traveling through the vehicle identification zone, a recognition process is initiated to recognize the action that the first vehicle will perform using sensors. The first vehicle that performs the predetermined action is identified as the target vehicle. It is configured in such a way Vehicle identification system.

2. A vehicle identification system according to claim 1, The aforementioned predetermined action is a predetermined visible action, The recognition process includes recognizing a visible action performed by the first vehicle using at least one camera. The one or more processors further include: A camera selection process is performed to select at least one camera so that it can recognize the start and end of the predetermined visual action performed by the first vehicle. It is configured in such a way Vehicle identification system.

3. A vehicle identification system according to claim 2, The aforementioned camera selection process is performed by To tentatively select a temporary camera, A determination process for determining whether the temporary camera can recognize the start and end of the predetermined visible action performed by the first vehicle, If the temporary camera can recognize the start and end of the predetermined visible action, the temporary camera is selected as the at least one camera. including Vehicle identification system.

4. A vehicle identification system according to claim 3, The second camera is positioned to photograph the first vehicle after the first camera. The aforementioned camera selection process is performed by The first camera is provisionally selected as the provisional camera, and the determination process is performed. If the first camera cannot recognize the start and end of the predetermined visible action, the second camera is provisionally selected as the provisional camera instead of the first camera, and the determination process is performed. including Vehicle identification system.

5. A vehicle identification system according to claim 3, The second camera is positioned to photograph the first vehicle after the first camera. The aforementioned camera selection process is performed by The first camera is provisionally selected as the provisional camera, and the determination process is performed. If the first camera cannot recognize the start and end of the predetermined visible action, the combination of the first camera and the second camera is provisionally selected as the provisional camera, and the determination process is performed. including Vehicle identification system.

Images