Position detection system and position detection apparatus

Abstract

This position detection system that detects the position of a portable device (20) with respect to a vehicle (2) comprises: a plurality of communication devices (12) that performs wireless communication with the portable device; and an ECU (11) that determines the position of the portable device on the basis of the wireless communication between the portable device and the communication device. The ECU comprises: an abnormality checking unit (S120) that determines whether or not an abnormality has occurred in any of the plurality of communication devices; a first determination unit (S130) that detects the position of the portable device by a first determination method that uses machine learning; and a second determination unit (S135, S140) that executes a second determination method that does not use machine learning. The first determination unit detects the position of the portable device by the first determination method when the abnormality checking unit determines that an abnormality has not occurred in the communication devices, and the second determination unit executes the second determination method when the abnormality checking unit determines that an abnormality has occurred in the communication devices.

Description

Position detection system and position detection device CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application is based on Japanese Patent Application No. 2024-91688, filed on June 5, 2024, the contents of which are incorporated herein by reference.

[0002] The present disclosure relates to a vehicle position detection system and a position detection device that detect the position of a portable device carried by a user in a vehicle, and is suitable for application to, for example, a Smart Key System (registered trademark).

[0003] Conventionally, vehicle door opening / closing systems, such as smart key systems, detect the location of a portable device carried by a user and, based on the results, permit door opening / closing and engine starting without the use of a mechanical key. As disclosed in Patent Document 1, the location of the portable device is detected, for example, using ultra-wideband (UWB) communication as a short-range communication standard, and using the time of flight (ToF (Time of Flight)) of a radio signal as a parameter indicating the distance between the UWB communication device and the portable device. For location detection using UWB communication and ToF, i.e., area determination for determining an area in which the portable device is located relative to the vehicle or position estimation for estimating the location of the portable device, machine learning, which has high determination accuracy, is often used as a method. Specifically, distance information between the UWB communication device and the portable device, such as ToF, and radio wave intensity information when radio waves are transmitted from the portable device are used as input data, and the location of the portable device is detected based on similarity with learning data.

[0004] JP 2023-160429 A

[0005] However, when detecting the position of a portable device using machine learning, a characteristic of machine learning is that the position of the portable device is detected based on the similarity between learning data and input data. Therefore, when an abnormality occurs, if the portable device is located in a position where a measured value of the distance between the UWB communication device and the portable device (hereinafter referred to as a distance measurement value) can be obtained but the measured value cannot be obtained, there is a concern that the position of the portable device cannot be detected accurately and an erroneous determination will be made. Examples of abnormalities include a malfunction of the UWB communication device or a disconnection of the harness between the UWB communication device and the on-board electronic control unit (hereinafter referred to as an ECU), and in these cases, the measured value may not be obtained.

[0006] An object of the present disclosure is to provide a position detection system and a position detection device that can accurately detect the position of a portable device even when an abnormality occurs in the communication device.

[0007] One aspect of the present disclosure is a position detection system that detects the position of a portable device relative to a vehicle, comprising: a plurality of communication devices that perform wireless communication with the portable device; and a control unit that detects the position of the portable device based on wireless communication between the portable device and the communication devices, wherein the control unit has an abnormality confirmation unit that determines whether an abnormality has occurred in any of the plurality of communication devices; a first judgment unit that detects the position of the portable device using a first judgment method that uses machine learning; and a second judgment unit that executes a second judgment method that does not use machine learning, wherein when the abnormality confirmation unit determines that no abnormality has occurred in the communication devices, the first judgment unit detects the position of the portable device using the first judgment method, and when it determines that an abnormality has occurred in the communication devices, the second judgment unit executes the second judgment method.

[0008] In this way, whether or not an abnormality has occurred in the communication devices is confirmed, and if no abnormality has occurred in the communication devices, location detection is performed using a first determination method based on machine learning. If an abnormality has occurred in any of the communication devices, the method switches to a second determination method. Therefore, when no abnormality has occurred in the communication devices, it is possible to perform accurate area determination based on machine learning. Furthermore, if an abnormality has occurred in any of the communication devices, a second determination method that is not based on machine learning is used. Then, as the second determination method, location detection is performed if location detection is possible using a relatively accurate method other than machine learning, but location detection is not performed if location detection cannot be performed accurately. This makes it possible to further improve the accuracy of location detection.

[0009] Another aspect of the present disclosure is a position detection device that causes multiple communication devices provided in a vehicle to communicate wirelessly with a portable device and that constitutes a control unit that detects the position of the portable device based on the wireless communication, the position detection device having an abnormality confirmation unit that determines whether an abnormality has occurred in any of the multiple communication devices, a first judgment unit that detects the position of the portable device using a first judgment method that uses machine learning, and a second judgment unit that executes a second judgment method that does not use machine learning, wherein when the abnormality confirmation unit determines that no abnormality has occurred in the communication devices, the first judgment unit detects the position of the portable device using the first judgment method, and when it determines that an abnormality has occurred in the communication devices, the second judgment unit executes the second judgment method.

[0010] In this way, the present invention can be understood as a disclosure of a position detection device that constitutes a control unit in a position detection system. This also makes it possible to obtain the effect of one aspect of the present disclosure described above.

[0011] FIG. 1 is a diagram showing a configuration of a position detection system according to a first embodiment of the present disclosure. FIG. 2 is a diagram showing a block configuration of each part of the position detection system shown in FIG. 1. FIG. 3 is a flowchart showing a position detection process executed by an ECU. FIG. 4 is a diagram showing a block configuration of a functional part of the ECU that executes area determination. FIG. 5 is a flowchart of area determination using a minimum distance measurement value. FIG. 6 is a diagram summarizing an example of area determination using a minimum distance measurement value. FIG. 7 is a flowchart showing details of a position detection process executed by an ECU of a position detection system according to a second embodiment of the present disclosure.

[0012] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. In the following, including other embodiments described below, identical or equivalent parts will be denoted by the same reference numerals.

[0013] (First Embodiment) A location detection system according to the first embodiment will be described. The location detection system according to the present embodiment detects the location of a portable device carried by a user in a vehicle, and is used, for example, as part of a smart key system. Here, an example is given in which the location detection system is used as part of a smart key system, but the location detection system can also be used in other vehicle systems that perform vehicle-related control based on the location detection of the portable device.

[0014] The smart key system determines whether a user's portable device is within a specified area of ​​the vehicle, and if the portable device is within the area, performs the area determination and permits the door opening and closing operations and the vehicle starting. The configuration of the location detection system will be described with reference to Figures 1 and 2, taking the case where the location detection system functions as part of the smart key system as an example.

[0015] 1, the location detection system 1 is configured with an in-vehicle system 10 attached to a vehicle 2, and detects the location of a portable device 20 carried by a user. The in-vehicle system 10 includes an ECU 11 and multiple communication devices 12. The ECU 11 and the multiple communication devices 12 wirelessly communicate with the portable device 20 to perform area determination as the location detection of the portable device 20.

[0016] While the area determination performed by a smart key system is used as an example of detecting the position of the portable device 20, other methods, such as position estimation, may be used to estimate the specific positional relationship of the portable device 20 with respect to the vehicle 2. In a typical smart key system, the in-vehicle system 10 also includes a door opening / closing actuator, a touch sensor, and other components, but these are not shown here. In a smart key system, the ECU 11 issues permission for a door opening / closing operation based on the area determination result. When permission is granted and the touch sensor confirms that a door handle or switch has been operated, the door opening / closing actuator is activated to open or close the door. In a smart key system, the ECU 11 issues permission for starting the vehicle 2 based on the area determination result. When permission is granted and the start switch of the vehicle 2 is operated, power is supplied to the electrical components of the vehicle 2 and the vehicle 2 is controlled to a state where it can run. If the vehicle is an engine vehicle, the engine is started.

[0017] The ECU 11 and the multiple communication devices 12 and the portable device 20 are capable of short-range wireless communication with each other. The short-range wireless communication is communication conforming to a predetermined short-range wireless communication standard in which the actual communication distance is within a range defined as short distance, for example, 5 to 100 meters. Any communication standard may be used for the wireless communication. For example, the wireless communication conforming to the BLE (Bluetooth Low Energy) standard is used between the ECU 11 and the portable device 20, and the wireless communication conforming to the UWB-IR (Impulse Radio) standard is used between the communication devices 12 and the portable device 20. Note that "Bluetooth" is a registered trademark. Communication methods such as communication connections and encrypted communications between the ECU 11 and the portable device 20 and between the communication devices 12 and the portable device 20 are implemented according to sequences defined by the respective wireless communication standards.

[0018] For example, BLE communication is performed by cooperative operation between the ECU 11 and the portable device 20, with one acting as a master device and the other acting as a slave device. Here, the ECU 11 is the master device and the portable device 20 is the slave device. For example, the portable device 20 intermittently transmits an advertising signal, and when the ECU 11 receives the advertising signal, the ECU 11 transmits a response signal, and a connection is established between the ECU 11 and the portable device 20. This enables large-volume data communication.

[0019] The advertising signal is a signal that notifies other devices of its own presence, and is used here as a signal by which the portable device 20 notifies the ECU 11 of its own presence. In BLE communication, various signals including the advertising signal contain transmission source information that is made up of unique identification information assigned to each portable device 20, such as a device address or a universally unique identifier (UUID). By comparing this transmission source information with information stored in the ECU 11, it is possible to confirm whether the portable device 20 is a legitimate device that corresponds to the vehicle 2.

[0020] First, a description will be given of the configuration of the ECU 11. The ECU 11 includes a processor 111, a memory 112, a storage 113, a Bluetooth module 114, an in-vehicle communication circuit 115, and the like, and constitutes a control unit in the in-vehicle system 10.

[0021] The processor 111 is hardware including a central processing unit (CPU) that executes arithmetic processing. The processor 111 accesses the memory 112 and the storage 113 to execute various processes for implementing the functions of each functional unit. The memory 112 is a volatile storage medium, such as a random access memory (RAM). The storage 113 is a non-volatile storage medium, such as a flash memory. The storage 113 stores various programs and data executed by the processor 111. In this embodiment, the storage 113 stores programs and learning data related to the smart key system, unique identification information of the authorized portable device 20 in the vehicle 2, and unique identifiers for each of the multiple communication devices 12. The in-vehicle communication circuit 115 is a circuit module for communicating with other devices via an in-vehicle communication network. For example, a controller area network (CAN) or the like is adopted as the in-vehicle communication network. The ECU 11 is capable of communicating with the multiple communication devices 12 installed in the vehicle 2 and other ECUs (not shown) via the in-vehicle communication network. "CAN" is a registered trademark. The Bluetooth module 114 is a communication module that is composed of a wireless communication circuit, an antenna, etc., and is capable of performing short-range wireless communication in accordance with the BLE standard. When performing BLE communication with the portable device 20, the Bluetooth module 114 is capable of measuring the strength of the wireless radio waves received from the portable device 20.

[0022] With this configuration, the processor 111 of the ECU 11 executes various processes based on the programs and learning data stored in the storage 113. The ECU 11 then detects the position of the portable device 20 in cooperation with the multiple communication devices 12 based on various data related to the portable device 20 temporarily stored in the memory 112. Note that the ECU 11 corresponds to a position detection device that executes position detection, and the execution of a program related to position detection by the ECU 11 corresponds to the execution of a position detection method corresponding to the program.

[0023] Next, the configuration of the multiple communication devices 12 will be described. The multiple communication devices 12 cooperate with the ECU 11 to detect the position of the portable device 20, for example, by performing UWB communication that enables distance measurement communication with the portable device 20 in accordance with instructions from the ECU 11, and constitute communication antennas. Each communication device 12 is configured to include a processor 121, a memory 122, a storage 123, a UWB module 124, an in-vehicle communication circuit 125, and the like. Note that although only one of the multiple communication devices 12 is shown in the block diagram of the position detection system 1 shown in FIG. 2, in reality, the same configuration is provided as the number of communication devices 12.

[0024] The processor 121, memory 122, storage 123, and in-vehicle communication circuit 125 may be configured similarly to or simplified from those provided in the ECU 11. However, the processor 121 of the communication device 12 accesses the memory 122 and storage 123 to perform processing for measuring the ToF and radio wave intensity of radio waves transmitted from the portable device 20 and transmitting the results to the ECU 11. The storage 123 stores programs related to the measurement of ToF and radio wave intensity, and the memory 122 temporarily stores various data related to radio waves received from the portable device 20 and data related to the measurement results of ToF and radio wave intensity. The UWB module 124 is a communication module that is configured with a wireless communication circuit, a UWB antenna, and the like, and is capable of performing short-range wireless communication in accordance with the UWB standard.

[0025] The multiple communication devices 12 are provided corresponding to locations where position detection, such as area determination, is desired. For example, as shown in FIG. 1 , a first communication device 12a is provided in a front position within the vehicle interior, e.g., in the central instrument panel, a second communication device 12b is provided near the driver's seat (hereinafter also referred to as the D seat) door, and a third communication device 12c is provided near the passenger seat (hereinafter also referred to as the P seat) door. A fourth communication device 12d is provided near the luggage compartment at the rear of the vehicle 2. If the vehicle 2 is equipped with a remote parking function, a fifth communication device 12e is provided at the front of the vehicle 2. If position detection is desired in the rear of the vehicle interior or in the trunk, a sixth communication device 12f is provided at the rear of the vehicle interior. Note that the locations of the communication devices 12 relative to the vehicle 2 shown here are merely examples, and the communication devices 12 may be provided corresponding to locations within the vehicle 2 where the position detection of the portable device 20 is desired.

[0026] Each communication device 12 is assigned a unique identifier, so that the ECU 11 can determine which communication device 12 has obtained various data obtained through communication with the portable device 20.

[0027] Next, the configuration of the portable device 20 will be described. The portable device 20 is a portable device used as an electronic key for the vehicle 2. While FIG. 1 illustrates a case in which the portable device 20 is a smartphone, the portable device 20 may be any other device that is carried by a user and capable of communication, such as an electronic key, a tablet terminal, or a wearable device. The location of the portable device 20 indicates the location of the user who carries it, and the user's location is detected by detecting the location of the portable device 20. Specifically, the portable device 20 is configured to include a control unit 21, a Bluetooth module 22, and a UWB module 23.

[0028] The control unit 21 is configured by a microcomputer or the like including a processor, storage, memory, etc. The configurations of the processor, storage, and memory may be the same as those of the ECU 11 or simplified versions. The storage of the control unit 21 stores programs related to location detection, as well as unique identification information of the portable device 20 and key information indicating that the user is an authorized user of the vehicle 2. The Bluetooth module 22 has the same configuration as the Bluetooth module 114 provided in the ECU 11 and is a communication module capable of short-range wireless communication compliant with the BLE standard. The UWB module 23 has the same configuration as the UWB module provided in the communication device 12 and is a communication module capable of short-range wireless communication compliant with the UWB standard.

[0029] The portable device 20, for example, transmits an advertising signal intermittently, and when the ECU 11 receives the signal and transmits a response signal, it establishes a connection with the ECU 11 and transmits key information and the like based on instructions from the ECU 11. Based on this, the ECU 11 verifies whether the key information transmitted from the portable device 20 belongs to the authorized user of the vehicle 2, and if the verification confirms that the portable device 20 is authorized and corresponds to the vehicle 2, it performs area determination.

[0030] The position detection system 1 according to this embodiment is configured as described above. Next, details of position detection by this position detection system 1 will be described. In the position detection system 1, the ECU 11 executes the position detection process shown in Fig. 3 to perform area determination as position detection. Note that although area determination is performed here as position detection, when performing position estimation to estimate the position of the portable device 20, the area determination part in Fig. 3 can be replaced with other position detection such as position estimation.

[0031] First, the ECU 11 performs the following operations before proceeding to each step of the position detection process shown in Fig. 3. That is, regardless of whether the vehicle 2 is started or not, the ECU 11 is in a state where it can receive an advertising signal from the portable device 20, even when the vehicle 2 is not started, and when the ECU 11 receives an advertising signal, it establishes a connection with the portable device 20. Then, the ECU 11 acquires transmission source information from the portable device 20 and determines whether the portable device 20 is authentic by comparing unique identification information of the portable device 20 included in the transmission source information with unique identification information of an authentic portable device 20 stored in the storage of the ECU 11.

[0032] Here, whether the portable device 20 is genuine or not is determined after a connection between the ECU 11 and the portable device 20 is established, but it is also possible to include unique identification information of the portable device 20 in the advertising signal and perform the verification before establishing the connection.

[0033] If the portable device 20 is determined to be authentic, the ECU 11 maintains the connection and constantly measures the radio wave strength of the BLE communication during BLE communication with the portable device 20 for location detection, and determines whether the radio wave strength exceeds a threshold. If the radio wave strength exceeds the threshold and it is confirmed that the user is within a predetermined range from the vehicle 2, the ECU 11 sends a command to each communication device 12 via the in-vehicle communication network to start distance measurement, causing each communication device 12 to measure a distance measurement value indicating the distance from itself to the portable device 20. For example, the ECU 11 measures the ToF and the radio wave strength of the portable device 20 that has reached each communication device 12. Here, both the ToF and the radio wave strength are measured, but only one of them may be measured.

[0034] For example, when each communication device 12 transmits an impulse signal from its UWB module, the portable device 20 responds to the impulse signal by returning a response signal to the impulse signal via the UWB module, and the communication device 12 acquires the interval between the transmission and reception as a time-of-flight-related value. The time-of-flight-related value is also called a ToF-related value, and is a parameter that directly or indirectly indicates the flight time of radio waves from the communication device 12 to the portable device 20. The ToF is determined based on the two-frequency phase difference and the round trip time (RTT), and the two-frequency phase difference and the RTT are the ToF-related value. Since the flight time of radio waves corresponds to the distance from the communication device 12 to the portable device 20, the ToF-related value is a value that represents that distance.

[0035] Furthermore, when an impulse signal is sent from the UWB module and a response signal to the impulse signal is returned from the portable device 20, each communication device 12 receives the response signal and measures the reception strength to determine the radio wave strength of the portable device 20. The signal indicating the radio wave strength or its measurement value is also called an RSSI (Received Signal Strength Indicator) value.

[0036] Then, when each communication device 12 measures the ToF or radio wave intensity, it transmits the measured distance values ​​to the ECU 11 via the in-vehicle communication network. The ECU 11 inputs the measured distance values ​​transmitted from each communication device 12 as a data input process shown in step S100 of Fig. 3, and receives the measured distance values ​​from all of the communication devices 12. However, while typically each communication device 12 performs distance measurement and transmits the measured distance value to the ECU 11, it is possible that one of the communication devices 12 is unable to perform distance measurement due to, for example, being too far from the portable device 20. In such a case, the communication device 12 that was unable to perform distance measurement transmits a signal to the ECU 11 to that effect.

[0037] Next, the process proceeds to step S110, where it is determined whether the area determination start condition has been met, i.e., whether the area determination start condition has been met. The area determination start condition here is that the data input process of step S100 has resulted in the transmission of distance measurements from all communication devices 12, or the transmission of a signal indicating that distance measurement was not possible. Since the data input process is ongoing until this start condition is met, the process waits until the start condition is met. Then, once the start condition has been met, the process proceeds to step S120.

[0038] In step S120, a fault check and a distance measurement value check are performed. The fault check here means checking whether any of the multiple communication devices 12 has a fault. The fault check here corresponds to an abnormality check that checks whether an abnormality has occurred in the communication device 12, and the part of the ECU 11 that performs this function corresponds to an abnormality check unit.

[0039] The ECU 11 has a fault diagnosis function and, as a separate flow from the process shown in FIG. 3 , detects a fault in the communication device 12, i.e., detects an abnormality in the communication device 12, based on the fault diagnosis function. For example, when the ECU 11 issues an instruction to start distance measurement as described above, each communication device 12 receives the instruction and returns a response signal indicating that it has received the instruction before starting distance measurement. The ECU 11 sets a fault determination flag if no response signal is returned even after issuing an instruction, preferably if no response signal is returned even after multiple retries. If this fault determination flag is set, the ECU 11 determines that the communication device 12 that did not return a response signal has failed. Alternatively, the ECU 11 sets a fault determination flag if a period of time lasting longer than a predetermined period of time has passed since the ECU 11 issued an instruction to each communication device 12 and no response is received. In this case, the ECU 11 also determines that the communication device 12 that did not respond has failed.

[0040] Further, checking the distance measurement value means checking which communication device 12 transmitted the distance measurement value. When the ECU 11 receives a distance measurement value from each communication device 12, the ECU 11 associates the distance measurement value with which communication device 12 it came from and temporarily stores it. At this time, for communication devices 12 that have not transmitted a distance measurement value, the ECU 11 temporarily stores data indicating that there is no distance measurement value.

[0041] If the result of the failure check is that no failure has occurred in the communication devices 12, the process proceeds to step S130, where area determination is performed using the first determination method, and if a failure has occurred in any of the communication devices 12, the process proceeds to step S140, where area determination is performed using the second determination method. In other words, the ECU 11 switches between the first determination method and the second determination method, which are different determination methods, depending on whether or not there is a failure in the communication devices 12. The parts of the ECU 11 that execute the first determination method and the second determination method correspond to the first determination unit and the second determination unit, respectively.

[0042] The first determination method is a method of performing area determination based on machine learning using distance measurements of the communication device 12 input during the data input process. The distance measurements may use both ToF and radio wave intensity, or only one of them. Although area determination is possible using only one of ToF and radio wave intensity, using both can achieve more accurate area determination. Machine learning, for example, uses deep learning. For example, training data is obtained by previously setting multiple locations inside and around the vehicle 2 as measurement locations and associating the distance measurements of each communication device 12 when the portable device 20 is located at each measurement location with the measurement location. Here, two types of training data are created: training data for interior area determination learned from multiple measurement locations inside the vehicle, and training data for exterior area determination learned from multiple measurement locations outside the vehicle. The training data does not include data when an abnormality occurs. If the training data were to take into account the occurrence of an abnormality, it would contain noise data, which could adversely affect area determination during normal operation. For this reason, learning data is obtained through machine learning without including data from when an abnormality occurs, and this learning data is used for area determination.

[0043] Here, the portable device 20 is determined to be present in both the vehicle interior area and the vehicle exterior area, and the results of these area determinations are combined to determine in which area the portable device 20 is present.

[0044] Specifically, as shown in FIG. 4 , input data of measured values ​​is input to the vehicle interior area determination unit 111a for vehicle interior area determination. Then, the data array formation processing unit 111aa arranges the data array used for area determination, and the area determination calculation unit 111ab performs area determination based on machine learning. For area determination, any method that can be used as an area determination method based on machine learning may be used, such as a method using distance measurements as input data and obtaining a determination result based on the similarity between the input data and learning data, such as the method used in Patent Document 1. For this reason, although details are omitted, for example, data most similar to the input data is extracted from the learning data, and the area including the measurement location corresponding to that data is determined to be the area where the portable device 20 is located. Since the learning result does not include data when an abnormality occurs, it is possible to perform accurate area determination based on machine learning when no abnormality occurs in the communication device 12.

[0045] In this way, it is determined whether the portable device 20 is present in the vehicle interior area, and further in which area of ​​the vehicle interior the portable device 20 is present, and data indicating the determination result is transmitted to the determination unit 111c.

[0046] Similarly, for the vehicle exterior area determination, the input data of the measurement values ​​is also input to the vehicle exterior area determination unit 111b. The data array formation processing unit 111ba then arranges the data array used for area determination, and the area determination calculation unit 111bb then performs area determination based on machine learning. The method of area determination based on machine learning is the same as that for the vehicle interior area determination.

[0047] In this way, it is determined whether the portable device 20 is present in the area outside the vehicle compartment, and further, in which area the portable device 20 is present relative to the vehicle 2, and data indicating the determination result is transmitted to the determination unit 111c. Then, when the results of the vehicle compartment area determination and the results of the vehicle compartment area determination are input to the determination unit 111c, an area determination result that combines these results is output.

[0048] That is, if the vehicle interior area determination determines that the portable device 20 is present inside the vehicle, a determination result to that effect is output, and if the vehicle exterior area determination determines that the portable device 20 is present outside the vehicle, a determination result to that effect is output. Basically, the portable device 20 is present only either inside or outside the vehicle, so if the portable device 20 is determined to be present in either the vehicle interior area determination or the vehicle exterior area determination, that determination result is output. The determination result of whether the portable device 20 is present inside or outside the vehicle is also output. In this way, the area determination using the first determination method in step S130 is completed, and the position detection process ends.

[0049] On the other hand, the second determination method is a method different from the first determination method. If one of the communication devices 12 is malfunctioning, data corresponding to the machine learning learning results may not have been input. In this case, area determination is performed using the communication device 12 with the smallest distance measurement value (hereinafter referred to as the minimum distance measurement value) among the distance measurement values ​​that have been input. In other words, since it is presumed that the portable device 20 is present near the communication device 12 that measured the minimum distance measurement value, it is determined that the portable device 20 is present in an area away from that communication device 12 at a distance equivalent to the minimum distance measurement value.

[0050] For example, area determination is performed based on the area determination flow using the minimum distance measurement value shown in Figure 5 and the chart shown in Figure 6. Here, an example is given in which all of the first to sixth communication devices 12a to 12f shown in Figure 1 are provided. The first communication device 12a used to perform area determination inside the vehicle cabin is designated No. 5, and the sixth communication device 12f is designated No. 6. The second communication device 12b used to perform area determination outside the vehicle cabin is designated No. 1, the third communication device 12c is designated No. 2, the fourth communication device 12d is designated No. 3, and the fifth communication device 12e is designated No. 4. The minimum distance measurement value may be calculated from either the ToF or the radio wave intensity, or may be an average value of values ​​calculated from both.

[0051] First, in step S200 of the area determination flow, the conditions of the communication devices 12 No. 5 and No. 6 are determined. Specifically, if the distance measurement value of the communication device 12 No. 5 or No. 6 is the minimum distance measurement value, the communication device 12 with the minimum distance measurement value is determined to satisfy the condition for assuming that the portable device 20 is present inside the vehicle interior. If the condition is satisfied, the area in which the portable device 20 is present is determined to be "inside the vehicle interior." If the condition is not satisfied, the area is determined to be "out of area." Here, as shown in FIG. 6 , the condition is satisfied when the distance indicated by the minimum distance measurement value is equal to or less than a threshold value N5 cm. The threshold value N5 cm, which is compared with the minimum distance measurement value, is set, for example, depending on the vehicle model and may be different for No. 5 and No. 6, but is set to the same value of 140 cm, for example. Furthermore, if neither the communication device 12 No. 5 nor No. 6 has the minimum distance measurement value, the communication device 12 is also determined to be "out of area." Note that here, the condition is also satisfied when the distance indicated by the minimum distance measurement value is equal to or less than a threshold value N5 cm. In FIG. 6 , the determination of "inside the vehicle cabin" or "out of area" is made based on the distance measurement value of the No. 6 communication device 12. However, it is assumed that the No. 6 communication device 12 is located either inside the vehicle cabin or in the trunk. Therefore, for example, if the minimum distance measurement value is N5 cm or less, the determination may be "inside the vehicle cabin or in the trunk." Of course, if the No. 6 communication device 12 is located in the trunk, the determination of "inside the trunk" or "out of area" may be made based on whether the distance measurement value of the No. 6 communication device 12 is N5 cm or less. In FIG. 6 , since the determination of "inside the vehicle cabin" or "out of area" is made in No. 6, the determination of "inside the vehicle cabin" or "out of area" is made only as a binary determination of whether the vehicle is inside the vehicle cabin or not, even when the determination of whether the vehicle is inside the vehicle cabin or not in No. 5 and the determination of whether the vehicle is inside or outside a predetermined area outside the vehicle cabin or not in No. 1 to No. 4 are included. In contrast, when the determination of whether the vehicle is inside the trunk is made in No. 6, the determination of whether the vehicle is inside the trunk is made as a ternary determination of "inside the vehicle cabin / inside the trunk / outside the vehicle cabin," which allows for more detailed area determination.

[0052] Next, the process proceeds to step S210, where it is determined whether or not there is no area. If it is determined in step S200 that there is no area, the process proceeds to step S220.

[0053] In step S220, the condition of the communication devices 12 No. 1 to No. 4 is determined. Specifically, it is determined whether the distance measurement value of the communication device 12 No. 1 to No. 4 with the smallest distance measurement value satisfies the condition that the portable device 20 is assumed to be present at a position near the vehicle 2 outside the passenger compartment. If the condition is satisfied, the area in which the portable device 20 is present is determined according to the distance indicated by the distance measurement value. Here, an area close to the communication device 12 with the smallest distance measurement value is designated "Near," an area farther from the communication device 12 with the smallest distance measurement value is designated "Far," and an area in between is designated "Middle." For example, for the second communication device 12b near the D-seat door, if the distance indicated by the smallest distance measurement value is N2 cm or less, it is designated "D-seat Near," if it is greater than N2 cm and less than N3 cm, it is designated "D-seat Middle," and if it is greater than N3 cm and less than N4 cm, it is designated "D-seat Far." Furthermore, if the distance indicated by the minimum distance measurement value is greater than N4 cm, it is determined that no portable device 20 is present near the driver's seat door and the vehicle is deemed "out of area." Similarly, the third communication device 12c located near the passenger's seat door determines whether the portable device 20 is "near," "middle," "far," or "out of area" relative to the passenger's seat. The fourth communication device 12d located near the luggage compartment determines whether the vehicle is "near," "middle," "far," or "out of area" outside the luggage compartment. The fifth communication device 12e used for remote parking uses N4 cm as a threshold value to determine whether the vehicle is in an area where remote parking is possible or "out of area." Note that N2 cm to N4 cm can also be set to any value depending on the vehicle model. For example, N2 cm is set to 200 cm, N3 cm to 400 cm, and N4 cm to 550 cm. Although the same thresholds N2 cm to N4 cm are used to compare the minimum distance for all communication devices 12, different thresholds may be set for each communication device 12.

[0054] In this manner, area determination is performed based on the minimum distance measurement value, and the area in which the portable device 20 is located is determined to be either "inside the vehicle cabin" or "outside the vehicle cabin." If the portable device 20 is located "outside the vehicle cabin," it is determined whether the portable device 20 is located in an area close to the communication device 12 used to determine the area outside the vehicle cabin (here, the second to fifth communication devices 12b to 12e), a far area, an intermediate area, or even an "outside area" that is farther than the far area. This area determination result is used to determine permission for various controls related to the vehicle 2 in the smart key system. For example, if the portable device 20 is located in an area close to the second communication device 12b near the driver's seat door, permission to unlock the door is issued. When the touch sensor detects that the user has touched the door handle or door switch, permission to open or close the door is issued. If the portable device 20 is located inside the vehicle cabin, permission to start the vehicle 2 is issued. When the user operates the start switch, power is supplied to the electrical components of the vehicle 2 and the vehicle 2 is controlled to a running state.

[0055] 3 is repeated at predetermined control intervals, and area determination is performed based on the most recent distance measurement value. Therefore, even if the position of the portable device 20 changes, area determination corresponding to the changed position can be performed accurately.

[0056] As described above, in the position detection system according to this embodiment, a fault check is performed on the communication devices 12, and if no abnormality occurs in the communication devices 12, area determination is performed using the first determination method based on machine learning. Specifically, the ECU 11 inputs distance measurements from each of the multiple communication devices 12 and performs area determination based on the distance measurements and training data. If an abnormality occurs in any of the communication devices 12, the ECU 11 switches to the second determination method. Therefore, area determination based on machine learning is performed only when no abnormality occurs in the communication devices 12, and area determination using machine learning is not performed if an abnormality occurs in any of the communication devices 12.

[0057] Therefore, when no abnormality occurs in the communication devices 12, it is possible to perform accurate area determination based on machine learning. Furthermore, when an abnormality occurs in any of the communication devices 12, the method switches to a second determination method that is not based on machine learning, and performs area determination based on the smallest distance measurement value among the distance measurement values ​​input from the communication devices 12 that are not malfunctioning. Therefore, even if the portable device 20 is located in a position where a distance measurement value should be obtained from the communication device 12 but a distance measurement value is not obtained, it is possible to perform area determination not based on machine learning. In other words, even though the accuracy is not as high as that of machine learning, it is possible to perform area determination even when an abnormality occurs, thereby making it possible to further improve the accuracy of area determination.

[0058] Furthermore, according to the position detection system of this embodiment, it is possible to exclude data on abnormalities from the learning data for machine learning, which makes it possible to perform position detection with higher accuracy when detecting the position of the portable device 20 using the first determination method based on machine learning.

[0059] Furthermore, distance measurement communication is performed as wireless communication between the communication device 12 on the vehicle 2 side and the portable device 20, which can acquire a distance measurement value relating to the distance from the communication device 12 to the portable device 20. Here, wireless communication is performed in which ToF and radio wave intensity are obtained as the distance measurement value. Based on this distance measurement value, the ECU 11 detects the position and determines the area of ​​the portable device 20, thereby improving the accuracy of the position detection and area determination.

[0060] Second Embodiment A second embodiment of the present disclosure will be described. This embodiment is similar to the first embodiment except for the method of area determination, and therefore only the differences from the first embodiment will be described.

[0061] In the first embodiment, the second determination method was described as a case where area determination is performed without using machine learning. However, in this embodiment, in addition to the case where area determination is performed without using machine learning, it is also possible to select a case where area determination is not performed.

[0062] 7, if none of the plurality of communication devices 12 is found to be faulty in the failure check in step S120, the process proceeds to step S130. On the other hand, if a failure has occurred in any of the plurality of communication devices 12, the process from step S135 onwards is executed as a second determination method.

[0063] First, in step S135, it is determined whether the communication device 12 that has failed is a specific communication device 12. The term "specific communication device 12" here refers to a communication device 12 for which accurate area determination may be difficult if distance measurements cannot be obtained. For example, if a communication device 12 within the vehicle cabin that is used to determine whether the portable device 20 is inside the vehicle cabin, particularly the first communication device 12a located at the front of the vehicle cabin, fails, accurate area determination may be difficult. Therefore, if the specific communication device 12 that has failed is a communication device 12 other than the first communication device 12a, for example, the process proceeds to step S140, where area determination is performed using the minimum distance measurement value, as in step S140 described in the first embodiment. If the specific communication device 12 has failed, area determination is prohibited, i.e., the position detection process is terminated without performing area determination.

[0064] As described above, in the second determination method of this embodiment, even if one of the communication devices 12 fails, area determination is performed using the minimum distance measurement value as long as the communication device 12 that can perform area determination relatively accurately is not failing. If a communication device 12 that may make area determination difficult fails, area determination is not performed. This allows area determination to be performed only when the reliability is relatively high, and prevents area determination with low reliability from being performed. Therefore, it is possible to further increase the reliability of area determination.

[0065] While the present disclosure has been described based on the above-described embodiment, it is not limited to the embodiment and encompasses various modifications and modifications within the scope of equivalents. In addition, various combinations and forms, as well as other combinations and forms including only one element, more than one element, or less than one element, are also within the scope and spirit of the present disclosure.

[0066] (1) For example, in the above-described embodiments, the multiple communication devices 12 include the first communication device 12a and the sixth communication device 12f used to determine the area inside the vehicle cabin, and the second to fifth communication devices 12b to 12e used to determine the area outside the vehicle cabin. However, the number and locations of the communication devices 12 may be determined arbitrarily depending on the vehicle model of the vehicle 2 and the type of vehicle control to be executed, and the number and locations of the communication devices 12 may be different from those shown in FIG. 1 . Typically, one interior communication device is used to determine the area inside the vehicle cabin, and multiple, e.g., three exterior communication devices are used to determine the area outside the vehicle cabin. In addition, if the vehicle 2 has a large cabin, another interior communication device may be provided, and if the vehicle 2 has a remote parking function, another interior communication device may be provided in the front of the vehicle 2.

[0067] (2) In the above embodiment, UWB communication is used between the communication device 12 and the portable device 20, and BLE communication is used between the ECU 11 and the portable device 20. However, the form of wireless communication is arbitrary, and wireless communication conforming to other standards may be used. For example, BLE communication may be used not only between the ECU 11 and the portable device 20, but also between the communication device 12 and the portable device 20. In addition, although a wired in-vehicle communication network is used between the ECU 11 and the communication device 12, wireless communication may also be used.

[0068] (3) In the above embodiment, a single threshold value is set to determine whether the area is "inside the vehicle cabin" or "outside the area" for the area determination inside the vehicle cabin. Furthermore, three threshold values ​​are set for each communication device 12 to determine whether the area is "near," "middle," "far," or "outside the area." The number of threshold values ​​shown here is arbitrary and may be different. For example, the threshold value may be set according to specifications, applications, etc., such as by using only one threshold value to determine whether the area is "inside the area" or "outside the area."

[0069] (4) In the above embodiment, the method of detecting a malfunction is to check the state of a malfunction determination flag that is set when the ECU 11 issues a command to start distance measurement and no response signal is returned from the communication device 12. This is just one example, and other methods may be used to detect a malfunction. For example, a sensor may be used to detect a malfunction in the communication device 12 or a disconnection in the harness connected to the communication device 12, and upon detection, the ECU 11 may be notified of the occurrence of an abnormality.

[0070] (5) In the above embodiment, the area determination based on the minimum distance measurement value is performed by comparing the minimum distance measurement value with a threshold value. However, other methods may be used. For example, for all communication devices 12 for which distance measurement values ​​have been obtained, areas where the portable device 20 is expected to be located may be extracted based on the respective distance measurement values, and the most likely area may be selected as the area determination result. Performing area determination in this manner essentially results in area determination based on the minimum distance measurement value. For example, assume that the portable device 20 is located inside the vehicle cabin and the area where the portable device 20 is located is determined to be "inside the vehicle cabin" based on the distance measurement value of the first communication device 12a located at the front of the vehicle cabin, and the area where the portable device 20 is located is determined to be "middle" based on the distance measurement value of the second communication device 12b located near the driver's seat door. In this case, the area with the shortest distance to the portable device 20, i.e., "inside the vehicle cabin" determined based on the distance measurement value of the first communication device 12a, is assumed to be the most likely area. Therefore, in this case, selecting "inside the vehicle" as the area determination result is essentially making an area determination based on the distance measurement value of the communication device 12 that is closest to the portable device 20, which is the same as making an area determination based on the smallest distance measurement value.

[0071] (6) In the above embodiment, the learning data is stored in the storage 113 of the ECU 11. However, the learning data may be updated by communicating with an off-vehicle server. Alternatively, the learning data may not be stored in the storage 113 of the ECU 11, but may be stored in an off-vehicle server, and the off-vehicle server may perform position detection based on machine learning by communicating with the off-vehicle server.

[0072] (7) It goes without saying that in each of the above embodiments, the elements constituting the embodiments are not necessarily essential unless they are specifically stated as essential or are clearly considered essential in principle. Furthermore, in each of the above embodiments, when the numbers, values, amounts, ranges, and other numerical values ​​of the components of the embodiments are mentioned, they are not limited to the specific numbers unless they are specifically stated as essential or are clearly limited to a specific number in principle. Furthermore, in each of the above embodiments, when the shapes, positional relationships, etc. of the components are mentioned, they are not limited to the shapes, positional relationships, etc., unless they are specifically stated or are clearly limited to a specific shape, positional relationship, etc. in principle.

[0073] (8) The control unit and the method described herein may be implemented by a special-purpose computer configured by configuring a processor and memory programmed to execute one or more functions embodied in a computer program. Alternatively, the control unit and the method described herein may be implemented by a special-purpose computer configured by configuring a processor with one or more dedicated hardware logic circuits. Alternatively, the control unit and the method described herein may be implemented by one or more special-purpose computers configured by combining a processor and memory programmed to execute one or more functions with a processor configured with one or more hardware logic circuits. Furthermore, the computer program may be stored as instructions executed by a computer on a computer-readable non-transitory tangible recording medium.

[0074] (Viewpoints of the Present Disclosure) The above-described present disclosure can be understood from the following viewpoints, for example.

[0075] [First Aspect] A position detection system for detecting the position of a portable device (20) relative to a vehicle (2), comprising: a plurality of communication devices (12) that perform wireless communication with the portable device; and a control unit (11) that determines the position of the portable device based on the wireless communication between the portable device and the communication devices, wherein the control unit has an abnormality confirmation unit (S120) that determines whether an abnormality has occurred in any of the plurality of communication devices, a first determination unit (S130) that detects the position of the portable device using a first determination method that uses machine learning, and a second determination unit (S135, S140) that executes a second determination method that does not use machine learning, wherein when the abnormality confirmation unit determines that no abnormality has occurred in the communication devices, the first determination unit detects the position of the portable device using the first determination method, and when it determines that an abnormality has occurred in the communication devices, the second determination unit executes the second determination method. [Second Aspect] The wireless communication between each of the plurality of communication devices and the portable device is distance measurement communication capable of acquiring a distance measurement value indicating the distance from the portable device, and the control unit detects the position of the portable device based on the distance measurement value. [Third Aspect] The position detection system according to the second aspect, wherein the control unit receives the distance measurement values ​​from each of the plurality of communication devices, and the first determination unit detects the position of the portable device based on the distance measurement values ​​and teacher data for each of the plurality of communication devices as the first determination method. [Fourth Aspect] The position detection system according to the second or third aspect, wherein the control unit receives a distance measurement value from a communication device among the plurality of communication devices that is not experiencing an abnormality, and when the abnormality check unit determines that an abnormality has occurred in the communication device, the second determination unit detects the position of the portable device based on a minimum distance measurement value that is the smallest distance measurement value among the received distance measurement values ​​as the second determination method. [Fifth Aspect] The control unit, using the second determination unit, determines, as the second determination method, whether a communication device among the plurality of communication devices in which an abnormality has occurred is a specific communication device, and if it is not the specific communication device, performs position detection of the portable device based on the minimum distance measurement value, but if it is the specific communication device, does not perform position detection of the portable device.[Sixth Aspect] The position detection system according to the fifth aspect, wherein the specific communication device is one of the plurality of communication devices used to determine whether the portable device is located inside the vehicle cabin. [Seventh Aspect] The position detection system according to the sixth aspect, wherein the plurality of communication devices include one or two communication devices used to determine whether the portable device is located inside the vehicle cabin and a plurality of communication devices used to determine whether the portable device is located outside the vehicle cabin. [Eighth Aspect] The position detection system according to any one of the second to seventh aspects, wherein the ranging communication is ultra-wideband communication. [Ninth Aspect] The position detection system according to any one of the second to eighth aspects, wherein the control unit is capable of wireless communication with the portable device, and when wireless communication between the plurality of communication devices and the portable device is established, instructs the plurality of communication devices to start distance measurement by wireless communication with the portable device, receives response signals transmitted from the plurality of communication devices in response to the instruction, and determines that an abnormality has occurred in a communication device that does not return the response signal. [Tenth Aspect] The position detection system according to any one of the second to eighth aspects, wherein the control unit is capable of wireless communication with the portable device, and when wireless communication between the plurality of communication devices and the portable device is established, instructs the plurality of communication devices to start distance measurement by wireless communication with the portable device, receives response signals transmitted from the plurality of communication devices in response to the instruction, and determines that an abnormality has occurred in a communication device that has failed or has a disconnected harness when any of the plurality of communication devices has failed or when a harness connected to each of the plurality of communication devices is disconnected. [Eleventh Aspect] A position detection device that causes a plurality of communication devices (12) provided in a vehicle (2) to wirelessly communicate with a portable device (20) and that constitutes a control unit that detects the position of the portable device based on the wireless communication, the position detection device having: an abnormality confirmation unit (S120) that determines whether an abnormality has occurred in any of the plurality of communication devices; a first determination unit (S130) that detects the position of the portable device by a first determination method that uses machine learning; and a second determination unit (S135, S140) that executes a second determination method that does not use machine learning, wherein when the abnormality confirmation unit determines that no abnormality has occurred in the communication devices, the first determination unit detects the position of the portable device by the first determination method, and when it determines that an abnormality has occurred in the communication devices, the second determination unit executes the second determination method.

Claims

1. A position detection system that detects the position of a portable device (20) relative to a vehicle (2), comprising: a plurality of communication devices (12) that perform wireless communication with the portable device; and a control unit (11) that detects the position of the portable device based on the wireless communication between the portable device and the communication devices, wherein the control unit has an abnormality confirmation unit (S120) that determines whether an abnormality has occurred in any of the plurality of communication devices; a first determination unit (S130) that detects the position of the portable device using a first determination method that uses machine learning; and a second determination unit (S135, S140) that executes a second determination method that does not use machine learning, wherein when the abnormality confirmation unit determines that no abnormality has occurred in the communication devices, the first determination unit detects the position of the portable device using the first determination method, and when it determines that an abnormality has occurred in the communication devices, the second determination unit executes the second determination method.

2. The position detection system described in claim 1, wherein the wireless communication performed by each of the plurality of communication devices with the portable device is distance measurement communication capable of acquiring a distance measurement value indicating the distance to the portable device, and the control unit detects the position of the portable device based on the distance measurement value.

3. The position detection system of claim 2, wherein the control unit receives distance measurements from each of the plurality of communication devices, and the first judgment unit detects the position of the portable device based on the distance measurements and teacher data from each of the plurality of communication devices as the first judgment method.

4. The position detection system described in claim 2, wherein the control unit receives a distance measurement value from a communication device among the plurality of communication devices that is not experiencing an abnormality, and when the abnormality confirmation unit determines that an abnormality has occurred in the communication device, the second judgment unit uses the second judgment method to detect the position of the portable device based on the smallest distance measurement value among the received distance measurements.

5. The control unit, using the second determination unit, determines as the second determination method whether the communication device in which an abnormality has occurred is a specific communication device among the plurality of communication devices, and if it is not the specific communication device, performs position detection of the portable device based on the minimum distance measurement value, but if it is the specific communication device, does not perform position detection of the portable device.

6. The position detection system according to claim 5, wherein the specific communication device is one of the plurality of communication devices that is used to determine whether the portable device is located inside the vehicle cabin.

7. The position detection system according to claim 6, wherein the plurality of communication devices are configured by one or two communication devices used to determine whether the portable device is located inside the vehicle cabin, and a plurality of communication devices used to determine whether the portable device is located outside the vehicle cabin.

8. The position detection system according to claim 2, wherein the ranging communication is ultra-wideband communication.

9. A position detection system as described in any one of claims 2 to 8, wherein the control unit is capable of wireless communication with the portable device, and when wireless communication is established between the multiple communication devices and the portable device, instructs the multiple communication devices to begin distance measurement by wireless communication with the portable device, receives response signals transmitted from the multiple communication devices in response to the instruction, and, if there is a communication device that does not return the response signal, determines that an abnormality has occurred in the communication device.

10. A position detection system as described in any one of claims 2 to 8, wherein the control unit determines that an abnormality has occurred in the communication device that has failed or whose harness is broken when any of the communication devices among the plurality of communication devices has failed or when a harness connected to each of the plurality of communication devices is broken.

11. A position detection device that causes multiple communication devices (12) provided in a vehicle (2) to communicate wirelessly with a portable device (20) and that constitutes a control unit that detects the position of the portable device based on the wireless communication, the position detection device having: an abnormality confirmation unit (S120) that determines whether an abnormality has occurred in any of the multiple communication devices; a first determination unit (S130) that detects the position of the portable device by a first determination method using machine learning; and a second determination unit (S135, S140) that executes a second determination method that does not use machine learning, wherein when the abnormality confirmation unit determines that no abnormality has occurred in the communication devices, the first determination unit detects the position of the portable device by the first determination method, and when it determines that an abnormality has occurred in the communication devices, the second determination unit executes the second determination method.

Images