Vehicle system, method for switching configuration of in-vehicle network, and recording medium

Abstract

Provided are a vehicle system, a method for switching the configuration of an in-vehicle network, and a recording medium with which it is possible to suppress wasteful data transmission from a plurality of types of object detection sensors.　This vehicle system includes a switch constituting an in-vehicle network, and a controller capable of switching the configuration of the in-vehicle network by controlling the switch. Two or more types of object detection sensors that use different measurement methods are connected to the in-vehicle network, and the controller is provided with an estimation means that estimates the obstacle recognition accuracy of at least one object detection sensor of the two or more types of object detection sensors. Furthermore, on the basis of the obstacle recognition accuracy of the at least one object detection sensor, the controller changes the configuration of the in-vehicle network and thereby changes the object detection sensors connected to the in-vehicle network.

Description

Vehicle system, in-vehicle network configuration switching method, and recording medium

[0001] The present invention relates to a vehicle system, a method for switching the configuration of an in-vehicle network, and a recording medium.

[0002] Patent Literature 1 discloses a driving assistance device that can maintain an active automated driving assistance function even if the image recognition accuracy of an on-board camera deteriorates. Specifically, this driving assistance device is equipped with a camera and a radar device, and when the camera cannot recognize lane markings, it sets estimated lane markings based on the relative distance between the road edge recognized by the radar device and the vehicle. The driving assistance device then continues to control the vehicle's driving based on the estimated lane markings.

[0003] JP 2023-46108 A

[0004] In the configuration of Patent Document 1, sensor devices such as cameras, radar, and sonar are connected to various ECUs (Electronic Control Units) via an in-vehicle communication line such as a Controller Area Network (CAN). Therefore, even when the cameras cannot recognize lane markings, data from the cameras is sent to the ECU. Conversely, even when the cameras can recognize lane markings, data from the radar is sent to the ECU, resulting in a kind of waste.

[0005] The present disclosure aims to provide a vehicle system, an in-vehicle network configuration switching method, and a recording medium that can reduce wasteful data transmission from an object detection sensor.

[0006] According to a first aspect, there is provided a vehicle system including a switch that configures an in-vehicle network, and a controller that can switch the configuration of the in-vehicle network by controlling the switch, wherein two or more types of object detection sensors with different measurement methods are connected to the in-vehicle network, and the controller has an estimation means that estimates the obstacle recognition accuracy of at least one of the two or more types of object detection sensors, and the system changes the configuration of the in-vehicle network based on the obstacle recognition accuracy of the one object detection sensor, thereby changing the object detection sensors connected to the in-vehicle network.

[0007] According to a second aspect, there is provided a method for switching the configuration of an in-vehicle network, in which a controller capable of switching the configuration of the in-vehicle network controls a switch of an in-vehicle network including a switch that constitutes the in-vehicle network and two or more types of object detection sensors with different measurement methods, estimates the obstacle recognition accuracy of at least one of the two or more types of object detection sensors, and changes the configuration of the in-vehicle network based on the obstacle recognition accuracy of the one object detection sensor, thereby changing the object detection sensors connected to the in-vehicle network.

[0008] According to a third aspect, there is provided a recording medium storing a program that causes a controller capable of switching the configuration of an in-vehicle network to execute the following processes: estimating the obstacle recognition accuracy of at least one of the two or more object detection sensors by controlling a switch that constitutes an in-vehicle network and the switch including two or more object detection sensors with different measurement methods; and changing the configuration of the in-vehicle network based on the obstacle recognition accuracy of the one object detection sensor, thereby changing the object detection sensor to be connected to the in-vehicle network.

[0009] According to the present disclosure, it is possible to provide a vehicle system, an in-vehicle network configuration switching method, and a recording medium that can reduce wasteful data transmission from multiple types of object detection sensors.

[0010] FIG. 1 is a diagram illustrating one configuration of the present disclosure. FIG. 2 is a flowchart illustrating the operation of the present disclosure. FIG. 3 is a diagram for explaining the operation of the present disclosure. FIG. 4 is a diagram for explaining the operation of the present disclosure. FIG. 5 is a diagram illustrating one configuration of the present disclosure. FIG. 6 is a diagram illustrating an example of a judgment table of predicted recognition accuracy referenced by a controller of the present disclosure. FIG. 7 is a diagram illustrating an example of a selection table of object detection sensors referenced by a controller of the disclosure. FIG. 8 is a flowchart illustrating the operation of the present disclosure. FIG. 9 is a diagram illustrating another configuration of the present disclosure. FIG. 10 is a flowchart illustrating the operation of another configuration of the present disclosure. FIG. 11 is a diagram illustrating another example of a selection table of object detection sensors referenced by a controller of the present disclosure. FIG. 12 is a flowchart illustrating the operation of another configuration of the present disclosure. FIG. 13 is a diagram illustrating the configuration of a computer constituting a vehicle system of the present disclosure.

[0011] First, an overview of one embodiment of the present disclosure will be described with reference to the drawings. In this disclosure, the drawings relate to one or more embodiments. The reference numerals in the drawings attached to this overview are attached to each element for convenience as an example to facilitate understanding, and are not intended to limit the present disclosure to the illustrated form. Furthermore, connecting lines between blocks in the drawings and the like referred to in the following description include both bidirectional and unidirectional lines. Unidirectional arrows are used to schematically indicate the flow of main signals (data) and do not exclude bidirectionality. A program is executed via a computer device, which includes, for example, a processor, a storage device, an input device, a communication interface, and, if necessary, a display device. Furthermore, this computer device is configured to be able to communicate with internal or external devices (including computers) via the communication interface, whether wired or wireless. Although ports or interfaces are present at the input / output connection points of each block in the drawings, they are not shown.

[0012] In one embodiment, the present disclosure can be realized in a vehicle system including a switch 20 that configures an in-vehicle network, and a controller 10 that can switch the configuration of the in-vehicle network by controlling the switch 20, as shown in FIG.

[0013] Two or more types of object detection sensors with different measurement methods are connected to this in-vehicle network. In the example of FIG. 1 , a camera C and a LiDAR (Light Detection and Ranging) L are connected as object detection sensors. The controller 10 includes an estimation unit 11 that estimates the obstacle recognition accuracy of at least one of the two or more types of object detection sensors. Furthermore, the controller 10 changes the configuration of the in-vehicle network based on the obstacle recognition accuracy of the one object detection sensor, thereby changing the object detection sensor connected to the in-vehicle network.

[0014] The vehicle system configured as described above operates as follows. First, the vehicle system controller 10 estimates the obstacle recognition accuracy of at least one of the two or more object detection sensors (step S01 in FIG. 2). The one object detection sensor may be a commonly used object detection sensor. Alternatively, for example, the one object detection sensor may be a sensor that periodically transmits data to an in-vehicle network at a frequency equal to or greater than a predetermined frequency. A typical example of such an object detection sensor is a camera C, whose obstacle recognition accuracy is significantly affected by day / night and weather conditions. The controller 10 acquires external information and estimates the obstacle recognition accuracy of the one object detection sensor.

[0015] Next, the controller 10 changes the configuration of the in-vehicle network based on the obstacle recognition accuracy of the one object detection sensor (step S02 in FIG. 2), thereby changing the object detection sensor connected to the in-vehicle network.

[0016] 3 and 4, the thick lines between the camera C, the LiDAR L, and the switch 20 indicate the section in which a communication path is set by the controller 10. For example, if it is estimated that the obstacle recognition accuracy of the camera C as one object detection sensor is high, the controller 10 controls the switch 20 to connect the camera C to the switch 20 as shown in Fig. 3, but does not set a communication path between the LiDAR L and the switch 20. As a result, data from the LiDAR L does not flow to the in-vehicle network.

[0017] Furthermore, for example, when it is estimated that the obstacle recognition accuracy of camera C serving as the one object detection sensor is low, controller 10 controls switch 20 to connect both camera C and LiDAR L to switch 20 as shown in Fig. 4. As a result, data from LiDAR L is sent to the in-vehicle network so as to compensate for the obstacle recognition accuracy of camera C.

[0018] By using a vehicle system that operates as described above, it is possible to reduce wasteful data transmission from multiple types of object detection sensors. In the examples of FIGS. 3 and 4 , an example was described in which one object detection sensor is camera C, but the one object detection sensor may be a sensor other than camera C. For example, if one object detection sensor is LiDAR L, the controller 10 estimates the obstacle recognition accuracy and selects a combination of object detection sensors to connect to the network. Furthermore, if the estimation of the obstacle recognition accuracy of camera C indicates that the recognition accuracy is extremely low, the communication path between camera C and switch 20 may not be established and data may be blocked.

[0019] [First Embodiment] Next, a first embodiment in which the present disclosure is applied to a vehicle equipped with a camera, LiDAR, and radar (millimeter-wave radar) will be described. Fig. 5 is a diagram showing one configuration of the present disclosure. Referring to Fig. 5, a vehicle system 500 is shown that includes switches (SW1, SW3) that connect six ECUs 1 to 6 with a sensor group, and a switch (controller & SW2 100) that has a controller function.

[0020] ECU 1 is a vehicle body ECU that controls each part of the vehicle body, ECU 2 is a powertrain ECU that controls the drive system, ECU 3 is an ADAS ECU related to ADAS (Advanced Driver Assistance Systems) functions, ECU 4 is a communication ECU that controls the communication system, ECU 5 is an infotainment ECU that controls the vehicle's audio / video system, and ECU 6 is an EV ECU that controls the electrical system. Note that the arrangement of these ECUs is merely an example and is not particularly limited. Also, various display devices, speakers, etc. connected to the in-vehicle network are omitted from Figure 5.

[0021] As shown in Figure 5, this vehicle is equipped with a front camera FC, a front LiDAR FL, and a front radar FR at the front of the vehicle as object detection sensors. Also, this vehicle is equipped with a rear camera RC, a rear LiDAR RL, and a rear radar RR at the rear of the vehicle as object detection sensors. Furthermore, this vehicle is equipped with a right radar RiR and a left radar LR on the left and right sides as object detection sensors.

[0022] 5 indicate a brightness sensor S1, a rain sensor S2, and a fog sensor S3, respectively. A device called a visibility meter or the like can also be used as the fog sensor S3.

[0023] The Controller & SW2 100 is a device that combines the functions of an SDN (Software Defined Networking) controller and an SDN switch. The Controller & SW2 100 has a function of estimating the recognition accuracy of the object detection sensors using sensor values ​​from the brightness sensor S1, the rain sensor S2, and the fog sensor S3, and selecting the object detection sensors to connect to the in-vehicle network based on the result. The Controller & SW2 100 may also combine the functions of an SDN controller and an SDN switch implemented using OpenFlow technology.

[0024] The switches 201 and 203 are SDN switches that have the function of transmitting received packets from a designated port in accordance with control information (flow entry) set by the controller & SW2 100. As described above, the controller & SW2 100 also has the function of an SDN switch, and has the function of transmitting received packets from a designated port in accordance with control information (flow entry) set by itself.

[0025] The controller & SW2 100 can block communication from devices connected to a specific port by setting control information (flow entries) for discarding packets received at the specific port in the switches 201 and 203 and its own switch function. Therefore, the controller & SW2 100 corresponds to a controller that can switch the configuration of the in-vehicle network by controlling the switches. Furthermore, from the viewpoint of speeding up the setting of control information (flow entries), it is desirable to set the necessary control information (flow entries) in advance in the switches 201 and 203 and its own switch function. For example, the controller & SW2 100 stores a control information table (flow table) in which the necessary control information (flow entries) is set in the switches 201 and 203 and its own switch function. The controller & SW2 100 can then speed up the switching of the in-vehicle network configuration by changing the order in which the controller & SW2 100 references the control information tables (flow tables) for the switches 201 and 203 and its own switch function.

[0026] FIG. 6 shows an example of a determination table used by the controller & SW2 100 to estimate the recognition accuracy of the object detection sensors. In the example of FIG. 6, if the sensor value of the brightness sensor S1 is less than the threshold L1, the controller & SW2 100 determines that the recognition accuracy of all the object detection sensors is so low that the accuracy cannot be guaranteed. Furthermore, if the sensor value of the rain sensor S2 is equal to or greater than the threshold R2, the controller & SW2 100 determines that the recognition accuracy of all the object detection sensors is so low that the accuracy cannot be guaranteed. Furthermore, if the sensor value of the fog sensor S3 is equal to or greater than the threshold F2, the controller & SW2 100 determines that the recognition accuracy of all the object detection sensors is so low that the accuracy cannot be guaranteed. Note that the term "recognition accuracy cannot be guaranteed" does not mean that a certain object detection sensor is incapable of sensing. For example, radar (millimeter wave) radar is, in principle, considered to be less affected by rainfall or fog, but it is known that its recognition accuracy decreases in extremely heavy rainfall. In such cases, radar (millimeter wave) radar cannot guarantee recognition accuracy, so a safe erroneous judgment is made.

[0027] Fig. 7 is an example of a selection table for selecting an object detection sensor by the controller & SW2 100. In the selection table in Fig. 7, the object detection sensor to be selected is determined according to the weather and other conditions defined in the left column.

[0028] Next, the operation of this embodiment will be described in detail with reference to the drawings. Fig. 8 is a flowchart showing the operation of this disclosure. Referring to Fig. 8, first, the controller & SW2 100 acquires sensor values ​​from the brightness sensor S1, the rain sensor S2, and the fog sensor S3 (step S001).

[0029] Next, the controller & SW2 100 determines whether the recognition accuracy of the object detection sensors can be guaranteed by referring to the determination table shown in Fig. 6 (step S002). If the sensor values ​​of the brightness sensor S1, the rain sensor S2, and the fog sensor S3 satisfy any of the conditions shown in Fig. 6 (LOW in step S002), the controller & SW2 100 determines that the recognition accuracy of the object detection sensors cannot be guaranteed.

[0030] Next, the controller & SW2 100 determines whether the sensor value of the rain sensor S2 is greater than a threshold value R1 or whether the sensor value of the fog sensor S3 is greater than a threshold value F1 (step S003). Note that the threshold values ​​R1 and F1 are smaller than the aforementioned threshold values ​​R2 and F2, respectively. If either of these is true (YES in step S003), the controller & SW2 100 determines that the weather is bad.

[0031] Next, the controller & SW2 100 determines whether the sensor value of the brightness sensor S1 is greater than a threshold value L2 (step S004). The threshold value L2 is greater than the aforementioned threshold value L1. If the sensor value of the brightness sensor S1 is greater than the threshold value L2 (YES in step S004), the controller & SW2 100 determines that it is sunny and daytime. On the other hand, if the sensor value of the brightness sensor S1 is equal to or less than the threshold value L2 (NO in step S004), the controller & SW2 100 determines that it is sunny and nighttime. Note that "daytime" in sunny and daytime means during the day.

[0032] Finally, the controller & SW2 100 selects a sensor based on the determination results of steps S002 to S004 and changes the network configuration (step S005). For example, if it is determined that it is fine weather and daytime, the controller & SW2 100 changes the network configuration so that only the front camera FC and the rear camera RC are connected to the in-vehicle network in accordance with the selection table in FIG. 7.

[0033] Figure 9 shows an example of a network configuration when it is determined that the weather is clear and daytime. As shown in Figure 9, image data captured by the front camera FC and rear camera RC flows through the in-vehicle network. Meanwhile, the X marks next to the LiDAR and radar in Figure 9 indicate that they are not connected to the in-vehicle network. Therefore, measurement data from the front and rear LiDAR and radar is discarded at the input ports of the controller & SW2 100 and switch SW3, respectively.

[0034] As described above, according to this embodiment, it is possible to select an object detection sensor based on the recognition accuracy of multiple object detection sensors and connect it to the in-vehicle network, thereby freeing up bandwidth on the in-vehicle network and allowing it to be used for transmitting and receiving data for other purposes.

[0035] 5, the controller and the switch are integrated as the controller & SW2, but it is also possible to adopt a configuration in which the controller and the SW2 are separated.It is also possible to assign some or all of the functions of the controller to one of the ECUs.

[0036] In the above embodiment, the recognition accuracy of the object detection sensor is estimated using the brightness sensor S1, the rainfall sensor S2, and the fog sensor S3. However, the combination of these sensors can be changed as appropriate. Of course, the vehicle system 500 does not necessarily need to include all of the brightness sensor S1, the rainfall sensor S2, and the fog sensor S3. Furthermore, the vehicle system 500 may include other sensors, such as a humidity sensor, in addition to the brightness sensor S1, the rainfall sensor S2, and the fog sensor S3. For example, by referring to the sensor value of the humidity sensor, it is possible to know that rain is imminent. This allows the vehicle system 500 to connect the LiDAR or radar to the in-vehicle network at an early stage.

[0037] In the above embodiment, the recognition accuracy of the object detection sensors is estimated using the brightness sensor S1, the rainfall sensor S2, and the fog sensor S3, but image data from the front camera FC or the rear camera RC can be used instead of these sensors. For example, if rainfall or fog is observed in the image from the front camera FC, the controller & SW2 100 will select an object detection sensor according to the selection table in FIG. 7.

[0038] [Second Embodiment] In the first embodiment described above, the recognition accuracy of an object detection sensor was estimated using a luminance sensor S1, etc. However, a second embodiment will be described in which the recognition accuracy of an object detection sensor is estimated using a communication function instead of these sensors. FIG. 10 is a diagram showing another configuration of the present disclosure. The first difference in configuration and operation from the first embodiment shown in FIG. 5 is that the vehicle system 500a is equipped with a communication unit 101 and a GPS 102 instead of the luminance sensor S1, etc. The second difference from the first embodiment shown in FIG. 5 is that the controller & SW2 100a selects an object detection sensor based on data obtained through the communication function. Since the other configurations are the same as those of the first embodiment, the following description will focus on these differences.

[0039] The communication unit 101 provides a function of transmitting and receiving data to and from an external server, etc., via short-range wireless communication, a mobile communication network, etc. A terminal of a mobile communication system can also be used as this communication unit 101.

[0040] The GPS (Global Positioning System) 102 is a device that receives signals from GPS satellites and determines the current location. The GPS 102 may be a device used in a car navigation system or the like. The GPS 102 may be a device that determines the current location using any positioning system such as the GNSS (Global Navigation Satellite System).

[0041] The controller & SW2 100a acquires current weather information, which indicates the actual weather information at the position obtained by the GPS 102, from an external weather information server or the like. The controller & SW2 100a estimates the accuracy of obstacle recognition by the object detection sensor based on the content of this current weather information.

[0042] 11 is another flowchart showing the operation of the present disclosure. The controller & SW2 100a acquires location information from the GPS 102 (step S101).

[0043] Next, the controller & SW2 100a accesses an external weather information server or the like via the communication unit 101 to obtain current weather information for the position obtained in step S101 (step S102).

[0044] Next, the controller & SW2 100a analyzes the acquired current weather information (step S103). If the current weather is stormy ("stormy weather" in step S103), the controller & SW2 100a determines that the recognition accuracy of the object detection sensor cannot be guaranteed.

[0045] Furthermore, if the actual weather is heavy rain or fog ("heavy rain / fog" in step S103), the controller & SW2 100a determines that the weather is bad.

[0046] Furthermore, if the actual weather is clear and the current time is daytime ("clear and daytime" in step S103), the controller & SW2 100a determines that it is clear and daytime.

[0047] Furthermore, if the actual weather is clear and the current time is night ("Clear and Night" in step S103), the controller & SW2 100a determines that it is clear and night.

[0048] Finally, the controller & SW2 100a selects a sensor based on the determination result of step S103, and changes the network configuration (step S105).

[0049] As described above, according to the present disclosure, the present invention can be modified to acquire current weather information from an external weather information server or the like. Furthermore, the configuration of the second embodiment may be supplemented with the brightness sensor S1, rain sensor S2, and fog sensor S3, similar to those of the first embodiment. In this case, the controller & SW2 100a can estimate the recognition accuracy of the object detection sensors by using the current weather information from the outside in combination with information from the brightness sensor S1, rain sensor S2, and fog sensor S3.

[0050] [Third Embodiment] In the first embodiment described above, the weather, etc. is determined from the sensor value, and an object detection sensor is selected by referring to the selection table in Fig. 7. However, a configuration in which an object detection sensor is selected directly from the sensor value can also be employed. Fig. 12 is a diagram showing another example of the object detection sensor selection table.

[0051] The selection table in Fig. 12 is almost equivalent to a combination of the decision table in Fig. 6 and the selection table in Fig. 7. The specific contents will be explained below together with the operation of the controller & SW2 100.

[0052] Next, the operation of this embodiment will be described in detail with reference to the drawings. Fig. 13 is another flowchart showing the operation of the present disclosure. Referring to Fig. 13, first, the controller & SW2 100 acquires sensor values ​​from the brightness sensor S1, the rain sensor S2, and the fog sensor S3 (step S201).

[0053] Next, the controller & SW2 100 selects an object detection sensor by referring to the selection table shown in Fig. 12. Specifically, if the sensor values ​​of the brightness sensor S1, the rain sensor S2, and the fog sensor S3 are either less than the threshold L1, greater than or equal to the threshold R2, or greater than or equal to the threshold F2, the controller & SW2 100 does not select an object detection sensor (stormy weather in step S202).

[0054] Furthermore, if the sensor value of the brightness sensor S1 is equal to or greater than the threshold L1 but less than the threshold L2, but the sensor value of the rainfall sensor S2 is greater than the threshold R1, the controller & SW2 100 selects the camera, LiDAR, and radar (heavy rain in step S202). This is the combination of object detection sensors to select in the daytime when it is raining, as described in the remarks column of FIG. 12.

[0055] Furthermore, if the sensor value of the brightness sensor S1 is equal to or greater than the threshold L1 but less than the threshold L2, but the sensor value of the fog sensor S3 is greater than the threshold F1, the controller & SW2 100 selects the camera, LiDAR, and radar (Fog in step S202). This is the combination of object detection sensors to select in a foggy daytime state, as described in the remarks column of FIG. 12 .

[0056] Furthermore, if the sensor value of the brightness sensor S1 is equal to or greater than the threshold L1 but less than the threshold L2, but the sensor values ​​of the rain sensor S2 and the fog sensor S3 are less than the threshold R1 and threshold F1, respectively, the controller & SW2 100 selects the camera and LiDAR (clear and night in step S202). In this case, as described in the remarks column of FIG. 12, this is the combination of object detection sensors to select when it is night and clear.

[0057] Furthermore, if the sensor value of the brightness sensor S1 is equal to or greater than the threshold L2 and the sensor value of the rain sensor S2 is greater than the threshold R1, the controller & SW2 100 selects only the camera (weather shower in step S202). As described in the remarks column of FIG. 12, this is a combination of object detection sensors to be selected in the daytime when it is so-called weather showers.

[0058] Furthermore, if the sensor value of the brightness sensor S1 is equal to or greater than the threshold L2, the sensor value of the rain sensor S2 is less than the threshold R1, and the sensor value of the fog sensor S3 is less than the threshold F1, the controller & SW2 100 selects only the camera (clear and daytime in step S202). This is the combination of object detection sensors to be selected when it is clear and daytime, as described in the remarks column of FIG. 12.

[0059] Finally, the controller & SW2 100 selects a sensor based on the determination result of step S202, and changes the network configuration (step S205).

[0060] As described above, the present disclosure can be modified to a configuration in which an object detection sensor is selected directly from a sensor value.

[0061] Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above-described embodiments, and further modifications, substitutions, and adjustments can be made without departing from the basic technical concept of the present disclosure. For example, the network configurations, element configurations, and data representation formats shown in the drawings are examples intended to aid in understanding the present disclosure, and are not limited to the configurations shown in these drawings.

[0062] For example, the weather conditions and the types of object detection sensors selected in the above-described embodiments are merely examples, and are not limited to the sensor selection patterns described above. For example, when it is raining, whether or not to use radar may be changed or the radar to be used may be selected depending on the level of rainfall. Furthermore, the types of object detection sensors are not limited to the three types described above. For example, an infrared camera may be added as an object detection sensor. In this case, a configuration may be adopted in which only an infrared camera or an infrared camera and LiDAR are selected at night and on a clear day.

[0063] Furthermore, the order of processing in the flowcharts shown in the above-described embodiments can be changed as appropriate. For example, the order of processing steps S002 to S004 is not limited to the order shown in Fig. 8. For example, it is possible to first determine whether it is day or night and then determine whether it is raining or foggy, and then further determine the order based on the recognition accuracy of the object detection sensor.

[0064] (Hardware Configuration) In each embodiment of the present disclosure, each component of each device represents a functional unit block. Some or all of the components of each device are realized by an arbitrary combination of an information processing device 900 and a program, for example, as shown in FIG. 14. FIG. 14 is a block diagram showing an example of the hardware configuration of the information processing device 900 that realizes each component of each device. The information processing device 900 includes, as an example, the following configuration: - CPU (Central Processing Unit) 901 - ROM (Read Only Memory) 902 - RAM (Random Access Memory) 903 - Program 904 loaded into RAM 903 - Storage device 905 that stores the program 904 - Drive device 907 that reads and writes to a recording medium 906 - Communication interface 908 that connects to a communication network 909 - Input / output interface 910 that inputs and outputs data - Bus 911 that connects each component

[0065] Each component of each device in each embodiment is realized by the CPU 901 acquiring and executing a program 904 that realizes the function. That is, the CPU 901 in FIG. 14 executes an object detection sensor accuracy estimation program and an in-vehicle network configuration change program, and performs an update process for each calculation parameter stored in the RAM 903, storage device 905, etc. The program 904 that realizes the function of each component of each device is stored in the storage device 905 or ROM 902 in advance, for example, and is read by the CPU 901 as needed. Note that the program 904 may be supplied to the CPU 901 via the communication network 909, or may be stored in advance on the recording medium 906, and the drive device 907 may read the program and supply it to the CPU 901.

[0066] There are various variations in the method of realizing each device. For example, each device may be realized by any combination of a separate information processing device 900 and a program for each component. Furthermore, multiple components of each device may be realized by any combination of a single information processing device 900 and a program. That is, each unit (processing means, function) of the vehicle system shown in the first to third embodiments can be realized by a computer program that causes a processor installed in the device to execute the above-mentioned processes using its hardware.

[0067] In addition, some or all of the components of each device may be realized by other general-purpose or dedicated circuits, processors, etc., or a combination of these. These may be configured by a single chip, or by multiple chips connected via a bus.

[0068] Some or all of the components of each device may be realized by a combination of the above-mentioned circuits and programs.

[0069] When some or all of the components of each device are realized by multiple information processing devices, circuits, etc., the multiple information processing devices, circuits, etc. may be centrally or decentralized. For example, the information processing devices, circuits, etc. may be realized as a client-server system, a cloud computing system, or the like, in a form in which each device is connected via a communication network.

[0070] It should be noted that the above-described embodiments are preferred embodiments of the present disclosure, and the scope of the present disclosure is not limited to only the above-described embodiments. In other words, those skilled in the art can modify or substitute the above-described embodiments to construct various modified forms without departing from the gist of the present disclosure.

[0071] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0072] [Supplementary Note 1] A vehicle system including: a switch configuring an in-vehicle network; and a controller capable of switching the configuration of the in-vehicle network by controlling the switch, wherein two or more types of object detection sensors using different measurement methods are connected to the in-vehicle network; the controller includes: estimation means for estimating the obstacle recognition accuracy of one of the two or more object detection sensors; and changing the configuration of the in-vehicle network based on the obstacle recognition accuracy of the one object detection sensor, thereby changing the object detection sensor connected to the in-vehicle network. [Supplementary Note 2] The estimation means of the vehicle system may be configured to estimate the obstacle recognition accuracy of the one object detection sensor based on a measurement value obtained by a luminance sensor. [Supplementary Note 3] The one object detection sensor of the vehicle system may be a camera. [Supplementary Note 4] The estimation means of the above-mentioned vehicle system may further estimate the obstacle recognition accuracy of object detection sensors other than the one object detection sensor based on measurements obtained by a rainfall sensor, and the controller may change the object detection sensors connected to the in-vehicle network based on the obstacle recognition accuracy of the other object detection sensors. [Supplementary Note 5] The estimation means of the above-mentioned vehicle system may further estimate the obstacle recognition accuracy of object detection sensors other than the one object detection sensor based on measurements obtained by a fog sensor, and the controller may change the object detection sensors connected to the in-vehicle network based on the obstacle recognition accuracy of the other object detection sensors. [Supplementary Note 6] The estimation means of the above-mentioned vehicle system may estimate the obstacle recognition accuracy of the one object detection sensor based on position information of the vehicle and the current weather at the position. [Supplementary Note 7] The two or more object detection sensors of the above-mentioned vehicle system may include a camera and LiDAR.[Supplementary Note 8] The controller of the above-mentioned vehicle system may be configured to select an object detection sensor to be used from the two or more types of object detection sensors based on a combination of measurements from a luminance sensor, a rainfall sensor, and a fog sensor. [Supplementary Note 9] The estimation means of the above-mentioned vehicle system may be configured to disconnect the two or more types of object detection sensors from the in-vehicle network if the obstacle recognition accuracy of each of the two or more types of object detection sensors is equal to or lower than a predetermined reference value. [Supplementary Note 10] An in-vehicle network configuration switching method may be configured in which a controller capable of switching the configuration of the in-vehicle network by controlling a switch constituting an in-vehicle network and the switch of an in-vehicle network including two or more types of object detection sensors with different measurement methods estimates the obstacle recognition accuracy of at least one of the two or more types of object detection sensors, and changes the configuration of the in-vehicle network based on the obstacle recognition accuracy of the one object detection sensor, thereby changing the object detection sensor to be connected to the in-vehicle network. [Supplementary Note 11] A recording medium storing a program that causes a controller capable of switching the configuration of an in-vehicle network by controlling a switch that configures an in-vehicle network of the above-mentioned vehicle system, the in-vehicle network including two or more types of object detection sensors with different measurement methods, to execute the following processes: estimating an obstacle recognition accuracy for at least one object detection sensor of the two or more types of object detection sensors, and changing the configuration of the in-vehicle network based on the obstacle recognition accuracy of the one object detection sensor, thereby changing the object detection sensor connected to the in-vehicle network. Furthermore, the forms of Supplementary Notes 10 to 11 can be expanded into the forms of Supplementary Notes 2 to 9, similar to Supplementary Note 1.

[0073] The disclosures of the above-cited patent documents are incorporated herein by reference and may be used as the basis or part of this disclosure, as necessary. Modifications and adjustments of the embodiments and examples are possible within the scope of this disclosure (including the claims), and further based on its basic technical concept. Furthermore, various combinations and selections (including partial deletions) of various disclosed elements (including elements of each claim, each element of each embodiment or example, each element of each drawing, etc.) are possible within the scope of this disclosure. In other words, this disclosure naturally includes various modifications and alterations that would be possible by a person skilled in the art in accordance with the entire disclosure, including the claims, and the technical concept. In particular, with regard to the numerical ranges described herein, any numerical value or subrange within that range should be construed as specifically described, even if not otherwise specified. Furthermore, the disclosures of the above-cited documents, when used in part or in whole in combination with the disclosures herein as part of this disclosure, in accordance with the spirit of this disclosure, are also deemed to be included in the disclosures of this application.

[0074] 10 Controller 11 Estimation means 20 Switch 100 Controller & SW2 500, 500a Vehicle system 900 Information processing device 901 CPU (Central Processing Unit) 902 ROM (Read Only Memory) 903 RAM (Random Access Memory) 904 Program 905 Storage device 906 Recording medium 907 Drive device 908 Communication interface 909 Communication network 910 Input / output interface 911 Bus C Camera FC Front camera FL Front LiDAR FR Front radar RC Rear camera RL Rear LiDAR RR Rear radar RiR Right radar L LiDAR LR Left radar S1 Brightness sensor S2 Rain sensor S3 Fog sensor SW1, SW3 Switch

Claims

1. A vehicle system comprising: a switch that configures an in-vehicle network; and a controller that can switch the configuration of the in-vehicle network by controlling the switch, wherein two or more types of object detection sensors with different measurement methods are connected to the in-vehicle network; the controller has an estimation means that estimates the obstacle recognition accuracy of at least one of the two or more types of object detection sensors; and changes the configuration of the in-vehicle network based on the obstacle recognition accuracy of the one object detection sensor, thereby changing the object detection sensor to be connected to the in-vehicle network.

2. The vehicle system according to claim 1, wherein said estimation means estimates the accuracy of obstacle recognition by said one object detection sensor based on a measurement value obtained by a brightness sensor.

3. The vehicle system of claim 2, wherein the one object detection sensor is a camera.

4. A vehicle system according to any one of claims 1 to 3, wherein the estimation means further estimates the obstacle recognition accuracy of object detection sensors other than the one object detection sensor based on measurements obtained by a rainfall sensor, and the controller changes the object detection sensor to be connected to the in-vehicle network based on the obstacle recognition accuracy of the other object detection sensors.

5. A vehicle system according to any one of claims 1 to 4, wherein the estimation means further estimates the obstacle recognition accuracy of object detection sensors other than the one object detection sensor based on measurements obtained by the fog sensor, and the controller changes the object detection sensors connected to the in-vehicle network based on the obstacle recognition accuracy of the other object detection sensors.

6. A vehicle system according to any one of claims 1 to 5, wherein the estimation means estimates the accuracy of obstacle recognition by the one object detection sensor based on the position information of the vehicle itself and the current weather conditions at that position.

7. The vehicle system of any one of claims 1 to 6, wherein the two or more types of object detection sensors include a camera and a LiDAR.

8. A vehicle system according to any one of claims 1 to 7, wherein the controller selects which of the two or more types of object detection sensors to use based on a combination of measurements from a brightness sensor, a rain sensor, and a fog sensor.

9. A vehicle system according to any one of claims 1 to 7, wherein the estimation means disconnects the two or more types of object detection sensors from the in-vehicle network when the obstacle recognition accuracy of each of the two or more types of object detection sensors is below a predetermined reference value.

10. A method for switching the configuration of an in-vehicle network, comprising: a controller capable of switching the configuration of an in-vehicle network by controlling a switch of an in-vehicle network including two or more types of object detection sensors with different measurement methods; estimating the obstacle recognition accuracy of at least one of the two or more types of object detection sensors; and changing the configuration of the in-vehicle network based on the obstacle recognition accuracy of the one object detection sensor, thereby changing the object detection sensor to be connected to the in-vehicle network.

11. A recording medium storing a program that causes a controller capable of switching the configuration of an in-vehicle network by controlling a switch of an in-vehicle network including two or more types of object detection sensors with different measurement methods to execute the following processes: a process of estimating the obstacle recognition accuracy of at least one of the two or more types of object detection sensors; and a process of changing the object detection sensor connected to the in-vehicle network by changing the configuration of the in-vehicle network based on the obstacle recognition accuracy of the one object detection sensor.

Images