Vehicle control device

Abstract

A vehicle control device includes: an execution idle duration prediction unit that predicts an execution idle duration of a current automatic driving control software program on the basis of external environment information of a vehicle; and a verification object selection unit that selects, as a verification object, a verification scene in which execution can be completed within the execution idle duration from among verification scenes for verifying the performance of the new automatic driving control software program.

Description

Technical Field

[0001] The invention relates to a vehicle control device. Background Art

[0002] In the past, as a safety evaluation method for a vehicle's autonomous driving control software program (hereinafter referred to as "autonomous driving control software"), there was a shadow mode evaluation method that used external environmental information to execute the autonomous driving control software in the background in an actual vehicle and perform evaluation. However, in order to realize the shadow mode, high-performance hardware needs to be installed on the vehicle, which increases the cost of vehicle manufacturing. Therefore, a technology that can verify the automatic driving control software without adding high-performance hardware to the vehicle has been proposed (see Patent Document 1).

[0003] Patent Document 1 states that a vehicle control device "parallel or parallel executes an old control software unit representing an old version of control software and a new control software unit representing a new version of control software" and "performs verification using idle resources (time, CPU) where the old control software is not executed." Prior art literature Patent Literature

[0004] Patent Document 1: Japanese Patent Application Publication No. 2022-013187 Summary of the invention Technical problem to be solved by the invention

[0005] As described above, in the past, a technology has been proposed for executing new autonomous driving control software during the idle time of the old autonomous driving control software to verify the safety of the new autonomous driving control software. However, depending on the size of the driving scenario, sometimes the verification of the new autonomous driving control software cannot be completed during the idle time of the old autonomous driving control software. That is, in the prior art, there is a problem that a driving scenario of the best size cannot be selected as the verification object according to the idle time of the old autonomous driving control software. When such a problem occurs, re-verification occurs, and the verification efficiency is reduced.

[0006] The present invention is completed to solve the above-mentioned problems. The purpose of the present invention is to provide a vehicle control device, which can dynamically select verification scenarios that can be executed within the execution idle duration, thereby improving the verification efficiency of the automatic driving control software program. Technical means for solving technical problems

[0007] The vehicle control device of the present invention includes: an execution idle duration prediction unit, which predicts the execution idle duration of the current automatic driving control software program based on the external environment information of the vehicle; and a verification object selection unit, which selects a verification scenario that can be executed within the execution idle duration as a verification object from the verification scenarios used to verify the performance of the new automatic driving control software program. Effects of the Invention

[0008] According to the present invention with the above structure, a vehicle control device can be provided, which can dynamically select verification scenarios that can be executed and completed within the execution idle duration, thereby improving the verification efficiency of the automatic driving control software program. Problems, structures, and effects other than those described above will become more apparent through the following description of each embodiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 This is a diagram for explaining the connection relationship between the vehicle control device according to the first embodiment of the present invention and various devices in the vehicle. Figure 2 This is a block diagram showing a configuration example of a vehicle control device according to Embodiment 1 of the present invention. Figure 3 This is a flowchart showing the procedure of a process of acquiring external environment information in the information acquiring unit of the vehicle control device according to the first embodiment of the present invention. Figure 4 This is a diagram showing a data example of external environment information acquired in the vehicle control device according to the first embodiment of the present invention. Figure 5 This is a diagram showing an example of new SW information in the vehicle control device according to the first embodiment of the present invention. Figure 6 This is a flowchart showing the procedure of a verification scenario storage process in a verification scenario storage unit of the vehicle control device according to the first embodiment of the present invention. Figure 7 It is a diagram showing an example of verification scenario data stored in the vehicle control device according to the first embodiment of the present invention. Figure 8 This is a flowchart showing the procedure of the execution idle continuation time prediction process in the execution idle continuation time prediction unit of the vehicle control device according to the first embodiment of the present invention. Fig. 9 This is a diagram showing an example of data of the execution idle duration in the vehicle control device according to the first embodiment of the present invention. Fig.10This is a flowchart showing a processing procedure in a calculation unit of the vehicle control device according to the first embodiment of the present invention. Fig.11 This is a flowchart showing the procedure of a verification scene selection process in the verification target selection unit of the vehicle control device according to the first embodiment of the present invention. Fig.12 This is a diagram showing a data example of automatic driving end information in the vehicle control device according to the first embodiment of the present invention. Fig.13 It is a diagram showing a data example of a verification scenario selected in the vehicle control device according to the first embodiment of the present invention. Fig.14 This is a diagram showing a data example of the execution result of the calculation unit of the vehicle control device according to the first embodiment of the present invention. Fig.15 This is a flowchart showing the procedure of the verification process of new automatic driving control software in the verification unit of the vehicle control device involved in the first embodiment of the present invention. Fig.16 This is a block diagram showing a functional configuration of a vehicle control device according to Embodiment 2 of the present invention. Fig.17 This is a flowchart showing the procedure of the execution idle continuation time prediction process in the execution idle continuation time prediction unit of the vehicle control device according to the second embodiment of the present invention. Fig.18 It is a diagram showing a data example of object information in the vehicle control device according to the second embodiment of the present invention. Fig.19 This is a diagram for explaining the connection relationship of the vehicle control device according to the third embodiment of the present invention within the vehicle. Fig. 20 This is a diagram showing an example of information acquired from the in-vehicle user interface in the vehicle control device according to the third embodiment of the present invention. Fig.21 This is a flowchart showing the procedure of the execution idle continuation time prediction process in the execution idle continuation time prediction unit of the vehicle control device according to the third embodiment of the present invention. Fig. 22 This is a flowchart showing the procedure of a verification target scene segmentation process in a verification target selection unit of a vehicle control device according to a fourth embodiment of the present invention. Fig.23 This is a diagram showing a data example of verification scenarios to which priorities are assigned in the vehicle control device according to the fifth embodiment of the present invention. Fig.24This is a flowchart showing the procedure of a verification scene selection process in a verification target selection unit of a vehicle control device according to Embodiment 5 of the present invention. Fig.25 This is a diagram showing an example of external information acquired in the vehicle control device according to the sixth embodiment of the present invention. Fig.26 This is a diagram showing an example of information on the internal state of a controller unit acquired in a vehicle control device according to a seventh embodiment of the present invention. Fig. 27 It is a block diagram showing the hardware configuration of a vehicle control device according to each embodiment of the present invention. DETAILED DESCRIPTION

[0010] Hereinafter, a mode for implementing the present invention will be described with reference to the accompanying drawings. In this specification and the accompanying drawings, components having substantially the same function or structure are denoted by the same reference numerals to omit repeated description.

[0011] <Implementation method 1> Before describing the configuration of the vehicle control device according to the present embodiment, first, a connection relationship between various devices in a vehicle equipped with the vehicle control device according to the present embodiment and the vehicle control device will be described. Figure 1 This is a diagram for explaining the connection relationship between the vehicle control device 1 according to the present embodiment and various devices in the vehicle.

[0012] like Figure 1 As shown, the vehicle control device 1 is connected to the gateway 2, and obtains vehicle data such as vehicle speed, information of new autonomous driving control software (hereinafter referred to as new SW information), etc. from the gateway 2. In addition, the vehicle control device 1 obtains various sensor information from various sensor control devices such as the camera control device 3, the LiDAR (Light Detection and Ranging) control device 4, and the sonar control device 5 through the in-vehicle network. In addition, the vehicle control device 1 obtains cloud information such as the red duration information of the traffic light in the intersection in front of the vehicle and map data from the server 6 via cloud communication.

[0013] [Configuration Example of Vehicle Control Device] Next, the configuration of the vehicle control device 1 according to the present embodiment will be described. Figure 2 1 is a block diagram showing a configuration example of the vehicle control device 1 according to the present embodiment. Figure 2As shown, the vehicle control device 1 includes an information acquisition unit 11, a verification scenario storage unit 12, an execution idle duration prediction unit 13, a calculation unit 14, a verification object selection unit 15, and a verification unit 16. The information acquisition unit 11 is connected to the verification scenario storage unit 12, the execution idle duration prediction unit 13, and the calculation unit 14. The verification scenario storage unit 12, the execution idle duration prediction unit 13, and the calculation unit 14 are connected to the verification object selection unit 15. In addition, the calculation unit 14 is also connected to the verification unit 16.

[0014] The information acquisition unit 11 acquires various sensor information from various sensor control devices as external environment information M1 via the in-vehicle network, and outputs the external environment information M1 to the verification scenario storage unit 12, the execution idle duration prediction unit 13, and the calculation unit 14. In addition, the information acquisition unit 11 acquires cloud information from the server 6 as external environment information M1 via cloud communication. Figure 3 The acquisition process of the external environment information in the information acquisition unit 11 is described in detail in FIG.

[0015] The verification scenario storage unit 12 performs a storage process of the verification scenario based on the new SW information M2 input from the gateway 2 and the external environment information M1 input from the information acquisition unit 11 . In addition, the verification scenario storage unit 12 outputs the stored verification scenario M3 to the verification target selection unit 15. Figure 6 The storage process of the verification scene in the verification scene storage unit 12 is described in detail in FIG.

[0016] The execution idle duration prediction unit (execution idle duration prediction unit 13) predicts the execution idle duration M4 of the current automatic driving control software based on the external environment information of the vehicle. For example, the execution idle duration prediction unit 13 predicts the execution idle duration M4 based on the external environment information M1 input from the information acquisition unit 11. The execution idle duration M4 is, for example, the time when the driver of the vehicle is driving and not performing automatic driving, or the time when the vehicle control device 1 is not performing automatic driving processing when the automatic driving mode is switched to the automatic parking mode, assuming that the operation unit 14 is not executing the current SW. The execution idle duration M4 can also be taken as the time when the execution ratio of the operation unit 14 (the amount of calculation used relative to the total amount of calculation of the operation unit 14) is less than a specified value (for example, 30%).

[0017] When the traffic light ahead changes from yellow to red during the vehicle's automatic driving, the idle duration prediction unit 13 can predict that the vehicle will stop in front of the traffic light in a few seconds, and thus can predict the period before the traffic light turns green as the idle measurement time M4. In addition, when the vehicle enters a parking lot and starts to decelerate, the idle duration prediction unit 13 automatically stops the automatic driving in a few seconds, and thus the period during which the automatic driving stops can also be predicted as the idle measurement time M4.

[0018] The vehicle's external environment information includes, for example, external environment information M1 acquired from a sensor that detects the vehicle's external environment, image information of an arbitrary object indicating the end of the automatic driving described later, and the like. Since the information acquisition unit 11 can acquire the vehicle's external environment information by various means, the execution idle duration prediction unit 13 can predict the execution idle measurement time M4 with high accuracy. In addition, the execution idle duration prediction unit 13 outputs the predicted execution idle duration M4 to the verification object selection unit 15. In the later-described Figure 8 The prediction process of the execution idle duration M4 in the execution idle duration prediction unit 13 will be described in detail in .

[0019] The operation unit 14 determines whether the automatic driving is terminated based on the external environment information M1 input from the information acquisition unit 11. When the operation unit 14 determines that the automatic driving is continuing, it continues to execute the current automatic driving control software (current SW) and outputs the execution result M7 of the automatic driving to the verification unit 16. In addition, when the operation unit 14 determines that the automatic driving is terminated, it outputs the automatic driving termination information M5 indicating the termination of the automatic driving to the verification object selection unit 15. In addition, the operation unit (operation unit 14) executes the selection scene M6 (verification object) with the new automatic driving control software program during the execution idle duration M4, and outputs the execution result M7 of the new SW to the verification unit 16. In the later described Fig.10 The above-mentioned processing in the operation unit 14 is described in detail in FIG.

[0020] The verification object selection unit (verification object selection unit 15) selects a verification scene that can be executed within the execution idle duration M4 as a verification object from the verification scenes M3 for verifying the performance of the new automatic driving control software stored in the verification scene storage unit 12. In addition, the verification object selection unit 15 outputs the selected verification scene (hereinafter referred to as the selected scene M6) to the calculation unit 14. Fig.11 The selection process of the verification scene in the verification object selection unit 15 is described in detail in FIG.

[0021] The verification unit (verification unit 16) verifies the new autonomous driving control software program based on the calculation results of the current autonomous driving control software program calculated by the calculation unit (calculation unit 14) outside the execution idle duration M4 and the calculation results of the new autonomous driving control software program calculated by the calculation unit (calculation unit 14) within the execution idle duration M4. The verification results of the new SW performed by the verification unit 16 are sent to the development company of the new SW via the Internet, and the developers of the new SW can confirm the verification results of the new SW. In the following Fig.15 The above-mentioned processing in the verification unit 16 is described in detail in FIG.

[0022] The above-mentioned new SW information M2 and verification scenario M3 are stored in a database (DB: Data Base) not shown in the figure, which is composed of a non-volatile storage device. The external environment information M1, the execution idle duration M4, the automatic driving end information M5, the selected scenario M6 and the execution result M7 can be stored in a database (DB) not shown in the figure, or temporarily stored in a storage device not shown in the figure, such as a RAM (Random Access Memory) or a ROM (Readonly memory).

[0023] [External Environment Information Acquisition Processing in Information Acquisition Section] Figure 3 The flowchart shows the procedure of the external environment information M1 acquisition process in the information acquisition unit 11 of the vehicle control device 1 according to the present embodiment. In order to prepare the external environment information M1 before performing various processes related to the verification of the new SW, the processes described below are executed at a predetermined cycle.

[0024] First, the information acquisition unit 11 obtains information from various sensor control devices connected to the vehicle control device 1, such as Figure 1 The camera control device 3, the LiDAR control device 4, and the sonar control device 5 shown in the figure acquire various external environment information M1 (refer to Figure 4 ) (Step S101). In this process, the information acquisition unit 11 acquires cloud information as external environment information M1 from the server 6 via cloud communication (see Figure 4 ).

[0025] Next, the information acquisition unit 11 outputs the acquired external environment information M1 to the verification scenario storage unit 12, the execution idle duration prediction unit 13, and the calculation unit 14 (step S102). After the processing of step S102, the sensor information acquisition processing ends.

[0026] Figure 4 is a diagram showing a data example of the external environment information M1 acquired by the information acquisition unit 11. Figure 4 As shown, the external environment information M1 includes information data of "type" and information data of "content". "No." is a number indicating the arrangement order of the external environment information M1, for example, a digital number of "1" to "8". The arrangement order of the external environment information M1 is arbitrary.

[0027] The information data of “type” is information data corresponding to the type of sensor that is the acquisition source of the external environment information M1. For example, the “type” of the external environment information M1 from the camera sensor is set to “camera image”, and the “type” of the external environment information M1 from the cloud is set to “cloud information”.

[0028] The information data of “content” is information data indicating the content of the external environment information M1. For example, there can be cited “image of pedestrians walking at the intersection (1)” indicating an image of the situation at the intersection, “image of green traffic light ahead” indicating an image of the color of the traffic light ahead of the vehicle, and “red traffic light ahead for 8 seconds” indicating the content of cloud information.

[0029] Figure 5 2 is a diagram showing an example of new SW information M2 acquired by the vehicle control device 1 via the gateway 2. Figure 5 As shown, the new SW information M2 includes information data of "item" and information data of "content". "No." is a number indicating the arrangement order of the new SW information M2, for example, a digital number of "1" to "2". The arrangement order of the new SW information M2 is arbitrary.

[0030] The information data of "project" is information data indicating that the new SW information M2 is the main information of the new SW (for example, "new SW"), or information data indicating that the new SW information M2 is information about the version upgrade part relative to the current SW (for example, "SW version upgrade part").

[0031] The information data of "content" is information data indicating the content of the new SW information M2 corresponding to the "project". For example, "vehicle control software" indicating the content of the "new SW", "image processing technology at intersections" indicating the content of the "version upgrade portion of SW", etc. can be cited. The vehicle control software is software required to execute the control of the new SW. In addition, as a result of the upgrade of the image processing technology at intersections in the new SW, if more pedestrians at intersections can be detected than before, verification scenes can be saved only before the vehicle enters the intersection and when driving at the intersection. In this way, it is possible to configure the verification scene to be saved only in the portion where the version upgrade is performed from the current SW.

[0032] [Authentication scene storage process in the authentication scene storage unit] Figure 6 This is a flowchart showing the procedure of the verification scene storage process in the verification scene storage unit 12 of the vehicle control device 1 according to the present embodiment. When the verification scene storage unit 12 acquires the external environment information M1 from the information acquisition unit 11, the process described below starts.

[0033] First, the verification scenario storage unit 12 acquires the external environment information M1 from the information acquisition unit 11 and the new SW information M2 from the gateway 2 (step S201 ).

[0034] Next, the verification scenario storage unit 12 generates a verification scenario M3 based on the "content" corresponding to the "SW version upgrade part" of the new SW information M2 and the external environment information M1, and stores it in the DB (step S202). Figure 5 The "SW version upgrade part" shown is the new SW information M2 of "image processing technology at intersections", and the extracted Figure 4 The external environment information M1 of "image of pedestrians walking at an intersection (1)" to "image of pedestrians walking at an intersection (4)" shown in the figure generates a verification scene M3 (see the following description) according to the time length of each image. Figure 7 ) and save.

[0035] Next, the verification scene storage unit 12 outputs the verification scene M3 to the verification target selection unit 15 (step S203). After the process of step S203, the verification scene storage process ends.

[0036] Figure 7 1 is a diagram showing an example of data of the verification scenario M3 stored in the verification scenario storage unit 12. Figure 7 As shown, the verification scenario M3 includes information data of "verification scenario candidate" and information data of "time attribute." "No." is a number indicating the arrangement order of the verification scenario M3, for example, a digital number of "1" to "2".

[0037] The information data of the "verification scene candidate" is information data indicating the content of the verification scene generated by the verification scene storage unit 12. The information data of the "time attribute" is information data indicating the time length of the verification scene (image) stored in the "verification scene candidate". For example, since the time length of the "image of pedestrians walking at an intersection (1)" is 10 seconds, the "verification scene candidate" is saved as "pedestrians walking at an intersection (1)" and the verification scene M3 with the "time attribute" of "10 seconds" is saved.

[0038] [Execution Idle Duration Prediction Process in Execution Idle Duration Prediction Unit] Figure 8This is a flowchart showing the procedure of the execution idle duration prediction process in the execution idle duration prediction unit 13 of the vehicle control device 1 according to the present embodiment. When the execution idle duration prediction unit 13 acquires the external environment information M1 from the information acquisition unit 11, the process described below starts.

[0039] First, the execution idle duration prediction section 13 acquires the external environment information M1 from the information acquisition section 11 (step S301 ).

[0040] Next, the execution idle duration prediction unit 13 predicts the execution idle duration M4 of the current SW based on the external environment information M1 (step S302). In this process, the execution idle duration prediction unit 13 predicts the execution idle duration M4 of the current SW based on the external environment information M1. Figure 4 The "cloud information" in the external environment information M1 shown is "the duration of the red traffic light ahead is 8 seconds", and the execution idle duration M4 of the current SW is predicted (refer to the following description). Fig. 9 ) is "8 seconds".

[0041] Next, the execution idle duration prediction unit 13 outputs the predicted execution idle duration M4 to the verification target selection unit 15 (step S303 ). After the process of step S303 , the execution idle duration prediction process ends.

[0042] Fig. 9 1 is a diagram showing an example of data of the execution idle duration in the vehicle control device 1 according to the present embodiment. The execution idle duration M4 includes information of "execution idle duration" indicating the predicted execution idle duration (e.g., "8 seconds"). "No." is a number indicating the arrangement order of the execution idle duration M4, for example, a digital number of "1".

[0043] [Processing in the calculation unit] Fig.10 1 is a flowchart showing the procedure of the processing in the calculation unit 14 of the vehicle control device 1 according to the present embodiment. When the calculation unit 14 acquires the external environment information M1 from the information acquisition unit 11, the processing described below starts.

[0044] First, the calculation unit 14 acquires the external environment information M1 from the information acquisition unit 11 (step S401 ).

[0045] Next, the operation unit 14 determines whether the automatic driving is terminated based on the external environment information M1 (step S402). Figure 4 If the external environment information M1 of the "green image of the traffic light ahead" shown in FIG. 1 determines that the automatic driving is to be continued, the step S402 is determined as "No". Figure 4If the external environment information M1 of the "red image of the traffic light ahead" shown indicates that the automatic driving is terminated, the decision in step S402 is "Yes".

[0046] In the process of step S402 , when the calculation unit 14 determines that the automatic driving is continuing (if the determination of step S402 is “NO”), the current SW is continued (step S403 ).

[0047] Next, the calculation unit 14 outputs the execution result M7 of the current SW to the verification unit 16 (step S404 ).

[0048] On the other hand, in the process of step S402, when the calculation unit 14 determines that the automatic driving is terminated (if the determination of step S402 is "yes"), the automatic driving termination information M5 (see the following description) is sent to the computer. Fig.12 ) is output to the verification object selection unit 15 (step S405).

[0049] Next, the calculation unit 14 obtains the new SW information M2 stored in the DB (see Figure 5 )(Step S406).

[0050] Next, the calculation unit 14 obtains the selected scene M6 (see the following description) from the verification object selection unit 15. Fig.13 )(Step S407).

[0051] Next, the calculation unit 14 executes the selected scene M6 using the automatic driving control software (new SW) included in the new SW information M2 (step S408 ).

[0052] Next, the calculation unit 14 outputs the execution result M7 of the selected scenario M6 in the new SW to the verification unit 16 (step S409 ).

[0053] After the process of step S404 or step S409 , the calculation unit 14 determines whether the operation of the vehicle control device 1 is stopped (step S410 ).

[0054] In the process of step S410 , when the calculation unit 14 determines that the operation of the vehicle control device 1 is not stopped (if the determination of step S410 is “NO”), the calculation unit 14 returns to the process of step S402 and repeatedly executes the processes of step S402 to step S410 .

[0055] On the other hand, when the calculation unit 14 determines in the process of step S410 that the operation of the vehicle control device 1 is stopped (if the determination of step S410 is “NO”), the process of the calculation unit 14 ends.

[0056] [Selection process of verification scene in verification target selection section] Fig.11 This is a flowchart showing the procedure of the verification scene selection process in the verification target selection unit 15 of the vehicle control device 1 according to the present embodiment. When the verification target selection unit 15 acquires the automatic driving end information M5 from the calculation unit 14, the process described below starts.

[0057] First, the verification target selection unit 15 acquires the automatic driving end information M5 from the calculation unit 14 (step S501 ).

[0058] Next, the verification object selection unit 15 determines whether the automatic driving is terminated (step S502). In this process, the verification object selection unit 15 obtains the automatic driving termination information M5, which is information data indicating the termination of the automatic driving, such as the following Fig.12 In the case of "1" shown in FIG. 1 , it is determined that the automatic driving is terminated (step S502 is determined as "yes"). In addition, when the automatic driving termination information M5 obtained by the verification object selection unit 15 is not information data indicating the termination of the automatic driving, for example, Fig.12 In the case other than the indicated "1", it is determined that the automatic driving is continuing ("No" determination in step S502).

[0059] In the process of step S502 , when the verification target selection unit 15 determines that the automatic driving is continuing (if the determination of step S502 is “NO”), it returns to the process of step S501 and repeatedly executes the processes of step S501 to step S502 .

[0060] On the other hand, in the process of step S502, when the verification object selection unit 15 determines that the automatic driving is completed (if the step S502 is determined to be "yes"), it obtains the verification scene M3 from the DB (step S503). In this process, the verification object selection unit 15 obtains, for example, the verification scene M3 to be verified that is specified in advance.

[0061] Next, the verification target selection unit 15 acquires the execution idle duration M4 predicted by the execution idle duration prediction unit 13 (step S504 ).

[0062] Next, the verification object selection unit 15 selects a verification scenario that can be executed from the obtained verification scenarios M3 as a selected scenario M6 based on the execution idle duration M4 (step S505). Fig. 9 The execution idle duration M4 of "8 seconds" shown is from Figure 7 In the verification scene M3 shown in the figure, the verification scene "No. 2" which can be executed and completed within "8 seconds" is selected as the selection scene M6 (refer to the following description). Fig.13 ).

[0063] Next, the verification target selection unit 15 outputs the selected selection scene M6 to the calculation unit 14 (step S506). After the process of step S506, the verification scene selection process ends.

[0064] Fig.12 2 is a diagram showing a data example of the automatic driving end information M5 in the vehicle control device 1 according to the present embodiment. Fig.12 As shown, the value "1" of the "autonomous driving end information" indicates that the automatic driving has ended. The present invention is not limited to this, and the value of the "autonomous driving end information" may be arbitrarily set as long as it is information data indicating that the automatic driving has ended.

[0065] Fig.13 : is a diagram showing a data example of a verification scene (selection scene M6) selected in the vehicle control device 1 according to the present embodiment. Fig.13 In, will be Fig.11 The verification object selection unit 15 selected by the verification object selection unit 15 described in step S505 Figure 7 The verification scenario of "No.2" is represented as the selection scenario M6. Fig.13 As shown, the time attribute of the selection scene M6 ("7 seconds") is shorter than the execution idle duration M4 ("8 seconds"), that is, the selection scene M6 can be executed and completed within the execution idle duration M4 ("8 seconds").

[0066] Fig.14 1 is a diagram showing a data example of the execution result M7 of the calculation unit 14 in the vehicle control device 1 according to the present embodiment. Fig.14 As shown, the execution result M7 includes information of the interface that outputs the execution result ("Interface" column), the output result of the current SW corresponding to the interface ("Current SW Output Value" column), and the output result of the new SW corresponding to the interface ("New SW Output Value" column). The "Current SW Output Value" and "New SW Output Value" corresponding to the "Interface" column represent the ratio of the output value of the interface to the maximum output value of the interface in percentage (%). For example, since the "Current SW Output Value" and "New SW Output Value" of "Steering" are both "20%", it can be seen that the steering performance has not changed. The verification unit 16 compares the "Current SW Output Value" and "New SW Output Value" of the execution result M7 to evaluate the performance of the new SW. Fig.14 The interface column also contains items for throttle and brake. Fig.14 The interface column can also include gear items (1st gear, 2nd gear, etc.).

[0067] [Evaluation process of new autonomous driving control software in the verification department] Fig.15This is a flowchart showing the procedure of the evaluation process of the new automatic driving control software in the verification unit 16 of the vehicle control device 1 according to the present embodiment. The process described below may be executed when the execution result M7 is output from the calculation unit 14 or may be executed at a predetermined cycle.

[0068] First, the verification unit 16 obtains the execution result M7 of the calculation unit 14 (step S601 ).

[0069] Next, the verification unit 16 performs a performance evaluation of the new SW based on the acquired execution result M7 (step S602). In this process, the verification unit 16 compares, for example, Fig.14 The performance of the new SW is evaluated based on the "current SW output value" and "new SW output value" of the execution result M7 shown. After the processing of step S602, the evaluation process of the new automatic driving control software ends.

[0070] [Effect] As described above, the vehicle control device 1 involved in embodiment 1 of the present invention predicts the execution idle duration (autonomous driving stop time) of the current automatic driving control software, and selects a verification scenario that can be executed and completed within the execution idle duration based on the predicted execution idle duration. That is, the vehicle control device 1 dynamically selects the verification scenario based on the execution idle duration, and executes the selected verification scenario with the new automatic driving control software for verification. Since the vehicle control device 1 involved in this embodiment dynamically selects the verification scenario, it is possible to improve the verification efficiency of the automatic driving control software.

[0071] <Implementation method 2> Next, a configuration example and an operation example of a vehicle control device according to Embodiment 2 of the present invention will be described. Fig.16 2 is a block diagram showing a configuration example of a vehicle control device 1A according to a second embodiment of the present invention. Fig.16 and Figure 2 It can be seen that the components of the vehicle control device 1A other than the idle duration prediction unit 13A are similar to Figure 2 The components shown are the same, so the description of the components that are the same as those in Embodiment 1 will be omitted.

[0072] The execution idle duration prediction unit 13A does not perform idle duration prediction based on the “cloud information” in the external environment information M1 (refer to Figure 4 ) predicts the execution idle duration M4, but based on Fig.16 The arbitrary object information M8 shown predicts the execution idle duration M4. That is, in the vehicle control device 1A, the object information M8 is acquired as an example of the external environment information.

[0073] Fig.171A is a diagram showing a data example of object information M8 in the vehicle control device 1A according to the present embodiment. The object information M8 is image information (camera sensor information) of an arbitrary object indicating that the automatic driving has ended. The object information M8 is, for example, Fig.17 As shown, it includes image information of "a yellow traffic light", image information of "railway crossing", image information of "temporary stop line and temporary stop sign", image information of "a bus stopped at a bus stop", etc.

[0074] Fig.18 This is a flowchart showing the procedure of the execution idle duration prediction process in the execution idle duration prediction unit 13A of the vehicle control device 1A according to the present embodiment. When the execution idle duration prediction unit 13A acquires the camera sensor information from the information acquisition unit 11, the process described below starts.

[0075] First, the idle duration prediction section 13A is executed to acquire camera sensor information from the information acquisition section 11 (step S701 ).

[0076] Next, the idle duration prediction unit 13A determines whether an object is detected from the acquired camera sensor information based on the object information M8 (step S702). In this process, the idle duration prediction unit 13A detects the object from the camera sensor information based on the image information of the object included in the object information M8. If the idle duration prediction unit 13A detects the object from the camera sensor information, step S702 is a "yes" determination, and if the idle duration prediction unit 13A does not detect the object from the camera sensor information, step S702 is a "no" determination.

[0077] In the process of step S702, if the idle duration prediction unit 13A does not detect an object from the camera sensor information (if step S702 is determined as "No"), the idle duration prediction unit 13A returns to the process of step S701 and repeatedly executes the processes of steps S701 to S702.

[0078] On the other hand, in the process of step S702, when the execution idle duration prediction unit 13A detects an object from the camera sensor information (if step S702 is determined to be "yes"), the execution idle duration prediction unit 13A predicts the start timing of the execution idle duration M4 based on the information of the detected object (step S703). In this process, the execution idle duration prediction unit 13A predicts the start timing of the execution idle duration M4, for example, based on the information of the detected object. Fig.17The timing of temporary parking of the vehicle is predicted based on the image information of the objects such as the "yellow traffic light", "railway crossing", "temporary parking line / temporary parking sign", and "bus stopping at a bus stop" shown in the figure, thereby predicting the start timing of the execution idle duration M4. After the processing of step S703, the execution idle duration prediction processing of the execution idle duration prediction unit 13A ends.

[0079] The verification object selection unit 15 dynamically selects an executable verification scenario from the verification scenarios M3 based on the start timing of the execution idle duration M4 predicted by the execution idle duration prediction unit 13A.

[0080] [Effect] As described above, in the vehicle control device 1A according to the present embodiment, the execution idle duration prediction unit 13A detects an object from the camera sensor information based on the image information of any object indicating the end of the automatic driving, i.e., the object information M8, and predicts the start timing of the execution idle duration M4. In addition, the verification object selection unit 15 dynamically selects an executable verification scenario based on the predicted start timing of the execution idle duration M4. Therefore, the vehicle control device 1A according to the present embodiment can obtain the same effect as the vehicle control device 1 according to the first embodiment.

[0081] <Implementation method 3> Next, a configuration example and an operation example of a vehicle control device according to Embodiment 3 of the present invention will be described. Fig.19 is a diagram for explaining the connection relationship of the vehicle control device involved in this embodiment in the vehicle. Fig.19 and Figure 1 It can be seen that in this embodiment, the vehicle control device 1 obtains information indicating the end of the automatic driving from the in-vehicle user interface 7 (for example, the dashboard in the vehicle) via the gateway 2. The destination for obtaining various information of the vehicle control device 1 other than the in-vehicle user interface 7 is different from Figure 1 The destinations for obtaining the various information described in (the camera control device 3, the LiDAR control device 4, the sonar control device 5, and the server 6) are the same, so repeated description is omitted.

[0082] In the vehicle control device 1 according to the present embodiment, each component other than the idle duration prediction unit 13 is executed in conjunction with Figure 2 The components shown are the same, so repeated description is omitted. In the vehicle control device 1 according to the present embodiment, the idle duration prediction unit 13 is not executed based on the "cloud information" in the external environment information M1 (refer to Figure 4 ) to predict the execution idle duration M4, but based on Fig.19The in-vehicle user interface (in-vehicle user interface 7 ) shown acquires information indicating the end of the automatic driving to predict the execution idle duration M4 .

[0083] Fig. 20 1 is a diagram showing an example of data of information acquired from the in-vehicle user interface 7 of the vehicle control device 1 according to the present embodiment. The information acquired from the in-vehicle user interface 7 is information generated by the driver's operation of the in-vehicle user interface 7 and indicates the end of the automatic driving, for example, Fig. 20 The “information of switching from the automatic driving mode to the automatic parking mode” shown in the figure, etc. For example, when the driver presses the parking button displayed on the in-vehicle user interface 7, the vehicle switches from the automatic driving mode to the automatic parking mode, and the vehicle is controlled to automatically park in the parking space.

[0084] Fig.21 This is a flowchart showing the procedure of the execution idle duration prediction process in the execution idle duration prediction unit 13 of the vehicle control device 1 according to the present embodiment. When the execution idle duration prediction unit 13 acquires information from the in-vehicle user interface 7, the process described below starts.

[0085] First, the idle duration prediction unit 13 acquires information from the in-vehicle user interface 7 (step S801 ).

[0086] Next, the execution idle duration prediction unit 13 predicts the execution idle duration M4 based on the information obtained from the in-vehicle user interface 7 (step S802). Fig. 20 The in-vehicle user interface 7 acquires information on switching from the automatic driving mode to the automatic parking mode, and predicts the execution idle duration M4 of the current SW in the automatic parking. After the processing of step S802, the execution idle duration prediction processing of the execution idle duration prediction unit 13 ends.

[0087] [Effect] As described above, in the vehicle control device 1 according to the third embodiment of the present invention, the execution idle duration prediction unit 13 predicts the execution idle duration M4 based on the information indicating the end of the automatic driving acquired from the in-vehicle user interface 7. In addition, the verification object selection unit 15 dynamically selects an executable verification scenario based on the predicted execution idle duration M4. Therefore, the vehicle control device 1 according to the third embodiment of the present invention can obtain the same effects as the vehicle control device 1 according to the first embodiment.

[0088] Assume that even if the driver does not perform an explicit operation such as pressing the parking button, the vehicle automatically switches from the automatic driving mode to the automatic parking mode when the vehicle reaches the vicinity of the destination and parks in the parking space. In this case, the execution idle duration prediction unit 13 may also predict the execution idle duration M4 when detecting that the vehicle switches from the automatic driving mode to the automatic parking mode.

[0089] <Implementation method 4> Next, an operation example of the vehicle control device according to the fourth embodiment of the present invention will be described. In the vehicle control device 1 according to the present embodiment, the verification target selection unit (the verification target selection unit 15) selects the verification scene in the verification scene selection process ( Fig.11 In step S505), if a verification scenario that can be executed within the idle duration M4 cannot be selected, the verification scenario M3 is divided into sizes that can be executed within the idle duration M4. For the same structure and various processing orders as in Example 1, repeated description is omitted.

[0090] Fig. 22 1 is a flowchart showing the steps of the verification target scene segmentation process in the verification target selection unit 15 of the vehicle control device 1 according to the present embodiment. Fig.11 The process described below is executed in step S505 of the verification scene selection process shown in the figure.

[0091] exist Fig.11 After the process of step S504 of the verification scenario selection process shown, the verification target selection unit 15 determines whether there is a verification scenario that can be executed and completed within the execution idle duration M4 (step S50501).

[0092] In the process of step S50501, when it is determined that there is no verification scenario that can be executed within the execution idle duration M4 (if the determination of step S50501 is "No"), the verification object selection unit 15 divides the verification scenario M3 into sizes that can be executed within the execution idle duration M4 (step S50502). After the process of step S50502, the verification object selection unit 15 returns to the process of step S50501.

[0093] On the other hand, in the process of step S50501, when it is determined that there is a verification scenario that can be executed and completed within the execution idle duration M4 (if the determination of step S50501 is "yes"), the verification object selection unit 15 selects the verification scenario that can be executed and completed (step S50503). After the process of step S50503, the verification object selection unit 15 executes Fig.11 The process of step S506.

[0094] The calculation unit 14 executes the divided verification scenarios in the new SW, combines the execution results of the divided verification scenarios, and outputs the combined results as the execution results of the new SW.

[0095] [Effect] As described above, in the vehicle control device 1 according to the fourth embodiment of the present invention, when the verification object selection unit 15 cannot select a verification scene that can be executed within the execution idle duration M4, the verification scene M3 is divided into sizes that can be executed within the execution idle duration M4 for selection. Therefore, the vehicle control device 1 according to the fourth embodiment of the present invention has the same effect as the vehicle control device 1 according to the first embodiment, and can further improve the verification efficiency of the automatic driving control software.

[0096] <Implementation method 5> Next, an operation example of the vehicle control device according to the fifth embodiment of the present invention will be described. In the vehicle control device 1 according to the present embodiment, the verification target selection unit (the verification target selection unit 15) selects the verification scene in the verification scene selection process ( Fig.11 In step S505), when there are multiple verification scenarios that can be executed within the execution idle duration M4, the verification scenarios are prioritized based on the preset verification scenario priorities (see the following description). Fig.23 ) to select the verification scenario. For the same structure and various processing steps as those in Implementation 1, repeated descriptions are omitted.

[0097] Fig.23 1 is a diagram showing an example of data of verification scenarios to which priorities are assigned in the vehicle control device 1 according to the present embodiment. Fig.23 As shown, in the verification scenario M10, for example, the verification scenarios "No. 1" to "No. 4" are assigned "1" to "4" as "priorities" respectively. In this embodiment, Fig.23 The "priority" "1" is the highest priority, and "1" to "4" are arranged in order from high priority to low priority. The setting method of "priority" is not limited to this, and any setting method can be applied as long as it is information data that can distinguish the priority of the verification scene.

[0098] Fig.24 1 is a flowchart showing the steps of the verification scene selection process in the verification target selection unit 15 of the vehicle control device 1 according to the present embodiment. Fig.11 The process described below is executed in step S505 of the verification scene selection process shown in the figure.

[0099] exist Fig.11After the process of step S504 of the verification scenario selection process shown, the verification target selection unit 15 determines whether there are a plurality of verification scenarios that can be executed and completed within the execution idle duration M4 (step S50504 ).

[0100] In the process of step S50504, if there are multiple verification scenarios that can be executed and completed within the execution idle duration M4 (if step S50504 is determined to be "yes"), the verification object selection unit 15 selects a verification scenario based on the priority of the multiple verification scenarios (step S50505). In this process, the verification object selection unit 15 selects a verification scenario based on the priority of the multiple verification scenarios, for example, based on the number of verification scenarios that can be executed and completed within "8 seconds" (execution idle duration M4). Fig.23 The verification scenes "No. 2" and "No. 4" shown have priorities "2" and "4" respectively, and the verification scene "No. 2" having the higher priority is selected.

[0101] On the other hand, in the processing of step S50504, when the verification object selection unit 15 determines that there are multiple verification scenarios that can be executed within the execution idle duration M4 (if step S50504 is determined as "yes"), it selects a verification scenario that can be executed (step S50506).

[0102] After the processing of step S5050505 or step S5050506, the verification object selection unit 15 executes Fig.11 The process of step S506.

[0103] [Effect] As described above, in the vehicle control device 1 according to the fifth embodiment of the present invention, when there are multiple verification scenarios that can be executed within the execution idle duration M4, the verification object selection unit 15 selects the verification scenario based on the priority of the multiple verification scenarios. Therefore, the vehicle control device 1 according to the fifth embodiment of the present invention has the same effect as the vehicle control device 1 according to the first embodiment, and can further improve the verification efficiency of the automatic driving control software.

[0104] <Implementation method 6> Next, an operation example of the vehicle control device according to the sixth embodiment of the present invention will be described. In the vehicle control device 1 according to the present embodiment, the idle duration prediction unit 13 is executed without Figure 4 The "cloud information" shown predicts the execution idle duration M4, but according to Fig.25 The arbitrary external information obtained by the cloud communication shown in the figure predicts the execution idle duration M4. For the same structure and various processing steps as those in the first embodiment, repeated description is omitted.

[0105] Fig.25 1 is a diagram showing an example of external information acquired by the vehicle control device 1 according to the present embodiment. The arbitrary external information acquired via cloud communication includes, for example, Fig.25 The execution idle duration prediction unit 13 predicts the execution idle duration of the vehicle during temporary parking due to congestion, for example, based on the "congestion occurrence information". In addition, the execution idle duration prediction unit 13 predicts the execution idle duration of the vehicle during the stop at the intersection, for example, based on the duration of the red light signal at the intersection in front of the vehicle and the "signal light switching timing". Fig.25 The information such as "congestion occurrence information" and "signal light switching timing" obtained by the cloud communication shown can also be used as Figure 4 The “cloud information” shown is used for processing.

[0106] [Effect] As described above, in the vehicle control device 1 according to the sixth embodiment of the present invention, the execution idle duration prediction unit 13 predicts the execution idle duration M4 based on any external information obtained via cloud communication. Since the execution idle duration prediction unit 13 predicts the execution idle duration M4 based on various external information, the vehicle control device 1 according to the fourth embodiment of the present invention obtains the same effect as the vehicle control device 1 according to the first embodiment, and can predict the execution idle duration M4 with high accuracy.

[0107] <Implementation method 7> Next, an operation example of the vehicle control device according to the seventh embodiment of the present invention will be described. The vehicle control device 1 according to the present embodiment is configured to be able to transmit and receive various data with other control devices (controller units) not shown connected to the vehicle control device 1 (this device). In addition, in the vehicle control device 1, the execution idle duration prediction unit (execution idle duration prediction unit 13) does not perform idle duration prediction based on the “cloud information” (refer to “cloud information”) in the external environment information M1. Figure 4 ) is not used to predict the execution idle duration M4, but the execution idle duration M4 is predicted based on the information of the internal state of other control devices obtained via the gateway 2. For the same structure and various processing steps as those in the first embodiment, repeated description is omitted.

[0108] Fig.26 1 is a diagram showing an example of information on the internal state of other control devices acquired by the vehicle control device 1 according to the present embodiment. The information on the internal state of other control devices acquired via the gateway 2 includes, for example, Fig.26Information showing the state of “switching from automatic driving mode to automatic parking mode”, etc. is shown.

[0109] [Effect] As described above, in the vehicle control device 1 according to the seventh embodiment of the present invention, the execution idle duration prediction unit 13 predicts the execution idle duration M4 based on the information of the internal state of other control devices. For example, in the case where the external environment information M1 cannot be acquired due to a sensor failure or a cloud communication failure, the execution idle duration prediction unit 13 can predict the execution idle duration M4 based on the information of the internal state of other control devices, so that the vehicle control device 1 according to the seventh embodiment of the present invention can obtain the same effect as the vehicle control device 1 according to the first embodiment, and can also verify the new SW in the case of a sensor failure or a cloud communication failure.

[0110] [Hardware Configuration Example of Vehicle Control Device] Fig. 27 1 is a block diagram showing an example of the hardware structure of the vehicle control device involved in each of the above-mentioned embodiments. The functions of the vehicle control device are implemented by an information processing device such as a microcomputer. Fig. 27 As shown, the vehicle control device includes a CPU (Central Processing Unit) 100a, a ROM (Read Only Memory) 100b, a RAM (Random Access Memory) 100c, a storage device 100d, and an input / output interface 100e. A bus 100f is a signal path that electrically connects various components and performs input / output of signals between the components.

[0111] The CPU 100a controls the operation of each unit in the vehicle control device. For example, the CPU 100a controls the acquisition of external environment information in the information acquisition unit 11, the storage of the verification scene in the verification scene storage unit 12, etc. In addition, the CPU 100a controls the prediction of the execution idle duration in the execution idle duration prediction unit 13, the processing in the calculation unit 14, the selection of the verification scene in the verification scene selection unit 15, and the verification of the new automatic driving control software in the verification unit 16.

[0112] The ROM 100 b is constituted by a storage medium such as a nonvolatile memory, for example, and stores programs and data executed and referred to by the CPU 100 a .

[0113] The RAM 100 c is constituted by a storage medium such as a volatile memory, for example, and temporarily stores information (data) necessary for each process performed by the CPU 100 a .

[0114] The storage device 100d is composed of a computer-readable non-disposable recording medium that stores the program executed by the CPU 100a, for example, a storage device such as a HDD (Hard Disk Drive). The storage device 100d stores programs used by the CPU 100a to control various parts, OS (Operating System), programs and data of the controller, etc. Part of the program and data stored in the storage device 100d can also be stored in the ROM 100b. In addition, the storage device 100d is not limited to the HDD, and can also be a recording medium such as an SSD (Solid State Drive), a CD (Compact Disc)-ROM, a DVD (Digital Versatile Disc)-ROM, etc.

[0115] The input / output interface 100e transmits and receives signals to and from the outside under the control of the CPU 100a.

[0116] The present invention is not limited to the above-described embodiments, and various other application examples and modified examples are of course possible without departing from the gist of the present invention described in the claims. For example, the above-mentioned embodiments have described the structure of the vehicle control device in detail and specifically in order to explain the present invention in an easy-to-understand manner, but are not necessarily limited to having all the structures described. In addition, a part of the structure of the embodiment described here can be replaced with the structure of other embodiments, and the structure of other embodiments can also be added to the structure of a certain embodiment. In addition, with respect to a part of the structure of each embodiment, other structures can also be added, deleted, or replaced. In addition, although control lines and information lines necessary for explanation are shown, this does not limit the display to all control lines and information lines necessary for the product. In fact, it can be considered that almost all structures are connected to each other. Description of symbols

[0117] 1, 1A... vehicle control device, 11... information acquisition unit, 12... verification scenario storage unit, 13, 13A... execution idle duration prediction unit, 14... calculation unit, 15... verification object selection unit, 16... verification unit.

Claims

1. A vehicle control device, characterized in that: include: an execution idle duration prediction unit, the execution idle duration prediction unit predicting the execution idle duration of the current automatic driving control software program based on external environment information of the vehicle; a verification object selecting unit configured to select, from among verification scenarios for verifying the performance of a new autonomous driving control software program, verification scenarios that can be executed to completion within the execution idle duration as verification objects; as well as A computing unit is configured to execute the verification object using a new automatic driving control software program during the execution idle duration.

2. The vehicle control device according to claim 1, characterized in that: It includes a verification unit that verifies a new autonomous driving control software program based on the calculation results of the current autonomous driving control software program calculated by the calculation unit at a time outside the execution idle duration and the calculation results of the new autonomous driving control software program calculated by the calculation unit during the execution idle duration.

3. The vehicle control device according to claim 2, characterized in that: The external environment information includes sensor information acquired from a sensor that detects an external environment of the vehicle.

4. The vehicle control device according to claim 3, characterized in that: The sensor information includes an image of an intersection in front of the vehicle and an image of a traffic light in front of the vehicle.

5. The vehicle control device according to claim 3, characterized in that: The external environment information includes cloud information obtained through cloud communication.

6. The vehicle control device according to claim 5, characterized in that: The cloud information includes the red duration of the traffic light ahead, congestion occurrence information, and traffic light switching timing.

7. The vehicle control device according to claim 3, characterized in that: The external environment information includes image information of an object indicating that the autonomous driving has ended.

8. The vehicle control device according to claim 7, characterized in that: The image information of the object includes image information of a yellow traffic light, image information of a railway crossing, image information of a temporary parking line, image information of a temporary parking sign, and image information of a bus parked at a bus stop.

9. The vehicle control device according to claim 2, characterized in that: The execution idle duration prediction unit predicts the execution idle duration based on information indicating the end of the automatic driving acquired from an in-vehicle user interface of the vehicle.

10. The vehicle control device according to claim 9, characterized in that: The information indicating the end of the automatic driving obtained from the in-vehicle user interface of the vehicle includes information that the vehicle is switched from the automatic driving mode to the automatic parking mode.

11. The vehicle control device according to claim 2, characterized in that: In the case that there is no verification scenario that can be executed to completion within the execution idle duration, The verification object selection unit divides the verification scenario into sizes that can be executed within the execution idle duration and selects the verification object.

12. The vehicle control device according to claim 2, characterized in that: In the case where there are multiple verification scenarios that can be executed and completed within the execution idle duration, The verification object selection unit selects the verification object according to a preset priority of the verification scenario.

13. The vehicle control device according to claim 2, characterized in that: The execution idle duration prediction unit predicts the execution idle duration based on information on internal states of other control devices of the vehicle.

14. The vehicle control device according to claim 13, characterized in that: The information on the internal state of the other control device includes information indicating a state in which the vehicle is switched from the automatic driving mode to the automatic parking mode.

Images