Task division system, in-vehicle task division system, and task division method

Abstract

To provide a task division system capable of dividing a task so that safety is not lost even if at least one arithmetic logical unit fails or becomes abnormal when a plurality of tasks are being assigned to a plurality of arithmetic logical units, an in-vehicle task division system, and a task division method.SOLUTION: A task division system comprises a task information holding unit which holds information of a plurality of tasks executed by a plurality of arithmetic logical units, an important-task extraction unit which extracts important tasks from among the plurality of tasks held in the task information holding unit, and a task division unit. The task division unit checks whether there exists another important task having a complementary relationship with the important task extracted by the important task extraction unit, and assigns attribute information indicating the complementary relationship to important tasks which complement each other.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a task division system for dividing tasks executed by an electronic control unit, an in-vehicle task division system, and a task division method. [Background technology]

[0002] Vehicles are equipped with many electronic control devices, such as electronic control devices that are connected to external recognition sensors to recognize vehicles and pedestrians, electronic control devices that integrate recognition results obtained from multiple electronic control devices and perform calculations for autonomous driving and driving assistance, and electronic control devices that control engines and actuators. In recent years, in order to reduce the number of electronic control devices installed, functions have been consolidated into a single electronic control device. However, electronic control devices that have only a single calculation component have a problem in that the calculation component becomes expensive in order to cope with the increasing processing load.

[0003] A plurality of electronic control units are used to distribute functions (tasks). Examples of such conventional techniques include those described in Patent Documents 1 and 2.

[0004] Patent Document 1 describes a core allocation device that allocates tasks to be executed by multiple types of cores included in a processor. Patent Document 1 also describes a technology that includes a feature acquisition unit that acquires feature information indicating the features of a task from design information that defines the task, and an allocation unit that allocates tasks to cores based on the feature information and the configuration of the cores in the processor.

[0005] Patent Document 2 describes a technique for maintaining and managing databases in a client-server system having multiple servers, each having a database storing different types of information necessary for executing business processes, and a business processing client that executes business processes by accessing each database stored in the servers. The system also includes a database monitoring device that extracts information necessary for continuing to execute business processes from the information stored in the databases stored in each server, and generates a standalone degenerate operation database for the business processing client based on the extracted information. The technology also describes a technique in which, when the business processing client is unable to access at least one server, the business processing client continues to execute business processes by switching its access destination to the standalone degenerate operation database. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Publication No. 2021-039666 [Patent Document 2] Japanese Patent Application Laid-Open No. 2000-181770 Summary of the Invention [Problem to be solved by the invention]

[0007] However, the technology described in Patent Document 1 does not take into consideration safety in the event that one of the multiple calculation units fails. Furthermore, Patent Document 2 discloses a database maintenance management system that generates a database for degenerate operation in order to continue processing execution even when at least one server goes down.

[0008] However, the technology described in Patent Document 2 requires that a database for generating a database for degenerate operation be prepared on a separate server, making it difficult to apply the technology described in Patent Document 2 to an in-vehicle electronic control unit that has strict resource constraints.

[0009] In consideration of the above problems, an object of the present invention is to provide a task division system, an in-vehicle task division system, and a task division method that can divide tasks so as not to lose safety when allocating multiple tasks to multiple processing units, even if at least one processing unit fails or malfunctions. [Means for solving the problem]

[0010] To solve the above problems and achieve the object of the present invention, a task division system includes a task information storage unit that stores information on multiple tasks executed by multiple processing units, an important task extraction unit that extracts important tasks from the multiple tasks stored in the task information storage unit, and a task division unit. The task division unit checks whether there are other important tasks that are complementary to the important tasks extracted by the important task extraction unit, and assigns attribute information indicating the complementary relationship to the important tasks that complement each other. The in-vehicle task division system includes a task information storage unit that stores information on a plurality of tasks executed by a plurality of processing units provided in the vehicle, an important task extraction unit that extracts important tasks from the plurality of tasks stored in the task information storage unit, and a task division unit. The task division unit checks whether there are other important tasks that are complementary to the important tasks extracted by the important task extraction unit, and assigns attribute information of the complementary relationship to the important tasks that complement each other.

[0011] The task division method includes the following processes (1) to (3). (1) A process for acquiring information on multiple tasks executed by multiple processing elements. (2) A process of extracting important tasks from the multiple tasks obtained. (3) A process of checking whether there are other important tasks that complement each other with respect to the extracted important tasks, and assigning attribute information of the complementary relationship to the important tasks that complement each other. [Effects of the Invention]

[0012] According to the task division system, in-vehicle task division system, and task division method configured as described above, when multiple tasks are assigned to multiple processing units, the tasks can be divided in such a way that safety is not compromised even if at least one processing unit fails or experiences an abnormality. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a block diagram showing an in-vehicle task division system according to a first embodiment; [Figure 2] 4 is a flowchart showing a task division process in the in-vehicle task division system according to the first embodiment. [Figure 3] FIG. 10 is a diagram illustrating an example of division of a recognition result integration processing task performed by an autonomous driving system. [Figure 4] FIG. 2 is a diagram showing an example of division of a recognition result integration processing task performed by an autonomous driving system using an in-vehicle task division system according to a first embodiment. [Figure 5] 10 is a flowchart showing a task division process in the in-vehicle task division system according to the second embodiment. [Figure 6] FIG. 10 is a diagram showing a flow of a specific example of importance extraction and task allocation using priorities in an in-vehicle task division system according to a second embodiment. [Figure 7] FIG. 10 is a block diagram showing an in-vehicle task division system and a vehicle system according to a third embodiment. [Figure 8] 10 is a flowchart showing a task division process in an in-vehicle task division system and a vehicle system according to a third embodiment. [Figure 9] FIG. 10 is a block diagram showing the flow of processing within a vehicle in an in-vehicle task division system and a vehicle system according to a third embodiment. [Figure 10] FIG. 10 is a block diagram showing an in-vehicle task division system according to a fourth embodiment. [Figure 11]10 is a flowchart showing a task division process in an in-vehicle task division system according to a fourth embodiment. [Figure 12] FIG. 10 is a block diagram showing the flow of processing within a vehicle in an in-vehicle task division system and a vehicle system according to a fourth embodiment. [Figure 13] FIG. 10 is a block diagram showing an in-vehicle task division system according to a fifth embodiment. [Figure 14] 13 is a flowchart showing a task division process in an in-vehicle task division system according to a fifth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, embodiments of a task division system, an in-vehicle task division system, and a task division method will be described with reference to Figures 1 to 14. Note that common members in each figure are given the same reference numerals.

[0015] 1. First embodiment 1-1. Configuration of the in-vehicle task division system (task division system) First, the configuration of an in-vehicle task division system according to a first embodiment (hereinafter referred to as "this example") will be described with reference to FIGS. 1 to 4. FIG. FIG. 1 is a block diagram showing an in-vehicle task division system.

[0016] 1, the in-vehicle task division system 100 includes a task division device 101 and a processing unit allocation device 102. The in-vehicle task division system 100 is also connected to a vehicle system (ECU) 103 mounted on the vehicle so as to be able to transmit information. The vehicle system 103 includes a plurality of in-vehicle processing units (hereinafter simply referred to as processing units) 121, 122, and 123.

[0017] In this example, the vehicle system 103 is provided with the calculation units 121, 122, and 123, which are multiple on-board electronic control units (autonomous driving electronic control units), but the present invention is not limited to this. The vehicle system 103 may be, for example, multiple electronic control units, multiple chips in one on-board electronic control unit (e.g., System on a Chip, hereinafter referred to as SoC), or calculation units such as multiple CPU cores or AI accelerators in a SoC in an on-board electronic control unit.

[0018] The task division device 101 also includes a task information storage unit 104, an important task extraction unit 105, and a task division unit .

[0019] The task information storage unit 104 stores all task information and task attribute information for which the multiple calculation units 121, 122, and 123 of the vehicle system 103 are responsible for calculations. The task attribute information may, for example, indicate which phase the task is in, from external world recognition to vehicle control, if the task is related to autonomous driving, or whether the task is forward recognition or rearward recognition, if the task is related to the vehicle's external world recognition function. The task information storage unit 104 outputs the task information to the important task extraction unit 105.

[0020] The important task extraction unit 105 acquires multiple pieces of task information and their attribute information stored in the task information storage unit 104. Then, the important task extraction unit 105 extracts important tasks that could cause a serious accident if they fail from the multiple pieces of task information and the attribute information. In addition, the important task extraction unit 105 outputs the extracted important task information to the task division unit 106.

[0021] The task division unit 106 checks whether there is another important task that is complementary to the important task extracted by the important task extraction unit 105. Then, for an important task that is determined to have another important task that is complementary to it (an important task with complementary relationships), the task division unit 106 assigns attribute information of the complementary relationship to the important task that complements it. Here, the task division unit 106 assigns the attribute information of the complementary relationship so that the processing unit allocation device 102, which will be described later, can allocate the important tasks that complement each other to different processing units.

[0022] Furthermore, the task division unit 106 divides an important task that is determined to have no other important task in a complementary relationship (a non-complementary important task) into two or more tasks that complement each other and assigns attribute information of the complementary relationship. An example of a non-complementary important task is a task such as white line recognition in an automated driving system. The task division unit 106 then divides the white line recognition task into right white line recognition and left white line recognition if the automated driving system can control the vehicle along the white line if it can recognize a white line on either the right or left side of the vehicle.

[0023] The processing unit allocation device 102 refers to the attribute information of the complementary relationship assigned by the task division device 101 for the tasks to be handled by the processing units 121, 122, and 123 in the vehicle system 103. Then, the processing unit allocation device 102 allocates tasks such that tasks that are complementary to each other are not executed by the same processing unit 121, 122, and 123. Then, the processing unit allocation device 102 outputs the allocated tasks to the vehicle system 103.

[0024] 1-2. Task division processing Next, the task division process in the in-vehicle task division system 100 having the above-described configuration will be described with reference to FIG. FIG. 2 is a flowchart showing the task division process.

[0025] 2, the in-vehicle task division system 100 acquires all tasks executed by the vehicle system 103 and stores them in the task information storage unit 104 (step S11). At this time, the task information storage unit 104 assigns attribute information to the tasks for extracting important tasks.

[0026] For example, the process from external recognition to vehicle control is divided into four phases: recognition, cognition (integration), judgment, and control, and the phase in which a task is included is assigned as attribute information for the task. Furthermore, for tasks that use external recognition sensors, information on the direction of the external recognition sensor being used and what is being recognized is assigned as attribute information. Furthermore, for tasks that involve actuators, information on which actuators are being used, such as brake or suspension, is assigned as attribute information.

[0027] Next, the task information holding unit 104 outputs the stored task information and attribute information to the important task extraction unit 105. Then, the important task extraction unit 105 extracts important tasks by referring to the attribute information of each task (step S12). Here, for example, in an autonomous driving system, a serious accident may be avoided by recognizing an object that poses a risk of collision and stopping or avoiding it. In other words, a serious accident may be avoided without integrating recognition results from other sensors or past recognition results, as performed in the recognition phase, or without determining which function to use or calculating how to generate a trajectory based on the integrated results of recognition information, as performed in the judgment phase.

[0028] Therefore, tasks in the recognition phase and control phase are extracted as more important than tasks in the recognition phase and decision phase. Also, even if the tasks are in the same recognition phase, if the vehicle can avoid a rear-end collision with a vehicle ahead or a collision with a pedestrian crossing a straight road as long as it can recognize what is ahead, the recognition function using a front sensor is extracted as more important than recognition using a side or rear sensor.

[0029] In this way, the important task extraction unit 105 extracts pedestrian recognition using the front camera, white line recognition using the front camera, vehicle recognition using the front camera, pedestrian recognition using the front radar, vehicle recognition using the front radar, vehicle deceleration control, and vehicle steering control as important tasks.

[0030] Next, the important task extraction unit 105 outputs the extracted important tasks to the task division unit 106. Then, the task division unit 106 determines whether there are any tasks that are complementary to each other by referring to the attribute information of the extracted important tasks (step S13). For example, pedestrian recognition by a front camera and pedestrian recognition by a front radar, vehicle recognition by a front camera and vehicle recognition by a front radar, and vehicle deceleration control and vehicle steering control are determined to be tasks that are complementary to each other (important tasks with complementation).

[0031] If it is determined in the process of step S13 that a task with a complementary relationship exists (YES in step S13), the task division unit 106 assigns attribute information of the complementary relationship to both the important complementary task and the task with the complementary relationship (step S14). For example, the information "is in a complementary relationship with vehicle recognition by front radar" is assigned to vehicle recognition by the front camera, and the information "is in a complementary relationship with vehicle recognition by front camera" is assigned to vehicle recognition by the front radar. Note that tasks may be expressed in other ways, such as by IDs.

[0032] Furthermore, if it is determined in the process of step S13 that there is no task having a complementary relationship (No in step S13), the task dividing unit 106 divides the non-complementary important task into a plurality of tasks that have a mutually complementary relationship (step S15). In the process of step S15, the task dividing unit 106 divides the non-complementary important task with a certain overlapping area so that each of the non-complementary important tasks can be computed by different computing units 121, 122, and 123 in a complementary manner.

[0033] Next, the task division unit 106 determines whether all important tasks have attribute information of a complementary relationship (step S16). If it is determined in the process of step S16 that all important tasks have attribute information (Yes in step S16), the task division process ends.

[0034] Furthermore, if it is determined that there is an important task that does not have attribute information of a complementary relationship (No in step S16), the task division unit 106 determines whether the determination in step S13 has been performed for all important tasks (step S17). If it is determined in the processing of step S17 that there is an important task that has not been determined in step S13, the task division unit 106 returns to the processing of step S13.

[0035] Furthermore, if it is determined that the determination in step S13 has been performed for all important tasks (Yes determination in step S16), there is an important task that cannot be divided into multiple tasks in the process of step S15. In this case, the task division unit 106 assigns attribute information indicating that the non-complementary important task cannot be divided (step S18). This ends the task division process.

[0036] The important tasks divided by the above-described process are output to the respective processing units 121 , 122 , and 123 of the vehicle system 103 by the processing unit allocation device 102 .

[0037] In this way, the important task extracted by the important task extraction unit 105 is guaranteed to always be executed simultaneously and in parallel with other tasks that are complementary to each other by the task division unit 106. This makes it possible to perform degenerate operation when an abnormality occurs in one of the calculation units without adding a new calculation unit to the vehicle. For example, even if an abnormality occurs in one of the multiple calculation units 121, 122, and 123, the camera or radar can recognize the vehicle ahead and the lanes to the right and left of the vehicle. As a result, degenerate operation, which at least performs emergency braking or emergency steering to avoid a collision when there is a risk of collision, becomes possible without adding a new on-board electronic control unit.

[0038] 1-3. Example of dividing the recognition result integration processing task Next, an example of dividing the recognition result integration processing task performed by the automatic driving system will be described with reference to FIGS. 3 and 4. FIG. Fig. 3 is a diagram showing an example of division of a recognition result integration processing task. Fig. 4 is a diagram showing an example of division of a recognition result integration processing task performed by an autonomous driving system using the in-vehicle task division system of this example.

[0039] As shown in Fig. 3, vehicle M1 is equipped with multiple calculation units 121, 122, 123, and 124 for recognizing objects in all directions around vehicle M1. If an important task can be spatially divided and parallelized, task division unit 106 divides the task into multiple tasks that have overlapping areas and are complementary to each other. For example, first calculation unit 121 is responsible for a right front area F1, and second calculation unit 122 is responsible for a right rear area F2. Third calculation unit 123 is responsible for a left front area F3, and fourth calculation unit 124 is responsible for a left rear area F4.

[0040] 4, the task dividing unit 106 divides the tasks so that the integration process for the area in front of the vehicle is always performed even if either the first calculation unit 121 in charge of the right front area F1 or the calculation unit 123 in charge of the left front area F3 fails. That is, the task dividing unit 106 divides the area F10 and the integrated task so that the right front area F1 and the left front area F3 overlap in front of the vehicle.

[0041] The method can be applied not only to integration tasks but also to any spatial task, such as a task of extracting potentially dangerous areas from the integrated vehicle surroundings after integrating external world information, or a task of generating multiple vehicle trajectories taking the extracted potentially dangerous areas into consideration.

[0042] In this way, the in-vehicle task division system 100 of this example divides an important task that could not be divided into multiple important tasks that have a mutually complementary relationship. Therefore, although the total calculation load may increase, it is possible to ensure safety with a smaller increase in calculation load than by adding a completely redundant safety task.

[0043] 2. Second embodiment Next, a task division system according to a second embodiment will be described with reference to FIGS. 5 is a flowchart showing the task division process in the in-vehicle task division system, showing a specific example of the flow of importance extraction and task allocation using priorities in the in-vehicle task division system.

[0044] 5, the in-vehicle task division system 100 acquires all tasks executed by the vehicle system 103 and stores them in the task information storage unit 104 (step S31). At this time, the task information storage unit 104 assigns attribute information to the tasks for extracting important tasks.

[0045] The task information storage unit 104 also sets the priority of important tasks by referring to the attribute information of each task (step S32). For example, the task information storage unit 104 calculates a priority score for each category of the attribute information of the task, and calculates a weighted sum of the priority scores for each task. Alternatively, the important tasks are compared to each other to set the priority order.

[0046] For example, tasks related to autonomous driving in the recognition and control phases are assigned a priority score of 3 points, tasks in the judgment phase are assigned a priority score of 2 points, and tasks in the recognition phase are assigned a priority score of 1 point. Furthermore, processing is performed based on task attribute information, such as assigning a priority score of 3 points to tasks related to the front of the vehicle and a priority score of 1 point to tasks related to other directions.

[0047] Then, the important task extraction unit 105 extracts important tasks based on the priority of the tasks (step S33). For example, the important task extraction unit 105 extracts tasks for which the weighted sum of the priority scores of each task is equal to or greater than a predetermined threshold as important tasks. Alternatively, the important task extraction unit 105 extracts tasks with a priority higher than a certain level as important tasks from the tasks arranged in order of priority.

[0048] Although the priority is expressed as a score, it is not limited to priority, and other safety-related indicators such as the likelihood of an abnormality occurring, controllability in the event of an abnormality, or the fatality of an accident in the event of an abnormality may also be used, or these may be combined.

[0049] Next, the important task extraction unit 105 outputs the extracted important tasks to the task division unit 106. Then, the task division unit 106 performs the processes from step S34 to step S39. Note that the processes from step S34 to step S39 are similar to the processes from step S13 to step S18 of the in-vehicle task division process according to the first embodiment, and therefore a description thereof will be omitted.

[0050] A specific example of setting priorities, extracting importance, and allocating tasks will be described with reference to Fig. 6. In the example shown in Fig. 6, functions of the recognition, cognition, and judgment phases as autonomous driving functions are assigned to multiple computing units.

[0051] 6, the task information storage unit 104 stores information on "recognition," "cognition," and "judgment" for each task. Then, with regard to the order of task priority, the following rules are established: "recognition" > "judgment" > "cognition," "camera recognition" > "radar recognition," "highly urgent judgment (application)" > "less urgent judgment (application)," "braking-related judgment" > "steering-related judgment," "forward" > "right front" > "left front" > "right side" > "left side" > "right rear" > "left rear" > "rear."

[0052] The above rules ensure that even in the worst possible conditions, the vehicle will monitor what is ahead and apply emergency braking or emergency steering to stop if something happens.

[0053] If prioritization is performed according to the rules described above, the order of priority will be "Forward Camera Recognition" > "Forward Radar Recognition" > "AEB (Automatic Emergency Braking)" > "AES (Automatic Emergency Steering)"...

[0054] At this time, the important task extraction unit 105 extracts tasks with a priority level of 4 or lower (1st to 4th) as important tasks. Then, the task division unit 106 divides the extracted important tasks into tasks and assigns the tasks to the calculation units 121, 122, and 123.

[0055] When allocating important tasks to two processing elements, for example, the processing element allocation device 102 allocates the important tasks alternately because important tasks with similar attributes have similar priority values. This creates two task lists in which important tasks that complement each other to a certain extent are executed in parallel. The processing element allocation device 102 then refers to the attribute information and swaps the important tasks as necessary. This makes it possible to obtain two task lists in which important tasks that complement each other are executed in parallel.

[0056] In this way, the in-vehicle task allocation system according to the second embodiment uses priority, precedence, or other safety-related indicators in the important task extraction section to clarify the criteria for tasks that must not be overlooked, thereby ensuring more reliable safety and enabling efficient task allocation.

[0057] 3. Third embodiment Next, an in-vehicle task division system and a vehicle system according to a third embodiment will be described with reference to FIGS. Fig. 7 is a block diagram showing an in-vehicle task division system and a vehicle system according to a third embodiment, Fig. 8 is a flowchart showing task division processing in the in-vehicle task division system and the vehicle system, and Fig. 9 is a block diagram showing the flow of processing in the vehicle in the in-vehicle task division system and the vehicle system.

[0058] 7, the in-vehicle task division system 400 includes a task division device 401 and a processing unit allocation device 402. The task division device 401 includes a driving situation storage unit 404, a task information holding unit 405, an important task extraction unit 406, and a task division unit 407.

[0059] Information on assumed vehicle driving conditions in a use case definition or virtual simulation environment is stored in the driving condition storage unit 404. The driving environment refers to, for example, road type information such as ordinary roads, expressways, or parking lots, road structure information such as straight roads or intersections, weather information such as dense fog or rain, the presence or absence of surrounding vehicles, and road surface condition information such as puddles or unevenness.

[0060] In this embodiment, an example has been described in which the driving situation storage unit 404 is implemented in the in-vehicle task division system 400, but the present invention is not limited to this. For example, the driving situation storage unit 404 may be implemented in a device separate from the in-vehicle task division system 400, and the in-vehicle task division system 400 may receive information about the driving situation from an external device.

[0061] Next, the task division process will be described with reference to FIG. 8, the in-vehicle task division system 400 acquires all tasks executed by the vehicle system 403 and stores them in the task information storage unit 405 (step S41). Next, the driving situation storage unit 404 stores use cases and virtual simulation data describing the driving situation of the vehicle (step S42). Here, the driving situation may be information about the driving environment of the vehicle, information about the direction of travel of the vehicle, or both.

[0062] Next, the important task extraction unit 406 extracts important tasks by referring to the attribute information of each task and the driving situation information stored in the driving situation storage unit 404 (step S43). For example, when referring to a use case of overtaking a slow-moving vehicle on a straight road on a highway, in addition to recognizing a vehicle ahead, recognizing a vehicle in the overtaking lane (which is considered to be the right rear in a Japanese environment) is extracted as an important task.

[0063] Next, the task division unit 407 performs the processes of steps S44 to S49. Note that the processes of steps S44 to S49 are similar to the processes of steps S13 to S18 of the in-vehicle task division process according to the first embodiment, and therefore a description thereof will be omitted.

[0064] When the processing of step S47 or step S49 is completed, the calculation unit allocation device 402 creates a task list that allocates each task to multiple calculation units 121, 122, 123 by referring to the attribute information of each task and the calculation processing capabilities of the multiple calculation units 121, 122, 123 of the vehicle system (step S50).

[0065] Next, the processing unit allocation device 402 determines whether task lists have been created for all driving situations (step S51). If it is determined in the processing of step S51 that there is a driving situation for which a task list has not been created (No in step S51), the in-vehicle task division system 400 returns to the processing of step S43. Also, if it is determined in the processing of step S51 that task lists have been created for all driving situations (Yes in step S51), the task division processing ends.

[0066] As a more concrete example of the relationship between driving conditions and task attributes, the direction of travel of the vehicle affects the "direction" of the task. When the vehicle moves forward, the importance of tasks related to the road ahead increases, and when the vehicle changes lanes to the right, the importance of tasks related to the right side increases. Furthermore, as part of the vehicle's driving environment, the type of road affects the "target" of the recognition task, as some objects do not need to be recognized on expressways. For example, the importance of recognizing bicycles and pedestrian crossings increases on ordinary roads, but decreases on expressways.

[0067] Furthermore, in a parking lot, the importance of recognizing lanes (or the priority according to the second embodiment) decreases, but the importance of recognizing pedestrians on the sides and rear and parking frame lines increases. Next, road structures such as straight roads and intersections are affected by the "direction" of the task and the "type of actuator to be controlled." For example, at an intersection, the importance of recognizing vehicles on the left and right increases even if the vehicle is going straight.

[0068] Furthermore, in situations where it is not possible to avoid the vehicle by turning left or right (such as narrow straight roads or one-lane roads), the importance of braking to stop the vehicle increases over steering to avoid the vehicle. Weather information such as dense fog or rain is affected by the "type of sensor used for recognition" and "type of actuator to control" of the task.

[0069] Among the external recognition sensors used in autonomous driving, there are sensors that are easily affected by rain and snow, and sensors that are relatively less affected. Therefore, in rainy weather, the importance of recognition tasks using sensors that are less affected by rain increases. Also, in situations where there is strong wind, controlling the vehicle's left and right movement using steering becomes more important than when there is no wind.

[0070] Information on road surface conditions such as puddles and unevenness is affected by the "type of sensor used for recognition," "recognition target," and "type of actuator to be controlled" of the task. For example, puddles and snow cover change the reflectivity of the road surface, which may impair the accuracy of some external recognition sensors. Therefore, the importance of the recognition task for sensors that are less affected by changes in reflectivity increases. Also, on road surfaces where white lines cannot be recognized due to snow accumulation and it is necessary to recognize utility poles and road edges, the importance of the road edge recognition task increases and the importance of the white line recognition task decreases.

[0071] Furthermore, to avoid accidents due to slippage, it is necessary to appropriately select whether to stop by braking, avoid by steering, or perform emergency operation depending on the change in the friction coefficient of the road surface. Therefore, the importance of "braking decision," "emergency braking decision," "steering decision," and "emergency steering decision" increases or decreases depending on the friction coefficient of the road surface. The relationship between the driving situation and the importance of the task is an example, and other relationships may also be used. Furthermore, the priority order or priority score in the second embodiment described above may be used to determine the importance, or an index related to safety may be used.

[0072] Extracting important tasks according to the driving situation enables safer and more efficient task division. For example, in the first embodiment, the task of recognizing vehicles ahead was extracted as an important task, but vehicles can also back up and make large turns to the left and right. Therefore, when reversing or turning left or right, the task of recognizing vehicles behind and on the left and right becomes more important than the task of recognizing vehicles ahead. Furthermore, by using information about the vehicle's traveling direction, it becomes possible to extract the task of recognizing vehicles ahead when the vehicle is moving forward and the task of recognizing vehicles behind when the vehicle is moving backward as an important task.

[0073] Furthermore, the important tasks to be extracted change depending on the driving environment information. For example, the task of recognizing pedestrian crossings is not an important task on a highway, but it is an important task on an ordinary road. By using the vehicle's driving conditions as described above, it is possible to prevent the overlooking of the extraction of tasks that are important in that driving condition, and to prevent tasks that are not important in that condition from being extracted as important tasks.

[0074] FIG. 9 is a block diagram showing the flow of processing within the vehicle in the in-vehicle task division system and the vehicle system. 9, each of the calculation units 121, 122, 123, ..., 12n has a driving situation recognition unit 31, a task list calling unit 32, and a task execution unit 33. Furthermore, each of the calculation units 121, 122, 123, ..., 12n is connected to a task list storage unit 36 ​​created by a calculation unit allocation device 402. Furthermore, each of the calculation units 121, 122, 123, ..., 12n is connected to an external environment recognition sensor 90.

[0075] The driving situation recognition unit 31 then recognizes the vehicle driving situation based on information from the external environment recognition sensor 90. The driving situation recognition unit 31 outputs the recognized driving situation information to the task list calling unit 32. The task list calling unit 32 then calls a predetermined task list from the task list storage unit based on the driving situation information. The called task list is input to the task execution unit 33. The task execution unit 33 then executes tasks based on the input task list.

[0076] 4. Fourth embodiment Next, an in-vehicle task division system and a vehicle system according to a fourth embodiment will be described with reference to FIGS. FIG. 10 is a block diagram of an in-vehicle task division system according to the fourth embodiment, and FIG. 11 is a flowchart showing task division processing in the in-vehicle task division system according to the fourth embodiment.

[0077] 10, an in-vehicle task division system 500 includes a task division device 501 and a processing unit allocation device 502. The task division device 501 includes a driving situation determination unit 504, a task information storage unit 505, an important task extraction unit 506, and a task division unit 507.

[0078] The driving situation determination unit 504 is connected to an external environment recognition sensor mounted on the vehicle, and calculates the driving situation from the vehicle's positioning information, the recognition results of the external environment recognition sensor, map information, and vehicle motion information such as the steering angle and accelerator release.

[0079] 12, the task division device 501 and the processing unit allocation device 502 are provided in the first processing unit 121 in the vehicle system 503. That is, in the fourth embodiment, the first processing unit 121 acts as a manager to determine the driving situation, extract important tasks, and allocate tasks to itself (the first processing unit 121) and the other processing units 122 and 123. However, there may be multiple managers, or the managers may be implemented in a processing unit different from the processing unit to which processing is allocated.

[0080] Next, the task division process will be described with reference to FIG. 11, the in-vehicle task allocation system 500 acquires all tasks executed by the vehicle system 503 and stores them in the task information storage unit 505 (step S61). Next, the driving situation determination unit 504 calculates (recognizes) the driving situation from the recognition results of the vehicle's positioning sensors and external recognition sensors, map information, and vehicle motion information such as the steering angle and accelerator release (step S62). Here, the driving situation may be the vehicle's driving environment, information on the vehicle's traveling direction, or both.

[0081] Next, the important task extraction unit 506 extracts important tasks by referring to the attribute information of each task and the driving situation information obtained by the driving situation determination unit 504 (step S63). Then, the task division unit 507 performs the processes of steps S64 to S69. Note that the processes of steps S64 to S69 are similar to the processes of steps S13 to S18 of the in-vehicle task division process according to the first embodiment, and therefore a description thereof will be omitted.

[0082] When the process of step S67 or step S69 is completed, the processing unit allocation device 502 refers to the attribute information of each task and the processing capabilities of the multiple processing units 121, 122, 123 of the vehicle system, and allocates each task to the multiple processing units 121, 122, 123 (step S70). This completes the task division process.

[0083] In the above-described task division process, important tasks depending on the driving situation may be determined again within the vehicle system 503, or a predetermined task list may be output to the vehicle system 503.

[0084] 5. Fifth embodiment Next, an in-vehicle task division system and a vehicle system according to a fifth embodiment will be described with reference to FIGS. FIG. 13 is a block diagram of an in-vehicle task division system according to the fifth embodiment, and FIG. 14 is a flowchart showing task division processing in the in-vehicle task division system according to the fifth embodiment.

[0085] 13, an in-vehicle task division system 800 includes a task division device 801 and a processing unit allocation device 802. The task division device 801 includes a task information storage unit 804, a task classification unit 805, and a task division unit 807.

[0086] The task classification unit 805 assigns tags to each task according to its attribute information. For example, for an autonomous driving task, the tags "recognition," "cognition (integration)," "judgment," and "control" are assigned to each task. Furthermore, for a "recognition" task, tags such as "vehicle," "white line," and "pedestrian" are assigned to the recognition object. Furthermore, for a task with a directional characteristic, tags such as "forward," "right side," "left side," and "rear" are assigned.

[0087] The task division unit 806 divides a task that does not have a single tag into multiple tasks that complement each other. For example, if the task with the tags "recognition," "white line," and "forward" is only white line recognition by the front camera, it will be divided into multiple tasks that complement each other, such as right white line recognition by the front camera and left white line recognition by the front camera.

[0088] Note that tagging and task division may be performed only on important tasks that have been extracted, or may be performed on all tasks. When important tasks are extracted, it is possible to combine this with the above-described embodiment. Furthermore, although the present invention has been described in the form of tagging, tasks may be grouped (for example, a group of tasks that recognize white lines ahead, a group of tasks that recognize vehicles ahead), and the tasks of the same group may be divided so that they are not implemented in a single processing unit.

[0089] Next, the task division process will be described with reference to FIG. 14, the in-vehicle task division system 800 acquires all tasks executed by the vehicle system 803 and stores them in the task information storage unit 804 (step S81). Next, the task classification unit 805 assigns a tag to each task based on the attribute information of each task (step S82).

[0090] Next, the task division unit 806 refers to the tag assigned in the processing of step S82 and determines whether there are tasks that are complementary to each other, i.e., tasks with the same tag (step S83). If it is determined in the processing of step S83 that there are no tasks that are complementary to each other (No in step S83), the task division unit 806 divides the non-complementary important task into multiple tasks that are complementary to each other (step S84). Next, the task division unit 806 assigns a tag to the non-complementary important task indicating that it cannot be divided (step S85). Then, the processing proceeds to step S86.

[0091] Furthermore, if it is determined in the processing of step S83 that there are tasks that are complementary to each other, i.e., that there are tasks with the same tag (Yes determination in step S83), the task division unit 806 determines whether there are tasks with the same tag for all tasks except for the non-divisible tasks (step S86).

[0092] In the process of step S86, if it is determined that there is a task for which the process of step S83 has not been performed (No in step S86), the task division unit 806 returns to the process of step S83. Then, if it is determined that the process of step S83 has been performed for all tasks (Yes in step S86), the task division process ends.

[0093] The present invention is not limited to the embodiments described above and shown in the drawings, and various modifications can be made without departing from the spirit of the invention as defined in the claims.

[0094] For example, the in-vehicle task division system 500 according to the fourth embodiment described above may generate a task list by predicting the driving conditions using the vehicle's destination, route information, and map information. For example, if the route from the current location to the destination includes both general roads and expressways, a task list for driving on general roads and a task list for driving on expressways may be created and stored during route search. Then, when the driving conditions change from general roads to expressways, the task list to be loaded may be changed from that for driving on general roads to that for driving on expressways. This eliminates the need to extract important tasks and divide tasks each time the driving conditions change, thereby reducing the computational load.

[0095] In all the embodiments, the important task extraction unit may extract important tasks using the results of learning from past driving data. For example, a database that collects driving situations at the time of past traffic accidents may be prepared in advance. Then, the database may be analyzed to determine which function operations are essential to avoid traffic accidents, and this may be used to extract important tasks for similar driving situations.

[0096] Furthermore, as shown in the fourth embodiment, the driving situation is a combination of information such as the direction of travel, the driving environment, road type, and weather. Therefore, important tasks in unknown driving situations can be extracted by learning from the results of important task extraction in driving situations experienced in the past. This eliminates the need to anticipate every possible driving situation at the time of design, making it possible to reduce the number of design and verification man-hours. Furthermore, it becomes possible to ensure safety even in unknown driving situations that arise due to changes in the times and environment.

[0097] Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations. Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be implemented in hardware, in part or in whole, by designing them as integrated circuits, for example. Furthermore, the above-described configurations, functions, etc. may be implemented in software by a processor interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function can be stored in memory, a recording device such as a hard disk or SSD (Solid State Drive), or a recording medium such as an IC card, SD card, or DVD. [Explanation of symbols]

[0098] 31...driving situation recognition unit, 32...task list calling unit, 33...task execution unit, 36...task list storage unit, 90...external environment recognition sensor, 100, 400, 500, 800...in-vehicle task division system, 101, 401, 501, 801...task division device, 102...computing unit allocation device, 103...vehicle system, 104...task information storage unit, 105...important task extraction unit, 106...task division unit, 121, 122, 123...computing unit (in-vehicle computing unit), 404...driving situation storage unit, 504...driving situation judgment unit, 805...task classification unit

Claims

1. a task information storage unit that stores information on a plurality of tasks executed by a plurality of processing units; an important task extraction unit that extracts an important task from the plurality of tasks stored in the task information storage unit; a task division unit that checks whether there is another important task that is complementary to the important task extracted by the important task extraction unit, and assigns attribute information of the complementary relationship to the complementary important task; A task division system with

2. When the task division unit determines that there is no other important task that is complementary to the important task, the task division unit assigns the attribute information so that the complementary important tasks can be assigned to different processing units. The task division system of claim 1 .

3. The task division unit The important tasks that are determined not to be complemented are divided with a certain overlapping area so that they can be complementarily calculated by different calculation units. The task division system according to claim 2 .

4. The task division unit The plurality of tasks are grouped based on the type of the tasks, and the attribute information is assigned so that tasks of the same group are not assigned to a single processing unit. The task division system of claim 1 .

5. The task information storage unit Setting priorities of the plurality of tasks based on the attribute information The task division system of claim 1 .

6. The important task extraction unit Based on the priority, tasks having a priority equal to or greater than a predetermined threshold are extracted as the important tasks from among the plurality of tasks. The task division system according to claim 5 .

7. The important task extraction unit Extract the important tasks based on safety during abnormal situations. The task division system of claim 1 .

8. The system further includes a processing unit allocation device that allocates the complementary important tasks to different processing units based on the attribute information of the complementary relationship assigned by the task division unit. The task division system of claim 1 .

9. the processing unit allocation device, Allocating the important tasks alternately to the plurality of processing units. The task division system according to claim 8 .

10. a task information storage unit that stores information on a plurality of tasks executed by a plurality of processing units provided in the vehicle; an important task extraction unit that extracts an important task from the plurality of tasks stored in the task information storage unit; a task division unit that checks whether there is another important task that is complementary to the important task extracted by the important task extraction unit, and assigns attribute information of the complementary relationship to the complementary important task; An in-vehicle task division system.

11. The task division unit When it is determined that there is no other important task that is complementary to the important task, the attribute information is assigned so that the complementary important tasks can be assigned to different processing units. The in-vehicle task division system according to claim 10.

12. The task division unit The attribute information is assigned with a certain overlap area so that the important tasks that are determined not to be complemented can be complementarily calculated by different calculation units. The in-vehicle task division system according to claim 11.

13. The task division unit The plurality of tasks are grouped based on the type of the tasks, and the attribute information is assigned so that tasks of the same group are not assigned to a single processing unit. The in-vehicle task division system according to claim 10.

14. The task information storage unit Setting priorities of the plurality of tasks based on the attribute information The in-vehicle task division system according to claim 10.

15. The important task extraction unit Based on the priority, tasks having a priority equal to or greater than a predetermined threshold are extracted as the important tasks from among the plurality of tasks. The in-vehicle task division system according to claim 14.

16. a driving condition determination unit for determining a driving condition of the vehicle; The important task extraction unit Extracting the important tasks based on the driving situation. The in-vehicle task division system according to claim 10.

17. The important task extraction unit Extract the important tasks based on safety during abnormal situations. The in-vehicle task division system according to claim 10.

18. The system further includes a processing unit allocation device that allocates the complementary important tasks to different processing units based on the attribute information of the complementary relationship assigned by the task division unit. The in-vehicle task division system according to claim 10.

19. the processing unit allocation device, Allocating the important tasks alternately to the plurality of processing units.

20. The in-vehicle task division system of claim 18.

20. A process of acquiring information on a plurality of tasks executed by a plurality of processing units; A process of extracting important tasks from the acquired plurality of tasks; a process of checking whether there are other important tasks that are complementary to the extracted important tasks, and assigning attribute information of the complementary relationship to the complementary important tasks; A task division method comprising:

Images