Vehicle control device, computer program product, and vehicle control method

Abstract

The invention provides a vehicle control apparatus, a computer program product, and a vehicle control method. The invention provides a vehicle control device which controls a vehicle in a manner of ensuring safety and reducing power consumption according to the condition of the vehicle. A vehicle control device includes: a first processing unit that generates a signal to be output using only a classifier on which machine learning has been performed; a second processing unit that consumes less power than the first processing unit and that generates a signal to be output without using a classifier on which machine learning has been performed; and a first determination unit that determines a processing ratio between the portion processed by the first processing unit and the portion processed by the second processing unit on the basis of at least one of vehicle information indicating a state of the vehicle, environment information indicating an environment around the vehicle, and terrain information indicating a terrain including a current position of the vehicle.

Description

Technical Field

[0001] The present invention relates to a vehicle control device, a computer program product for vehicle control, and a vehicle control method. Background Art

[0002] In a vehicle, the processing controlled by an automatic control device is increasing. Therefore, the power consumed by the automatic control device for controlling the vehicle is also increasing.

[0003] Among automatic control devices, there are: a control device that generates a signal to be output only using a classifier that has undergone machine learning (a pure AI (Artificial Intelligence) model); a control device that has a control unit that generates a signal to be output only using a classifier that has undergone machine learning and a control unit that generates a signal to be output without using a classifier that has undergone machine learning (a hybrid model); and a control device that generates a signal to be output without using a classifier that has undergone machine learning (a rule-based model). The power consumption of the pure AI model is the highest, the power consumption of the rule-based model is the lowest, and the power consumption of the hybrid model is between the power consumption of the pure AI model and the power consumption of the rule-based model.

[0004] For example, Patent Document 1 proposes reducing the arithmetic load (power consumption) of an ECU by appropriately switching to an AI model corresponding to a driving scenario and a driving position.

[0005] Prior Art Documents

[0006] Patent Documents

[0007] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2023-094745

[0008] Reducing the power consumption of a vehicle is important. On the other hand, ensuring the safety of the vehicle is also required. The safety of a vehicle with a pure AI model is the highest, the safety of a vehicle with a rule-based model is the lowest, and the safety of a vehicle with a hybrid model is between the safety of a vehicle with a pure AI model and the safety of a vehicle with a rule-based model. The order in terms of vehicle safety is different from the order in terms of power consumption.

[0009] Therefore, it is desirable to control the vehicle in a manner that ensures safety and reduces power consumption according to the condition of the vehicle. Summary of the Invention

[0010] Therefore, an object of the present disclosure is to provide a vehicle control device that controls a vehicle in a manner that ensures safety and reduces power consumption according to the condition of the vehicle.

[0011] (1)According to one embodiment, a vehicle control device is provided. The vehicle control device includes: a first processing unit that generates a signal to be output only using a classifier that has undergone machine learning; a second processing unit that generates a signal to be output with less power consumption than the first processing unit and without using a classifier that has undergone machine learning; and a first determination unit that determines a processing ratio between a part processed by the first processing unit and a part processed by the second processing unit based on at least one of vehicle information indicating the state of the vehicle, environment information indicating the environment around the vehicle, and terrain information indicating the terrain including the current position of the vehicle.

[0012] (2)In the vehicle control device of (1), preferably, the vehicle control device includes a plurality of first processing units and a plurality of second processing units, and the vehicle control device includes: a second control unit having one first processing unit and one second processing unit; a first control unit that has greater power consumption than the second control unit and generates a signal to be output only using other first processing units; and a third control unit that has less power consumption than the second control unit and generates a signal to be output only using other second processing units. The vehicle control device includes a selection unit that selects a selection control unit for controlling the vehicle from among the first control unit, the second control unit, and the third control unit based on the processing ratio determined by the first determination unit.

[0013] (3)In the vehicle control device of (1) or (2), preferably, the vehicle information includes the degree of movement of the vehicle, and the first determination unit determines the processing ratio according to the degree of movement of the vehicle.

[0014] (4)In the vehicle control device of (3), preferably, the vehicle information includes the speed of the vehicle, and the first determination unit determines the processing ratio in such a manner that when the vehicle speed is slow, the part processed by the first processing unit is larger than the part processed by the second processing unit compared to when the vehicle speed is fast.

[0015] (5)In the vehicle control device according to any one of (1) to (4), preferably, the environment information includes the degree of complexity of the environment around the vehicle, and the first determination unit determines the processing ratio in such a manner that when the degree of complexity of the environment around the vehicle is high, the part processed by the first processing unit is larger than the part processed by the second processing unit compared to when the degree of complexity of the environment around the vehicle is low.

[0016] (6) In the vehicle control device according to any one of (1) to (5), preferably, the terrain information includes the degree of complexity of the terrain including the current position of the vehicle, and the first determination unit determines the processing ratio in such a manner that the part processed by the first processing unit is larger than the part processed by the second processing unit when the degree of complexity of the terrain including the current position of the vehicle is high, compared with when the degree of complexity of the terrain including the current position of the vehicle is low.

[0017] (7) In the vehicle control device according to (2), preferably, it has a second determination unit that determines the amount of information input to the selection control unit selected by the selection unit based on at least one of vehicle information, environment information, and terrain information.

[0018] (8) In the vehicle control device according to (7), preferably, the amount of information includes the number of sensors to which the detected information is input to the selection control unit, the resolution of the image input to the selection control unit, or the detection frequency of the sensors to which the detected information is input to the selection control unit.

[0019] (9) According to another embodiment, there is provided a computer program product for vehicle control. The computer program product for vehicle control causes a processor to execute a process including: determining a processing ratio of a part processed by a first processing unit and a part processed by a second processing unit based on at least one of vehicle information indicating the state of the vehicle, environment information indicating the environment around the vehicle, and terrain information indicating the terrain including the current position of the vehicle, where the first processing unit generates a signal to be output only using a classifier that has undergone machine learning, and the second processing unit generates a signal to be output with a power consumption smaller than that of the first processing unit and without using a classifier that has undergone machine learning.

[0020] (10) According to still another embodiment, there is provided a vehicle control method. The vehicle control method includes the following process executed by a vehicle control device: determining a processing ratio of a part processed by a first processing unit and a part processed by a second processing unit based on at least one of vehicle information indicating the state of the vehicle, environment information indicating the environment around the vehicle, and terrain information indicating the terrain including the current position of the vehicle, where the first processing unit generates a signal to be output only using a classifier that has undergone machine learning, and the second processing unit generates a signal to be output with a power consumption smaller than that of the first processing unit and without using a classifier that has undergone machine learning.

[0021] Advantages of the Invention

[0022] The vehicle control device of the present invention determines the processing ratio between the part processed by the first processing unit and the part processed by the second processing unit, and thus can control the vehicle in a manner that ensures safety and reduces power consumption according to the vehicle conditions. Description of the Drawings

[0023] Figure 1 It is a diagram for explaining the outline of the operation of the determination device of the present embodiment.

[0024] Figure 2 It is a hardware configuration diagram of a vehicle equipped with the determination device of the present embodiment.

[0025] Figure 3 It is a diagram for explaining the control device.

[0026] Figure 4 It is an example of the operation flowchart of the vehicle control process of the determination device.

[0027] Figure 5 (A) of is a diagram for explaining the determination of the processing ratio based on vehicle information, Figure 5 (B) of is a diagram for explaining the relationship between vehicle information and power consumption.

[0028] Figure 6 (A) of is a diagram for explaining the determination of the processing ratio based on environmental information, Figure 6 (B) of is a diagram for explaining the relationship between environmental information and power consumption.

[0029] Figure 7 (A) of is another diagram for explaining the determination of the processing ratio based on environmental information, Figure 7 (B) of is another diagram for explaining the relationship between environmental information and power consumption.

[0030] Figure 8 (A) of is a diagram for explaining the determination of the processing ratio based on terrain information, Figure 8 (B) of is a diagram for explaining the relationship between terrain information and power consumption.

[0031] Figure 9 It is an example of the operation flowchart of the change process of the determination device.

[0032] Figure 10 (A) of is a diagram for explaining the determination of the amount of information based on vehicle information, Figure 10 (B) of is a diagram for explaining the determination of the amount of information based on environmental information.

[0033] Figure 11 (A) of is another diagram for explaining the determination of the amount of information based on environmental information, Figure 11(B) is a diagram for explaining the determination of the amount of information based on terrain information.

[0034] Figure 12 (A) is a diagram for explaining an example of the operation of the switching unit. Figure 12 (B) is a diagram for explaining another example of the operation of the switching unit.

[0035] Explanation of Reference Numerals

[0036] 2: Communication device; 3: Sensor group; 4: Positioning information receiver; 5: Navigation device; 10: Vehicle; 11: Map information storage device; 12: Control device; 13: Determination device; 21: Communication interface; 22: Memory; 23: Processor; 231: Determination unit; 232: Selection unit; 233: Switching unit; 24: Signal line; 14: Steering device; 15: Driving device; 16: Braking device; 17: In-vehicle network. Detailed Description of the Invention

[0037] Figure 1 is a diagram for explaining the outline of the operation of the determination device 13 of the present embodiment. Hereinafter, refer to Figure 1 to explain the outline of the operation of the determination device 13 of the present embodiment.

[0038] The vehicle 10 includes a control device 12 and a determination device 13. The vehicle 10 may be an autonomous driving vehicle. The control device 12 inputs vehicle information indicating the state of the vehicle, environmental information indicating the environment around the vehicle, terrain information indicating the terrain including the current position of the vehicle, etc., and outputs a steering signal for controlling the steering device 14, a driving signal for controlling a driving device 15 such as an engine or a motor, and a braking signal for controlling the braking device 16. The control device 12 and the determination device 13 are an example of a vehicle control device.

[0039] The control device 12 includes: a first processing unit 12A that generates a signal to be output using only a classifier that has undergone machine learning; and a second processing unit 12B that generates a signal to be output without using a classifier that has undergone machine learning. The second processing unit 12B is a so-called rule-based control device that generates a signal according to a predetermined algorithm. On the other hand, the first processing unit 12A is a so-called AI-based control device that does not substantially perform rule-based control processing.

[0040] The first processing unit 12A can safely control the vehicle based on various vehicle information, complex environmental information, and terrain information. On the other hand, the operation of the first processing unit 12A consumes relatively more power.

[0041] The power consumption of the second processing unit 12B is smaller than that of the first processing unit 12A. Specifically, the average power consumption of the second processing unit 12B is smaller than that of the first processing unit 12A, but in terms of the safety when controlling the vehicle 10, the second processing unit 12B has a worse aspect than the first processing unit 12A.

[0042] In the control device 12, the processing ratio between the part processed by the first processing unit 12A and the part processed by the second processing unit 12B is variable.

[0043] The determination device 13 determines the processing ratio in the control device 12 based on at least one of vehicle information, environment information, and terrain information. For example, the speed of the vehicle 10 is an example of vehicle information.

[0044] The determination unit 13 determines the processing ratio in such a way that when the speed of the vehicle 10 is slow, the part processed by the first processing unit 12A is larger than the part processed by the second processing unit 12B compared to when the speed of the vehicle 10 is fast.

[0045] When the speed of the vehicle 10 is slow, it is considered that the vehicle 10 is traveling on a road such as a street. In the street, there are many moving objects such as other vehicles and pedestrians. In addition, in the street, control of the vehicle 10 corresponding to the state of intersections or traffic lights is performed. Therefore, when the speed of the vehicle 10 is slow, it is preferable that the control device 12 can safely control the vehicle according to the complex environment and terrain.

[0046] On the other hand, when the speed of the vehicle 10 is fast, it is considered that the vehicle 10 is traveling on an expressway for automobiles or the like. In the expressway for automobiles, there are no traffic lights and pedestrians. In addition, in the expressway for automobiles, there are many straight roads and few terrains of branching or merging. Therefore, when the speed of the vehicle 10 is fast, it is sufficient that the control device 12 can safely control the vehicle according to a relatively simple environment and terrain.

[0047] Therefore, when the speed of the vehicle 10 is slow, the determination device 13 increases the processing ratio of the part processed by the first processing unit 12A to ensure safety. On the other hand, when the speed of the vehicle 10 is fast, the determination device 13 increases the processing ratio of the part processed by the second processing unit 12B to reduce power consumption.

[0048] The determination device 13 of the present embodiment described above determines the processing ratio between the part processed by the first processing unit and the part processed by the second processing unit, and thus can control the vehicle in a manner that ensures safety and reduces power consumption according to the vehicle condition.

[0049] Next, hereinafter, with reference to Figure 2 The vehicle 10 equipped with the determination device 13 will be described.Figure 2 This is a hardware configuration diagram of a vehicle equipped with the determination device 13 of the present embodiment.

[0050] The vehicle 10 includes a communication device 2, a sensor group 3, a positioning information receiver 4, a navigation device 5, a map information storage device 11, a control device 12, a determination device 13, a steering device 14, a driving device 15, a braking device 16, and the like.

[0051] The communication device 2, the sensor group 3, the positioning information receiver 4, the navigation device 5, the map information storage device 11, the control device 12, the determination device 13, the steering device 14, the driving device 15, and the braking device 16 are communicably connected via an in-vehicle network 17 that complies with a standard such as Controller Area Network.

[0052] The communication device 2 has an interface circuit for connecting the determination device 13 and the like to a communication network (not shown) via a macrocell base station (not shown).

[0053] The sensor group 3 has a plurality of sensors for detecting vehicle information, environmental information, and terrain information. For example, the sensor group 3 has a speed sensor for detecting information indicating the speed of the vehicle 10 and a fuel sensor for detecting information indicating the remaining amount of battery or fuel as sensors for detecting vehicle information.

[0054] The sensor group 3 has a front camera, a rear camera, a LiDAR sensor, a millimeter-wave radar sensor, an ultrasonic sensor, etc. as sensors for detecting environmental information. The front camera acquires an image of the environment in a predetermined range in front of the vehicle 10. The rear camera acquires an image of the environment in a predetermined range behind the vehicle 10. The LiDAR sensor acquires reflected wave information of laser reflectors around the vehicle 10. The millimeter-wave radar sensor acquires reflected wave information of millimeter-wave reflectors around the vehicle 10. The ultrasonic sensor acquires reflected wave information of ultrasonic reflectors around the vehicle 10. The sensor group 3 may also have a rainfall sensor for detecting information indicating the rainfall around the vehicle 10 as a sensor for detecting environmental information.

[0055] The front camera and the millimeter-wave radar for detecting the environment in front of the vehicle 10 are an example of a front sensor for detecting the environmental information in front of the vehicle 10. The rear camera and the millimeter-wave radar for detecting the environment behind the vehicle 10 are an example of a rear sensor for detecting the environmental information behind the vehicle 10. The millimeter-wave radar and the LiDAR sensor for detecting the environment on the side of the vehicle 10 are an example of a side sensor for detecting the environmental information on the side of the vehicle. The ultrasonic sensor is an example of a surrounding sensor for detecting the environmental information near the periphery of the vehicle.

[0056] Sensors for detecting environmental information, such as a front camera and a LiDAR sensor, are also used as sensors for obtaining topographic information of the road surrounding the vehicle 10.

[0057] The sensor group 3 outputs the information detected by the sensors to the control device 12, the decision device 13, etc. via the in-vehicle network 17.

[0058] The positioning information receiver 4 outputs positioning information indicating the current position of the vehicle 10. For example, the positioning information receiver 4 can adopt a GNSS (Global Navigation Satellite System) receiver. Whenever positioning information is obtained at a prescribed reception cycle, the positioning information receiver 4 outputs the positioning information and the positioning information acquisition time when the positioning information is obtained to the navigation device 5, the map information storage device 11, etc.

[0059] Based on the navigation map information, the destination position of the vehicle 10, and the positioning information indicating the current position of the vehicle 10 input from the positioning information receiver 4, the navigation device 5 generates a navigation route from the current position of the vehicle 10 to the destination position. When the destination position is newly set or when the current position of the vehicle 10 deviates from the navigation route, etc., the navigation device 5 newly generates the navigation route of the vehicle 10. Whenever a navigation route is generated, the navigation device 5 outputs the navigation route to the control device 12, etc. via the in-vehicle network 17.

[0060] The map information storage device 11 stores wide-area map information including a relatively wide range (for example, a range of 10 km square to 30 km square) including the current position of the vehicle 10. This map information has high-precision map information, which includes three-dimensional information of the road surface, the speed limit of the road, the curvature of the road, information on road feature objects such as lane dividing lines on the road, the types and positions of structures, etc. In the map information, one lane is represented as a connection of multiple lane links.

[0061] The map information storage device 11 receives wide-area map information from an external server (not shown) via a macro cell base station (not shown) through wireless communication via the communication device 2 mounted on the vehicle 10 according to the current position of the vehicle 10 and stores it in the storage device. Whenever positioning information is input from the positioning information receiver 4, the map information storage device 11 refers to the stored wide-area map information and outputs map information of a relatively narrow area (for example, a range of 100 m square to 10 km square) including the current position indicated by the positioning information to the control device 12, the decision device 13, etc. via the in-vehicle network 17. The map information is an example of topographic information.

[0062] The control device 12 obtains the current position and orientation of the vehicle 10 based on the terrain information and the environmental information. The control device 12 acquires the state of the vehicle 10 such as the speed based on the vehicle information. The control device 12 detects the objects around the vehicle 10 based on the environmental information. The objects include moving objects such as other vehicles or pedestrians and stationary objects such as guardrails. In addition, the control device 12 detects road features such as lane dividing lines, signs, or traffic lights based on the environmental information. The control device 12 acquires the information indicating the road around the vehicle 10 based on the terrain information.

[0063] The control device 12 generates a driving lane plan indicating the predetermined driving lane on which the vehicle 10 is to travel based on the current position of the vehicle 10, the navigation route, the vehicle information, the environmental information, and the terrain information. In addition, the control device 12 generates a driving plan indicating the predetermined driving trajectory of the vehicle 10 until a specified time (e.g., 5 seconds) before based on the driving lane plan.

[0064] The control device 12 controls each part of the vehicle 10 based on the driving plan. The control device 12 generates a steering signal for controlling the steering device 14 that controls the steering wheel of the vehicle 10 based on the driving plan. The control device 12 generates a drive signal for controlling a drive device 15 such as an engine or a motor of the vehicle 10 based on the driving plan. The control device 12 generates a brake signal for controlling the brake device 16 of the vehicle 10 based on the driving plan. The control device 12 outputs the steering signal, the drive signal, or the brake signal to the steering device 14, the drive device 15, or the brake device 16 via the in-vehicle network 17.

[0065] Figure 3 This is a diagram for explaining the control device 12. The first processing unit 12A of the control device 12 includes a plurality of first processing units 1211 and first processing units 1221. In addition, the second processing unit 12B of the control device 12 includes a plurality of second processing units 1222 and second processing units 1231. The first processing units 1211 and 1221 can be, for example, a so-called end-to-end model that outputs a steering signal, a drive signal, or a brake signal based on the vehicle information, the environmental information, and the terrain information. Alternatively, the first processing unit 1221 may execute a process of generating a driving plan described later based on the vehicle information, the environmental information, and the terrain information, and the second processing unit 1222 may execute a process of outputting a steering signal, a drive signal, or a brake signal based on the driving plan.

[0066] The control device 12 includes a first control unit 121, a second control unit 122, and a third control unit 123. The first control unit 121 generates a signal to be output using only the first processing unit 1211. The second control unit 122 includes: a first processing unit 1221 that generates a signal to be output using only a classifier that has undergone machine learning; and a second processing unit 1222 that generates a signal to be output without using a classifier that has undergone machine learning. The third control unit 123 generates a signal to be output using only the second processing unit 1231. The average power consumption of the first control unit 121 is greater than the average power consumption of the second control unit 122. The average power consumption of the third control unit 123 is less than the average power consumption of the second control unit 122.

[0067] The determination device 13 selects a selection control unit for controlling the vehicle 10 from among the first control unit 121, the second control unit 122, and the third control unit 123. The control device 12 inputs vehicle information, environment information, and terrain information, and outputs drive signals, steering signals, braking signals, etc. using the selection control unit. It should be noted that in addition to outputting drive signals, steering signals, and braking signals, the control device 12 can also output other information or signals such as information notified to the driver.

[0068] The first control unit 121, the second control unit 122, and the third control unit 123 can also operate on different semiconductor devices. The semiconductor devices other than the selection control unit selected by the determination device 13 can operate in standby power, or the power supply to this semiconductor device can also be stopped. Thereby, the power consumption of the control device 12 can be reduced.

[0069] The determination device 13 performs determination processing, selection processing, and switching processing. For this purpose, the determination device 13 includes a communication interface (I / F) 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 are connected via a signal line 24. The communication interface 21 has an interface circuit for connecting the determination device 13 to the in-vehicle network 17.

[0070] The memory 22 is an example of a storage unit, and includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. Also, the memory 22 stores a computer program of an application program used in information processing executed by the processor 23 and various data.

[0071] All or part of the functions of the determination device 13 are, for example, functional modules implemented by a computer program operating on the processor 23. The processor 23 has a determination unit 231, a selection unit 232, and a switching unit 233. Alternatively, the functional modules of the processor 23 may be dedicated arithmetic circuits provided in the processor 23. The processor 23 has one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 23 may further have other arithmetic circuits such as a logical arithmetic unit, a numerical arithmetic unit, or a graphics processing unit. The determination device 13 is, for example, an electronic control unit (ECU). The determination unit 231 is an example of a first determination unit and a second determination unit.

[0072] In Figure 2 the control device 12 and the determination device 13 have been described as separate devices, but these devices may also be configured as a single device. Specifically, the first processing unit 12A and the second processing unit 12B may be configured as a device different from the determination device 13, or the first processing unit 12A and the second processing unit 12B may be configured as the same device as the determination device 13.

[0073] Figure 4 is an example of an operation flowchart of the vehicle control process of the determination device 13. Hereinafter, with reference to Figure 4 the vehicle control process of the determination device 13 will be described. At a vehicle control moment with a specified cycle, the determination device 13 executes the vehicle control process according to the Figure 4 shown operation flowchart.

[0074] First, the determination unit 231 acquires vehicle information, environment information, and terrain information (step S101). The vehicle information, environment information, and terrain information are input to the determination device 13 via the in-vehicle network 17.

[0075] Next, the determination unit 231 determines the processing ratio in the control device 12 based on at least one of the vehicle information, environment information, and terrain information (step S102). In the control device 12, the processing ratio between the part processed by the first processing unit 12A and the part processed by the second processing unit 12B is variable.

[0076] In the present embodiment, when the portion processed by the first processing unit 12A is 100% and the portion processed by the second processing unit 12B is 0%, the processing ratio is expressed as 1:0. Further, when the portion processed by the first processing unit 12A is 0% and the portion processed by the second processing unit 12B is 100%, the processing ratio is expressed as 0:1. Further, when the portion processed by the first processing unit 12A is 50% and the portion processed by the second processing unit 12B is 50%, the processing ratio is expressed as 0.5:0.5. It should be noted that the processing ratio may also be other ratios such as 0.3:0.7 or 0.7:0.3, for example.

[0077] Thus, the processing ratio is determined within the range of 1:0 to 0:1. The processing ratio of 0.5:0.5 means, for example, that the ratio of the average power consumption generated by the operation of the first processing unit 12A to the average power consumption generated by the operation of the second processing unit 12B is 0.5:0.5.

[0078] The processing ratio of 1:0 means, for example, that the ratio of the average power consumption generated by the operation of the first processing unit 12A to the average power consumption generated by the operation of the second processing unit 12B is 1:0. Here, it is considered that the average standby power when the first processing unit 12A or the second processing unit 12B does not substantially operate is substantially 0.

[0079] The processing ratio of 0:1 means, for example, that the ratio of the average power consumption generated by the operation of the first processing unit 12A to the average power consumption generated by the operation of the second processing unit 12B is 0:1. Similarly, it is considered that the average standby power when the first processing unit 12A or the second processing unit 12B does not substantially operate is substantially 0.

[0080] In the present embodiment, the determination unit 231 determines the processing ratio from among 1:0, 0.5:0.5, and 0:1.

[0081] Next, the selection unit 232 selects a selection control unit for controlling the vehicle 10 from among the first control unit 121, the second control unit 122, and the third control unit 123 based on the processing ratio determined by the determination unit 231 (step S103), and ends a series of processes.

[0082] In the case where the processing ratio is 1:0, the selection unit 232 selects the first control unit 121 as the selection control unit. In the case where the processing ratio is 0.5:0.5, the selection unit 232 selects the second control unit 122 as the selection control unit. In the case where the processing ratio is 0:1, the selection unit 232 selects the third control unit 123 as the selection control unit. In the second control unit 122, the ratio of the average power consumption generated by the operation of the first processing unit 1221 to the average power consumption generated by the operation of the second processing unit 1222 is 0.5:0.5.

[0083] It should be noted that in the case where the control device 12 has a selection control unit corresponding to another processing ratio (for example, 0.7:0.3 or 0.3:0.7), the determination unit 231 can also determine the processing ratio from among 1:0, 0.7:0.3, 0.5:0.5, 0.3:0.7, and 0:1.

[0084] Next, an example of determining the processing ratio based on vehicle information, environmental information, and terrain information will be described below with reference to Figures 5 - 8 FIG.

[0085] Figure 5 FIG. (A) illustrates determining the processing ratio based on vehicle information, Figure 5 and FIG. (B) illustrates the relationship between vehicle information and power consumption.

[0086] The vehicle information includes information indicating the degree of operation of the vehicle 10. For example, the vehicle information includes the speed of the vehicle 10, the change amount of the steering angle per unit time, the number of braking times per unit time, and the available travel distance. The determination unit 231 determines the processing ratio based on the degree of operation of the vehicle 10.

[0087] The determination unit 231 determines the processing ratio in such a manner that when the speed of the vehicle 10 is slow, the part processed by the first processing unit 12A is larger than the part processed by the second processing unit 12B compared to when the speed of the vehicle 10 is fast.

[0088] The determination unit 231 determines the processing ratio in such a manner that when the change amount of the steering angle per unit time is large, the part processed by the first processing unit 12A is larger than the part processed by the second processing unit 12B compared to when the change amount of the steering angle per unit time is small.

[0089] The determination unit 231 determines the processing ratio in such a manner that when the number of braking times per unit time is large, the part processed by the first processing unit 12A is larger than the part processed by the second processing unit 12B compared to when the number of braking times per unit time is small.

[0090] The determination unit 231 determines the processing ratio such that when the available driving distance is long, the portion processed by the first processing unit 12A is larger than the portion processed by the second processing unit 12B, compared to when the available driving distance is short. The available driving distance is obtained based on information indicating the remaining amount of power storage or fuel and the power consumption rate or fuel consumption rate of the vehicle 10.

[0091] Figure 5 of (A) and Figure 5 of (B) shows an example where the vehicle information is the speed of the vehicle 10. For example, the average speed of the vehicle 10 over a recent specified period can be used as the speed of the vehicle 10.

[0092] In the present embodiment, when the speed of the vehicle 10 is slower than the first reference speed v1, the determination unit 231 determines the processing ratio as 1:0. Further, when the speed of the vehicle 10 is faster than the second reference speed v2, the determination unit 231 determines the processing ratio as 0:1. Further, when the speed of the vehicle 10 is equal to or higher than the first reference speed v1 and equal to or lower than the second reference speed v2, the determination unit 231 determines the processing ratio as 0.5:0.5.

[0093] As Figure 5 shown in (A) of, when the processing ratio is 1:0, the selection unit 232 selects the first control unit 121 as the selection control unit. Further, when the processing ratio is 0.5:0.5, the selection unit 232 selects the second control unit 122 as the selection control unit. Further, when the processing ratio is 0:1, the selection unit 232 selects the third control unit 123 as the selection control unit.

[0094] As Figure 5 shown in (B) of, when the speed of the vehicle 10 is slower than the first reference speed v1, the power consumption of the control device 12 is the highest. When the speed of the vehicle 10 is faster than the second reference speed v2, the power consumption of the control device 12 is the lowest. When the speed of the vehicle 10 is equal to or higher than the first reference speed v1 and equal to or lower than the second reference speed v2, the power consumption of the control device 12 becomes an intermediate value.

[0095] As described above, when the speed of the vehicle 10 is slower than the first reference speed v1, it is considered that the vehicle 10 is traveling on a road such as a street. In a street, there are many moving objects such as other vehicles and pedestrians. Further, in a street, control of the vehicle 10 corresponding to the state of an intersection or a traffic signal is performed. Therefore, when the speed of the vehicle 10 is slow, it is preferable that the control device 12 can safely control the vehicle according to a complex environment and terrain.

[0096] On the other hand, when the speed of the vehicle 10 is faster than the second reference speed v2, it is considered that the vehicle 10 is traveling on an expressway or the like. On an expressway, there are no traffic lights or pedestrians. In addition, on an expressway, there are many straight roads and few branched or converging terrains. Therefore, when the speed of the vehicle 10 is high, the control device 12 can safely control the vehicle according to a relatively simple environment and terrain.

[0097] Therefore, when the speed of the vehicle 10 is slower than the first reference speed v1, the first control unit 121 is selected, and the processing ratio of the part processed by the first processing unit 12A is increased, thereby ensuring safety. On the other hand, when the speed of the vehicle 10 is faster than the second reference speed v2, the third control unit 123 is selected, and the processing ratio of the part processed by the second processing unit 12B is increased, thereby reducing power consumption.

[0098] In addition, when the speed of the vehicle 10 is equal to or higher than the first reference speed v1 and lower than the second reference speed v2, it is considered that the vehicle 10 is traveling on a road in the suburbs or the like. On a road in the suburbs, the number of moving objects around the vehicle 10 is not large, and the road conditions are not so complex.

[0099] Therefore, when the speed of the vehicle 10 is equal to or higher than the first reference speed v1 and lower than the second reference speed v2, the second control unit 122 is selected, thereby ensuring a certain degree of safety and reducing power consumption.

[0100] Figure 6 (A) is a diagram for explaining the determination of the processing ratio based on environmental information. Figure 6 (B) is a diagram for explaining the relationship between environmental information and power consumption.

[0101] The environmental information includes information indicating the complexity of the environment around the vehicle 10. For example, the environmental information includes the number of moving objects around the vehicle 10, the number of road features around the vehicle 10, and the amount of precipitation around the vehicle 10. The more the number of moving objects, the more the number of road features, or the more the amount of precipitation, the higher the complexity of the environment around the vehicle 10.

[0102] The determination unit 231 determines the processing ratio in such a way that the part processed by the first processing unit 12A is larger than the part processed by the second processing unit 12B when the environment around the vehicle 10 is complex compared to when the environment around the vehicle 10 is not complex.

[0103] Figure 6 (A) and Figure 6(B) shows an example where the environmental information is the number of moving objects. The determination unit 231 acquires the number of moving objects around the vehicle 10 from the control device 12 via the in-vehicle network 17.

[0104] In the present embodiment, when the number of moving objects is greater than the first reference number c1, the determination unit 231 determines the processing ratio as 1:0. Further, when the number of moving objects is less than the second reference number c2, the determination unit 231 determines the processing ratio as 0:1. Further, when the number of moving objects is equal to or less than the first reference number c1 and equal to or greater than the second reference number c2, the determination unit 231 determines the processing ratio as 0.5:0.5.

[0105] As Figure 6 shown in (A), when the processing ratio is 1:0, the selection unit 232 selects the first control unit 121 as the selection control unit. Further, when the processing ratio is 0.5:0.5, the selection unit 232 selects the second control unit 122 as the selection control unit. Further, when the processing ratio is 0:1, the selection unit 232 selects the third control unit 123 as the selection control unit.

[0106] As Figure 6 shown in (B), when the number of moving objects is greater than the first reference number c1, the power consumption of the control device 12 is the highest. When the number of moving objects is less than the second reference number c2, the power consumption of the control device 12 is the lowest. When the number of moving objects is equal to or less than the first reference number c1 and equal to or greater than the second reference number c2, the power consumption of the control device 12 becomes an intermediate value.

[0107] When the number of moving objects is greater than the first reference number c1, there are many moving objects moving around the vehicle 10. Preferably, the vehicle 10 is controlled to avoid approaching other objects in an environment with heavy traffic and many obstacles. It is considered that the vehicle 10 is traveling on a road in a commercial area, on the way to and from school, or on a road in an area where an event is being held. When the number of moving objects is greater than the first reference number c1, preferably, the control device 12 can safely control the vehicle according to the complex environment.

[0108] On the other hand, when the number of moving objects is less than the second reference number c2, there are not many moving objects around the vehicle 10. It is considered that the vehicle 10 is traveling on a road or in a wide parking lot during the early morning or late night period. It is sufficient that the control device 12 can safely control the vehicle according to a relatively simple environment.

[0109] Therefore, when the number of moving objects is greater than the first reference number c1, the first control unit 121 is selected, and the processing ratio of the part processed by the first processing unit 12A is increased, thereby ensuring safety. On the other hand, when the number of moving objects is less than the second reference number c2, the third control unit 123 is selected, and the processing ratio of the part processed by the second processing unit 12B is increased, thereby reducing power consumption.

[0110] In addition, when the number of moving objects is less than or equal to the first reference number c1 and greater than or equal to the second reference number c2, preferably, the vehicle 10 is controlled to avoid approaching other objects in an environment with relatively low traffic volume and relatively few obstacles. It is considered that the vehicle 10 is traveling on a general road during the day.

[0111] Therefore, when the number of moving objects is less than or equal to the first reference number c1 and greater than or equal to the second reference number c2, the second control unit 122 is selected, thereby ensuring a certain degree of safety and seeking to reduce power consumption.

[0112] Figure 7 of (A) and Figure 7 (B) of shows an example where the environmental information is precipitation. The determination unit 231 obtains the precipitation around the vehicle 10 from the sensor group 3 via the in-vehicle network 17. In addition, the determination unit 231 may also obtain the precipitation around the vehicle 10 from the communication network via the communication device 2.

[0113] In the present embodiment, when the precipitation is greater than the first reference value w1, the determination unit 231 determines the processing ratio as 1:0. In addition, when the precipitation is less than the second reference value w2, the determination unit 231 determines the processing ratio as 0:1. The precipitation being less than the second reference value w2 includes the cases of no rain or no snow. In addition, when the precipitation is less than or equal to the first reference value w1 and greater than or equal to the second reference value w2, the determination unit 231 determines the processing ratio as 0.5:0.5.

[0114] As Figure 7 shown in (A) of, when the processing ratio is 1:0, the selection unit 232 selects the first control unit 121 as the selection control unit. In addition, when the processing ratio is 0.5:0.5, the selection unit 232 selects the second control unit 122 as the selection control unit. In addition, when the processing ratio is 0:1, the selection unit 232 selects the third control unit 123 as the selection control unit.

[0115] As Figure 7As shown in (B), when the precipitation is more than the first reference value w1, the power consumption of the control device 12 is the highest. When the precipitation is less than the second reference value w2, the power consumption of the control device 12 is the lowest. When the precipitation is equal to or more than the second reference value w2 and equal to or less than the first reference value w1, the power consumption of the control device 12 becomes an intermediate value.

[0116] When the precipitation is more than the first reference value w1, it is raining heavily or snowing heavily around the vehicle 10. When raindrops or the like adhere to the sensors of the sensor group 3, it is difficult to accurately detect the environment around the vehicle 10. In addition, in order for the vehicle 10 to travel on a road surface wet with rain or covered with snow, more precise control of the vehicle 10 is required. When the precipitation is more than the first reference value w1, preferably, the control device 12 can safely control the vehicle according to the complex environment.

[0117] On the other hand, when the precipitation is less than the second reference value w2, the sensors of the sensor group 3 of the vehicle 10 can accurately detect the environment around the vehicle 10. In addition, the road surface is in a state that is still dry but slightly wet. The control device 12 can safely control the vehicle according to a relatively simple environment.

[0118] Therefore, when the precipitation is more than the first reference value w1, the first control unit 121 is selected, and the processing ratio of the part processed by the first processing unit 12A is increased, thereby ensuring safety. On the other hand, when the precipitation is less than the second reference value w2, the third control unit 123 is selected, and the processing ratio of the part processed by the second processing unit 12B is increased, thereby reducing power consumption.

[0119] In addition, when the precipitation is equal to or more than the second reference value w2 and equal to or less than the first reference value w1, relatively light rain or relatively light snow is falling around the vehicle 10. The sensors of the sensor group 3 can relatively accurately detect the environment around the vehicle 10. In addition, it is considered that the state of the road surface is relatively good.

[0120] Therefore, when the precipitation is equal to or more than the second reference value w2 and equal to or less than the first reference value w1, the second control unit 122 is selected, thereby ensuring a certain degree of safety and reducing power consumption.

[0121] Figure 8 (A) is a diagram for explaining the determination of the processing ratio based on terrain information. Figure 8 (B) is a diagram for explaining the relationship between terrain information and power consumption.

[0122] The terrain information includes information indicating the degree of complexity of the terrain including the current position of the vehicle 10. For example, the terrain information includes the number of vehicle lanes around the vehicle 10, the curvature of the road, and the slope of the road. The greater the number of vehicle lanes, the greater the curvature of the road, or the greater the slope of the road, the higher the degree of complexity of the terrain including the current position of the vehicle 10. The number of vehicle lanes around the vehicle 10, the curvature of the road, and the slope of the road are obtained based on map information, for example.

[0123] The determination unit 231 determines the processing ratio in such a manner that, compared with when the terrain is not complex, when the terrain is complex, the portion processed by the first processing unit 12A is larger than the portion processed by the second processing unit 12B.

[0124] Figure 8 of (A) and Figure 8 (B) of shows an example where the terrain information is the number of vehicle lanes around the vehicle 10. On a road with a large number of lanes or near an intersection, the number of vehicle lanes around the vehicle 10 increases. The determination unit 231 obtains the number of vehicle lanes around the vehicle 10 from the map information. In addition, the determination unit 231 may also obtain the number of vehicle lanes obtained by the control device 12 based on the camera image via the in-vehicle network 17.

[0125] In the present embodiment, when the number of vehicle lanes is greater than the first reference value k1, the determination unit 231 determines the processing ratio as 1:0. In addition, when the number of vehicle lanes is less than the second reference value k2, the determination unit 231 determines the processing ratio as 0:1. In addition, when the number of vehicle lanes is less than or equal to the first reference value k1 and greater than or equal to the second reference value k2, the determination unit 231 determines the processing ratio as 0.5:0.5.

[0126] As Figure 8 shown in (A) of, when the processing ratio is 1:0, the selection unit 232 selects the first control unit 121 as the selection control unit. In addition, when the processing ratio is 0.5:0.5, the selection unit 232 selects the second control unit 122 as the selection control unit. In addition, when the processing ratio is 0:1, the selection unit 232 selects the third control unit 123 as the selection control unit.

[0127] As Figure 8 shown in (B) of, when the number of vehicle lanes is greater than the first reference value k1, the power consumption of the control device 12 is the highest. When the number of vehicle lanes is less than the second reference value k2, the power consumption of the control device 12 is the lowest. When the number of vehicle lanes is less than or equal to the first reference value k1 and greater than or equal to the second reference value k2, the power consumption of the control device 12 becomes an intermediate value.

[0128] When the number of vehicle lane segments is greater than the first reference value k1, it is considered that the vehicle 10 is traveling near a road or intersection with many lanes. It is considered that there are multiple vehicles or pedestrians around the vehicle 10. In addition, depending on the intersection, the signal state of the traffic lights sometimes changes complexly. It is considered that the vehicle 10 is traveling in the center or commercial area of a large city. When the number of vehicle lane segments is greater than the first reference value k1, preferably, the control device 12 can safely control the vehicle according to the complex environment and terrain.

[0129] On the other hand, when the number of vehicle lane segments is less than the second reference value k2, it is considered that the vehicle 10 is traveling on a road with few lanes or a road far from the intersection. It is considered that the vehicle 10 is traveling on a highway or a straight road in the suburbs. When the number of vehicle lane segments is less than the second reference value k2, it is sufficient that the control device 12 can safely control the vehicle according to a relatively simple environment and terrain.

[0130] Therefore, when the number of vehicle lane segments is greater than the first reference value k1, the first control unit 121 is selected, and the processing ratio of the part processed by the first processing unit 12A is increased, thereby ensuring safety. On the other hand, when the number of vehicle lane segments is less than the second reference value k2, the third control unit 123 is selected, and the processing ratio of the part processed by the second processing unit 12B is increased, thereby reducing power consumption.

[0131] In addition, when the number of vehicle lane segments is less than or equal to the first reference value k1 and greater than or equal to the second reference value k2, it is considered that the vehicle 10 is traveling on a road in a residential area or a city road. In the roads of residential areas or cities, the road conditions are not so complex.

[0132] Therefore, when the number of vehicle lane segments is less than or equal to the first reference value k1 and greater than or equal to the second reference value k2, the second control unit 122 is selected, thereby ensuring a certain degree of safety and seeking to reduce power consumption.

[0133] In the above description, the processing ratio is determined based on one of the vehicle information, environment information, and terrain information, but the processing ratio can also be determined based on multiple of the vehicle information, environment information, and terrain information. For example, it can also be that a table showing the relationship between the speed of the vehicle 10 and the number of moving objects and the selected control unit is used, and the processing ratio is determined based on the speed of the vehicle 10 and the number of moving objects.

[0134] Figure 9 This is an example of the operation flowchart of the change process of the determination device 13. Hereinafter, with reference to Figure 9 The change process of the determination device 13 will be described. At the change time with a specified cycle, the determination device 13 follows Figure 9Execute change processing according to the action flow chart shown below.

[0135] First, the decision unit 231 acquires vehicle information, environment information, and terrain information (step S201). The vehicle information, environment information, and terrain information are input to the decision device 13 via the in-vehicle network 17.

[0136] Next, the decision unit 231 determines the amount of information input to the selection control unit selected by the selection unit 232 based on at least one of the vehicle information, environment information, and terrain information (step S202).

[0137] The information indicating the degree of the action of the vehicle 10 described above can be used as the vehicle information. In addition, the information indicating the degree of complexity of the environment around the vehicle 10 can be used as the environment information. In addition, the information indicating the degree of complexity of the terrain including the current position of the vehicle 10 can be used as the terrain information.

[0138] By reducing the amount of information input to the selected first control unit 121, second control unit 122, or third control unit 123, the power used for the operation of the control device 12 can be reduced.

[0139] The amount of information may include the number of sensors to which the detected information is input to the selection control unit, the resolution of the image input to the selection control unit, or the detection frequency of the sensors to which the detected information is input to the selection control unit.

[0140] The decision unit 231 changes the amount of information input to the selection control unit by changing the number of sensors. As described above, the sensor group 3 includes a front sensor, a surrounding sensor, a rear sensor, and a side sensor. Priorities are set for these sensors. The priority of the front sensor is 4, the priority of the surrounding sensor is 3, the priority of the rear sensor is 2, and the priority of the side sensor is 1. The higher the numerical value, the higher the priority.

[0141] For the driving of the vehicle 10, at least the detection information of the sensor with a priority of 4 is required. By adding the detection information of the sensors with lower priorities together with the detection information of the sensor with a priority of 4, the vehicle 10 can be controlled more safely according to the situation.

[0142] The decision unit 231 determines the amount of information of the sensors based on at least one of the vehicle information, environment information, and terrain information. The detection information of the sensors is input to the selection control unit according to the amount of information of the sensors.

[0143] The determination unit 231 determines the amount of information of the sensors based on the information indicating the degree of operation of the vehicle 10. In addition, the determination unit 231 determines the amount of information of the sensors based on the degree of complexity of the environment around the vehicle 10. In addition, the determination unit 231 determines the amount of information of the sensors based on the degree of complexity of the terrain including the current position of the vehicle 10. The higher the driving difficulty of the vehicle 10, the higher the amount of information of the sensors is determined.

[0144] For example, when the amount of information of the sensors is 4, the information detected by all priority sensors is input to the selection control unit. Specifically, the information detected by the front sensor, the surrounding sensors, the rear sensor, and the side sensors is input to the selection control unit. When the amount of information of the sensors is 3, the information detected by the sensors with a priority of 2 or higher is input to the selection control unit. Specifically, the information detected by the front sensor, the surrounding sensors, and the rear sensor is input to the selection control unit. When the amount of information of the sensors is 2, the information detected by the sensors with a priority of 3 or higher is input to the selection control unit. Specifically, the information detected by the front sensor and the surrounding sensors is input to the selection control unit. When the amount of information of the sensors is 1, the information detected by the sensors with a priority of 4 or higher is input to the selection control unit. Specifically, only the information detected by the front sensor is input to the selection control unit.

[0145] In addition, the determination unit 231 changes the amount of information input to the selection control unit by changing the resolution of the image input to the selection control unit. The front camera and the rear camera can change the resolution of the image to be acquired. The higher the resolution of the image used, the more accurately the environment around the vehicle 10 can be detected, so the safety of the vehicle 10 is improved.

[0146] The determination unit 231 determines the resolution of the image to be acquired based on at least one of vehicle information, environment information, and terrain information.

[0147] The determination unit 231 determines the resolution of the image to be acquired based on the information indicating the degree of operation of the vehicle 10. In addition, the determination unit 231 determines the resolution of the image to be acquired based on the degree of complexity of the environment around the vehicle 10. In addition, the determination unit 231 determines the resolution of the image to be acquired based on the degree of complexity of the terrain including the current position of the vehicle 10.

[0148] The determination unit 231 notifies the sensor group 3 of the determined resolution of the image. The front camera and the rear camera acquire images at the notified resolution.

[0149] Furthermore, the determination unit 231 determines the detection frequency of the information detected by the sensor that inputs the detected information to the selection control unit based on at least one of the vehicle information, the environment information, and the terrain information. When the sensor is a front camera or a rear camera, the detection frequency corresponds to the frame rate. The higher the detection frequency, the more accurately the environment around the vehicle 10 can be detected, and thus the safety of the vehicle 10 is improved. In the case of a LiDAR sensor, a millimeter-wave radar, or an ultrasonic sensor, the detection frequency corresponds to the period of obtaining the reflected wave information.

[0150] The determination unit 231 determines the detection frequency of the sensor based on the information indicating the degree of movement of the vehicle 10. In addition, the determination unit 231 determines the detection frequency of the sensor based on the complexity of the environment around the vehicle 10. In addition, the determination unit 231 determines the detection frequency of the sensor based on the complexity of the terrain including the current position of the vehicle 10.

[0151] The determination unit 231 notifies the sensor group 3 of the determined detection frequency. Each sensor of the sensor group 3 detects information at a period corresponding to the detection frequency notified by the determination unit 231.

[0152] Figure 10 The (A) of is a diagram for explaining the determination of the amount of information based on the vehicle information. The vehicle information is the speed of the vehicle 10.

[0153] In the present embodiment, when the speed of the vehicle 10 is slower than the first reference speed v1, the determination unit 231 determines to input a larger amount of information to the selection control unit than the first reference value r1. In addition, when the speed of the vehicle 10 is faster than the second reference speed v2, the determination unit 231 determines to input a smaller amount of information to the selection control unit than the second reference value r2. In addition, when the speed of the vehicle 10 is equal to or higher than the first reference speed v1 and equal to or lower than the second reference speed v2, the determination unit 231 determines to input an amount of information that is equal to or lower than the first reference value r1 and equal to or higher than the second reference value r2.

[0154] When the speed of the vehicle 10 is slower than the first reference speed v1, the power consumption of the selection control unit is the highest. When the speed of the vehicle 10 is faster than the second reference speed v2, the power consumption of the selection control unit is the lowest. When the speed of the vehicle 10 is equal to or higher than the first reference speed v1 and equal to or lower than the second reference speed v2, the power consumption of the selection control unit becomes an intermediate value.

[0155] When the amount of information corresponds to the number of sensors, the first reference value r1 and the second reference value r2 correspond to the number of sensors, and the number of sensors for the first reference value r1 is larger than the number of sensors for the second reference value r2.

[0156] When the amount of information corresponds to the resolution of the image, the first reference value r1 and the second reference value r2 correspond to the resolution, and the resolution of the first reference value r1 is higher than that of the second reference value r2.

[0157] When the amount of information corresponds to the detection frequency of the sensor, the first reference value r1 and the second reference value r2 correspond to the detection frequency, and the detection frequency of the first reference value r1 is higher than that of the second reference value r2.

[0158] When the speed of the vehicle 10 is slower than the first reference speed v1, it is considered that the vehicle 10 is traveling on a road such as a street. In the street, there are many moving objects such as other vehicles and pedestrians. In addition, in the street, the control of the vehicle 10 corresponding to the state of the intersection or traffic signal is performed. When the speed of the vehicle 10 is slow, preferably, more information than the first reference value r1 is input to the selection control unit, so that the vehicle can be controlled safely.

[0159] On the other hand, when the speed of the vehicle 10 is faster than the second reference speed v2, it is considered that the vehicle 10 is traveling on an expressway for automobiles or the like. In the expressway for automobiles, there are no traffic signals and pedestrians. In addition, in the expressway for automobiles, there are many straight roads and few branched or converged terrains. When the speed of the vehicle 10 is fast, less information than the second reference value r2 is input to the selection control unit, thereby reducing power consumption.

[0160] In addition, when the speed of the vehicle 10 is equal to or higher than the first reference speed v1 and lower than the second reference speed v2, it is considered that the vehicle 10 is traveling on a road in the suburbs or the like. In the road in the suburbs, the number of moving objects around the vehicle 10 is not large, and the road conditions are not so complicated.

[0161] Therefore, when the speed of the vehicle 10 is equal to or higher than the first reference speed v1 and lower than the second reference speed v2, information amount that is equal to or lower than the first reference value r1 and equal to or higher than the second reference value r2 is input to the selection control unit, thereby ensuring a certain degree of safety and seeking to reduce power consumption.

[0162] It should be noted that the priority of the sensor can be set according to the detection range from the vehicle 10. In this case, it may also be that when the speed of the vehicle 10 is slow, the priority of the sensor for detecting the vicinity of the vehicle 10 is increased, and when the speed of the vehicle 10 is fast, the priority of the sensor for detecting the distance of the vehicle 10 is increased.

[0163] Figure 10 (B) is a diagram for explaining the determination of the amount of information based on the environmental information. The environmental information is the number of moving objects around the vehicle 10.

[0164] In the present embodiment, when the number of moving objects around the vehicle 10 is greater than the first reference number c1, the determination unit 231 determines to input more information amount to the selection control unit than the first reference value r1. Further, when the number of moving objects around the vehicle 10 is less than the second reference number c2, the determination unit 231 determines to input less information amount to the selection control unit than the second reference value r2. Further, when the number of moving objects around the vehicle 10 is equal to or less than the first reference number c1 and equal to or greater than the second reference number c2, the determination unit 231 determines to input an information amount that is equal to or less than the first reference value r1 and equal to or greater than the second reference value r2 to the selection control unit.

[0165] When the number of moving objects around the vehicle 10 is greater than the first reference number c1, the power consumption of the selection control unit is the highest. When the number of moving objects around the vehicle 10 is less than the second reference number c2, the power consumption of the selection control unit is the lowest. When the number of moving objects around the vehicle 10 is equal to or less than the first reference number c1 and equal to or greater than the second reference number c2, the power consumption of the selection control unit becomes an intermediate value.

[0166] When the information amount corresponds to the number of sensors, the first reference value r1 and the second reference value r2 correspond to the number of sensors, and the number of sensors for the first reference value r1 is greater than the number of sensors for the second reference value r2.

[0167] When the information amount corresponds to the resolution of the image, the first reference value r1 and the second reference value r2 correspond to the resolution, and the resolution of the first reference value r1 is higher than the resolution of the second reference value r2.

[0168] When the information amount corresponds to the detection frequency of the sensors, the first reference value r1 and the second reference value r2 correspond to the detection frequency, and the detection frequency of the first reference value r1 is higher than the detection frequency of the second reference value r2.

[0169] When the number of moving objects around the vehicle 10 is greater than the first reference number c1, there are many moving objects moving around the vehicle 10. Preferably, the vehicle 10 is controlled to avoid approaching other objects in an environment with heavy traffic and many obstacles. It is considered that the vehicle 10 is traveling on a road in a commercial area, on the way to and from school, or in an area where an event is being held. When the number of moving objects is greater than the first reference number c1, preferably, more information amount than the first reference value r1 is input to the selection control unit, so that the vehicle can be safely controlled.

[0170] On the other hand, when the number of moving objects around the vehicle 10 is less than the second reference number c2, there are not many moving objects around the vehicle 10. It is considered that the vehicle 10 is traveling on a road or a wide parking lot during the early morning or late night period. When the number of moving objects is less than the second reference number c2, as for the control device 12, information amount less than the second reference value r2 is input to the selection control unit, and thus the vehicle can be safely controlled.

[0171] In addition, when the number of moving objects is equal to or less than the first reference number c1 and equal to or more than the second reference number c2, preferably, the vehicle 10 is controlled to avoid approaching other objects in an environment with relatively low traffic volume and relatively few obstacles. It is considered that the vehicle 10 is traveling on a general road during the day.

[0172] Therefore, when the number of moving objects is equal to or less than the first reference number c1 and equal to or more than the second reference number c2, information amount equal to or less than the first reference value r1 and equal to or more than the second reference value r2 is input to the selection control unit, thereby ensuring a certain degree of safety and seeking to reduce power consumption.

[0173] Figure 11 (A) is another diagram for explaining the determination of the information amount based on the environmental information. The environmental information is the precipitation amount around the vehicle 10.

[0174] In the present embodiment, when the precipitation amount around the vehicle 10 is more than the first reference value w1, the determination unit 231 determines to input information amount more than the first reference value r1 to the selection control unit. In addition, when the precipitation amount around the vehicle 10 is less than the second reference value w2, the determination unit 231 determines to input information amount less than the second reference value r2 to the selection control unit. In addition, when the precipitation amount around the vehicle 10 is equal to or less than the first reference value w1 and equal to or more than the second reference value w2, the determination unit 231 determines to input information amount equal to or less than the first reference value r1 and equal to or more than the second reference value r2 to the selection control unit.

[0175] When the precipitation amount around the vehicle 10 is more than the first reference value w1, the power consumption of the selection control unit is the highest. When the precipitation amount around the vehicle 10 is less than the second reference value w2, the power consumption of the selection control unit is the lowest. When the precipitation amount around the vehicle 10 is equal to or less than the first reference value w1 and equal to or more than the second reference value w2, the power consumption of the selection control unit becomes an intermediate value.

[0176] When the information amount corresponds to the number of sensors, the first reference value r1 and the second reference value r2 correspond to the number of sensors, and the number of sensors of the first reference value r1 is more than the number of sensors of the second reference value r2.

[0177] When the amount of information corresponds to the resolution of the image, the first reference value r1 and the second reference value r2 correspond to the resolution, and the resolution of the first reference value r1 is higher than that of the second reference value r2.

[0178] When the amount of information corresponds to the detection frequency of the sensor, the first reference value r1 and the second reference value r2 correspond to the detection frequency, and the detection frequency of the first reference value r1 is higher than that of the second reference value r2.

[0179] When the precipitation is more than the first reference value w1, it is raining heavily or snowing heavily around the vehicle 10. When raindrops or the like adhere to the sensors of the sensor group 3, it is difficult to accurately detect the environment around the vehicle 10. In addition, in order for the vehicle 10 to travel on a road surface wet with rain or snow, more precise control of the vehicle 10 is required. When the precipitation is more than the first reference value w1, preferably, an amount of information more than the first reference value r1 is input to the selection control unit, so that the vehicle can be controlled safely.

[0180] On the other hand, when the precipitation is less than the second reference value w2, the sensors of the sensor group 3 of the vehicle 10 can accurately detect the environment around the vehicle 10. In addition, the road surface is in a state that is still dry but slightly wet. When the precipitation around the vehicle 10 is less than the second reference value w2, an amount of information less than the second reference value r2 is input to the selection control unit, so that the vehicle can be controlled safely.

[0181] In addition, when the precipitation is equal to or less than the first reference value w1 and equal to or more than the second reference value w2, relatively light rain or relatively light snow is falling around the vehicle 10. The sensors of the sensor group 3 can detect the environment around the vehicle 10 relatively accurately. In addition, the state of the road surface is considered to be relatively good.

[0182] Therefore, when the precipitation is equal to or less than the first reference value w1 and equal to or more than the second reference value w2, an amount of information equal to or less than the first reference value r1 and equal to or more than the second reference value r2 is input to the selection control unit, thereby ensuring a certain degree of safety and seeking to reduce power consumption.

[0183] Figure 11 (B) is a diagram for explaining the determination of the amount of information based on terrain information. The terrain information is the number of vehicle lanes around the vehicle 10.

[0184] In the present embodiment, when the number of lane segments around the vehicle 10 is greater than the first reference value k1, the determination unit 231 determines to input to the selection control unit an amount of information greater than the first reference value r1. Further, when the number of lane segments around the vehicle 10 is less than the second reference value k2, the determination unit 231 determines to input to the selection control unit an amount of information less than the second reference value r2. Further, when the number of lane segments around the vehicle 10 is equal to or less than the first reference value k1 and equal to or greater than the second reference value k2, the determination unit 231 determines to input to the selection control unit an amount of information that is equal to or less than the first reference value r1 and equal to or greater than the second reference value r2.

[0185] When the number of lane segments around the vehicle 10 is greater than the first reference value k1, the power consumption of the selection control unit is the highest. When the number of lane segments around the vehicle 10 is less than the second reference value k2, the power consumption of the selection control unit is the lowest. When the number of lane segments around the vehicle 10 is equal to or less than the first reference value k1 and equal to or greater than the second reference value k2, the power consumption of the selection control unit becomes an intermediate value.

[0186] When the amount of information corresponds to the number of sensors, the first reference value r1 and the second reference value r2 correspond to the number of sensors, and the number of sensors for the first reference value r1 is greater than the number of sensors for the second reference value r2.

[0187] When the amount of information corresponds to the resolution of the image, the first reference value r1 and the second reference value r2 correspond to the resolution, and the resolution of the first reference value r1 is higher than the resolution of the second reference value r2.

[0188] When the amount of information corresponds to the detection frequency of the sensors, the first reference value r1 and the second reference value r2 correspond to the detection frequency, and the detection frequency of the first reference value r1 is higher than the detection frequency of the second reference value r2.

[0189] When the number of lane segments is greater than the first reference value k1, it is considered that the vehicle 10 is traveling near a road or intersection with many lanes. It is considered that there are multiple other vehicles or pedestrians around the vehicle 10. Further, according to the intersection, the signal state sometimes changes complexly due to the traffic lights. It is considered that the vehicle 10 is traveling in the central part or commercial area of a large city. When the number of lane segments is greater than the first reference value k1, preferably, an amount of information greater than the first reference value r1 is input to the selection control unit so that the vehicle can be controlled safely.

[0190] On the other hand, when the number of lane sections is less than the second reference value k2, it is considered that the vehicle 10 is traveling on a road with a small number of lanes or a road far from the intersection. It is considered that the vehicle 10 is traveling on a straight road on an expressway or in the suburbs. When the number of lane sections is less than the second reference value k2, an amount of information less than the second reference value r2 is input to the selection control unit, and thus the vehicle can be safely controlled.

[0191] In addition, when the number of lane sections is less than or equal to the first reference value k1 and greater than or equal to the second reference value k2, it is considered that the vehicle 10 is traveling on a road in a residential area or a road in a city. Among the roads in a residential area or a city, the road conditions are not so complicated.

[0192] Therefore, when the number of lane sections is less than or equal to the first reference value k1 and greater than or equal to the second reference value k2, an amount of information less than or equal to the first reference value r1 and greater than or equal to the second reference value r2 is input to the selection control unit, thereby ensuring a certain degree of safety and seeking to reduce power consumption.

[0193] In the above description, the amount of information is determined based on one of the vehicle information, the environment information, and the terrain information, but the amount of information can also be determined based on a plurality of the vehicle information, the environment information, and the terrain information. For example, it may be that a table showing the relationship between the speed of the vehicle 10, the number of moving objects, and the amount of information is used, and the amount of information is determined based on the speed of the vehicle 10 and the number of moving objects.

[0194] Next, hereinafter, with reference to Figure 12 of (A) and Figure 12 of (B), the switching unit 233 of the determination device 13 will be described.

[0195] The switching unit 233 inputs the signal output from the control unit before switching and the signal output from the control unit after switching, and controls the control device 12 so that the signal output from the control device 12 is switched as continuously as possible before and after the switching.

[0196] In Figure 12 the example shown in (A), the switching unit 233 controls the control device 12 in such a manner as to generate a signal that gradually switches from the signal of the control unit before switching to the signal of the control unit after switching. Preferably, the control device 12 has a signal control unit 124 that is controlled by the switching unit 233 and generates such a signal.

[0197] For example, the switching unit 233 gradually changes the ratio of the signal of the previous control unit to the signal of the subsequent control unit in the signal output from the control device 12 from 1:0 to 0:1 within a specified time.

[0198] In addition, in the example shown in (B) of Figure 12 the switching unit 233 controls the control device 12 in such a manner that the signal output from the control unit before switching and the signal output from the control unit after switching are within a specified reference value, and then outputs the signal output from the control unit after switching as the signal output from the control device 12. The signal control unit 124 functions as a state prediction buffer.

[0199] It may also be set that when the operation of the vehicle 10 is relatively stable, the switching unit 233 switches from the signal of the control unit before switching to the signal of the control unit after switching. For example, when the vehicle 10 is stopped or traveling at a specified speed, etc., the switching unit 233 switches from the signal of the control unit before switching to the signal of the control unit after switching.

[0200] In addition, the signal control unit 124 of the control device 12 may also apply low-pass filtering or Kalman filtering to the signal output from the control unit before switching and the signal output from the control unit after switching to smooth out the sharp changes in the signal.

[0201] According to the determination device of the present embodiment described in detail above, the processing ratio of the part processed by the first processing unit and the part processed by the second processing unit is determined, so that the vehicle can be controlled in a manner that ensures safety and reduces power consumption according to the vehicle conditions.

[0202] In the present invention, as long as the gist of the present invention is not deviated from, the vehicle control device, the vehicle control computer program, and the vehicle control method of the above-described embodiment can be appropriately changed. In addition, the technical scope of the present invention is not limited to these embodiments, but relates to the invention described in the claims and its equivalents.

[0203] For example, the scheme for the determination unit to determine the processing ratio and the scheme for the selection unit to select the selection control unit are not limited to the above description.

[0204] It may also be that when information indicating that congestion has occurred in front of the vehicle in the traveling direction is obtained through communication with other vehicles around the vehicle via the communication device, the determination unit determines the processing ratio based on this information. In this case, the processing ratio may be determined as 1:0 or 0.5:0.5. Thus, the vehicle can be safely controlled with respect to the moving objects around the vehicle.

[0205] In addition, it may also be that, when information indicating that an accident has occurred or an obstacle has arisen ahead in the traveling direction of the vehicle is obtained via the communication device through communication with other vehicles or infrastructure around the vehicle, the determination unit determines the processing ratio based on this information. In this case, the processing ratio may be determined as 1:0 or 0.5:0.5. Thereby, the vehicle can be safely controlled according to the environment around the vehicle.

[0206] In addition, it may also be that, when information indicating that the weather ahead in the traveling direction of the vehicle is rain, fog, snow, etc. is obtained via the communication device through communication with other vehicles around the vehicle, the determination unit determines the processing ratio based on this information. In this case, the processing ratio may be determined as 1:0. Thereby, the vehicle can be safely controlled according to the road surface conditions.

[0207] In addition, it may also be that, when information indicating that there is road construction or a temporary road closure ahead in the traveling direction of the vehicle is obtained via the communication device through communication with other vehicles around the vehicle, the determination unit determines the processing ratio based on this information. In this case, the processing ratio may be determined as 1:0 or 0.5:0.5. Thereby, the vehicle can be safely controlled according to the environment around the vehicle.

[0208] Moreover, it may also be that, when information indicating a vehicle that is driving abnormally ahead in the traveling direction of the vehicle is obtained via the communication device through communication with other vehicles around the vehicle, the determination unit determines the processing ratio based on this information. In this case, the processing ratio may be determined as 1:0 or 0.5:0.5. Thereby, the vehicle can be safely controlled in a timely manner in response to the environment around the vehicle.

Claims

1. A vehicle control device, comprising: A first processing unit that generates a signal to be output using only a classifier that has undergone machine learning; a second processing unit, the second processing unit consuming less power than the first processing unit and generating a signal to be output without using a classifier that performs machine learning; as well as The first determination unit determines a processing ratio between a portion processed by the first processing unit and a portion processed by the second processing unit based on at least one of vehicle information indicating a state of the vehicle, environmental information indicating an environment surrounding the vehicle, and terrain information indicating a terrain including a current position of the vehicle.

2. The vehicle control device according to claim 1, wherein: The vehicle control device includes a plurality of the first processing units and a plurality of the second processing units. The vehicle control device comprises: a second control unit having one of the first processing units and one of the second processing units; a first control unit, wherein the power consumption of the first control unit is greater than the power consumption of the second control unit and the first control unit generates a signal to be output using only the other first processing unit; and a third control unit, the power consumption of the third control unit being smaller than the power consumption of the second control unit and the third control unit generating a signal to be output using only the other second processing unit, The vehicle control device includes a selection unit that selects a selection control unit for controlling the vehicle from among the first control unit, the second control unit, and the third control unit based on the processing ratio determined by the first determination unit.

3. The vehicle control device according to claim 1, wherein: The vehicle information includes the degree of movement of the vehicle, The first determination unit determines the processing ratio according to the degree of movement of the vehicle.

4. The vehicle control device according to claim 3, wherein: The vehicle information includes the speed of the vehicle. The first determination unit determines the processing ratio such that when the speed of the vehicle is slow, the portion processed by the first processing unit is larger than the portion processed by the second processing unit than when the speed of the vehicle is fast.

5. The vehicle control device according to claim 1, wherein: The environmental information includes the complexity of the environment around the vehicle. The first determination unit determines the processing ratio such that when the degree of complexity of the environment around the vehicle is high, the portion processed by the first processing unit is larger than the portion processed by the second processing unit, compared to when the degree of complexity of the environment around the vehicle is low.

6. The vehicle control device according to any one of claims 1 to 5, wherein: The terrain information includes the complexity of the terrain including the current position of the vehicle, The first determination unit determines the processing ratio in the following manner: when the complexity of the terrain including the current position of the vehicle is high, the part processed by the first processing unit is larger than the part processed by the second processing unit compared to when the complexity of the terrain including the current position of the vehicle is low.

7. The vehicle control device according to claim 2, comprising: A second determination unit determines an amount of information to be input to the selection control unit selected by the selection unit based on at least one of the vehicle information, the environment information, and the terrain information.

8. The vehicle control device according to claim 7, wherein: The amount of information includes the number of sensors whose detected information is input to the selection control unit, the resolution of an image input to the selection control unit, or the detection frequency of the sensors whose detected information is input to the selection control unit.

9. A computer program product for vehicle control, causing a processor to execute a process, the process comprising: Based on at least one of vehicle information indicating a state of the vehicle, environmental information indicating an environment surrounding the vehicle, and terrain information indicating a terrain including a current position of the vehicle, a processing ratio of a portion processed by a first processing unit to a portion processed by a second processing unit is determined, wherein the first processing unit generates a signal to be output using only a classifier that has performed machine learning, and the power consumption of the second processing unit is smaller than the power consumption of the first processing unit and the second processing unit generates a signal to be output without using a classifier that has performed machine learning.

10. A vehicle control method, comprising: performing the following processing by a vehicle control device: The processing ratio of the portion processed by the first processing unit to the portion processed by the second processing unit is determined based on at least one of vehicle information indicating a state of the vehicle, environmental information indicating an environment surrounding the vehicle, and terrain information indicating a terrain including a current position of the vehicle, wherein: The first processing unit generates a signal to be output using only a classifier that has undergone machine learning, and the second processing unit consumes less power than the first processing unit and generates a signal to be output without using a classifier that has undergone machine learning.

Images