Control device

Abstract

To provide a control device capable of estimating a concentration degree of a driver by considering a preceding vehicle and a following vehicle while a vehicle is traveling.SOLUTION: A control device includes a control unit for controlling a vehicle. The control unit estimates a concentration degree of a driver in the vehicle while the vehicle is traveling, based on a relation between an inter-vehicle distance between the vehicle and a preceding vehicle traveling in front of the vehicle, an inter-vehicle distance between the vehicle and a following vehicle traveling behind the vehicle, and a vehicle speed of the vehicle relative to a predetermined vehicle speed, and executes vehicle control to restore the concentration of the driver based on the estimation result.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a control device. [Background technology]

[0002] Patent Document 1 discloses that a control device mounted on a vehicle issues a warning to the driver based on the distance between the vehicle and the vehicle ahead while the vehicle is traveling. The control device described in Patent Document 1 can change the distance between the vehicles for issuing a warning according to the driver's level of concentration. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 6-119600 Summary of the Invention [Problem to be solved by the invention]

[0004] Regarding the configuration described in Patent Document 1, it is possible to change the following distance for issuing a warning, for example, by using a trained model created by machine learning. However, if the driver's concentration decreases while driving and the driver is unable to grasp the surrounding situation, the configuration described in Patent Document 1 can prevent a rear-end collision with the vehicle ahead, but cannot take into consideration the vehicle traveling behind the vehicle.

[0005] The present invention has been made in consideration of the above-mentioned circumstances, and aims to provide a control device that can estimate the driver's level of concentration while taking into account the vehicles in front and behind when the vehicle is traveling. [Means for solving the problem]

[0006] The present invention is a control device having a control unit that controls a vehicle, wherein the control unit estimates the driver's concentration level in the vehicle while the vehicle is traveling based on the distance between the vehicle and a preceding vehicle traveling in front of the vehicle, the distance between the vehicle and a following vehicle traveling behind the vehicle, and the relationship between the vehicle's speed and a predetermined vehicle speed, and performs vehicle control to restore the driver's concentration based on the estimation result.

[0007] According to this configuration, the driver's concentration level can be estimated based on the distance between the front and rear vehicles, and therefore the driver's concentration level can be estimated while taking into consideration the vehicles ahead and behind while the vehicle is traveling.

[0008] The vehicle control may also include notification control for issuing a warning by sound or image display.

[0009] According to this configuration, a warning can be issued to the driver by sound or image display when the driver's concentration decreases, thereby encouraging the driver to regain his / her concentration.

[0010] In addition, the specified vehicle speed may be the speed limit for the road on which the vehicle is traveling, and the control unit may estimate that the driver's concentration is declining when the vehicle speed of the vehicle is slower than the speed limit when the distance between the vehicle and the vehicle in front is large and the distance between the vehicle and the vehicle behind is small.

[0011] According to this configuration, when the distance between the vehicle ahead and the vehicle behind is narrow despite the distance between the vehicle ahead and the vehicle behind being wide, the driver's concentration level can be estimated from the relationship between the vehicle speed and the speed limit. Therefore, the driver's concentration level can be estimated while taking into consideration the vehicle behind.

[0012] In addition, the specified vehicle speed is a reference vehicle speed set to reflect the driving tendencies of the driver based on the vehicle's driving history, and the control unit may estimate that the driver's concentration is declining when the vehicle speed of the vehicle is slower than the reference vehicle speed when the vehicle distance to the vehicle in front is wide and the vehicle distance to the vehicle behind is narrow.

[0013] In addition, if it is estimated that the driver's concentration is declining while an automatic driving control that requires monitoring by the driver is being executed during automatic driving of the vehicle, the control unit may suppress intervention of the automatic driving control of the vehicle.

[0014] According to this configuration, even when the driver needs to monitor the vehicle during automatic driving, the driver can be notified that the driver's concentration is decreasing, thereby encouraging the driver to regain his / her concentration. Effect of the Invention

[0015] According to the present invention, the driver's concentration level can be estimated while taking into consideration the vehicles ahead and behind the vehicle when the vehicle is traveling. [Brief description of the drawings]

[0016] [Figure 1] 1 is a block diagram for explaining a vehicle in an embodiment. [Diagram 2] FIG. 10 is a diagram illustrating an estimation flow. [Diagram 3] FIG. 4 is a flowchart showing estimation control. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] Hereinafter, a control device according to an embodiment of the present invention will be specifically described, however, the present invention is not limited to the embodiment described below.

[0018] FIG. 1 is a block diagram for explaining a vehicle in an embodiment. FIG. 2 is a diagram that shows a schematic diagram of an estimation flow. A vehicle 1 estimates a concentration level of a driver 2 while driving. The driver 2 of the vehicle 1 is a target for estimating the concentration level while driving, that is, a target for monitoring emotions while driving. An estimation model generated by machine learning is used to estimate the concentration level. Then, when it is estimated that the concentration level of the driver 2 is decreasing while driving, the vehicle 1 issues a warning to the driver 2. By the vehicle 1 issuing a warning to the driver, the driver can be informed that the concentration level is decreasing and the driver can be prompted to recover his / her concentration.

[0019] As shown in FIG. 1, a vehicle 1 includes a control device 3, a notification device 4, a surrounding sensor 5, a vehicle speed sensor 6, and a navigation system .

[0020] The control device 3 is an electronic control device that controls the vehicle 1. The electronic control device includes a processor and a memory (main storage unit). The processor includes a CPU (Central Processing Unit), a DSP (Digital Signal Processor), an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), etc. The memory includes a RAM (Random Access Memory), a ROM (Read Only Memory), etc. Signals from various sensors mounted on the vehicle 1 are input to the control device 3. The control device 3 executes vehicle control based on the signals input from the various sensors.

[0021] For example, signals from the surrounding sensor 5 and the vehicle speed sensor 6 are input to the control device 3. The surrounding sensor 5 acquires information about three-dimensional objects present around the vehicle 1. The surrounding sensor 5 includes a radar sensor and a camera sensor. The radar sensor is a so-called millimeter wave radar. The camera sensor includes a front camera and a rear camera. The front camera captures an image of the scenery in front of the vehicle 1 and acquires image data. The rear camera captures an image of the scenery behind the vehicle 1 and acquires image data. The vehicle speed sensor 6 detects the speed of the vehicle 1. The surrounding sensor 5 outputs driving information including information about the distance between the front and rear vehicles of the vehicle 1 to the control device 3. The vehicle speed sensor 6 outputs driving information including information about the speed of the vehicle 1 to the control device 3.

[0022] Furthermore, a signal from a navigation system 7 is input to the control device 3. The navigation system 7 outputs driving information to the control device 3, including information regarding the speed limit of the road on which the vehicle 1 is traveling.

[0023] The control device 3 includes a control unit 10 that executes vehicle control using the driving information, and a storage unit 20 that stores a configuration for executing vehicle control.

[0024] While the vehicle 1 is traveling, the control unit 10 executes vehicle control using information input to the control device 3 from the surroundings sensor 5, the vehicle speed sensor 6, and the navigation system 7, as well as information stored in the memory unit 20.

[0025] The vehicle control includes estimation control for estimating the concentration level of the driver 2 while driving, and notification control for notifying the driver 2 that the concentration level of the driver 2 is decreasing while driving. The control unit 10 estimates the concentration level of the driver 2 using an estimation model. The control unit 10 issues a warning to the driver 2 according to the estimation result. The estimation model is a trained model generated by machine learning. When the control unit 10 estimates the concentration level of the driver 2 using the estimation model, the control unit 10 estimates the concentration level of the driver 2 using driving information. That is, the control unit 10 is able to estimate the concentration level of the driver 2 without using biological information of the driver 2.

[0026] The control unit 10 includes a model generation unit 11, a concentration level estimation unit 12, and a vehicle control unit 13.

[0027] The model generation unit 11 generates an estimation model by machine learning. The estimation model is an estimation model that estimates the concentration level of the driver 2, and is a trained model trained by machine learning.

[0028] For example, the model generation unit 11 generates an estimation model by supervised machine learning. In supervised machine learning, a pair of driving information acquired in the past and the concentration level of the driver 2 is used as teacher data. The teacher data uses the driving information of the vehicle 1 as input data and the concentration level of the driver 2 of the vehicle 1 as output data.

[0029] The driving information, which is input data among the teacher data, includes the distance from the vehicle ahead, the distance from the vehicle behind, and the vehicle speed relative to the speed limit. The distance from the vehicle ahead is the distance between the vehicle 1 and the vehicle ahead traveling in front of the vehicle 1. The distance from the vehicle behind is the distance between the vehicle 1 and the vehicle behind the vehicle 1. The speed relative to the speed limit is the current speed of the vehicle 1 relative to the speed limit of the road on which the vehicle 1 is traveling.

[0030] The concentration level of the driver 2, which is output data from the teacher data, is a preset concentration level. The concentration level of the driver 2 is divided into two states: a decreased state indicating that the driver 2's concentration is decreasing, and a normal state indicating that the driver 2's concentration is normal. Therefore, the output data used as the teacher data is one of the decreased state and the normal state.

[0031] As an example, when the input data includes information indicating that the distance between the vehicle and the vehicle ahead is large, information indicating that the vehicle speed is slower than the speed limit, and information indicating that the distance between the vehicle and the vehicle behind is small, the output data is a degraded state indicating that the driver 2's concentration is degraded. In this way, the model generation unit 11 can determine in advance the conditions under which the driver 2's concentration is judged to be degraded, and perform machine learning using teacher data that satisfies the conditions as input data. In other words, the model generation unit 11 can determine in advance the conditions under which the driver 2's concentration is judged to be normal, and perform machine learning using teacher data that satisfies the conditions as input data. Then, the model generation unit 11 stores the generated estimation model in the storage unit 20.

[0032] Moreover, the model generation unit 11 generates an estimation model when the vehicle 1 is stopped. When the vehicle 1 is stopped, the model generation unit 11 generates an estimation model based on the driving history of the vehicle 1. The driving history of the vehicle 1 is information indicating driving results stored in the storage unit 20. The control unit 10 stores driving information acquired while the vehicle 1 is traveling in the storage unit 20 as driving results. Therefore, the control unit 10 can acquire the driving history by referring to the storage unit 20.

[0033] The concentration level estimation unit 12 estimates the concentration level of the driver 2 while driving, using driving information acquired while driving and an estimation model generated before driving. The concentration level estimation unit 12 calculates the distance to the vehicle ahead, the distance to the vehicle behind, and the relationship of the vehicle speed to the speed limit, based on information acquired from the surroundings sensor 5, the vehicle speed sensor 6, and the navigation system 7 while driving. The relationship of the vehicle speed to the speed limit indicates that the current vehicle speed of the vehicle 1 is faster than the speed limit, that the current vehicle speed of the vehicle 1 is slower than the speed limit, or that the current vehicle speed of the vehicle 1 is the same as the speed limit. The concentration level estimation unit 12 estimates the concentration level of the driver 2 using this calculation result and the estimation model stored in the storage unit 20. The concentration level estimation unit 12 acquires the estimation model by referring to the storage unit 20.

[0034] As shown in FIG. 2, the concentration level estimation unit 12 outputs the estimation result to the vehicle control unit 13. The estimation result by the concentration level estimation unit 12 includes a result indicating that the driver's concentration is normal and a result indicating that the driver's concentration is declining. The concentration level estimation unit 12 judges whether or not the driver 2's concentration is declining based on the driving information and the estimation model. The concentration level estimation unit 12 performs a process of estimating the concentration level and a process of judging whether or not the concentration is declining. When the concentration level estimation unit 12 judges that the driver 2's concentration is declining, the estimation result output from the concentration level estimation unit 12 to the vehicle control unit 13 includes a judgment result indicating that the driver 2's concentration is declining.

[0035] The vehicle control unit 13 notifies the driver 2 that the concentration of the driver 2 is decreasing according to the estimation result. The vehicle control unit 13 executes notification control. The vehicle control unit 13 controls the notification device 4.

[0036] The notification device 4 is a speaker, a display device, etc. The notification device 4 is an HMI (Human Machine Interface). When the vehicle control unit 13 executes notification control, the notification device 4 outputs a sound and displays an image.

[0037] 3 is a flow chart showing the estimation control, which is repeatedly executed by the control device 3 while the vehicle 1 is traveling.

[0038] The control device 3 acquires driving information (step S1). In the process of step S1, driving information indicating the current state of the vehicle 1 is acquired. The control device 3 acquires the distance from the vehicle ahead and the distance from the vehicle behind based on an input signal from the surroundings sensor 5. The control device 3 also acquires the current vehicle speed of the vehicle 1 based on an input signal from the vehicle speed sensor 6. Furthermore, the control device 3 acquires the speed limit of the road on which the vehicle 1 is traveling based on an input signal from the navigation system 7.

[0039] The control device 3 determines whether the driver 2 is losing concentration (step S2). In step S2, the concentration level of the driver 2 is estimated based on the driving information acquired in step S1 and an estimation model generated in advance. Furthermore, in step S2, it is determined whether the estimated concentration level indicates a loss of concentration of the driver 2. For example, in step S2, the control device 3 determines whether the vehicle speed is slower than the speed limit while the distance between the vehicle ahead is large, and the distance between the vehicle behind is small.

[0040] If it is determined that the concentration of the driver 2 has not decreased (step S2: No), this control routine ends.

[0041] If it is determined that the driver 2's concentration is declining (step S2: Yes), the control device 3 executes notification control as vehicle control (step S3). In step S3, the notification device 4 issues a warning to the driver 2. The notification device 4 outputs a sound or displays an image. When the process of step S3 is performed, this control routine ends.

[0042] As described above, according to the embodiment, the control device 3 can estimate the concentration level of the driver 2 while the vehicle 1 is traveling. Then, when the control device 3 estimates that the concentration of the driver 2 has decreased, the control device 3 executes notification control to inform the driver 2 that the concentration has decreased. This makes it possible to prompt the driver 2 to regain his / her concentration. Therefore, when the driver 2 loses concentration while driving the vehicle 1, the driver 2 can be quickly returned to a concentrated state.

[0043] The method of acquiring the distance between the vehicle ahead and the vehicle behind is not particularly limited. It is not limited to a method of calculating the distance between the vehicles ahead and behind using a front camera and a rear camera. The distance between the vehicle ahead and the vehicle behind may be calculated using a millimeter wave radar. Similarly, the distance between the vehicle ahead and the vehicle behind may be calculated using a millimeter wave radar.

[0044] Also, the method of acquiring the speed limit is not particularly limited. It is not limited to the method of acquiring the speed limit using the navigation system 7. For example, the image data captured by the forward camera can be analyzed to acquire information about the speed limit of the road based on the image of the sign. Alternatively, the control device 3 can receive information about the road by wireless communication with the roadside device. In other words, the information acquired by the road-to-vehicle communication includes information about the speed limit of the road.

[0045] Furthermore, the estimation model does not have to be generated by the vehicle 1. For example, a server or the like installed outside the vehicle 1 may generate the estimation model. That is, the model generation unit 11 may be provided in the server. The vehicle 1 acquires the estimation model through wireless communication with the server. The estimation model acquired from the server is stored in the storage unit 20. In this case, the estimation model may be updated to the latest information by storing the estimation model in the storage unit 20.

[0046] Also, variations of the control device 3 can be constructed.

[0047] The control device 3 of the first modified example is configured to estimate the concentration level of the driver 2 based on the characteristics of the driver 2. The characteristics of the driver 2 are identified by the driving tendency when driving the vehicle 1. The driving tendency includes a tendency to normally drive slowly at a speed slower than the speed limit. When the driver 2 having this characteristic drives at an even slower speed than usual, the control device 3 can determine that the driver 2's concentration is declining.

[0048] Specifically, when the distance between the vehicle 1 and the vehicle ahead is wide but the distance between the vehicle 1 and the vehicle behind is narrow, and the speed of the vehicle 1 is slower than the normal speed, the control device 3 estimates that the driver 2 is losing concentration. The slowness of the vehicle speed is determined not only in relation to the speed limit but also in accordance with the characteristics of the driver 2. The control device 3 uses a reference vehicle speed that is set to reflect the driving tendency of the driver 2 based on the driving history of the vehicle 1.

[0049] For example, in machine learning, the deviation width indicating how much the normal vehicle speed deviates from the speed limit is learned. This allows learning as to whether the driver 2 normally drives slowly or normally drives fast. Input data used in machine learning includes the distance to the vehicle ahead, the assumed current vehicle speed, the normal vehicle speed (reference vehicle speed), and the distance to the vehicle behind.

[0050] Furthermore, the control device 3 of the second modification can estimate the concentration level of the driver 2 assuming automatic driving. For example, the vehicle 1 is a vehicle compatible with automatic driving. It is assumed that the vehicle 1 is currently performing automatic driving control that requires monitoring by the driver 2 during the automatic driving.

[0051] Specifically, the control unit 10 of the second modified example can execute control to suppress intervention of automatic driving control. When automatic driving control that requires monitoring by the driver 2 is being executed, the control unit 10 suppresses intervention of automatic driving control when it determines that the driver 2 has lost concentration. This makes it possible to prompt the driver 2 to regain concentration.

[0052] Furthermore, the control unit 10 can execute air conditioning control to control the air conditioner of the vehicle 1 as vehicle control for restoring the concentration of the driver 2. In the air conditioning control, the air conditioner is controlled to blow cool air to the driver 2, thereby providing a cooling sensation to the driver 2. Alternatively, in the air conditioning control, the air conditioner is controlled to lower the carbon dioxide concentration by ventilation through the introduction of outside air. [Explanation of symbols]

[0053] 1 vehicle 2. Driver 3. Control device 4. Notification device 5. Ambient Sensor 6 Vehicle speed sensor 7 Navigation system 10 Control section 11 Model Generation Unit 12 Concentration degree estimation part 13 Vehicle control unit 20 Memory section

Claims

1. A control device including a control unit for controlling a vehicle, The control unit is While the vehicle is traveling, a concentration level of a driver of the vehicle is estimated based on a vehicle-to-vehicle distance between the vehicle and a leading vehicle traveling in front of the vehicle, a vehicle-to-vehicle distance between the vehicle and a trailing vehicle traveling behind the vehicle, and a relationship between a vehicle speed of the vehicle and a predetermined vehicle speed; Based on the estimation result, a vehicle control is executed to restore the driver's concentration. the predetermined vehicle speed is a speed limit of a road on which the vehicle is traveling, Furthermore, the control unit estimates that the driver's concentration is decreasing when the vehicle speed of the vehicle is slower than the speed limit in a state where the vehicle distance from the front vehicle is large and the vehicle distance from the rear vehicle is small. A control device comprising:

2. A control device having a control unit for controlling a vehicle, The control unit is While the vehicle is traveling, a concentration level of a driver of the vehicle is estimated based on a vehicle-to-vehicle distance between the vehicle and a leading vehicle traveling in front of the vehicle, a vehicle-to-vehicle distance between the vehicle and a trailing vehicle traveling behind the vehicle, and a relationship between a vehicle speed of the vehicle and a predetermined vehicle speed; Based on the estimation result, a vehicle control is executed to restore the driver's concentration. the predetermined vehicle speed is a reference vehicle speed that is set based on a driving history of the vehicle and reflects a driving tendency of the driver, Furthermore, the control unit estimates that the driver's concentration is decreasing when the vehicle speed of the vehicle is slower than the reference vehicle speed in a state where the vehicle distance from the front vehicle is wide and the vehicle distance from the rear vehicle is narrow. A control device comprising:

Images