Vehicle control device, vehicle control method and storage medium

By judging the emotional and driving characteristics parameters of the passenger in an autonomous driving vehicle and calculating the shared control characteristic parameters, the problem of inconsistent driving control caused by the emotional differences of passengers is solved, and coordinated control between vehicles and passenger emotions are achieved. stability.

CN111731280BActive Publication Date: 2024-11-05SUBARU CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010052561.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2019-03-25
Filing Date
2020-01-17
Publication Date
2024-11-05
Estimated Expiration
2040-01-17

AI Technical Summary

Technical Problem

In many autonomous vehicles, differences in driving characteristics and mood of passengers lead to inconsistent driving controls, increasing anxiety and discomfort, and the prior art is difficult to effectively deal with this situation.

Method used

By judging the interacting vehicles during autonomous driving, obtaining and weighting the emotional and driving characteristics parameters of their passengers, calculating common control characteristics parameters, achieving coordinated control between vehicles and ensuring the stability of the passengers' emotions.

Benefits of technology

The optimal autonomous driving control between vehicles is achieved, reducing anxiety and discomfort among passengers, and ensuring consistency and safety of the driving experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111731280B_ABST
    Figure CN111731280B_ABST
Patent Text Reader

Abstract

This invention provides a vehicle control device, a vehicle control method, and a storage medium. Optimal automatic driving is achieved based on the driving characteristics of passengers between vehicles. The provided vehicle driving control system (1000) includes: an interaction determination unit (170) that determines the vehicles interacting during automatic driving; and a vehicle control unit (185) that controls the interacting vehicles based on the emotions of the passengers between the interacting vehicles. With this configuration, optimal automatic driving can be achieved based on the driving characteristics of the passengers between vehicles.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a vehicle control device, a vehicle control method and a storage medium. Background Art

[0002] Conventionally, for example, as described in Patent Documents 1 and 2 listed below, technologies have been proposed for suppressing anxiety and / or discomfort in an autonomous vehicle by reflecting the driving characteristics of passengers (driver, fellow passengers) in driving control.

[0003] In addition, as described in Patent Documents 3 and 4 listed below, a technology is proposed that detects the anxiety of a passenger, determines the main cause of the anxiety, and adjusts the driving control accordingly to reduce the anxiety.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Publication No. 2015-89801

[0007] Patent Document 2: International Publication No. 2017 / 057060

[0008] Patent Document 3: Japanese Patent Application Publication No. 2016-52881

[0009] Patent Document 4: Japanese Patent Application Publication No. 2017-136922

[0010] Non-patent literature

[0011] Non-patent document 1: Automotive Engineering Society Proceedings Vol. 40, No. 3, May 2009 "Analysis of individual and situational differences in acceleration and steering"

[0012] Non-patent document 2: Automotive Engineering Society Seminar Text, No. 06-05, p. 71-78 Summary of the invention

[0013] Technical issues

[0014] In the case of multiple vehicles driving, in order to make them drive in a coordinated manner, it is desired to drive without causing stress to the passengers. However, even if the vehicles are in the same condition, the driving characteristics and / or emotional levels will be different if the passengers are different. For example, if the distance between the vehicle and the vehicle in front is taken as an example, some people think that 20m is the best and feel scared if the distance between the vehicle and the vehicle is less than 20m, while on the other hand, some people think that 30m is the best and feel scared if the distance between the vehicle and the vehicle is less than 30m. In addition, the distance that makes people feel scared will also change according to the speed of the vehicle, the width of the road, the traffic volume and other conditions.

[0015] In addition, if driving control that reflects driving characteristics is applied to each vehicle, the actions of each vehicle may be inconsistent in certain situations, which may increase anxiety and / or discomfort. For example, if two autonomous vehicles are lined up and waiting for a traffic light, the driver of the vehicle in front is cautious and the driver of the vehicle behind is impatient, and driving control that reflects their characteristics is applied to each vehicle, the acceleration of the vehicle in front and the vehicle behind from a stop is different, and it is conceivable that the driver of the vehicle behind will feel anxious.

[0016] In addition, as described in Patent Documents 3 and 4, in the method of adjusting according to the detected emotion, since the control is performed after the anxiety and / or discomfort is perceived, there is a problem of post-event response.

[0017] Therefore, the present invention is made in view of the above-mentioned problems, and an object of the present invention is to provide a novel and improved vehicle control device, vehicle control method and storage medium that can perform optimal automatic driving corresponding to the driving characteristics of passengers between vehicles.

[0018] Technical Solution

[0019] In order to solve the above-mentioned problem, according to one aspect of the present invention, a vehicle control device is provided, comprising: an interaction determination unit, which determines vehicles that interact with each other during the automatic driving process; a passenger emotion acquisition unit, which acquires the emotions of passengers between vehicles that are determined by the above-mentioned interaction determination unit as interacting with each other; and a vehicle control unit, which controls the interacting vehicles based on the emotions of the above-mentioned passengers.

[0020] The above control may be coordinated control of multiple vehicles.

[0021] In addition, it may also be a control device for a vehicle comprising: a control characteristic parameter acquisition unit, which acquires the control characteristic parameters of the above-mentioned interacting vehicles; and a common control characteristic parameter calculation unit, which calculates the common control characteristic parameters based on the above-mentioned control characteristic parameters of the above-mentioned interacting vehicles, and the above-mentioned vehicle control unit controls the vehicle based on the above-mentioned common control characteristic parameters.

[0022] In addition, the control characteristic parameter may be a parameter representing the driving characteristics of the passenger.

[0023] Furthermore, the vehicle control device may be configured such that the interaction determination unit determines the interacting vehicles based on a preset interaction threshold value, wherein the interaction threshold value is set according to the emotion of the passenger associated with the surrounding environment during manual driving.

[0024] Furthermore, the vehicle control device may include a surrounding environment determination unit that determines a surrounding environment, wherein the interaction determination unit determines the interacting vehicle based on the interaction threshold value corresponding to the surrounding environment determined by the surrounding environment determination unit.

[0025] In addition, the vehicle control device may be as follows: the common control characteristic parameter calculation unit weights the control characteristic parameters of the interacting vehicles based on the emotions of the passengers of the interacting vehicles and calculates the common control characteristic parameters.

[0026] Furthermore, the vehicle control device may be such that the common control characteristic parameter calculation unit calculates the common control characteristic parameter for improving the emotions of the passengers of the interacting vehicles based on the emotions of the passengers of the interacting vehicles.

[0027] Furthermore, the vehicle control device may be configured such that the common control characteristic parameter calculation unit makes the common control characteristic parameter close to the control characteristic parameter of a vehicle having a lower emotion level among the interacting vehicles.

[0028] In addition, the vehicle control device may also be as follows: a passenger emotion estimating unit is provided for estimating the passenger's emotion, the passenger emotion estimating unit estimates the passenger's emotion before and after the vehicle control reflecting the common control characteristic parameters, and the common control characteristic parameter calculation unit calculates the common control characteristic parameters based on the estimated emotion so that the passenger's emotion does not deteriorate before and after the vehicle control.

[0029] Furthermore, the vehicle control device may be such that the common control characteristic parameter calculation unit calculates the common control characteristic parameter by weighting based on the driving safety levels of the passengers of the interacting vehicles.

[0030] Alternatively, the vehicle control device may calculate the control characteristic parameter based on the driving characteristics of the passenger during manual driving.

[0031] In addition, it may also be a control device for the following vehicle: the above-mentioned control characteristic parameters are pre-stored in a database corresponding to the driving characteristics of the passenger during manual driving and the surrounding environment during manual driving, and the above-mentioned control characteristic parameter acquisition unit obtains the above-mentioned control characteristic parameters corresponding to the surrounding environment based on the surrounding environment when it is judged as the above-mentioned interacting vehicle.

[0032] In addition, in order to solve the above-mentioned problem, according to another aspect of the present invention, a vehicle control method is provided, comprising the following steps: determining vehicles that interact with each other during the automatic driving process; and controlling the interacting vehicles based on the emotions of passengers in the interacting vehicles.

[0033] In addition, in order to solve the above-mentioned problem, according to another aspect of the present invention, a program is provided for causing a computer to function as: a unit for judging vehicles that interact with each other during automatic driving; and a unit for controlling vehicles that interact with each other based on the emotions of passengers in the vehicles that interact with each other.

[0034] In addition, in order to solve the above-mentioned problem, according to another aspect of the present invention, a vehicle control device is provided, comprising: a control characteristic parameter acquisition unit, which acquires control characteristic parameters of multiple vehicles during automatic driving; a common control characteristic parameter calculation unit, which weights the control characteristic parameters of the multiple vehicles based on the emotions of the passengers of the multiple vehicles and calculates the common control characteristic parameters; and a vehicle control unit, which controls the vehicle based on the common control characteristic parameters.

[0035] In addition, in order to solve the above-mentioned problem, according to another aspect of the present invention, a vehicle control method is provided, comprising the following steps: obtaining control characteristic parameters of multiple vehicles during the automatic driving process; weighting the control characteristic parameters of the multiple vehicles based on the emotions of the passengers of the multiple vehicles, and calculating common control characteristic parameters; and controlling the vehicle based on the common control characteristic parameters.

[0036] In addition, in order to solve the above-mentioned problem, according to another aspect of the present invention, a storage medium is provided, storing a program for causing a computer to function as the following unit: a unit for acquiring control characteristic parameters of multiple vehicles; a unit for calculating common control characteristic parameters based on the above-mentioned control characteristic parameters of the above-mentioned multiple vehicles and weighting them based on the emotions of the passengers of the above-mentioned multiple vehicles; and a unit for controlling the above-mentioned multiple vehicles based on the above-mentioned common control characteristic parameters.

[0037] Technical Effects

[0038] According to the present invention, it is possible to perform optimal automatic driving in accordance with the driving characteristics of passengers between vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a schematic diagram showing a vehicle driving control system and its peripheral configuration according to an embodiment of the present invention.

[0040] Figure 2 : is a flowchart showing the processing performed by the vehicle travel control system.

[0041] Figure 3 : is a flowchart showing the processing performed by the vehicle travel control system.

[0042] Figure 4 : is a flowchart showing the processing performed by the vehicle travel control system.

[0043] Figure 5 is a schematic diagram showing a method for determining an interaction threshold.

[0044] Figure 6 is a schematic diagram showing a method of determining whether vehicles can interact with each other.

[0045] Figure 7 Schematic diagram showing the control characteristic parameters before and after the change.

[0046] Explanation of symbols

[0047] 100 devices

[0048] 160 Passenger Emotion Acquisition Department

[0049] 170 Interaction Judgment Department

[0050] 175 Control characteristic parameter acquisition unit

[0051] 180 Average control characteristic parameter calculation unit

[0052] 185 Vehicle Control Department

[0053] 1000 Vehicle driving control system DETAILED DESCRIPTION

[0054] The following is a reference to the attached Figure 1 It should be noted that in this specification and the drawings, components having substantially the same functional configuration are denoted by the same reference numerals to omit repeated description.

[0055] In this embodiment, for each vehicle under driving control reflecting driving characteristics, when these vehicles are in a position of interaction, by weighted averaging (weighting) the parameters (control characteristic parameters) that give characteristics to driving control, an average control characteristic parameter is produced, and driving control reflecting the parameter is applied to each vehicle, thereby achieving coordinated driving. It should be noted that "interaction" refers to a situation where each vehicle is affected by each other and causes one vehicle to perform driving control that deviates from the driving characteristics intended by the driver. In addition, "driving characteristics" are driving characteristics intended by the driver, and are driving characteristics achieved by acceleration, braking, steering, etc. performed by the driver. For example, in the case where the front and rear vehicles follow each other, or in the case where there are vehicles at a close distance to the extent that there is a possibility of collision when changing lanes, etc., due to interaction, one vehicle deviates from the driving characteristics intended by the driver. For example, if starting from the above-mentioned stop state, the front vehicle relatively increases acceleration and the rear vehicle reduces acceleration.

[0056] In addition, when making the above-mentioned average control characteristic parameter, weighting that reflects the emotional state of the passengers in each vehicle may also be performed. Specifically, the emotional state is grasped based on biological information, etc., and weighting is performed in a manner that the emotional state between the vehicles is improved. For example, when starting from the above-mentioned parking state, if the emotional state of the passengers in the rear vehicle is bad and the emotional state of the passengers in the front vehicle is good, weighting is performed with emphasis on the passengers in the rear vehicle. If the emotional state can be quantified, weighting can be performed based on the numerical value.

[0057] When creating the average control characteristic parameter, weighting may be performed based on the driving safety level of each vehicle occupant, that is, the driving characteristics of a driver who drives safely may be prioritized.

[0058] This technology can be applied not only to autonomous vehicles that reflect driving characteristics. For example, in the case of autonomous driving that does not reflect driving characteristics, the parameters that determine its driving control are also set by the manufacturer. Since these parameters are different for each manufacturer, this technology can be applied.

[0059] Figure 11 is a schematic diagram showing a vehicle driving control system 1000 and its peripheral configuration according to an embodiment of the present invention. The vehicle driving control system (vehicle control device) 1000 is configured to include: a driving control mode switching unit 100, a surrounding environment determination unit 110, a driving operation learning unit 120, an interaction threshold determination unit 130, a control feature parameter database (DB) 140, an interaction threshold database (DB) 150, a passenger emotion acquisition unit 160, an interaction determination unit 170, a control feature parameter acquisition unit 175, an average control feature parameter calculation unit (common control feature parameter calculation unit) 180, and a vehicle control unit 185. It should be noted that each component of the vehicle driving control system 1000 can be configured by a circuit (hardware) or a central processing unit such as a CPU and a program (software) for making it function.

[0060] In addition, the vehicle driving control system 1000 is connected to a passenger recognition sensor 200, a control setting interface 300, an ambient environment sensor 400, a vehicle operation sensor 500, a navigation device 600, a biosensor 700, a communication device 800, and a driving actuator 900. The vehicle driving control system 1000 can communicate with an external server 2000 via the communication device 800.

[0061] The passenger recognition sensor 200 is composed of, for example, a camera that takes a picture of the passenger, and recognizes the passenger based on the passenger's facial image. The control setting interface 300 is an interface for setting the driving control mode. In addition, the passenger recognition sensor 200 includes a microphone that captures the passenger's voice.

[0062] The surrounding environment sensor 400 is composed of a stereo camera, a monocular camera, a millimeter wave radar, an infrared sensor, etc., and detects the position and speed of people and / or vehicles around the vehicle. When the surrounding environment sensor 400 is composed of a stereo camera, the stereo camera is composed of a pair of left and right cameras including a CCD sensor, a CMOS sensor, etc., and captures the external environment outside the vehicle, and sends the captured image information to the vehicle driving control system 1000. As an example, the stereo camera is composed of a color camera that can obtain color information and is installed on the upper part of the front windshield of the vehicle.

[0063] The vehicle operation sensor 500 is a sensor that detects vehicle operation quantities such as the accelerator opening, the brake pedal depression amount, and the steering wheel steering angle, and detects parameters of the driving state that represent the result of the vehicle operation, such as the vehicle speed, acceleration, and yaw rate. The vehicle operation sensor 500 may also be a sensor that acquires information that is communicated using a CAN (Controller Area Network) in the vehicle.

[0064] The navigation device 600 searches for a route from the current location to the destination based on the map information. Therefore, the navigation device 600 can obtain the current location of the vehicle through the global positioning system (GPS) or the like. In addition, the navigation device 600 stores the route for the vehicle to travel to the current location.

[0065] The biosensor 700 is a sensor that detects brain waves and / or cerebral blood flow, blood pressure, sweating, electrocardiogram, heart rate, eye movement, pupil diameter, etc. The emotions of the passenger are estimated based on such information detected by the biosensor 700 and the facial information of the passenger recognized by the passenger recognition sensor 200.

[0066] The communication device 800 communicates with the outside of the vehicle and sends and receives various information. In particular, the communication device 800 communicates with an external server 2000 and / or performs inter-vehicle communication with other vehicles. The vehicle driving control system 1000 shares information with other vehicles through communication via the server 2000 or inter-vehicle communication.

[0067] Figure 2 to Figure 4 1 is a flowchart showing the processing performed in the vehicle driving control system 1000. First, in step S10, the system is started. In the next step S12, the passenger recognition sensor 200 recognizes the passenger. As the recognition method, for example, a method of distinguishing based on a facial image such as a driver monitoring system (DMS) using a camera is used. Alternatively, it may be a form of answering a question from the vehicle driving control system 1000 using a speaker using a microphone, etc.

[0068] In the next step S14, the driving control mode is set. In the case of a vehicle capable of automatic driving, two driving control modes are foreseeable: a manual driving mode and an automatic driving mode. When the passenger gets in the vehicle and starts the vehicle driving control system 1000, one of the manual driving mode and the automatic driving mode is selected. In addition, switching sometimes occurs during driving. The driving control mode is set by the passenger's input to the control setting interface 300 such as a touch screen, and the driving control mode switching unit 100 performs mode switching.

[0069] In the next step S16, it is determined whether the automatic driving mode is in progress. If the automatic driving mode is in progress, the automatic driving mode is entered. Figure 4 Step S54. When the vehicle is operated by manual driving, it becomes an opportunity to learn the driving operation characteristics of the driving operator (driver). The learning stage performed after step S54 will be described below.

[0070] In step S54, the emotions of the passengers are acquired. When the vehicle starts driving by manual driving or when the automatic driving mode is switched to manual driving, the emotions of the passengers (driver and fellow passengers) are acquired. The reason for acquiring emotions at this stage is that by grasping the initial emotions when driving starts or when the driving mode is changed, the emotional changes in the subsequent manual mode (for example, whether it changes from negative to positive) can be grasped in chronological order.

[0071] The passenger emotion acquisition unit 160 acquires the passenger emotion based on the information acquired by the biosensor 700 and the information recognized by the passenger recognition sensor 200. It should be noted that the passenger emotion acquisition unit 160 can also acquire the passenger emotion from a device such as a smart phone. As the information detected by these sensors, brain waves, cerebral blood flow, blood pressure, sweating, electrocardiogram, heart rate, eye movement, pupil diameter, movement of sight and / or the number of blinks can be listed, and these can be used to estimate the passenger emotion. As an example, when the blood pressure and / or heart rate increase compared to the initial value, it can be estimated that the passenger is excited and the emotion is damaged. In addition, when the amount of sweat increases compared to the initial value, it can be estimated that the passenger's emotion is damaged. In addition, the passenger's emotion can also be estimated by acquiring the passenger's voice content and voice volume, and analyzing the voice content and / or voice volume. For example, when a wording that is not usually used is used, or the voice volume is louder than usual, it can be estimated that the passenger's emotion is damaged.

[0072] In the next step S56, the vehicle is manually operated by the driver and starts to travel. In the next step S58, the surrounding environment is identified and grasped by the surrounding environment sensor 400. For example, the surrounding environment judgment unit 110 identifies and grasps the surrounding environment information by using the information obtained from the front and rear cameras and / or the front and rear laser radars as the surrounding environment sensor 400, and the position information, map information, etc. obtained from the navigation device 600. Specifically, the surrounding environment judgment unit 110 can generate and obtain the distance information to the object from the deviation amount of the corresponding position using the principle of triangulation for the left and right sets of stereo images captured by the left and right sets of cameras constituting the stereo camera of the surrounding environment sensor 400. At the same time, the surrounding environment judgment unit 110 can obtain the position information of the subject based on the image information. In addition, the surrounding environment judgment unit 110 performs a known grouping process on the distance information generated using the principle of triangulation, and compares the distance information obtained by the grouping process with the pre-set three-dimensional solid object data, thereby detecting the solid object data and / or white line data, etc. Thus, the surrounding environment judgment unit 110 can also identify people, other vehicles, temporary parking signs, stop lines, ETC gantries, etc. In addition, the surrounding environment judgment unit 110 can use the distance information between people and other vehicles generated according to the principle of triangulation to calculate the change in distance and relative speed between people and / or other vehicles. The change in distance can be obtained by accumulating the distance between frame images detected per unit time. In addition, the relative speed can be obtained by dividing the distance detected per unit time by the unit time. It should be noted that the method described in the above-mentioned patent document 1 can also be appropriately applied to the recognition of the surrounding environment.

[0073] In the next step S60, the operation performed by the driver in the recognized surrounding environment during the driving of the vehicle is detected via the vehicle operation sensor 500 (accelerator opening sensor, steering angle sensor, etc.), and the driving operation learning unit 120 performs learning. The learning result is stored in the control characteristic parameter DB 140 as the control characteristic parameter of the driver.

[0074] The following describes a method for extracting the driver's driving operation characteristics based on the combination of the detected driving operation and the surrounding environment. Although there are various previous studies on individual driving operations that vary depending on the situation, this description is based on the driving operation model shown in the above-mentioned non-patent document 1. The model is exemplified by the model when accelerating from a start and when driving on a curve.

[0075] According to Non-Patent Document 1, when accelerating from a stopped state (or a low-speed running state), the length of the period from the start of acceleration to the end of acceleration (until the target speed is reached) is t obj It is represented by the following formula (1).

[0076] [Mathematical formula 1]

[0077]

[0078] Here, v obj is the target speed after acceleration, which is subject to personal preference and / or road shape, speed limit, speed of the vehicle in front / around, etc. Therefore, it is collected for each situation before learning the driving operation during manual driving, and is assumed to be known here. In addition, v o is the vehicle speed at the start of acceleration, and a is the average acceleration. In order to further express the transient response of the vehicle speed, the vehicle speed and feedback gain during acceleration are changed according to the following equations (2) and (3).

[0079] [Mathematical formula 2]

[0080]

[0081]

[0082] Here, k is a parameter representing the difference in transient response of acceleration and has a value in the range of (0, 1). Thus, by applying equations (2) and (3) to the time series data of vehicle speed during manual driving and performing parameter fitting, it is possible to obtain v representing the individual characteristics of acceleration under certain conditions. obj 、k. v obj , k are stored in the control feature parameter DB 140 as control feature parameters together with the surrounding environment information, vehicle operation information, passenger emotions and other information corresponding to that moment.

[0083] In addition, according to non-patent document 1, a steering model including the front and rear speed adjustment of the vehicle when traveling on a curve is proposed. That is, it is a model in which the driver steers according to the position error between the forward gaze point and the target track when turning. Here, the distance L to the forward gaze point is calculated based on the driver's inherent prediction time T p and the vehicle speed v during the turn are expressed by the following equation (4).

[0084] [Mathematical formula 3]

[0085] L=T p v (4)

[0086] In addition, regarding the speed v during the turn, it is assumed that it depends on the curve curvature c and the allowable lateral acceleration a y , and before learning the driving operation during manual driving, it is collected for each surrounding condition such as the curvature of the curve, and is assumed to be known here. The steering gain G is represented by the following equation (5).

[0087] [Formula 4]

[0088]

[0089] Here, n represents the total transmission ratio of the steering system, and l represents the distance between the front and rear axles. By applying equation (5) to the foresight and predictive control model shown in non-patent document 2 and performing parameter fitting, v, T, and t representing the driver's personal characteristics when driving on a curve are obtained. p . v、T p As control feature parameters, they are stored in the control feature parameter DB 140 together with the corresponding surrounding environment information.

[0090] In addition to the above, various models are proposed for various conditions. In this way, the driver's inherent characteristics (feature quantities) can be extracted for driving operations under various conditions. The extracted characteristics are stored in the control characteristic parameter DB 140. It should be noted that a method of functionalizing the driving characteristics themselves as shown in Patent Document 2 can also be used. In this case, the subsequent averaging operation is based on the function.

[0091] It should be noted that the obtained control characteristic parameter is uploaded to the server 2000 via the communication device 800 in order to be applied to the calculation of the average control characteristic parameter described later.

[0092] In the next step S62, after the driving characteristics (control characteristic parameters associated with individuals) are extracted, the passenger emotions are obtained. This has two purposes: first, it is to determine the interaction with other vehicles (described later), and second, it is to obtain how the passenger (driver / passenger) feels about manual operation.

[0093] Regarding the above two purposes, if the driver's mood has deteriorated, the possibility of performing the operation regardless of his or her own intention can be considered. For example, it can be considered that the brake pedal is stepped on urgently in response to a sudden lateral intrusion. Although such operations contain personal characteristics, it is not necessary to actively reproduce them, so they do not need to be reflected in the automatic driving mode (only when a safer and more reliable method can be provided on the vehicle system side).

[0094] In addition, when the mood of the passenger has deteriorated, it can be considered that the passenger does not like the driver's driving operation characteristics. In addition, when the mood of the passenger has improved, it can be considered that the passenger accepts the driver's driving operation characteristics in good faith. Therefore, in the case where the passenger does not drive and does not have the above-mentioned control characteristic parameters, the passenger's emotional response to the driver's driving characteristics can also be used as the passenger's driving characteristics (using the driver's pleasing parameters as the passenger's control characteristic parameters).

[0095] In the next step S64, based on the passenger's emotion during manual driving, the interaction threshold determination unit 130 determines the interaction threshold with other vehicles. Here, the interaction with other vehicles refers to a state where the vehicle control needs to be changed due to approaching other vehicles when the vehicle is traveling in the automatic driving mode reflecting the driving characteristics.

[0096] For example, suppose that the vehicle is cruising at a speed of 60 km / h on a straight road with one lane on one side through automatic driving, and the passengers of the vehicle prefer 60 km / h. There is another vehicle in front that is traveling at 40 km / h, and the passengers of the other vehicle prefer 40 km / h. As the distance between the two vehicles gradually closes, a collision will occur if the two vehicles continue to travel without changing control. Therefore, the speed is changed when a certain distance is reached to avoid a collision. If the deceleration of the following vehicle is taken into account, the passengers will feel fear, anxiety and / or discomfort depending on the distance (time) when deceleration starts. For example, it is suitable for the situation where deceleration starts from a closer distance to the vehicle in front than the passengers imagine. In such a case, it is necessary to start decelerating earlier.

[0097] Since the same situation also occurs during manual driving, the characteristics of the passengers are understood at that time. That is, if the above-mentioned follow-up driving example is performed during manual driving, the passengers may feel fear, anxiety and / or discomfort depending on the driver's operation, so by repeatedly experiencing various situations, it is possible to learn a distance that does not make each passenger feel fear, etc. Therefore, a value obtained by providing a margin for the distance associated with the information obtained from the emotion is used as the appropriate control change time and as the interaction threshold. It should be noted that the value of the interaction threshold can be set to a predetermined initial value when the vehicle leaves the factory, or it can be set to a constant value without changing according to the experience of manual driving.

[0098] Figure 5 is a schematic diagram showing a method for determining an interaction threshold. Here, the value related to the interaction is set to the distance to the preceding vehicle (interaction object). Figure 5 , the relationship between the distance to the preceding vehicle (horizontal axis) and the anxiety level of the passenger (vertical axis) as the interaction object is shown. Figure 5 As shown in FIG. 1 , the smaller the distance to the interaction object becomes, the greater the anxiety level of the passenger becomes. By obtaining the anxiety level of the passenger associated with the distance to the preceding vehicle during manual driving, it is known that Figure 5 The interaction threshold can be set to a value obtained by adding a margin to the distance to the fear-generating location. The determined interaction threshold is stored in the interaction threshold DB 150. In addition, the interaction threshold can be shared with other vehicles via the communication device 800.

[0099] It should be noted that in the above example, the vehicle distance is illustrated as a parameter for determining the interaction, but various parameters other than the vehicle distance can also be used. For example, the anxiety level of the passengers varies depending on the main factors such as the width of the road, the number of vehicles parked on the roadside, the number of pedestrians (pedestrians coming and going), the curvature of the curve, the road surface condition (dry, wet), the weather, the time of day, etc. In addition, the anxiety level of the passengers varies depending on the vehicle operation during manual driving. When specifying the interaction threshold, the interaction threshold is specified in association with these main factors (surrounding environment information, vehicle operation information). In the interaction threshold DB150, the interaction threshold associated with the surrounding environment information and the vehicle operation information is stored.

[0100] It should be noted that the objects of interaction are several vehicles in front and behind on the same lane and several vehicles in the left and right lanes (including the same direction / opposite direction). For example, vehicles within 20m in front and behind and 5m in the left and right are the objects.

[0101] According to the above description, the driving characteristics (control characteristic parameters) under a certain condition and the passenger emotions and interaction thresholds associated with the characteristics can be obtained. In the next step S66, the vehicle driving control system 1000 registers them in the control characteristic parameter DB 140 and the interaction threshold DB 150, and applies them during automatic driving.

[0102] It should be noted that the control characteristic parameters, passenger emotions, and interaction thresholds are expected to reflect the essential characteristics of the driver more as learning is repeated, and therefore they may be updated by taking cumulative averages or the like.

[0103] The learning during manual driving is implemented by the above-described processing. This processing ends when the driving control mode is switched to the automatic driving mode in the judgment of step S68 (the processing content is transferred to Figure 2 Alternatively, the process ends when the vehicle system is transferred to a stopped state in the judgment of step S70.

[0104] Next, the driving characteristics reflection stage during automatic driving is described. When the vehicle is set to the automatic driving mode, the vehicle driving control is performed according to the control characteristic parameters obtained during manual driving. Below, the technology that can coordinate and control multiple vehicles in the automatic driving mode when these vehicles are in positions where they may interact with each other is described.

[0105] First, in Figure 2If it is determined in step S16 that the automatic driving mode is in progress, the process proceeds to step S18. In step S18, the route is set. By setting the destination using the navigation device 600, a plurality of travel routes are presented from the perspectives of distance and / or required time, passenger intention, traffic conditions, etc. A route is set from a plurality of candidate routes based on the passenger's choice or the best choice made by the system.

[0106] Although the information of the driving path is modified according to the change of the situation, the vehicle knows the path from the current position to the end position and drives. The path information is used when judging the interaction between vehicles (described later). Therefore, the path information is sent to the server 2000 and sent to other vehicles via the server 2000. In addition, the path information is sent to other vehicles through vehicle-to-vehicle communication. Thus, each vehicle shares each path information.

[0107] In the next step S20, the emotions of the passengers are acquired before the start of driving. By acquiring the emotions before driving, the initial value of the emotions at the start of driving can be grasped. In the next step S22, driving is started by automatic driving control that reflects the characteristics of the passengers. In the next step S24, the emotions of the passengers are acquired by using the Figure 4 The same method as step S56 is used to identify and grasp the surrounding environment.

[0108] In the next step S26, driving control corresponding to the driving characteristics and emotions is performed. Based on the learning during manual driving, the driving characteristics under a certain condition and the passenger emotions associated therewith are obtained. During automatic driving, driving control in which the passenger emotions change to good (or neutral) is implemented based on the driving operation model and the control characteristic parameters. As described above, the control characteristic parameters are associated with the surrounding environment information, vehicle operation information, passenger emotions and other information and stored in the control characteristic parameter DB140. Therefore, it is possible to extract the control characteristic parameters with the best emotions from the control characteristic parameter DB140 for the surrounding environment identified in step S24. Then, by using the extracted control characteristic parameters for automatic driving, the passenger emotions can be made good.

[0109] In the next step S28, surrounding vehicles are detected, and then it is determined whether there is any interaction with other autonomous driving vehicles during the execution of the autonomous driving mode.

[0110] Specifically, first, by referring to the route information of each vehicle, it is determined whether the vehicles can interact with each other. Figure 6 is a schematic diagram showing a method of determining whether vehicles can interact with each other. Figure 6 In the figure, when there is a left fork in the middle of a straight road and vehicles A and B are traveling, the situation of interaction is shown in the left figure, and the situation of non-interaction is shown in the right figure.

[0111] For example, consider a situation where the vehicle A is approaching the vehicle ahead (vehicle B) at a faster speed in the same lane. Figure 6 As shown in the left figure, when the paths of the two vehicles are the same, it can be predicted that the inter-vehicle distance will reach the interaction threshold sooner or later. In such a state, the preceding vehicle (vehicle B) is detected as a vehicle (surrounding vehicle) that can interact with the vehicle (vehicle A).

[0112] On the other hand, Figure 6 As shown in the right figure of , when the paths of vehicles A and B are different and vehicle B chooses a path that branches and bends to the left, the inter-vehicle distance will not reach the interaction threshold. In this state, the leading vehicle (vehicle B) is detected as a vehicle (surrounding vehicle) that does not interact with the vehicle (vehicle A).

[0113] Here, the condition for judging whether the two vehicles can interact is set as whether they are close enough to reach the interaction distance after t seconds. This can be judged by sharing the information of the two vehicles, and referring to the relative speed of the two vehicles and the relative distance on the path. t can be set individually by the user or by the manufacturer in advance. It should be noted that if the distance between the vehicles is above the interaction threshold after t seconds, it is judged that there is no interaction. The information of the two vehicles (vehicle speed, acceleration and / or relative distance on the path, etc.) is shared through communication via the server 2000 or vehicle-to-vehicle communication.

[0114] In the next step S30, it is determined whether there is a possibility of interaction. If there is a possibility of interaction, the process proceeds to step S40. Figure 3 On the other hand, if there is no possibility of interaction, return to step S24.

[0115] If the mutual determination in step S32 is performed for all other vehicles, the processing load for the mutual determination may increase. On the other hand, the processing load can be greatly reduced by performing the mutual determination only for vehicles that may interact based on the path information of each vehicle.

[0116] exist Figure 3In step S32, the interaction judgment unit 170 uses the interaction threshold determined during manual driving to perform interaction judgment. At this time, since the interaction threshold associated with the surrounding environment information is stored in the interaction threshold DB 150, the corresponding interaction threshold is applied based on the information of the surrounding environment obtained in step S28. As a result, it is possible to transfer to the coordinated control of the interacting vehicles based on the surrounding environment information without making the passengers feel anxious. Regarding the interaction judgment, if the distance between the host vehicle and the preceding vehicle is used as an example, in step S34, when the distance between the host vehicle and the preceding vehicle is less than the interaction threshold, the next step S36 is entered. On the other hand, when the distance between the host vehicle and the preceding vehicle is not less than the interaction threshold, the process returns to step S32 and continues to use the interaction threshold for judgment. It should be noted that when the mutual judgment thresholds are different between the host vehicle and the preceding vehicle, a threshold that is easier to make a mutual judgment can be used. For example, when the mutual judgment threshold of the host vehicle is 30m for the inter-vehicle distance and the mutual judgment threshold of the preceding vehicle is 20m for the inter-vehicle distance, the mutual judgment threshold of the host vehicle that is easier to make a mutual judgment can be used for the interaction judgment. In this case, if the interaction determination condition of the own vehicle is satisfied, by sending this message to the other vehicle, the interaction determination condition is also satisfied for the other vehicle, and the two vehicles start coordinated control.

[0117] In step S36, before the control parameters are changed according to the coordinated control described later, the emotions (levels) of the passengers are obtained to understand the emotions of the passengers. The purpose of obtaining the emotions is to: (1) set the limiting feedback for parameter changes; (2) implement the weighted calculation of vehicle control parameters according to the change of emotion level in the following steps. Both are described later.

[0118] In the next step S38, average control of multiple interacting vehicles is implemented. Specifically, the control characteristic parameter acquisition unit 175 acquires the control characteristic parameters of multiple interacting vehicles (including the vehicle) via the communication device 800, and the average control characteristic parameter calculation unit 180 calculates the average control characteristic parameters and applies them to these multiple vehicles. Then, each interacting vehicle shares the average control characteristic parameters among the vehicles. The following method can be applied as a sharing method: each vehicle obtains the average control characteristic parameters uploaded to the server 2000, communicates with each other using vehicle-to-vehicle communication, and the like. Based on the average control characteristic parameters, the vehicle control unit 185 controls the driving actuator 900 of each interacting vehicle. As a result, vehicle control is performed between multiple interacting vehicles using the shared average control characteristic parameters (shared control characteristic parameters).

[0119] The control parameters are not only parameters that reflect the driving characteristics of the driver, but can also be values ​​set by the manufacturer, etc. After being totaled, the average value of these control characteristic parameters is calculated. The simplest method is to take the arithmetic mean (additive mean).

[0120] Based on the emotions before the control characteristic parameters are changed, weighting can also be performed on the vehicle side with an emphasis on passengers with poor emotional states. For example, consider the following vehicle: it is equipped with a system that can set five levels of emotions, positive and negative, and can perform automatic driving that reflects driving characteristics. In a situation where the two vehicles are lined up and start from a stopped state, the emotional level of the passengers in the rear vehicle is set to negative 3, and the emotional level of the passengers in the front vehicle is set to positive 2. At this time, if positive 5 (the optimal emotional level) is used as the benchmark, the emotional levels of the two vehicles are represented as 8 (=|-3-5|) for the rear vehicle and 3 (=|2-5|) for the front vehicle. Based on this, for example, when weighted averaging is performed, the average control parameters during acceleration can be calculated as shown in the following formulas (6) and (7).

[0121] [Formula 5]

[0122]

[0123]

[0124] Among them, v obj,front is the target vehicle speed after acceleration preferred by the front vehicle passengers, v obj,rear is the target vehicle speed after acceleration preferred by the rear vehicle passengers, k front is the transient response parameter of the front vehicle occupant, k rear are the transient response parameters of the rear vehicle passengers. These values ​​are the values ​​obtained in advance as the control characteristic parameters by the above-mentioned equations (2) and (3). As a result, the average control parameter v close to the control characteristic parameter of the rear vehicle passengers can be obtained. obj,ave , k ave .

[0125] Figure 7 2 is a schematic diagram showing the control characteristic parameters before and after the change in the above example. Consider a situation where the host vehicle (vehicle A) approaches from behind the preceding vehicle (vehicle B) at a faster speed. Before the control parameter is changed, the target vehicle speed of vehicle A is v obj,rear , the target speed of vehicle B is v obj,front In addition, the transient response parameter of vehicle A is k rear , the transient response parameter of vehicle B is k front After the control parameters are changed, the target speeds of vehicle A and vehicle B are both v obj,ave , the transient response parameters are kave Thereby, the mood of all passengers of vehicle A and vehicle B can be improved.

[0126] In addition, when driving on a curve, when the two vehicles are at an interaction distance and are in the same emotional state as mentioned above (the emotional level of the passengers in the rear vehicle is negative 3, and the emotional level of the passengers in the front vehicle is positive 2), when performing, for example, weighted averaging, the average control parameters are calculated using the following equations (8) and (9).

[0127] [Mathematical formula 6]

[0128]

[0129]

[0130] Among them, v front is the target speed of the passengers in the front vehicle, v rear is the target speed of the rear vehicle passengers, T p,front is the predicted time of the passengers in the previous car, T p,rear is the predicted time of the rear car passengers. These values ​​are the values ​​obtained in advance as the control characteristic parameters by the above equations (4) and (5). The result is the average control parameter v close to the control characteristic parameter of the rear car passengers. ave , T p,ave .

[0131] When there are multiple passengers, it is possible to set which passenger is the target. For example, there is a method of setting the passenger sitting in the driver's seat as the target before driving. Or there is also a method of setting the person with the worst emotional level at the time as the target. Or it can be the average value of all passengers in the vehicle.

[0132] As a weighting method, in addition to the emotions of the passengers, for example, the safe driving level of the passengers can be used as a variable. As a method for calculating the driving safety level, a method based on the number and frequency of traffic accidents and / or violations, or the usual (manual) driving operation, the manufacturer, etc., can be considered to calculate. In the above example, the weight of the rear vehicle passengers is increased, and the average control feature parameters close to the emotions of the rear vehicle passengers are set, but when the safe driving level is used, the average control feature parameters close to the passengers with a high safe driving level are set.

[0133] Then, the calculated average control parameter is applied to the plurality of vehicles interacting with each other. As a result, the control parameters between the vehicles interacting with each other become the same. Then, based on the average control parameter, the various driving actuators 900 of the vehicles interacting with each other are driven. Since the control parameters of the vehicles interacting with each other are the same, coordinated driving control can be performed.

[0134] When the average control characteristic parameter is reflected to each interacting vehicle, there is a possibility that the passengers feel uncomfortable due to the change of control. Therefore, when the change is made, the meaning can be notified by voice or displayed on the display.

[0135] In the next step S40, in each interacting vehicle, the emotional state of the passengers is obtained after the control parameters are changed.

[0136] In the next step S42, it is determined whether the mood has improved. If the mood of the passenger has improved, the process proceeds to the next step S44. If the mood has not improved (has deteriorated), the process returns to step S38 and the average control parameter is calculated again according to the emotional state.

[0137] In step S42, the judgment of the improvement of the passenger's mood is performed on the passenger who is the object when calculating the average control parameter. Alternatively, the judgment of the improvement of the mood may be performed on the passenger with the worst mood level. In addition, the judgment of the improvement of the mood may be performed based on the average value of the mood levels of all passengers in the vehicle.

[0138] Regarding the judgment of mood improvement, for example, a situation may occur where the mood of passenger a in vehicle A improves while the mood of passenger b in vehicle B deteriorates. In such a case, if the mood of all interacting vehicles improves, it is considered to be improved. For example, in the above-mentioned following driving where the mood level of the passengers in the rear vehicle is negative 3 and the mood level of the passengers in the front vehicle is positive 2, it is assumed that after the parameter change, the mood level of the passengers in the rear vehicle is negative 1 and the mood level of the passengers in the front vehicle is positive 2. At this time, if positive 5 is used as the benchmark, the mood levels of the two vehicles are 6 (=|-1-5|) for the rear vehicle and 3 (=|2-5|) for the front vehicle. Before the change: 11 (=8+3), after the change: 9 (=6+3). In this case, it is judged to be improved.

[0139] In the case of the average control parameter corresponding to the safe driving level, no feedback based on the emotional state is performed.

[0140] It should be noted that, when the mood deteriorates significantly during the change of the control parameter, the average control parameter can be regarded as a driving characteristic that the passenger dislikes, and avoids it in subsequent control.

[0141] In step S44, an interaction judgment is performed. From a situation where multiple vehicles interact with each other (for example, a situation where the distance between vehicles is less than the interaction threshold), the situation where there is no interaction is reached during the process of continuing to travel. For example, if two vehicles are traveling side by side in the same lane, but one of the vehicles deviates to another road according to the destination, the interaction disappears.

[0142] As for whether the interaction disappears, it is determined based on the interaction threshold value in the same manner as in step S34. In step S46, if the inter-vehicle distance is greater than the interaction threshold value, the process proceeds to the next step S48, and since the interaction disappears, the control characteristic parameters are restored to the original state. Thus, driving is performed based on the driving operation characteristic parameters of the vehicle passengers. In addition, a notification may be made when the control characteristic parameters are restored to the original state.

[0143] The control during automatic driving is implemented by the above-described processing. In the judgment of step S50, when the driving control mode is switched to the manual driving mode, the processing is terminated (the processing content enters Figure 2 Alternatively, if the vehicle system enters a stopped state in step S52, the processing is terminated.

[0144] It should be noted that in the above description, an example of vehicle control performed using a vehicle driving control system 1000 installed in a vehicle is given, but part or all of the components of the vehicle driving control system 1000 may be installed on an external server (cloud server), and processing such as learning driving operations, acquiring control characteristic parameters, determining interaction thresholds, judging interactions, and calculating average control characteristic parameters may also be performed on the server side.

[0145] As described above, according to this embodiment, automatic driving that reflects the driving characteristics of the passengers can be achieved without interaction, and coordinated driving control can be achieved under interaction, thereby avoiding or suppressing the passengers' frustration, anxiety and / or discomfort.

[0146] Furthermore, since the control parameter adjustment (calculation and application of average control characteristic parameters) is performed at the time point when interaction is determined before the passenger feels negative emotions such as anxiety and / or discomfort, it is possible to prevent the passenger from having negative emotions.

[0147] Furthermore, even if negative emotions cannot be avoided, by understanding the emotions of each vehicle passenger and providing feedback to the average control characteristic parameter generation, adaptive control can be performed according to the emotional state at the time.

[0148] In addition, by reflecting the driving safety level of each vehicle occupant when creating the average control characteristic parameter, safer driving control can be achieved when multiple autonomous driving vehicles interact with each other.

[0149] The preferred embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the relevant examples. It should be clear that a person with ordinary knowledge in the technical field to which the present invention belongs can think of various variations or modifications within the scope of the technical concept described in the claims, and it is understood that these variations or modifications also fall within the technical scope of the present invention.

Claims

1. A vehicle control device, characterized in that: have: an interaction determination unit that determines vehicles that interact with each other during the autonomous driving process; a passenger emotion acquisition unit that acquires emotions of passengers of the vehicles determined to be interacting with each other by the interaction determination unit; a control characteristic parameter acquisition unit, which acquires control characteristic parameters of the interacting vehicles; a common control characteristic parameter calculation unit that weights the control characteristic parameters of the interacting vehicles based on the emotions of the passengers of the interacting vehicles and calculates the common control characteristic parameters; as well as a vehicle control unit that controls the interacting vehicles based on the common control characteristic parameter, When calculating the common control characteristic parameter, weighting is performed with emphasis on the vehicle in which a passenger having a poor emotional state among passengers of the interacting vehicles is riding.

2. The vehicle control device according to claim 1, characterized in that: The control is coordinated control of multiple vehicles.

3. The vehicle control device according to claim 1, characterized in that: The control characteristic parameter is a parameter indicating the driving characteristics of the passenger.

4. The vehicle control device according to claim 1, characterized in that: The interaction determination unit determines the interacting vehicle based on a preset interaction threshold value, wherein the interaction threshold value is set according to the emotion of the passenger associated with the surrounding environment during manual driving.

5. The vehicle control device according to claim 4, characterized in that: The vehicle control device includes a surrounding environment determination unit for determining the surrounding environment. The interaction determination unit determines the interacting vehicle based on the interaction threshold corresponding to the surrounding environment determined by the surrounding environment determination unit.

6. The vehicle control device according to claim 1, characterized in that: The common control characteristic parameter calculation unit calculates the common control characteristic parameter for improving the emotions of the passengers of the interacting vehicles based on the emotions of the passengers of the interacting vehicles.

7. The vehicle control device according to claim 1, characterized in that: The common control characteristic parameter calculation section makes the common control characteristic parameter close to the control characteristic parameter of a vehicle having a worse emotion level among the interacting vehicles.

8. The vehicle control device according to claim 1, characterized in that: The passenger emotion acquisition unit estimates the passenger's emotion before and after the vehicle control reflecting the common control characteristic parameter, The common control characteristic parameter calculation unit calculates the common control characteristic parameter based on the estimated emotion so that the emotion of the passenger does not deteriorate before and after the vehicle control.

9. The vehicle control device according to claim 1, characterized in that: The common control characteristic parameter calculation unit calculates the common control characteristic parameter by performing weighting based on the driving safety levels of the passengers of the interacting vehicles.

10. The vehicle control device according to claim 1, characterized in that: The control characteristic parameter is calculated based on the driving characteristics of the passenger during manual driving.

11. The vehicle control device according to claim 10, characterized in that: The control characteristic parameters are stored in advance in a database in correspondence with the driving characteristics of the passenger during manual driving and the surrounding environment during manual driving. The control characteristic parameter acquisition unit acquires the control characteristic parameter corresponding to the surrounding environment based on the surrounding environment when the vehicle is determined to be the interacting vehicle.

12. A vehicle control method, characterized in that: The following steps are required: Identify vehicles that interact with each other during autonomous driving; obtaining emotions of passengers in the interacting vehicles; Acquiring control characteristic parameters of the interacting vehicles; Based on the emotions of passengers between the interacting vehicles, weighting the control characteristic parameters of the interacting vehicles and calculating a common control characteristic parameter; as well as Based on the common control characteristic parameters, the interacting vehicles are controlled, When calculating the common control characteristic parameter, weighting is performed with emphasis on the vehicle in which a passenger having a poor emotional state among passengers of the interacting vehicles is riding.

13. A storage medium, characterized in that: A program for causing the computer to function as the following means is stored: A unit for making judgments about vehicles that interact with each other during autonomous driving; a unit for acquiring emotions of passengers between the interacting vehicles; A unit for acquiring control characteristic parameters of the interacting vehicles; A unit for weighting the control characteristic parameters of the interacting vehicles based on the emotions of the passengers between the interacting vehicles, and calculating the common control characteristic parameters in a manner that emphasizes the weighting of the vehicle side where the passengers in the interacting vehicles are riding and have a poor emotional state; as well as A unit for controlling interacting vehicles based on the common control characteristic parameters.