Processing device and evaluation method

Abstract

To provide a processing device and an evaluation method capable of appropriately evaluating a driving skill of a rider of a saddle-riding vehicle.SOLUTION: The processing device evaluates a driving skill of a rider of a saddle-riding vehicle, and comprises an evaluation part that evaluates the driving skills of the rider of the saddle-riding vehicle on the basis of a degree of turning in traveling of the saddle-riding vehicle and a relative angle of a direction of a rider's face relative to a traveling direction of the saddle-riding vehicle. The evaluation method evaluates the driving skills of the rider of the saddle-riding vehicle, in which the evaluation part of the processing device evaluates the driving skills of the rider of the saddle-riding vehicle on the basis of the degree of turning in travelling of the saddle-riding vehicle and the relative angle of the direction of the rider's face relative to the traveling direction of the saddle-riding vehicle.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present disclosure relates to a processing device and an evaluation method that can appropriately evaluate the driving skill of a rider of a saddle-ride type vehicle. [Background technology]

[0002] Conventionally, there are techniques for evaluating the driving skills of drivers of vehicles such as automobiles. In addition, in recent years, as a technique for evaluating driving skills, a technique for evaluating the driving skills of riders of saddle-ride type vehicles such as motorcycles has been proposed (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2018-172090 Summary of the Invention [Problem to be solved by the invention]

[0004] In the field of evaluating the driving skills of riders of saddle-ride type vehicles, it is considered desirable to more appropriately evaluate the driving skills of riders. For example, the aspects of a driver's driving operation that differ depending on differences in driving skill differ between saddle-ride type vehicles and vehicles other than saddle-ride type vehicles (e.g., automobiles). However, conventional techniques have not adequately evaluated driving skills that focus on the aspects specific to saddle-ride type vehicles that differ depending on differences in driving skill in driving operation.

[0005] The present invention has been made in light of the above-mentioned problems, and aims to provide a processing device and an evaluation method that can appropriately evaluate the driving skills of a rider of a saddle-ride type vehicle. [Means for solving the problem]

[0006] The processing device according to the present invention is a processing device that evaluates the driving skill of a rider of a saddle-ride type vehicle, and includes an evaluation unit that evaluates the driving skill of the rider of the saddle-ride type vehicle based on the degree of turning of the saddle-ride type vehicle and the relative angle of the rider's face relative to the direction of travel of the saddle-ride type vehicle.

[0007] The evaluation method of the present invention is a method for evaluating the driving skills of a rider of a saddle-ride type vehicle, in which an evaluation unit of a processing device evaluates the driving skills of the rider based on the degree of turning of the saddle-ride type vehicle and the relative angle of the rider's face relative to the direction of travel of the saddle-ride type vehicle. [Effects of the Invention]

[0008] The processing device and evaluation method according to the present invention evaluate the driving skill of a rider of a saddle-ride type vehicle based on the degree of turning while the saddle-ride type vehicle is traveling and the relative angle of the rider's face relative to the direction of travel of the saddle-ride type vehicle. This makes it possible to evaluate driving skill by focusing on the relationship between the degree of turning and the relative angle, which is a feature unique to saddle-ride type vehicles that differs depending on differences in driving skill in driving operations. Therefore, it is possible to appropriately evaluate the driving skill of a rider of a saddle-ride type vehicle. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a schematic diagram showing a general configuration of a motorcycle on which a processing device according to an embodiment of the present invention is mounted; [Figure 2] 1 is a block diagram illustrating an example of a functional configuration of a processing device according to an embodiment of the present invention. [Figure 3] 1 is a flowchart illustrating an example of a flow of processing performed by a processing device according to an embodiment of the present invention. [Figure 4] 10A and 10B are diagrams illustrating an example of a vehicle position at each detection time and a traveling direction vector and a face direction vector at each vehicle position according to an embodiment of the present invention. [Figure 5]FIG. 10 is a diagram showing an example of the relationship between the curvature and the dot product when a highly skilled rider and a less skilled rider are riding; DETAILED DESCRIPTION OF THE INVENTION

[0010] The processing apparatus according to the present invention will be described below with reference to the drawings.

[0011] Although the following description focuses on a processing device used in a two-wheeled motorcycle, the processing device according to the present invention may also be used in saddle-ride vehicles other than two-wheeled motorcycles (for example, three-wheeled motorcycles, bicycles, etc.) A saddle-ride vehicle refers to a vehicle on which a rider straddles, and includes scooters and the like.

[0012] In the following, a case where the processing device 15 is mounted on the motorcycle 1 will be described, but the processing device according to the present invention may be mounted on something other than a saddle-ride type vehicle, for example, on a helmet 3. Furthermore, the processing device according to the present invention may be a processing device different from the processing device that controls the operation of the display device 13.

[0013] In addition, the following describes a case where the inertial measurement unit 14 is used as a device to detect the vehicle position, which is the position of the motorcycle 1, but a device other than the inertial measurement unit 14 (for example, a device that detects position using signals received from GPS (Global Positioning System) satellites, such as a smartphone carried by the rider 2) may also be used as a device to detect the vehicle position.

[0014] The configuration and operation etc. described below are merely examples, and the processing apparatus and evaluation method according to the present invention are not limited to such configuration and operation etc.

[0015] In the following, descriptions of identical or similar parts are appropriately simplified or omitted. In addition, in each drawing, reference numerals are omitted or the same reference numerals are used for identical or similar parts or components. In addition, illustrations of detailed structures are appropriately simplified or omitted.

[0016] <Motorcycle configuration> The configuration of a motorcycle 1 equipped with a processing device 15 according to an embodiment of the present invention will be described with reference to FIGS.

[0017] Fig. 1 is a schematic diagram showing the general configuration of a motorcycle 1 equipped with a processing device 15. Specifically, Fig. 1 shows a rider 2 wearing a helmet 3 riding the motorcycle 1.

[0018] 1, the motorcycle 1 includes an engine 11, a hydraulic control unit 12, a display device 13, an inertial measurement unit (IMU) 14, and a processing device 15. The motorcycle 1 runs using power output from the engine 11. However, the motorcycle 1 may also run using power output from a motor.

[0019] The engine 11 is an example of a drive source for the motorcycle 1 and is capable of outputting power to drive the wheels. For example, the engine 11 is provided with one or more cylinders each having a combustion chamber formed therein, a fuel injection valve that injects fuel into the combustion chamber, and a spark plug. When fuel is injected from the fuel injection valve, a mixture containing air and fuel is formed in the combustion chamber, and the mixture is ignited by the spark plug and burns. This causes pistons in the cylinders to reciprocate, rotating the crankshaft. In addition, a throttle valve is provided in an intake pipe of the engine 11, and the amount of air taken into the combustion chamber changes depending on the throttle opening of the throttle valve.

[0020] The hydraulic pressure control unit 12 is a unit that has the function of controlling the braking force acting on the wheels. For example, the hydraulic pressure control unit 12 is provided on an oil passage that connects the master cylinder and the wheel cylinders, and includes components (e.g., a control valve and a pump) for controlling the brake hydraulic pressure of the wheel cylinders. The braking force acting on the wheels is controlled by controlling the operation of the components of the hydraulic pressure control unit 12. The hydraulic pressure control unit 12 may control the braking force acting on both the front and rear wheels, or may control only the braking force acting on either the front or rear wheels.

[0021] The display device 13 is a device that displays images, and is provided, for example, near the handlebars on the body of the motorcycle 1. The display device 13 displays various information such as the vehicle speed of the motorcycle 1, for example.

[0022] The inertial measurement unit 14 is equipped with a three-axis gyro sensor and a three-directional acceleration sensor, and detects the position of the motorcycle 1 (hereinafter also referred to as the vehicle position). For example, the inertial measurement unit 14 detects the x and y coordinates of the motorcycle 1 in an x ​​and y coordinate system set on a horizontal plane as the vehicle position, and outputs the detection results. Note that the inertial measurement unit 14 may also detect other physical quantities that can be substantially converted into the x and y coordinates of the motorcycle 1. The x and y coordinates of the motorcycle 1 may also be determined by the processing device 15 using the detection results of the inertial measurement unit 14.

[0023] Here, in addition to the inertial measurement unit 14 on the vehicle body, an inertial measurement unit 31 is also provided on the helmet 3 of the rider 2. Like the inertial measurement unit 14, the inertial measurement unit 31 is equipped with a three-axis gyro sensor and a three-directional acceleration sensor. The inertial measurement unit 31 detects the orientation of the helmet 3 to detect the face direction of the rider 2 (i.e., the direction in which the rider 2's face is facing). For example, the inertial measurement unit 31 detects a unit vector (hereinafter referred to as a face direction vector) that indicates the face direction of the rider 2 in the above-mentioned xy coordinate system. In other words, the face direction vector is a vector on the above-mentioned xy coordinate system, and the length of the face direction vector is 1. The face direction vector may be identified by the processing device 15 using the detection result of the inertial measurement unit 31.

[0024] The processing unit 15 controls the operation of each device mounted on the motorcycle 1.

[0025] For example, part or all of the processing device 15 is configured with a microcomputer, a microprocessor unit, etc. Also, for example, part or all of the processing device 15 may be configured with updatable firmware, etc., or may be a program module executed by instructions from a CPU, etc. The processing device 15 may be, for example, one unit, or may be divided into multiple units.

[0026] FIG. 2 is a block diagram showing an example of the functional configuration of the processing device 15.

[0027] As shown in FIG. 2, the processing device 15 includes, for example, an acquisition unit 151 and a control unit 152.

[0028] The acquisition unit 151 acquires information output from each device mounted on the motorcycle 1 and outputs the information to the control unit 152. For example, the acquisition unit 151 acquires information output from the inertial measurement unit 14 on the vehicle body side and the inertial measurement unit 31 on the helmet 3 side.

[0029] The control unit 152 outputs operation commands to the engine 11, hydraulic control unit 12, and display device 13 mounted on the motorcycle 1, thereby controlling the operation of each of these devices.

[0030] The control unit 152 includes, for example, an engine control unit 152a, a brake control unit 152b, a display control unit 152c, and an evaluation unit 152d, which function in cooperation with a program.

[0031] The engine control unit 152a controls the operation of each device (for example, a throttle valve, a fuel injection valve, and a spark plug) of the engine 11. This controls the driving force transmitted from the engine 11 to the wheels of the motorcycle 1, and controls the acceleration of the motorcycle 1.

[0032] The brake control section 152b controls the operation of each device (for example, a control valve, a pump, etc.) of the hydraulic control unit 12. This controls the braking force acting on the wheels of the motorcycle 1, and the deceleration of the motorcycle 1.

[0033] The display control unit 152c outputs a control command to the display device 13 to control the display of an image by the display device 13.

[0034] The evaluation unit 152d evaluates the driving skill of the rider 2 of the motorcycle 1. The evaluation result of the driving skill by the evaluation unit 152d is used in each control by, for example, the engine control unit 152a, the brake control unit 152b, and the display control unit 152c. Details of how the evaluation result by the evaluation unit 152d is used in each control will be described later.

[0035] Here, the evaluation unit 152d evaluates the driving skill of the rider 2 of the motorcycle 1 based on the degree of turning of the motorcycle 1 and the relative angle of the rider's 2 face direction with respect to the direction of travel of the motorcycle 1. This makes it possible to appropriately evaluate the driving skill of the rider 2 of the motorcycle 1. Details of the process related to the evaluation of driving skill performed by the evaluation unit 152d of the processing device 15 will be described later.

[0036] <Operation of the processing device> The operation of the processing device 15 according to the embodiment of the present invention will be described with reference to FIGS.

[0037] Fig. 3 is a flowchart showing an example of the flow of processing performed by the processing device 15. Specifically, the control flow shown in Fig. 3 is an example of the flow of processing related to the evaluation of driving skill performed by the evaluation unit 152d of the processing device 15, and is executed repeatedly. Furthermore, step S510 and step S590 in Fig. 3 correspond to the start and end of the control flow shown in Fig. 3, respectively.

[0038] The detection of the vehicle position by the inertial measurement unit 14 on the vehicle body side and the detection of the face direction vector by the inertial measurement unit 31 on the helmet 3 are repeatedly performed at preset time intervals. The detection times (i.e., the times at which detection is performed) of the inertial measurement units 14 and 31 are approximately the same. The evaluation unit 152d repeatedly executes the control flow shown in FIG. 3 every time detection is performed by the inertial measurement units 14 and 31. Hereinafter, the current detection time (i.e., the detection time immediately before the control flow shown in FIG. 3 is executed) will be referred to as detection time t i The previous detection time is set as detection time t i-1 The detection time before last is set as detection time t i-2 It will be explained as follows.

[0039] FIG. 4 is a diagram showing an example of a vehicle position p at each detection time, and a traveling direction vector a and a face direction vector f at each vehicle position p. Specifically, FIG. 4 shows a vehicle position p (for example, the current detection time t) at each detection time when the motorcycle 1 travels on a travel route 9. i Vehicle position at p i , the previous detection time t i-1 Vehicle position at p i-1 and the detection time t i-2 Vehicle position at p i-2 In the following, as mentioned above, the specific detection time t j The vehicle position at j and the vehicle position at any detection time is called the vehicle position p.

[0040] The direction vector a (for example, the previous detection time t i-1 Vehicle position at p i-1 Direction vector a in i-1 The face direction vector f (e.g., the face direction vector a) is a unit vector indicating the traveling direction of the motorcycle 1, and is indicated by a thick solid arrow in FIG. 4. The direction of the traveling direction vector a corresponds to the direction of the tangent to the traveling path 9 at the vehicle position p corresponding to the traveling direction vector a. i-1 Vehicle position at p i-1 The face direction vector f i-1 ) is a unit vector indicating the face direction of the rider 2, and is indicated by a thin solid arrow in FIG. 4. In the following, as described above, the specific vehicle position p j The travel direction vector and face direction vector in j and face direction vector f j and the traveling direction vector and face direction vector at an arbitrary vehicle position p are called traveling direction vector a and face direction vector f, respectively.

[0041] When the control flow shown in FIG. 3 is started, in step S511, the evaluation unit 152d calculates the previous detection time t i-1 Vehicle position at p i-1 Curvature κ of the travel path 9 ini-1 In the following, the specific vehicle position p j The curvature at κ j and the curvature at any vehicle position p is called curvature κ.

[0042] For example, the evaluation unit 152d evaluates the current detection time t i Vehicle position at p i and the previous detection time t i-1 Vehicle position at p i-1 and the detection time t i-2 Vehicle position at p i-2 and based on the vehicle position p i-1 Curvature κ of the travel path 9 in i-1 As described above, each vehicle position p is the x and y coordinates of the motorcycle 1 at each detection time detected by the inertial measurement unit 14 on the vehicle body side.

[0043] The evaluation unit 152d calculates the vehicle position p i and vehicle position p i-1 and vehicle position p i-2 and based on the curvature κ i-1 For example, the initial vehicle position p0 is on a straight road, and in this case, the curvature κ -1 will be 0.

[0044]

number

[0045] In addition, in formula (1), R i-1 is the vehicle position p i-1 corresponds to the radius of curvature of the travel path 9 in the equation, and det corresponds to the determinant.

[0046] Next, in step S513, the evaluation unit 152d calculates the previous detection time t i-1 Vehicle position at p i-1 Direction vector a in i-1 Identify.

[0047] For example, the evaluation unit 152d evaluates the current detection time t i Vehicle position at p i and the previous detection time t i-1 Vehicle position at p i-1 and based on the vehicle position p i-1 Direction vector a in i-1 Identify.

[0048] The evaluation unit 152d calculates the vehicle position p i and vehicle position p i-1 Based on this, the direction vector a i-1 Identify.

[0049]

number

[0050] Next, in step S515, the evaluation unit 152d calculates the previous detection time t i-1 Vehicle position at p i-1 The face direction vector f of Rider 2 in i-1 Identify.

[0051] Specifically, the evaluation unit 152d evaluates the previous detection time t i-1 The face direction vector f detected by the inertial measurement unit 31 on the helmet 3 side is expressed as the face direction vector f i-1 Identify as:

[0052] Next, in step S517, the evaluation unit 152d calculates the moving direction vector a i-1 and face direction vector f i-1 The dot product I i-1 In the following, we will calculate the specific moving direction vector a j and face direction vector f j and the corresponding dot product is the dot product I j and the inner product corresponding to an arbitrary moving direction vector a and face direction vector f is called inner product I.

[0053] As mentioned above, the traveling direction vector a and the face direction vector f are both unit vectors (i.e., the magnitude of each vector is 1). Therefore, the dot product I corresponds to the cosine of the relative angle θ of the face direction vector f with respect to the traveling direction vector a (i.e., the relative angle θ of the face direction of the rider 2 with respect to the traveling direction of the motorcycle 1). In other words, when the dot product I is 1, this corresponds to the case where the face direction of the rider 2 is aligned with the traveling direction of the motorcycle 1. When the dot product I is 0, this corresponds to the case where the face direction of the rider 2 is perpendicular to the traveling direction of the motorcycle 1. When the dot product I is -1, this corresponds to the case where the face direction of the rider 2 is facing in the opposite direction to the traveling direction of the motorcycle 1. In the following, when a specific traveling direction vector a j and face direction vector f j The corresponding relative angle is the relative angle θ j and the relative angle corresponding to an arbitrary traveling direction vector a and face direction vector f is called a relative angle θ.

[0054] Next, in step S519, the evaluation unit 152d evaluates the driving skill of the rider 2, and the control flow shown in FIG. 3 ends.

[0055] As described above, the evaluation unit 152d evaluates the driving skill of the rider 2 of the motorcycle 1 based on the degree of turning of the motorcycle 1 and the relative angle of the face direction of the rider 2 with respect to the traveling direction of the motorcycle 1. The degree of turning corresponds to the degree of curvature of the traveling path 9, and for example, the smaller the turning radius, the higher the degree of turning.

[0056] Specifically, in the control flow shown in FIG. 3, the evaluation unit 152d takes into account the curvature κ of the travel path 9 of the motorcycle 1 as the degree of turning. Specifically, the evaluation unit 152d determines that the greater the curvature κ, the higher the degree of turning. Furthermore, the evaluation unit 152d takes into account the dot product I of the traveling direction vector a and the facial direction vector f as the relative angle θ of the facial direction with respect to the traveling direction. Specifically, the evaluation unit 152d determines that the smaller the dot product I, the larger the relative angle θ. For example, the evaluation unit 152d determines that the curvature κ i-1and the inner product I i-1 is used to evaluate driving skills.

[0057] 5 is a diagram showing an example of the relationship between the curvature κ and the dot product I when a highly skilled rider and a less skilled rider are riding. The highly skilled rider has higher driving skills than the less skilled rider.

[0058] 5 shows an area D1 where multiple pairs of curvature κ and dot product I are distributed when a highly skilled rider rides, and an area D2 where multiple pairs of curvature κ and dot product I are distributed when a less skilled rider rides. Also shown in FIG. 5 is an approximated line L1 that shows the relationship between curvature κ and dot product I when a highly skilled rider rides, and an approximated line L2 that shows the relationship between curvature κ and dot product I when a less skilled rider rides. Approximate lines L1 and L2 were derived based on the distribution of pairs of curvature κ and dot product I in areas D1 and D2, respectively.

[0059] Meanwhile, in the travel route 9 shown in Fig. 4, sections Sec1, Sec2, Sec3, Sec4, Sec5, Sec6, and Sec7, each having a different curvature κ, are connected in this order. The curvature κ increases in the order of sections Sec1, Sec7, sections Sec2, Sec6, sections Sec3, Sec5, and section Sec4. Specifically, sections Sec1 and Sec7 are straight roads, and the curvature κ of sections Sec1 and Sec7 is 0. On the other hand, sections Sec2, Sec3, Sec4, Sec5, and Sec6 are curved roads, and the curvature κ of these sections is greater than 0.

[0060] Furthermore, the relative angle θ of the face direction vector f with respect to the traveling direction vector a (i.e., the relative angle of the face direction of the rider 2 with respect to the traveling direction of the motorcycle 1) increases in the order of sections Sec1, Sec7, Sec2, Sec6, Sec3, Sec5, and Sec4. In other words, as the curvature κ increases, the relative angle θ increases, and therefore the dot product I of the traveling direction vector a and the face direction vector f decreases.

[0061] In the approximated straight line L1 corresponding to the highly skilled rider and the approximated straight line L2 corresponding to the less skilled rider shown in Figure 5, the inner product I decreases as the curvature κ increases, as in the example shown in Figure 4. Note that when riding on a straight road where the curvature κ is 0, the face direction of the rider 2 coincides with the direction of travel of the motorcycle 1, regardless of the driving skill. Therefore, in both the approximated straight line L1 corresponding to the highly skilled rider and the approximated straight line L2 corresponding to the less skilled rider, the inner product I is 1 when the curvature κ is 0.

[0062] As shown in Figure 5, the approximated line L1 corresponding to the highly skilled rider has a larger ratio of the decrease in the dot product I to the increase in the curvature κ than the approximated line L2 corresponding to the less skilled rider. Therefore, the approximated line L1 corresponding to the highly skilled rider has a smaller dot product I at each curvature κ (i.e., a larger relative angle θ) than the approximated line L2 corresponding to the less skilled rider. Furthermore, the approximated line L1 corresponding to the highly skilled rider has a smaller curvature κ at each dot product I (i.e., a larger relative angle θ) than the approximated line L2 corresponding to the less skilled rider.

[0063] As described above, the tendency for the face direction to be tilted more with respect to the direction of travel as the curvature κ increases (i.e., the dot product I becomes smaller) is a tendency shared by both highly skilled and less skilled riders. On the other hand, for the same curvature κ, highly skilled riders tend to tilt their face direction with respect to the direction of travel more than less skilled riders (i.e., the dot product I becomes smaller than less skilled riders). In other words, highly skilled riders tend to tilt their face direction more toward the exit of the curved road at a relatively early stage after entering the curved road. This allows the motorcycle 1 to be turned appropriately as intended.

[0064] Therefore, the evaluation unit 152d evaluates the driving skill of the rider 2 so that the smaller the inner product I is at each curvature κ, the higher the driving skill of the rider 2 becomes, and the smaller the curvature κ is at each inner product I. For example, the evaluation unit 152d evaluates the driving skill of the rider 2 so that the smaller the inner product I is at each curvature κ, the higher the driving skill of the rider 2 becomes. i-1 and the inner product Ii-1 If the point corresponding to the pair is on the side of the approximate line L1 rather than the reference line L0 that passes between the approximate lines L1 and L2 (for example, a line where the inner product I for each curvature κ is the average value of the value on the approximate line L1 and the value on the approximate line L2), the driving skill of rider 2 can be evaluated as high, and if the point is on the side of the approximate line L2 rather than the reference line L0, the driving skill of rider 2 can be evaluated as low.

[0065] In this way, from the viewpoint of more appropriately evaluating the driving skills of rider 2, it is preferable that the evaluation unit 152d evaluates the driving skills of rider 2 so that the greater the relative angle θ at each turning degree, the higher the evaluation, and the lower the turning degree at each relative angle θ, the higher the evaluation.

[0066] Here, from the viewpoint of improving the accuracy of the evaluation of the driving skill, it is preferable that the evaluation unit 152d evaluates the driving skill using an evaluation model that is trained in advance for evaluating the driving skill. Specifically, the evaluation model is generated using the relationship between the degree of turning and the relative angle θ when a reference rider (for example, a highly skilled rider or a less skilled rider) is riding. Note that the evaluation model may be generated by the processing device 15 or may be generated by a device other than the processing device 15.

[0067] For example, the pre-trained evaluation model is a function that uses a pair of curvature κ and dot product I as a variable and outputs driving skill. For example, as such an evaluation model, a model can be generated using data prepared in advance: a plurality of pairs of curvature κ and dot product I when a highly skilled rider drives in area D1 shown in FIG. 5, and a plurality of pairs of curvature κ and dot product I when a less skilled rider drives in area D2 shown in FIG. 5. The pre-prepared pairs of curvature κ and dot product I and the driving skill corresponding to the pair (i.e., the driving skill of a highly skilled rider or the driving skill of a less skilled rider) correspond to training data in supervised learning. Then, for example, a pair of curvature κ and dot product I (e.g., the curvature κ obtained by the control flow shown in FIG. 3) can be used according to an existing algorithm such as a support vector machine. i-1 and the inner product Ii-1 An evaluation model for evaluating driving skills is constructed from the pair of the driving skills. It is more preferable to construct the evaluation model using ensemble learning to further improve the accuracy of the evaluation of driving skills using the evaluation model.

[0068] From the viewpoint of more appropriately improving the accuracy of the evaluation of the driving skill, it is preferable that the evaluation unit 152d evaluates the likelihood of the driving skill of the above-mentioned reference rider (for example, a highly skilled rider or a less skilled rider) as the driving skill of the rider 2. For example, when data pairs of the curvature κ and the dot product I in the regions D1 and D2 shown in FIG. 5 are prepared in advance as described above and an evaluation model is generated using these data, the evaluation unit 152d may evaluate the likelihood of the driving skill of the rider 2 being a highly skilled rider or a less skilled rider (i.e., the likelihood of matching the driving skill of a highly skilled rider or the likelihood of matching the driving skill of a less skilled rider) as the driving skill of the rider 2. For example, the curvature κ obtained by the control flow shown in FIG. i-1 and the inner product I i-1 and the evaluation model (specifically, the curvature κ i-1 and the inner product I i-1 By substituting the above pair into an evaluation model, which is a function, the likelihood of the driving skill of rider 2 being that of a highly skilled rider or a low-skilled rider can be evaluated as the driving skill of rider 2. In particular, a support vector machine is used to perform binary classification (i.e., classification into either a highly skilled rider or a low-skilled rider). For example, if the classification result is a highly skilled rider, the probability estimate in the binary classification can be used as an evaluation result corresponding to the likelihood of the driving skill of a highly skilled rider. On the other hand, if the classification result by the binary classification is a low-skilled rider, the probability estimate in the binary classification can be used as an evaluation result corresponding to the likelihood of the driving skill of a low-skilled rider. Note that the evaluation unit 152d may specify the likelihood of the driving skill of a highly skilled rider or a low-skilled rider as a percentage, or may specify the level of likelihood by dividing the level into several levels.

[0069] From the viewpoint of further appropriately improving the accuracy of the evaluation of the driving skill, it is preferable that the evaluation unit 152d evaluates the likelihood of the driving skill of a reference rider (e.g., a highly skilled rider or a less skilled rider) based on multiple pairs of the turning degree and the relative angle θ. For example, by using an evaluation model and a pair of the curvature κ and the dot product I at each vehicle position p obtained by repeatedly executing the control flow shown in FIG. 3, the likelihood of the driving skill of the rider 2 being that of a highly skilled rider or a less skilled rider can be evaluated as the driving skill of the rider 2. In this case, specifically, each time the control flow shown in FIG. 3 is repeated, a pair of the curvature κ and the dot product I newly identified in the control flow can be added as data used to evaluate the driving skill of the rider 2, thereby allowing the evaluation results to be updated as needed.

[0070] The above has described the process related to the evaluation of the driving skill of the rider 2 performed by the evaluation unit 152d. Here, the details of how the evaluation result of the evaluation unit 152d is used for each control will be described. The evaluation result of the evaluation unit 152d can be used for each control by the control unit 152.

[0071] For example, if the control unit 152 is capable of performing adaptive cruise control (specifically, control that causes the motorcycle 1 to travel in accordance with the distance from the motorcycle 1 to a vehicle in front, the movement of the motorcycle 1, and instructions from the rider 2), the adaptive cruise control may control the acceleration / deceleration of the motorcycle 1 based on the evaluation result of the evaluation unit 152d. Specifically, the lower the evaluation result of the rider 2's driving skill, the more preferably the engine control unit 152a and brake control unit 152b of the control unit 152 control the acceleration / deceleration of the motorcycle 1 so that sudden changes in acceleration / deceleration of the motorcycle 1 are less likely to occur in the adaptive cruise control.

[0072] Furthermore, for example, if the control unit 152 is capable of executing emergency braking control (specifically, control to stop the motorcycle 1 before an obstacle ahead without the rider 2 performing any acceleration or deceleration operations), the deceleration of the motorcycle 1 during emergency braking control may be controlled based on the evaluation result of the evaluation unit 152d. Specifically, the lower the evaluation result of the rider 2's driving skill, the more preferably the brake control unit 152b of the control unit 152 controls the deceleration of the motorcycle 1 so that a sudden change in the deceleration of the motorcycle 1 is less likely to occur during emergency braking control.

[0073] Furthermore, for example, the display control unit 152c of the control unit 152 may cause the evaluation result of the evaluation unit 152d to be displayed on the display device 13. Specifically, the display control unit 152c may cause the display device 13 to display the likelihood of the driving skill of a high-skill rider or a low-skill rider as a percentage as the evaluation result of the driving skill of the rider 2, or may cause the display device 13 to display the level of the likelihood.

[0074] In the above example, the curvature κ of the travel path 9 of the motorcycle 1 is taken into account as the degree of turning of the motorcycle 1, but the evaluation unit 152d may take other parameters into account as the degree of turning.

[0075] For example, the evaluation unit 152d may take into account the lean angle of the motorcycle 1 (i.e., the angle indicating the tilt of the motorcycle 1 in the roll direction relative to the vertically upward direction) as the degree of turning. In this case, specifically, the evaluation unit 152d determines that the greater the lean angle, the greater the degree of turning. The lean angle of the motorcycle 1 can be detected, for example, by the inertial measurement unit 14. Note that the inertial measurement unit 14 may also detect another physical quantity that can be substantially converted into the lean angle of the motorcycle 1.

[0076] Furthermore, for example, the evaluation unit 152d may also take into account the lateral acceleration of the motorcycle 1 (i.e., the component of the acceleration occurring on the motorcycle 1 in the width direction of the motorcycle 1) as the degree of turning. In this case, specifically, the evaluation unit 152d determines that the greater the lateral acceleration, the greater the degree of turning. The lateral acceleration of the motorcycle 1 may be detected, for example, by a lateral acceleration sensor (not shown) provided on the body or the like of the motorcycle 1. Note that the lateral acceleration sensor may also detect other physical quantities that can be substantially converted into the lateral acceleration of the motorcycle 1.

[0077] <Effects of the treatment device> The effects of the processing device 15 according to the embodiment of the present invention will be described.

[0078] In the processing device 15, the evaluation unit 152d evaluates the driving skill of the rider 2 of the motorcycle 1 based on the degree of turning of the motorcycle 1 and the relative angle θ of the rider 2's face relative to the direction of travel of the motorcycle 1. This makes it possible to evaluate the driving skill of the rider 2 by focusing on the relationship between the degree of turning and the relative angle θ, which is a feature unique to the motorcycle 1 that differs depending on differences in driving skill in driving operations. Therefore, the driving skill of the rider 2 of the motorcycle 1 can be appropriately evaluated.

[0079] Preferably, in the processing device 15, the evaluation unit 152d evaluates the driving skill of the rider 2 so that the evaluation increases as the relative angle θ increases for each degree of turning, and increases as the degree of turning decreases for each relative angle θ. This makes it possible to more appropriately evaluate the driving skill of the rider 2, focusing on the relationship between the degree of turning and the relative angle θ. Therefore, it is possible to more appropriately evaluate the driving skill of the rider 2.

[0080] Preferably, in the processing device 15, the evaluation unit 152d evaluates the driving skill of the rider 2 using a pre-trained evaluation model for evaluating the driving skill of the rider 2. This makes it possible to accurately evaluate the driving skill of the rider 2 based on data indicating the relationship between the degree of turning and the relative angle θ that has been prepared in advance. Therefore, it is possible to improve the accuracy of the evaluation of the driving skill of the rider 2.

[0081] Preferably, in the processing device 15, the evaluation model is generated using the relationship between the degree of turning and the relative angle θ when a reference rider is traveling. This allows the evaluation model to be appropriately constructed as a model for evaluating the driving skill of the rider 2. Therefore, it is possible to appropriately improve the accuracy of the evaluation of the driving skill of the rider 2.

[0082] Preferably, in the processing device 15, the evaluation unit 152d evaluates the likelihood of the rider's driving skill serving as the reference as the driving skill of the rider 2. This allows for evaluation in more stages than when the driving skill of the rider 2 is evaluated in two stages, high skill and low skill, for example. Therefore, the accuracy of the evaluation of the driving skill of the rider 2 can be more appropriately improved.

[0083] Preferably, in the processing device 15, the evaluation unit 152d evaluates the likelihood of the rider's driving skill serving as the reference, based on multiple pairs of the turning degree and the relative angle θ. This makes it possible to evaluate the likelihood using more data indicating the relationship between the turning degree and the relative angle θ when the rider 2 drives the motorcycle 1. This makes it possible to further appropriately improve the accuracy of the evaluation of the rider 2's driving skill.

[0084] Preferably, in the processing device 15, the evaluation unit 152d considers the curvature κ of the travel path 9 of the motorcycle 1 as the degree of turning. This allows the driving skill of the rider 2 to be appropriately evaluated by focusing on the relationship between the curvature κ of the travel path 9 of the motorcycle 1 and the relative angle θ.

[0085] Preferably, in the processing device 15, the evaluation unit 152d considers the lean angle of the motorcycle 1 as the degree of turning. This allows the driving skill of the rider 2 to be appropriately evaluated by focusing on the relationship between the lean angle of the motorcycle 1 and the relative angle θ.

[0086] Preferably, in the processing device 15, the evaluation unit 152d considers the lateral acceleration of the motorcycle 1 as the degree of turning. This allows the driving skill of the rider 2 to be appropriately evaluated by focusing on the relationship between the lateral acceleration of the motorcycle 1 and the relative angle θ.

[0087] The present invention is not limited to the description of the embodiments, and for example, only a part of the embodiments may be implemented. [Explanation of symbols]

[0088] 1 Motorcycle, 2 Rider, 3 Helmet, 11 Engine, 12 Hydraulic control unit, 13 Display device, 14 Inertial measurement unit, 15 Processing device, 31 Inertial measurement unit, 151 Acquisition unit, 152 Control unit, 152a Engine control unit, 152b Brake control unit, 152c Display control unit, 152d Evaluation unit.

Claims

1. A processing device (15) for evaluating the driving skills of a rider (2) of a saddle-ride type vehicle (1), an evaluation unit (152d) that evaluates the driving skill of a rider (2) of the saddle-ride type vehicle (1) based on the degree of turning of the saddle-ride type vehicle (1) while traveling and the relative angle of the face direction of the rider (2) with respect to the traveling direction of the saddle-ride type vehicle (1) identified based on the vehicle positions at multiple times during the turn; The evaluation unit (152d) evaluates the driving skill so that the driving skill is higher as the relative angle is larger for each of the turning degrees, and higher as the turning degree is lower for each of the relative angles. Processing equipment.

2. The evaluation unit (152d) evaluates the driving skill using a pre-trained evaluation model for evaluating the driving skill. The processing device of claim 1 .

3. The evaluation model is generated using the relationship between the degree of turning and the relative angle when a reference rider is riding. The processing device of claim 2 .

4. The evaluation unit (152d) evaluates the likelihood of the driving skill of the reference rider as the driving skill. The processing device according to claim 3 .

5. The evaluation unit (152d) evaluates the likelihood based on a plurality of pairs of the turning degree and the relative angle. The processing device according to claim 4 .

6. The evaluation unit (152d) takes into account the curvature of the travel path of the saddle-ride type vehicle (1) as the degree of turning. The processing device according to any one of claims 1 to 5.

7. The evaluation unit (152d) takes into account the lean angle of the saddle-ride type vehicle (1) as the degree of turning. The processing device according to any one of claims 1 to 5.

8. The evaluation unit (152d) takes into account the lateral acceleration of the saddle-ride type vehicle (1) as the degree of turning. The processing device according to any one of claims 1 to 5.

9. A method for evaluating the driving skills of a rider (2) of a saddle-ride type vehicle (1), comprising: an evaluation unit (152d) of a processing device (15) evaluates the driving skill of the rider (2) based on the degree of turning of the saddle-ride type vehicle (1) while traveling and the relative angle of the face direction of the rider (2) with respect to the traveling direction of the saddle-ride type vehicle (1) identified based on the vehicle position at a plurality of times during the turn, so that the driving skill is higher as the relative angle is larger for each of the turning degrees and higher as the degree of turning is lower for each of the relative angles; Evaluation method.

Images