JP2019093896A - Information processing device, classification method and computer program - Google Patents

Abstract

To provide an information processing device or the like capable of executing a highly accurate classification of a driving characteristic of a driver.SOLUTION: An information processing device includes: generation means for generating at least one group by grouping a plurality of driver models on the basis of a weight of a plurality of driver models for determining the operation of a vehicle to a travel environment on the basis of a prescribed object function using the weight of each of a plurality of indexes; and determination means for determining the group to which a target driver model belongs, and outputting a determination result.SELECTED DRAWING: Figure 1

Description

  The present disclosure relates to an information processing device that classifies a driver model that causes a vehicle to travel, a classification method, and a computer program.

  An apparatus has been proposed which evaluates a driver model for driving a vehicle and detects a driving characteristic.

  For example, Patent Document 1 discloses an apparatus for evaluating the driving characteristic of a driver based on a sensor mounted on a vehicle. In this device, a model of the driver in motion is identified and characterized by comparing the model with the previously identified model of the same driver. In this device, the error between the maneuver target value and the actual movement value is used as an input, and the operation amount is used as an output to identify the driver's model.

  Further, Patent Document 2 discloses a driver model creation device that creates a more accurate driver model, which serves as an evaluation standard of an operating state in a normal state. This device detects the driver's biometric information to recognize whether the driver is in a normal state. Then, this device collects operating state data while the driver is operating, and extracts a portion of the operating state data in which the driver operates in a normal state to create a driver model.

  Further, Patent Document 3 discloses a sewage treatment process simulator capable of automatically setting parameters required for modeling. The simulator compares the analysis data stored in the data storage device with the data stored in the simulation result storage device, and evaluates the simulation result based on a predetermined equation.

  Here, it is required to classify the driving characteristics of the driver. On the other hand, as described above, techniques for generating a driver model have been proposed. Therefore, it is conceivable to classify the driving characteristic of the driver by the generated driver model.

Patent No. 5158677 gazette JP 2007-272834 A JP 2000-167585 A

  Generally, there are a plurality of indicators such as vehicle speed, acceleration / deceleration, fuel consumption, etc. as indicators for evaluating the driver's driving preference and habit. On the other hand, Patent Document 1 to Patent Document 3 described above do not disclose that the driver model is evaluated in consideration of a plurality of indices. Therefore, the accuracy of the generated driver model is not high, and even if it is applied to classification, the accuracy of the classification is not high.

  The present invention has been made in view of the above problems, and has as its main object to provide an information processing apparatus and the like which can carry out classification with high accuracy of driving characteristics of a driver.

  The information processing apparatus according to an aspect of the present invention determines the operation of the vehicle with respect to the traveling environment based on a predetermined objective function using a weight related to each of the plurality of indicators, based on the weights of the plurality of driver models. By grouping the plurality of driver models, a generation unit that generates at least one group, and a determination unit that determines the group to which the target driver model belongs and outputs a determination result.

  The classification method according to an aspect of the present invention is based on the weights of a plurality of driver models that determine the operation of the vehicle with respect to the traveling environment based on a predetermined objective function that uses the weights for each of the plurality of indicators. By grouping a plurality of driver models, at least one group is generated, the group to which the target driver model belongs is determined, and the determination result is output.

  A computer program according to an aspect of the present invention is based on the weights of a plurality of driver models that determine the operation of the vehicle relative to the driving environment based on a predetermined objective function that uses the weights for each of the plurality of indicators. By grouping the plurality of driver models, the computer is caused to execute processing of generating at least one group and processing of determining the group to which the target driver model belongs and outputting the determination result.

  According to the present invention, it is possible to obtain the effect of being able to carry out highly accurate classification of the driving characteristics of the driver.

It is a block diagram showing composition of an information processor concerning a 1st embodiment of the present invention. It is a block diagram showing composition of an information processor concerning a 2nd embodiment of the present invention. It is a figure showing an example of the real run data of the information processor concerning a 2nd embodiment of the present invention. It is a figure which shows an example of the simulation driving | running | working data memorize | stored in the simulation driving | running | working data storage part of the information processing apparatus which concerns on the 2nd Embodiment of this invention. It is a flowchart which shows operation | movement of the information processing apparatus which concerns on the 2nd Embodiment of this invention. It is a figure which shows an example of the evaluation value of the real driving | running | working data calculated | required by the evaluation part of the information processing apparatus which concerns on the 2nd Embodiment of this invention. It is a figure which shows an example of the evaluation value of simulation driving | running | working data calculated | required by the evaluation part of the information processing apparatus which concerns on the 2nd Embodiment of this invention. It is a figure which shows an example of the comparison result of the simulation driving | running | working data and real driving | running | working data by the evaluation part of the information processing apparatus which concerns on the 2nd Embodiment of this invention. It is a figure which shows the other example of the comparison result of the simulation driving | running | working data and real driving | running | working data by the evaluation part of the information processing apparatus which concerns on the 2nd Embodiment of this invention. It is a block diagram showing composition of an information processor concerning a 3rd embodiment of the present invention. It is a flow chart which shows operation of an information processor concerning a 3rd embodiment of the present invention. It is a figure which shows an example of the comparison result of the simulation driving | running | working data and real driving | running | working data by the evaluation part of the information processing apparatus which concerns on the 3rd Embodiment of this invention. It is a block diagram showing composition of a vehicle concerning a 4th embodiment of the present invention. It is a block diagram which shows the structure of the vehicle and information processor which concern on the 5th Embodiment of this invention. It is a block diagram showing composition of an information processor concerning a 6th embodiment of the present invention. It is a flowchart which shows operation | movement of the information processing apparatus which concerns on the 6th Embodiment of this invention. It is a figure which shows the example of the separate driver model stored in the separate driver model storage part of the information processing apparatus which concerns on the 6th Embodiment of this invention. It is a block diagram which shows the structure of the classification | category part of the information processing apparatus which concerns on the 6th Embodiment of this invention. It is a figure which shows an example of the representative driver model of the group produced | generated by the information processing apparatus which concerns on the 6th Embodiment of this invention. It is a figure which shows an example of the driver assistance screen displayed on the display part of the information processing apparatus which concerns on the 6th Embodiment of this invention. It is a figure which shows the other example of the driver assistance screen displayed on the display part of the information processing apparatus which concerns on the 6th Embodiment of this invention. It is a figure which shows the other example of the driver assistance screen displayed on the display part of the information processing apparatus which concerns on the 6th Embodiment of this invention. It is a figure which shows an example of the hardware constitutions which implement | achieve the apparatus shown to each embodiment.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

First Embodiment FIG. 1 is a block diagram showing a configuration of an information processing apparatus 100 according to a first embodiment of the present invention. As shown in FIG. 1, the information processing apparatus 100 includes a generation unit 110 and a determination unit 120.

  The generation unit 110 divides the plurality of driver models into groups based on the weights of the plurality of driver models that determine the operation of the vehicle with respect to the traveling environment based on a predetermined objective function using the weights related to each of the plurality of indicators. To generate at least one group.

  The determination unit 120 determines the group to which the target driver model belongs, and outputs the determination result.

  The generation unit 110 and the determination unit 120 are realized by a group generation unit 631 and a group determination unit which will be described in the following embodiments, as an example.

  By adopting the above configuration, according to the first embodiment, it is possible to obtain an effect that classification with high accuracy of the driving characteristic of the driver can be performed.

Second Embodiment FIG. 2 is a block diagram showing a configuration of an information processing apparatus 200 according to a second embodiment of the present invention. As shown in FIG. 2, the information processing apparatus 200 includes an actual travel data storage unit 210, an actual travel data acquisition unit 211, a travel environment data storage unit 220, a vehicle travel simulator 230, a simulation travel data storage unit 240, and simulation travel data acquisition. A unit 241, an evaluation unit 250, and a display unit 260 are provided. The vehicle travel simulator 230 includes a control unit 231 and a driver model 232. The driver model 232 includes weight parameters 233.

  The outline of each component of the information processing apparatus 200 will be described.

  The actual traveling data storage unit 210 stores information obtained by traveling of the vehicle by the driver, for example, actual traveling data including the position, direction, speed and the like of the vehicle. The actual traveling data acquisition unit 211 acquires the actual traveling data and stores the acquired actual traveling data in the actual traveling data storage unit 210. FIG. 3 is a diagram showing an example of actual traveling data. As shown in FIG. 3, the actual travel data may include, for example, information indicating the position, direction, speed, acceleration, operation, and fuel consumption of the vehicle corresponding to the time every predetermined time. The operation may include values of accelerator, brake, and steering wheel operations.

  The actual travel data may be the above information when the driver travels the vehicle on an actual road, or may be the above information when traveling in a simulator that reproduces the travel of the vehicle by the driver.

  The traveling environment data storage unit 220 stores traveling path information, environment information, and other object information when the actual traveling data stored in the actual traveling data storage unit 210 is obtained. The travel path information includes information on the shape of the travel path, the road width, the road surface condition, and the like. The environmental information includes information on lighting, weather, wind and the like related to the traveling route. The other object information includes information on the traveling path and the shapes, positions, speeds, accelerations, indicators and the like of the other objects present in the vicinity thereof. The traveling environment data storage unit 220 may store the above-mentioned respective information for each predetermined time. The traveling environment data may be acquired by the actual traveling data acquisition unit 211 and stored in the traveling environment data storage unit 220.

  The vehicle traveling simulator 230 reads the traveling environment data stored in the traveling environment data storage unit 220 in the control unit 231, simulates the operation of the driver using the driver model 232, and operates the vehicle. Output various information about driving.

  The driver model 232 is an algorithm that determines an operation for traveling the vehicle, such as an accelerator, a brake, and a steering wheel, based on the traveling environment data, that is, according to the traveling environment. The weight parameter 233 is a parameter used to reflect the driving preference of the driver when the driver model 232 determines the operation. The driver model 232 includes a predetermined objective function, and the weight parameter 233 is determined by optimizing the objective function. Thereby, the driving preference of the driver is reflected in the determined operation.

In the case of using, for example, the speed, the fuel consumption, and the ride quality as the evaluation index reflecting the driving preference of the driver, the objective function can be represented by, for example, the following formula (1).
Objective function = (W1 * VS) + (W2 * VF) + (W3 * VA) (1)
Here, VS is a speed evaluation index, VF is a fuel consumption evaluation index, and VA is a variable that indicates a ride evaluation index. W1, W2, and W3 are weight parameters 233 for the speed evaluation index VS, the fuel consumption evaluation index VF, and the ride evaluation index VA, respectively, and it is assumed that the following equation (2) is satisfied.
W1 + W2 + W3 = 1 (2)
The control unit 231 inputs traveling environment data, and determines an operation of the vehicle at predetermined time intervals such as optimizing (for example, minimizing) the objective function using the driver model 232. Then, the control unit 231 virtually controls the vehicle by the determined operation.

  The simulation travel data acquisition unit 241 acquires simulation travel data indicating information such as a position, a direction, and a speed for each predetermined time of the vehicle virtually operated based on the above control. The simulation travel data storage unit 240 stores simulation travel data acquired by the simulation travel data acquisition unit 241.

  FIG. 4 is a view showing an example of simulation travel data stored in the simulation travel data storage unit 240. As shown in FIG. As shown in FIG. 4, the simulation travel data includes information of the same items as the actual travel data shown in FIG. 3.

  The evaluation unit 250 has a function of comparing the actual travel data stored in the actual travel data storage unit 210 with the simulation travel data stored in the simulation travel data storage unit 240.

  FIG. 5 is a flowchart showing the operation of the information processing apparatus 200 according to the second embodiment. The operation of the information processing apparatus 200 will be described with reference to FIG. It is assumed that the actual traveling data shown in FIG. 3 is stored in the actual traveling data storage unit 210. Further, it is assumed that traveling environment data storage unit 220 stores traveling environment data relating to the environment where the actual traveling data is acquired.

  The vehicle traveling simulator 230 reads the traveling environment data stored in the traveling environment data storage unit 220 in the control unit 231, and executes a simulation of the vehicle traveling using the driver model 232 (step S201). At this time, the control unit 231 determines the operation of the vehicle such as an accelerator, a brake, and a steering wheel at predetermined time intervals so as to optimize the objective function using the driver model 232. Then, the control unit 231 virtually controls the vehicle by the determined operation.

  The control unit 231 generates simulation travel data including the position, the direction, and the speed of the vehicle for each predetermined time when the vehicle is virtually operated by the operation determined using the driver model 232 as described above. The simulation travel data is stored in the simulation travel data storage unit 240 (step S202). Here, it is assumed that the simulation travel data shown in FIG. 4 is stored in the simulation travel data storage unit 240.

  Subsequently, the evaluation unit 250 obtains an evaluation value regarding an evaluation index for the simulation travel data stored in the simulation travel data storage unit 240 as described above and the actual travel data stored in the actual travel data storage unit 210. (Step S203). The evaluation index is determined in advance, and here, for example, it is assumed that the speed, the fuel consumption, and the ride quality are set as the evaluation index.

  FIG. 6 is a diagram showing an example of the evaluation value of actual traveling data, which is obtained by the evaluation unit 250. As shown in FIG. As shown in FIG. 6, evaluation values of speed, fuel consumption, and ride quality are obtained for each time included in the actual travel data shown in FIG. 3.

The evaluation value of the speed is obtained, for example, from the value of "speed" included in the actual traveling data. For example, the evaluation value VS ₁ of the velocity at time _{T 1,} as shown in the following equation (3) may be determined from the speed _{S 1} and the target speed VTS ₁ time _{T 1.}
Evaluation value of speed at time T ₁ VS ₁ = Speed S ₁ -Target speed VTS ₁ (3)
The target speed VTS ₁ may be given in advance according to the road condition. For example, the speed limit may be given based on the map information.

The evaluation value of the fuel efficiency is calculated, for example, from each value of "remaining amount of fuel" and "position" included in the actual traveling data. For example, the evaluation value VF ₁ fuel consumption at time _{T 1} may be determined by the following equation (4).
Evaluation value of fuel efficiency at time T ₁ VF ₁ =
(Fuel remaining amount F ₁ -Fuel remaining amount F ₂ ) ÷ (Position L ₂ -Position L ₁ ) (4)
The evaluation value of the ride quality is acquired, for example, from the value of “acceleration” included in the actual traveling data. For example, the evaluation value VA ₁ ride comfort at the time _{T 1,} as shown in the following equation (5) may be an acceleration _{A 1} at time _{T 1.}
Evaluation value of acceleration at time T ₁ VA ₁ = acceleration A ₁ (5)
The ride quality may be determined from the derivative value of the acceleration. FIG. 7 is a diagram showing an example of evaluation values of simulation travel data obtained by the evaluation unit 250. As shown in FIG. FIG. 7 shows that each evaluation value of speed, fuel consumption, and ride comfort is acquired from the simulation travel data shown in FIG. 4 as in the evaluation values of the actual travel data shown in FIG.

  The evaluation unit 250 displays on the display unit 260 the comparison result of the simulation travel data and the actual travel data based on each evaluation value obtained as described above (step S204). FIGS. 8A, 8B, and 8C are diagrams showing an example in which the comparison result between the simulation travel data and the actual travel data is displayed on the display unit 260. FIG. 8 (a), (b) and (c) show the comparison results of the simulation travel data and the actual travel data, respectively, in the case where the evaluation index is speed, fuel consumption and ride comfort.

  8 (a), (b) and (c) show simulation travel data on XY coordinates with "time" as the horizontal axis (X axis) and "evaluation value" as the vertical axis (Y axis). The result of having plotted each evaluation value to time of real driving data is shown, respectively. It is assumed that the evaluation value of the simulation travel data is shown by a dotted line and the evaluation value of the actual travel data is shown by a solid line.

  As shown in FIG. 8A, the evaluation values of the simulation travel data and the actual travel data when the speed is used as the evaluation index have a relatively small degree of deviation. Therefore, it is considered that the driver model well reflects the driver's preference regarding the speed. The evaluation unit 250 may display an evaluation index (here, speed) considered to be well reflected by the driver model as a result of the evaluation.

  Here, the degree of deviation may be a time average error rate of the evaluation value of the simulation travel data with respect to the evaluation value of the actual travel data. If this time average error rate is smaller than a predetermined value, it is determined that the driver model well reflects the driver's preference with respect to the evaluation index, and if it is the predetermined value or more, the driver's preference is not reflected much It may be determined that

  As shown in FIG. 8B, the simulation travel data and the actual travel data when fuel efficiency is used as the evaluation index has a relatively large degree of deviation. Therefore, it is considered that the driver model does not reflect much the driver's preference regarding fuel consumption. The evaluation unit 250 may display, as a result of the evaluation, an evaluation index (here, the fuel consumption) that is considered not to reflect much on the driver model.

  Furthermore, as shown in FIG. 8C, the simulation travel data and the actual travel data when the ride comfort is used as the evaluation index has a relatively small degree of deviation. Therefore, it is considered that the driver model well reflects the driver's preference regarding the ride quality.

  Evaluation part 250 may display the comparison result which used the value which normalized each evaluation value of simulation driving data and real driving data, respectively. By performing normalization, the evaluation unit 250 can display the comparison result that is not influenced by the magnitude of the absolute value of each evaluation value. Moreover, the evaluation part 250 may display the comparison result which used each time average value of each evaluation value of simulation driving | running | working data and real driving | running | working data. By displaying the comparison result using the time average value, it is possible to remove and evaluate the instantaneous change of the traveling data.

  FIG. 9 is a diagram showing another example of the comparison result of each evaluation value of the simulation travel data and the actual travel data by the evaluation unit 250. As shown in FIG. As shown in FIG. 9, the evaluation unit 250 may indicate the degree of coincidence (percentage of coincidence) of the evaluation value of the simulation travel data with the evaluation value of the actual travel data.

  FIG. 9 shows the degree of coincidence of the evaluation value of the simulation travel data with the evaluation value of the actual travel data, each of which is the evaluation index, which is the speed, the fuel consumption and the ride quality. The degree of coincidence may be, for example, the degree of coincidence of time average values of each evaluation value of simulation travel data and actual travel data. In addition, the evaluation unit 250 may calculate an average value of the above-mentioned degree of coincidence regarding each of the speed, the fuel efficiency, and the ride quality which is the evaluation index, and may display the calculated result as a comprehensive evaluation.

  As described above, according to the second embodiment, the information processing apparatus 200 performs simulation using the actual travel data obtained by the travel of the vehicle by the driver and the driver model 232 by the vehicle travel simulator 230. Get driving data. The evaluation unit 250 compares the respective evaluation values on the basis of a plurality of evaluation indicators, and displays the comparison result, so that an effect of enabling evaluation in consideration of a plurality of evaluation indicators can be obtained.

Third Embodiment FIG. 10 is a block diagram showing a configuration of an information processing apparatus 300 according to a third embodiment of the present invention. As shown in FIG. 10, an information processing apparatus 300 according to the third embodiment includes an adjustment unit 270 in addition to the information processing apparatus 200 according to the second embodiment.

  The adjustment unit 270 has a function of adjusting the weight parameter 233 included in the driver model 232 of the vehicle travel simulator 230 based on the comparison result by the evaluation unit 250.

  The weight parameter 233 is weight information for determining the operation of the vehicle so as to travel the vehicle reflecting the driving preference of the driver as described in the second embodiment, and the above-mentioned equation (1) It can be expressed as

  As described in the second embodiment, when the deviation of the evaluation value of the simulation travel data with respect to the evaluation value of the actual traveling data is more than a predetermined value with respect to the evaluation value of the actual traveling data, the driver model is: It is considered that the driver's driving preference is not reflected so much. Therefore, in the third embodiment, adjustment of the weight parameter is described in such a manner that the driver's driving preference which is considered to be not reflected much by the driver model is more reflected in the driver model.

  FIG. 11 is a flowchart showing the operation of the information processing apparatus 300 according to the third embodiment. In FIG. 11, steps S201 to S204 are the same processes as the processes of the same reference numerals in FIG. 5 of the second embodiment, so the description thereof is omitted, and in the present embodiment, the steps S205 to S210 are described. Do.

  Adjustment unit 270 calculates the degree of difference (difference) between the evaluation value of the actual traveling data and the evaluation value of the simulation traveling data with respect to the evaluation value of the actual traveling data based on the comparison result in step S204 (step S205). ). For example, a time average error rate of the evaluation value of simulation traveling data to the evaluation value of actual traveling data may be used as the gap degree.

  Here, let E1, E2, and E3 be the deviations of the evaluation values of the simulation travel data with respect to the evaluation values of the actual travel data regarding the respective evaluation indexes, that is, the speed, fuel efficiency, and ride comfort.

  In addition, weight parameters after adjustment for the weight parameters W1, W2, and W3 in Equation (1) are respectively W1 ', W2', and W3 '.

The adjustment unit 270 calculates weight parameters W1 ′, W2 ′, W3 ′ based on the gap degree (step S206). For example, the adjustment unit 270 calculates weight parameters W1 ′, W2 ′, and W3 ′ so as to satisfy the following Expressions (6) and (7).
Wn '= Wn * (1 + En) * C (n = 1, 2, 3) (6)
W1 '+ W2' + W3 '= 1 (7)
However, C is a constant whose denominator is the sum of Wn * (1 + En) relating to n = 1, 2, 3 respectively.

The adjusting unit 270 reflects the calculated weight parameters W1 ′, W2 ′, and W3 ′ on the weight parameter 233 of the driver model 232 (step S207). At this time, the objective function of the driver model 232 is the equation shown in the following equation (1) ′.
Objective function = (W1 '* VS) + (W2' * VF) + (W3 '* VA) (1)'
As shown in the equation (6), the value of the weighting parameter is set larger as the gap degree is larger. As a result, the driver model 232 using the adjusted weight parameter 233 becomes an algorithm for more emphasizing the evaluation index having a large gap degree to determine the operation. Equation (6) is an example, and the adjustment range of a parameter having a large divergence may be increased by using En ² instead of En, or excessive adjustment may be performed by setting En within the maximum value range. The width may not be too large.

  The vehicle traveling simulator 230 reads the traveling environment data in the control unit 231, and uses the driver model 232 to optimize the objective function using the weighting parameter 233 adjusted (updated) as described above. The operation of the vehicle's accelerator, brake, steering wheel, etc. is determined at predetermined time intervals.

  The control unit 231 virtually controls the vehicle by the operation determined as described above. The control unit 231 generates simulation travel data after adjustment using the weight parameter 233 adjusted as described above. The control unit 231 stores the generated simulation travel data in the simulation travel data storage unit 240 (step S208).

  Subsequently, the evaluation unit 250 evaluates the above-described evaluation index for the adjusted simulation travel data stored in the simulation travel data storage unit 240 and the actual travel data stored in the actual travel data storage unit 210 as described above. The evaluation value regarding X is obtained in the same manner as step S203 above (step S209).

  Subsequently, the evaluation unit 250 displays, on the display unit 260, the comparison result of the simulation travel data and the actual travel data based on each evaluation value obtained as described above (step S210). 12 (a), (b) and (c) are diagrams showing an example in which the comparison result between the simulation travel data and the actual travel data is displayed on the display unit 260. FIG. FIGS. 12 (a), (b) and (c) show the comparison results of simulation travel data and actual travel data, respectively, in the case where the evaluation index is speed, fuel consumption and ride comfort.

  As shown in FIG. 11 (b), the simulation travel data related to the fuel efficiency has a smaller deviation from the actual travel data than the result shown in FIG. 8 (b). As described above, by adjusting the weight parameters based on the difference between the evaluation values of the simulation travel data and the actual travel data, it is possible to generate the driver model 232 more in line with the driver's driving preference.

  As described above, according to the third embodiment, the evaluation unit 250 compares the simulation travel data with the actual travel data based on a plurality of evaluation indicators, and emphasizes the evaluation indicators having a large gap degree. Then, the weight parameter 233 in the driver model 232 is adjusted. By adopting this configuration, according to the third embodiment, an effect of being able to generate a driver model in which the balance of a plurality of evaluation indexes is considered can be obtained.

Fourth Embodiment FIG. 13 is a block diagram showing a configuration of a vehicle 400 according to a fourth embodiment of the present invention. As shown in FIG. 13, a vehicle 400 according to the fourth embodiment includes the information processing device 300 according to the third embodiment, and a sensor group 410.

  The sensor group 410 includes one or more sensors for acquiring information on a vehicle in motion, such as the position, direction, velocity, and acceleration of the vehicle. The actual travel data acquisition unit 211 of the information processing device 300 acquires the information on the traveling vehicle acquired by the sensor group 410 as actual travel data and stores the information in the simulation travel data storage unit 240.

  Similarly to the operation described in the third embodiment, the information processing apparatus 300 uses the actual travel data stored as described above and the simulation travel data generated by the vehicle travel simulator 230 as a plurality of evaluation indexes. Compare based on. Then, the adjustment unit 270 adjusts the weight parameter 233 so as to place more importance on the evaluation index having a large gap.

  As described above, according to the fourth embodiment, the information processing apparatus 300 and the sensor group 410 are mounted on the vehicle 400, and the information processing apparatus 300 is based on the actual travel data acquired by the sensor group 410. And adjust the weight parameter 233.

  By adopting this configuration, according to the fourth embodiment, even if the driver model 232 of the vehicle travel simulator 230 initially mounted on the vehicle 400 is a driver model that represents average behavior, The following effects can be obtained. That is, since the sensor group 410 acquires information of the vehicle 400 and the information processing apparatus 300 generates a driver model reflecting the driver's preference based on the information, the driver model balances a plurality of evaluation indexes. An effect is obtained that the traveling can be controlled in consideration.

Fifth Embodiment FIG. 14 is a block diagram showing a configuration of a vehicle 500 and an information processing apparatus 510 according to a fifth embodiment of the present invention. As shown in FIG. 14, a vehicle 500 according to the fifth embodiment includes the sensor group 410 described in the fourth embodiment, and a communication unit 520. An information processing apparatus 510 according to the fifth embodiment includes a communication unit 530 in addition to the configuration of the information processing apparatus 300 described in the third embodiment.

  The information processing device 510 is installed outside the vehicle 500. The vehicle 500 and the information processing apparatus 510 communicate with each other via the communication unit 520 and the communication unit 530.

  The information processing apparatus 510 acquires information on the traveling vehicle acquired by the sensor group 410 of the vehicle 500, for example, the position, direction, speed, and acceleration of the vehicle via the communication unit 530, and acquires the acquired information. It stores in the actual travel data storage unit 210 as travel data. The information processing device 510 adjusts the weight parameter 233 based on the stored actual travel data as described in the third embodiment, and the driver model 232 including the adjusted weight parameter 233 is added to the vehicle 500. Send.

  As described above, according to the fifth embodiment, the vehicle 500 includes the sensor group 410 and the communication unit 520, and the information processing apparatus 510 receives the information acquired by the sensor group 410. Equipped with The information processing device 510 adjusts the weight parameter 233 based on the received information, and transmits a driver model 232 including the adjusted weight parameter 233 to the vehicle 500.

  By adopting this configuration, according to the fifth embodiment, it is assumed that driver model 232 of vehicle travel simulator 230 initially mounted on information processing device 510 is a driver model representing average behavior. Also, the following effects can be obtained. That is, the sensor group 410 acquires the information of the vehicle 500, and the information processing device 510 generates a driver model reflecting the preference of the driver based on the information and transmits the driver model to the vehicle 500. According to the driver model, it is possible to control traveling in consideration of the balance of a plurality of evaluation indexes.

  In addition, even when the vehicle driven by the driver is different, the traveling can be controlled to reflect the driver's preference by receiving a driver model reflecting the driver's preference from the outside of the vehicle. can get.

  In the present embodiment, it has been described that the vehicle 500 transmits and receives information to and from the information processing apparatus 510 via the communication units 520 and 530. However, the present invention is not limited to this. Information may be exchanged using a storage medium.

Sixth Embodiment FIG. 15 is a functional block diagram of an information processing apparatus 600 according to a sixth embodiment of the present invention. As shown in FIG. 15, the information processing apparatus 600 according to the sixth embodiment replaces the adjusting section 270 of the information processing apparatus 300 described in the third embodiment with reference to FIG. The configuration further includes an individual driver model storage unit 620 and a classification unit 630.

  In addition to the function of the adjustment unit 270 described in the third embodiment, the adjustment unit 610 has a function of repeatedly adjusting the value of the weight parameter until a predetermined timing. That is, the adjustment unit 610 has a function of feeding back the adjusted weight parameter to the simulation of vehicle travel and adjusting the value of the weight parameter so as to conform to the driving preference of the driver.

  Here, the driver model using the value of the weight parameter adjusted by the adjustment unit 610 is hereinafter referred to as an “individual driver model”. The individual driver model is a driver model generated so as to conform to the driving preference of each driver under various traveling environments.

  The individual driver model storage unit 620 of FIG. 15 has a function of storing an individual driver model. The classification unit 630 has a function of classifying the individual driver model stored in the individual driver model storage unit 620 based on the similarity of the driving preference of the driver.

  In the sixth embodiment, an individual driver model is generated, classification is performed on the generated individual driver model based on the similarity of driving preference of the driver, and the classification result is applied to various applications. explain.

  In FIG. 15, the components given the same reference numerals as those in FIG. 10 have the same functions as the components described in the third embodiment. However, in the sixth embodiment, it is assumed that the actual traveling data storage unit 210 stores a plurality of actual traveling data regarding a plurality of drivers. In addition, it is assumed that the traveling environment data storage unit 220 stores traveling road information, environmental information, other object information, and the like when the plurality of pieces of actual traveling data are obtained. It is assumed that actual traveling data stored in the actual traveling data storage unit 210 and traveling environment data stored in the traveling environment data storage unit 220 are associated with each other.

  The actual traveling data storage unit 210 may store a plurality of actual traveling data in different traveling environments regarding one driver, not limited to a plurality of actual traveling data related to a plurality of drivers.

  The generation of an individual driver model will be described.

  The adjustment unit 610 includes a separation degree calculation unit 611, an adjustment determination unit 612, and a weight calculation unit 613.

  The deviation calculation unit 611 calculates the deviation of the evaluation value of the simulation travel data with respect to the evaluation value of the actual traveling data for each evaluation index described in the third embodiment. The adjustment determination unit 612 determines the necessity of adjustment of the value of the weighting parameter based on a predetermined standard based on the separation calculated by the separation calculation unit 611. When the adjustment determination unit 612 determines that the adjustment is necessary, the weight calculation unit 613 adjusts (calculates) the value of the weight parameter so as to emphasize the evaluation index having a large divergence as described in the third embodiment. I do.

  FIG. 16 is a flowchart showing the operation of the information processing apparatus 600 according to the sixth embodiment. In FIG. 16, steps S201 to S207 are the same processing as the processing of the same reference numerals in FIG. 11 of the third embodiment, and in the sixth embodiment, steps S300 and S301 are newly added. . The operation of the information processing apparatus 600 will be described with reference to FIG. Note that FIG. 16 does not include the operation of the classification unit 630 of the information processing device 600. Further, in FIG. 16, the detailed description of the processes denoted by the same reference numerals in FIG. 11 will be omitted.

  Step S 205 of FIG. 16 is performed by the deviation calculation unit 611 of the adjustment unit 610. That is, based on the comparison result in step S204, the gap deviation calculation unit 611 calculates the gap degree of the evaluation value of the simulation travel data to the evaluation value of the actual travel data for each evaluation index.

  Subsequently, the adjustment determination unit 612 determines the necessity of adjustment of the value of the weight parameter based on a predetermined standard based on the degree of separation calculated by the degree of separation calculation unit 611 (step S300). For example, the adjustment determination unit 612 sets in advance each threshold value of the divergence with respect to each evaluation index, and if all the divergences are smaller than the respective thresholds, “adjustment unnecessary”, otherwise “adjustment” It may be determined that it is necessary. However, the criterion of the determination is not limited to this.

  If the adjustment determination unit 612 determines that “adjustment is unnecessary” (No in step S300), the driver model using the value of the weight parameter at that time is stored in the individual driver model storage unit 620 as an individual driver model (step S301).

  On the other hand, when the adjustment determination unit 612 determines that “adjustment is necessary” (Yes in step S300), the adjustment determination unit 612 instructs the weight calculation unit 613 to calculate the value of the weight parameter. The weight calculation unit 613 calculates the value of the weight parameter so as to emphasize the evaluation index having a large degree of separation according to the instruction (step S206).

  Subsequently, the weight calculation unit 613 reflects the calculated value of the adjusted weight parameter on the driver model 232 of the vehicle travel simulator 230 (step S207).

  Thereafter, the process returns to step S201, and steps S201 to S207 are repeated until it is determined by the adjustment determination unit 612 that "adjustment is unnecessary" in step S300.

  In step S300, if the adjustment determination unit 612 determines that “adjustment is unnecessary”, as described above, the driver model using the value of the weight parameter at that time is stored in the individual driver model storage unit 620 as an individual driver model ( Step S301).

  The information processing apparatus 600 executes the operation shown in FIG. 16 described above on each actual traveling data in various traveling environments stored in the actual traveling data storage unit 210.

  FIG. 17 is a diagram showing an example of the individual driver model 621 stored in the individual driver model storage unit 620 as a result of the above-described operation. As shown in FIG. 17, the individual driver model 621 includes a driver ID (IDentification), a traveling environment, and a weight (individual value).

  The driver ID is identification information of the driver that has obtained the actual travel data used to generate the individual driver model. The traveling environment indicates the environment when the actual traveling data used to generate the individual driver model is obtained. Here, as an example, it is indicated that "traveling path" and "weather" are designated as the traveling environment.

  The weight (individual value) indicates the value of the weight parameter adjusted until it is determined by the adjustment unit 610 as “adjustment unnecessary” as described above. The weights (individual values) respectively corresponding to the weight parameters W1, W2, and W3 described in the third embodiment are respectively denoted as W1i, W2i, and W3i.

  In FIG. 17, for example, with regard to the driver with the driver ID = “001”, the driver model while adjusting the value of the weighting parameter as described above in the traveling environment where the type of traveling path is “city area” and the type of weather is “fine”. As a result of executing a simulation of vehicle travel using the above, it is shown that weights W1i = “0.2”, W2i = “0.4”, and W3i = “0.4” are obtained.

  The other individual driver model 621 of FIG. 17 is also a model obtained similarly.

  Next, classification of the individual driver model 621 obtained as shown in FIG. 17 by the classification unit 630 included in the information processing apparatus 600 based on the weight similarity will be described.

  FIG. 18 is a block diagram showing the configuration of the classification unit 630 included in the information processing apparatus 600. As shown in FIG. 18, the classification unit 630 includes a group generation unit 631, a target driver model acquisition unit 632, a group determination unit 633, and a group storage unit 634.

  The classification unit 630 classifies the individual driver model 621 at a predetermined timing after the plurality of individual driver models 621 are stored in the above individual driver model storage unit 620. For example, the classification unit 630 may perform classification at the timing when the number of individual driver models 621 equal to or greater than the threshold is stored in the individual driver model storage unit 620, or may perform classification according to an instruction from the user. May be Here, the classification includes grouping the individual driver models 621 stored in the individual driver model storage unit 620 and determining which group the newly generated individual driver model 621 belongs to. .

  Each component of the classification unit 630 will be specifically described.

  The group generation unit 631 acquires the individual driver model 621 from the individual driver model storage unit 620 shown in FIG. 15, and groups the acquired individual driver models 621 based on the weight similarity. Specifically, the group generation unit 631 generates at least one group by grouping the acquired individual driver models 621 based on the degree of similarity of the weights (individual values) W1i, W2i, and W3i. The individual driver model 621 belongs to any of the generated groups.

  The group generation unit 631 may group the individual driver models 621 based on the weight similarity using, for example, an existing method such as k-means. As a result, the individual driver models 621 of drivers whose weights are close, that is, close in driving preference, belong to the same group.

  The grouping method is not limited to the k-means method, and any method may be used as long as it can generate at least one group based on the similarity of target data.

  In general, when grouping is performed using the k-means method, representative values of values of grouped data are obtained. Here, when grouping is performed by the k-means method based on the respective weights (individual values) W1i, W2i, and W3i of the plurality of individual driver models 621, representative values of the weights W1i, W2i, and W3i can be obtained. The group generation unit 631 may use this representative value as a weight of the generated driver model of each group. A driver model using a representative value of this weight is referred to as a "representative driver model". Further, representative values of the weights (individual values) W1i, W2i, and W3i will be denoted as weights (representative values) W1r, W2r, and W3r, respectively.

  FIG. 19 is a view showing an example of a representative driver model of a group generated by the group generation unit 631 based on a plurality of individual driver models 621. As described above, the weights (representative values) W1r, W2r, and W3r are representative values obtained from the weights (individual values) of the individual driver models 621 belonging to the respective groups.

  Even when classification is performed using a method other than k-means, the group generation unit 631 may calculate a representative value such as an average value and use the calculated value as the weight of each group. In addition, the weight of the representative driver model is not limited to using the representative value. For example, weights (individual values) W1i, W2i, and W3i used for any of the individual driver models 621 belonging to the same group may be used as the weights of the representative driver model of that group.

  Here, in addition to the weights (individual values), the group generation unit 631 may use the type of traveling environment such as “traveling road”, “weather” or the like in grouping of the individual driver models 621. In this case, the classification method may be applied by replacing these types of traveling environments, for example, "city area", "suburbs", etc., with category values.

  Specifically, for example, the group generation unit 631 replaces “city area” with “1”, “suburbia” with “2”, etc., and “sunny” is “1” for “weather”. After replacing “cloudy” with “2” or the like, the k-means method may be applied.

  At this time, the group generation unit 631 sets the necessary number of thresholds in advance for each traveling environment, compares the threshold with each representative value of the category value of each traveling environment, and The type may be determined. For example, it is assumed that “1.5” is set as the threshold value for “weather”. At this time, the group generation unit 631 selects the type of travel environment of the group, "sunny" if the representative value of "weather" is less than "1.5", "sunny / cloudy" if "1.5". If it is larger than "1.5", it may be "cloudy".

  As described above, the group generation unit 631 generates a group of individual driver models having similar driving preferences to each other. The group generation unit 631 stores the generated representative driver model of the group in the group storage unit 634.

  Next, the function of the classification unit 630 to determine to which group the individual driver model 621 newly generated by the information processing apparatus 600 belongs will be described. This function may be performed, for example, in response to an instruction from the user after the above-described group is generated.

  Specifically, the classification unit 630 performs the following operation. That is, the target driver model acquisition unit 632 illustrated in FIG. 18 acquires an individual driver model (hereinafter also referred to as “target driver model”) newly generated by the information processing apparatus 600. The group determination unit 633 determines which group the acquired target driver model belongs to. The method of determining the group is not particularly limited.

  For example, the group determination unit 633 compares the weights (individual values) W1i, W2i, and W3i of the target driver model with the weights (representative values) W1r, W2r, and W3r of the representative driver models of the respective groups, respectively. A group of representative driver models having weights (representative values) W1r, W2r, and W3r closest to the value W1i, W2i, and W3i may be determined as a group to which the target driver model belongs.

  The output unit 635 may display the group determined by the group determination unit 633 on the display unit 260 of the information processing device 600. FIG. 20 is a diagram showing an example of the driver support screen 640 displayed on the display unit 260 by the output unit 635. As shown in FIG.

  Here, after the target driver model is obtained by the target driver model obtaining unit 632, the group determining unit 633 described above causes the group to be displayed in response to pressing of the group determining button 641 included in the driver support screen 640 by the user. You may determine the

  The output unit 635 displays the result determined by the group determination unit 633 on the display unit 260. As shown in FIG. 20, the output unit 635 may display, for example, a group ID in which the target driver model is determined to belong, such as “your driving is included in“ group A ””.

  The output unit 635 may display various information related to the group to which the target driver model belongs, on the display unit 260, not limited to the determination result as described above. That is, the output unit 635 can display information according to the driving preference of the target driver model by holding in advance information on driving preference according to the weight of the representative driver model of each group.

  For example, the output unit 635 holds, for each group, information representing driving preferences (driving characteristics) according to the weight of the representative driver model, for example, information such as “driving is rough” and “driving is cautious”. deep. Then, the output unit 635 may display, on the display unit 260, together with the group ID to which the target driver model belongs, information indicating the driving characteristics thereof.

  In addition, the output unit 635 may determine a good representative driver model in advance, and display the result of comparison between the target driver model and the good representative driver model on the display unit 260.

  In addition, the above classification results can be used for various applications. Hereafter, the application of the classification result will be described.

  Classification results can be used to set car insurance premiums. That is, the output unit 635 holds in advance insurance information for determining automobile insurance premiums and the like according to the weight of the representative driver model for each group. Then, based on the insurance information of the group to which the target driver model belongs, the output unit 635 calculates a car insurance premium suitable for the group, and displays it on the display unit 260.

  FIG. 21 is a view showing another example of the driver support screen 640 displayed on the display unit 260 by the output unit 635. As shown in FIG. As shown in FIG. 21, the output unit 635 may display, for example, the group name to which the target driver model belongs and the automobile insurance premium applied to the group on the display unit 260.

  As described above, by using the classification result for setting the car insurance premium, for example, the accident incidence rate according to the weight of the representative driver model is calculated, and the insurance premium of the group having a relatively high accident incidence rate is compared. You can make settings such as making it higher.

  The classification results can also be used to recommend product purchases. That is, the output unit 635 holds, in advance, vehicle information for determining a vehicle or a vehicle control option corresponding to the weight of the representative driver model for each group. Then, based on the vehicle information of the group to which the target driver model belongs, the output unit 635 determines a recommended product (vehicle type, brake assist, etc.) suitable for the group, and displays it on the display unit 260.

  FIG. 22 is a diagram showing another example of the driver support screen 640 displayed on the display unit 260 by the output unit 635. As shown in FIG. As shown in FIG. 22, the output unit 635 may display, for example, the group name to which the target driver model belongs and the recommended product suitable for the group on the display unit 260.

  The information processing apparatus 600 may also be mounted on a vehicle as shown in FIG. In this case, the classification result can be used to search for a driving route. That is, the output unit 635 holds, in advance, information (route information) of the driving route according to the weight of the representative driver model for each group. For example, according to the weight, the output unit 635 holds driving characteristics such as “I want to run a near route even if traffic jams” or “I want to run traffic as much as possible” in association with the group. Then, the output unit 635 searches for a driving route suitable for the driving characteristic of the group to which the individual driver model of the driver of the vehicle belongs, and displays the driving route on the display of the vehicle.

  Also, the classification result may be used for road guidance. That is, the output unit 635 holds, in advance, road guidance information corresponding to the weight of the representative driver model for each group. For example, the output unit 635 associates and holds preferences regarding congestion and groups. Then, the output unit 635 displays a route with less traffic congestion or a route with congestion on the display of the vehicle according to the preference of the group to which the target driver model belongs.

  Also, the classification result may be used for driving support. That is, the output unit 635 holds, in advance, driving support information corresponding to the weight of the representative driver model for each group. The output unit 635 determines driving support suitable for the group to which the individual driver model of the driver of the vehicle belongs, and reflects it in the operation of the vehicle. The output unit 635 may operate, for example, to step on or off the accelerator in accordance with the driver model of the group, or may operate to perform safer operation without complying.

  Also, the classification result may be used for warning display. That is, the output unit 635 holds in advance warning information corresponding to the weight of the representative driver model for each group. Then, the output unit 635 may display warning information associated with the group to which the target driver model belongs, on the display of the vehicle. For example, when it is determined that the warning information is associated in advance with the group considered to have a relatively high accident rate, the output unit 635 determines that the individual driver model of the driver of the vehicle belongs to the group, The display of the vehicle may display a warning prompting safe driving.

  For example, when it is determined that an individual driver model for a certain driver is generated and classified on a daily basis, and it is determined that the individual driver model relating to a certain day's driving is classified into a group different from normal, the output unit 635 outputs A warning may be displayed on the display. Alternatively, in such a case, the output unit 635 may instruct the vehicle to limit the depression of the accelerator.

  The output unit 635 may also transmit the information obtained as described above to a communicable management device or the like. For example, the information obtained as described above regarding the individual driver model of the driver of the sales vehicle may be transmitted from the information processing device 600 mounted on the sales vehicle to the management device of the sales center.

  As described above, according to the sixth embodiment, the information processing apparatus 600 causes the adjusting unit 610 to simulate the traveling of the vehicle while adjusting the value of the weight, thereby making the individual driver closer to the actual traveling of the driver. Generate a model. Then, the classification unit 630 generates at least one group from the generated plurality of individual driver models based on the similarity of the driver model weight, and the newly generated individual driver model belongs to any group. Determine if

  By adopting the above configuration, according to the sixth embodiment, classification of a driver model generated in consideration of a plurality of indexes can be performed, so classification of driving characteristics of the driver with high accuracy is performed. The effect of being able to In addition, since the information is provided to the driver based on the result of the classification with high accuracy as described above, it is possible to provide information more suitable for the driving characteristic of the driver.

  Each part of the information processing apparatus shown in FIG. 1 etc. is realized by the hardware resources illustrated in FIG. That is, the configuration shown in FIG. 23 includes a processor 11, a random access memory (RAM) 12, a read only memory (ROM) 13, an external connection interface 14, a recording device 15, and a bus 16 for connecting each component.

  In each embodiment described above, as an example executed by the processor 11 shown in FIG. 23, after supplying a computer program capable of realizing the functions described above to the information processing apparatus, the processor 11 executes the computer program. The case where the implementation is realized by reading out to the RAM 12 and execution is described. However, some or all of the functions shown in each block of the information processing apparatus shown in FIG. 1 and the like may be realized as hardware.

  The supplied computer program may be stored in a computer readable storage device such as a readable / writable memory (temporary storage medium) or a hard disk drive. And, in such a case, the present invention can be understood as being constituted by a code representing such a computer program or a storage medium storing such a computer program.

  The present invention has been described above with reference to the embodiments described above. However, the present invention is not limited to the embodiments described above. That is, the present invention can apply various modes that can be understood by those skilled in the art, such as various combinations or selections of various disclosed elements, within the scope of the present invention.

11 processor 12 RAM
13 ROM
14 external connection interface 15 recording device 16 bus 100, 200, 300, 510, 600 information processing device 110 generation unit 120 determination unit 210 actual traveling data storage unit 211 actual traveling data acquisition unit 220 traveling environment data storage unit 230 vehicle traveling simulator 231 Control unit 232 Driver model 233 Weight parameter 240 Simulation traveling data storage unit 241 Simulation traveling data acquisition unit 250 Evaluation unit 260 Display unit 270 Adjustment unit 400 Vehicle 410 Sensor group 500 Vehicle 520, 530 Communication unit 610 Adjustment unit 611 Gap calculation unit 612 Adjustment determination unit 613 Calculation unit 620 Individual driver model storage unit 621 Individual driver model 630 Classification unit 631 Group generation unit 632 Target driver model acquisition unit 633 Flop discrimination section 634 group storage unit 635 output unit 640 driver support screen 641 group determination button

Claims (10)

By grouping the plurality of driver models based on the weights of the plurality of driver models that determine the operation of the vehicle relative to the driving environment based on a predetermined objective function that uses the weights for each of the plurality of indicators. Generating means for generating at least one group;
An information processing apparatus comprising: a determination unit that determines the group to which a target driver model belongs and outputs a determination result. The information processing apparatus according to claim 1, wherein the generation unit generates the group based on the degree of similarity of the weights. The generation means calculates a representative value of the weight of the group based on the weight used for the driver model belonging to the generated group;
The information processing apparatus according to claim 1, wherein the determination unit determines a group to which the target driver model belongs based on a distance between a weight used for the target driver model and a representative value of the calculated weight. . An output unit that holds predetermined information associated with the group and outputs the predetermined information associated with the group to which the target driver model determined by the determination unit belongs based on the predetermined information The information processing apparatus according to any one of claims 1 to 3, comprising: The predetermined information is insurance information for determining a premium.
The information processing apparatus according to claim 4, wherein the output unit outputs, based on the insurance information, a premium of a group to which the target driver model determined by the determination unit belongs. The predetermined information is route information indicating a travel route,
5. The information processing apparatus according to claim 4, wherein the output unit outputs the route information associated with a group to which the target driver model determined by the determination unit belongs based on the route information. The predetermined information is warning information indicating a warning to the driver,
5. The information processing apparatus according to claim 4, wherein the output unit outputs the warning information associated with a group to which the target driver model determined by the determination unit belongs based on the warning information. further,
Using the values of the plurality of indicators of the actual travel data, which is travel data obtained by the travel of the vehicle by the driver, the travel environment data representing the travel environment related to the travel, and the driver model, the driver Adjusting means for adjusting a weight related to each of the plurality of indicators based on a difference between values of the plurality of indicators of simulation traveling data which is traveling data obtained from a simulator simulating the traveling of a vehicle;
The generation unit generates at least one group by grouping the plurality of driver models whose weights are adjusted by the adjustment unit.
The information processing apparatus according to any one of claims 1 to 7, wherein the determination unit determines the group to which the target driver model whose weight is adjusted by the adjustment unit belongs, and the determination result. By grouping the plurality of driver models based on the weights of the plurality of driver models that determine the operation of the vehicle relative to the driving environment based on a predetermined objective function that uses the weights for each of the plurality of indicators. Create at least one group,
A classification method of determining the group to which a target driver model belongs and outputting the determination result. By grouping the plurality of driver models based on the weights of the plurality of driver models that determine the operation of the vehicle relative to the driving environment based on a predetermined objective function that uses the weights for each of the plurality of indicators. A process of generating at least one group;
A computer program that causes a computer to execute the process of determining the group to which a target driver model belongs and outputting the determination result.

Images