Information processing device and information processing method

Abstract

To provide an information processing device that proposes the optimal setup of a vehicle using feedback information from a driver driving the vehicle as a constraint condition.SOLUTION: An information processing device includes a processor. The processor inputs information about a course a vehicle travels, setup information about the setup of the vehicle, and feedback information from a driver driving the vehicle into a learned model, and proposes the optimum setup when the vehicle travels the course with the output from the learned model.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus and an information processing method.

Background Art

[0002] Patent Document 1 describes design specifications of a structure constituting a facility machine as explanatory variables, each of a plurality of performance elements having a trade-off relationship in the structure as objective variables, and a plurality of learned models generated by machine learning using each of a plurality of training data sets including each of the explanatory variables and the objective variables. A learned model storage unit that stores the models, and a plurality of performance element estimated values output when the design specifications are input to each of the plurality of learned models are obtained, and the optimal value of the design specifications is determined by multi-objective optimization based on a plurality of objective functions related to the plurality of performance element estimated values. By including an optimal value determination unit, it discloses a technique aimed at providing a design apparatus capable of determining the optimal value of the design specifications of a structure constituting a facility machine in a short time while considering the performance elements of the structure having a trade-off relationship.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in motorsports, the optimal values of vehicle setups vary due to disturbance factors such as the temperature, humidity, wind speed, and wind direction on the day, so it is necessary to consider those disturbance factors. Since the learned models generated by conventional machine learning consider the disturbance factors as constant, a difference from the measured values occurs.

[0005] Furthermore, if a user requests that some of the explanatory variables not be changed, or that a certain value of the target variable not be changed, the trained model will treat all of these variables as variables and predict the optimal value unless these constraints are applied.

[0006] This disclosure is made in view of the above points, and aims to provide an information processing device and information processing method that propose an optimal vehicle setup using feedback information from a driver operating a vehicle as constraints. [Means for solving the problem]

[0007] An information processing device according to a first aspect of this disclosure comprises a processor which inputs information on the course on which the vehicle travels, setup information regarding the vehicle's setup, and feedback information from the driver operating the vehicle into a trained model, and the trained model Using the above setup information, the lap time and handling characteristics at each corner included in the course are predicted for multiple predicted cases, and in accordance with the evaluation of the handling characteristics input for each corner as feedback information from the driver, the multiple predicted cases are narrowed down to the predicted case having handling characteristics consistent with the evaluation, and among the narrowed down predicted cases, the setup that produces the shortest lap time is selected. Optimal setup when the aforementioned vehicle runs on the aforementioned course as suggest.

[0008] An information processing device according to a second aspect of the present disclosure is an information processing device according to a first aspect, wherein the optimal setup is a setup that takes into account the handling characteristics of the vehicle according to the driver, and the feedback information includes information regarding the handling characteristics of the vehicle according to the driver.

[0011] History of this disclosure 3 The information processing method relating to the embodiment involves a processor inputting information about the course the vehicle travels, setup information about the vehicle's setup, and feedback information from the driver operating the vehicle into a trained model, and the trained model Using the above setup information, the lap time and handling characteristics at each corner included in the course are predicted for multiple predicted cases, and in accordance with the evaluation of the handling characteristics input for each corner as feedback information from the driver, the multiple predicted cases are narrowed down to the predicted case having handling characteristics consistent with the evaluation, and among the narrowed down predicted cases, the setup that produces the shortest lap time is selected. Optimal setup when the aforementioned vehicle runs on the aforementioned course as Execute the proposed process. [Effects of the Invention]

[0012] According to the present disclosure, it is possible to provide an information processing apparatus that proposes an optimal setup of a vehicle using feedback information from a driver who drives the vehicle as a constraint condition.

Brief Description of the Drawings

[0013] [Figure 1] It is a block diagram showing an example of the hardware configuration of the information processing apparatus according to the present embodiment. [Figure 2] It is a block diagram showing an example of the functional configuration of the information processing apparatus. [Figure 3] It is a flowchart showing an example of the information processing flow by the information processing apparatus. [Figure 4] It is a flowchart showing an example of the information processing flow by the information processing apparatus. [Figure 5] It is a diagram showing an example of extraction of an optimal setup by the information processing apparatus. [Figure 6] It is a diagram showing an example of presentation of information by the information processing apparatus. [Figure 7] It is a diagram showing an example of presentation of information by the information processing apparatus

Modes for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of the present disclosure will be described with reference to the drawings. In each drawing, the same or equivalent components and parts are given the same reference numerals. Also, the dimensional ratios in the drawings are exaggerated for convenience of explanation and may be different from the actual ratios.

[0015] FIG. 1 is a block diagram showing an example of the hardware configuration of an information processing apparatus 10 according to the present embodiment. The information processing apparatus 10 is an apparatus that proposes an optimal setup for a vehicle, particularly a vehicle used in motor sports, using a learned model created by machine learning. Items that the information processing apparatus 10 proposes as an optimal setup using the learned model include engine output, vehicle height, wing height, wing angle, and the like.

[0016] As shown in FIG. 1, the information processing apparatus 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a storage 14, an input unit 15, a display unit 16, and a communication interface (I / F) 17. Each component is connected to be communicable with each other via a bus 19.

[0017] The CPU 11 is a central processing unit that executes various programs and controls each unit. That is, the CPU 11 reads a program from the ROM 12 or the storage 14 and executes the program using the RAM 13 as a work area. The CPU 11 performs control of the above-described components and various arithmetic processes according to the program recorded in the ROM 12 or the storage 14. In the present embodiment, an information processing program for proposing an optimal setup of a vehicle is stored in the ROM 12 or the storage 14.

[0018] The ROM 12 stores various programs and various data. The RAM 13 temporarily stores a program or data as a work area. The storage 14 is composed of a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a flash memory, and stores various programs including an operating system and various data.

[0019] The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used to perform various inputs.

[0020] The display unit 16 is, for example, a liquid crystal display, and displays various information. The display unit 16 may adopt a touch panel method and function as the input unit 15.

[0021] The communication interface 17 is an interface for communicating with other devices, and for example, standards such as Ethernet (registered trademark), FDDI, Wi-Fi (registered trademark) are used.

[0022] When executing the above information processing program, the information processing device 10 uses the above hardware resources to implement various functions. The functional configuration implemented by the information processing device 10 will now be described.

[0023] Figure 2 is a block diagram showing an example of the functional configuration of the information processing device 10.

[0024] As shown in Figure 2, the information processing device 10 has a functional configuration consisting of an acquisition unit 101, an optimal setup proposal unit 102, a model update unit 103, and a learned model 104. Each functional configuration is realized by the CPU 11 reading and executing an information processing program stored in the ROM 12 or storage 14.

[0025] The acquisition unit 101 acquires various information to propose an optimal vehicle setup. The various information acquired by the acquisition unit 101 includes information about the course the vehicle is traveling on, environmental information when the vehicle is traveling, setup information about the vehicle's setup, and feedback information from the driver operating the vehicle. Information about the course the vehicle is traveling on includes, for example, information about the total length of the course, distance information about the straights between corners, distance information for each corner, angle information for each corner, etc. Environmental information when the vehicle is traveling includes information such as weather, temperature, humidity, wind speed, wind direction, and road surface grip. Setup information includes, for example, information such as engine output, tire pressure, suspension damping force, vehicle height, wing height, and wing angle. Feedback information includes, for example, information about the driver's feeling about each corner (whether it was oversteer or understeer) when driving the vehicle on the course.

[0026] The acquisition unit 101 also acquires the actual time taken when a vehicle that has undergone the optimal setup proposed by the optimal setup proposal unit 102 (described later) runs on the course.

[0027] The optimal setup proposal unit 102 inputs the information acquired by the acquisition unit 101 into a pre-trained model 104, and uses the data output from the pre-trained model 104 to propose the optimal setup for the vehicle when it drives the course. The optimal setup proposed by the optimal setup proposal unit 102 is a setup that takes into account the vehicle's KPIs (Key Performance Indicators) according to the vehicle driver, for example, a setup that takes into account the handling characteristics according to the vehicle driver. The optimal setup proposal unit 102 also provides information on the estimated time when driving the course with the proposed optimal setup. The pre-trained model 104 is a model that has been machine-trained using an arbitrary method, taking into account environmental information such as weather, temperature, humidity, wind speed, wind direction, and road surface grip.

[0028] The model update unit 103 updates the trained model 104 using the information acquired by the acquisition unit 101. Specifically, the model update unit 103 compares the expected time and the actual time when driving the course with the optimal setup, and updates the trained model 104 based on the comparison result.

[0029] This shows an example of the update process of the trained model 104 by the model update unit 103 in the case of driving on a circuit. n is the number of corners on the circuit, the average vehicle speed at each corner, and the maximum value of lateral gravitational acceleration G. max measured and calculated values ​​such as b i (i is 1 to n), the prediction result by the trained model 104 is f i Let's assume that f i Let x be the environment variables required to find the value, where t is the number of environment variables.

[0030]

number

[0031] The error δ between the measured value and the prediction result from the trained model 104 can be expressed by the following formula.

[0032]

number

[0033] The user tunes the environment variable x so that this δ is minimized for each indicator, such as average vehicle speed and lateral gravitational acceleration. Optimized environment variable x opt This can be expressed by the following formula.

[0034]

number

[0035] The information processing device 10, with this configuration, can propose an optimal setup for when a vehicle is driving on a course, and can also tune the learned model 104 used when proposing the optimal setup.

[0036] Next, the operation of the information processing device 10 will be explained.

[0037] Figure 3 is a flowchart illustrating an example of the information processing flow by the information processing device 10. The CPU 11 reads an information processing program from the ROM 12 or storage 14, loads it into the RAM 13, and executes it, thereby performing information processing.

[0038] In step S101, the CPU 11 decides whether to perform tuning of the trained model 104 using the measured data as instructed by the user. If the CPU 11 decides not to perform tuning of the trained model 104 using the measured data as instructed by the user (step S101; No), the CPU 11 terminates the subsequent processing.

[0039] If tuning of the trained model 104 using actual measured data is performed (step S101; Yes), following step S101, in step S102, the CPU 11 acquires the actual measured data and divides it into laps.

[0040] Following step S102, in step S103, the CPU 11 selects a lap to be used for tuning, according to the user's instructions.

[0041] Following step S103, in step S104, the CPU 11 acquires information on the average vehicle speed and lateral acceleration (lateral GMAX) for corners from the measured data.

[0042] Following step S104, in step S105, the CPU 11 obtains initial environmental information based on user input. This initial environmental information includes climate-related information such as weather, temperature, humidity, wind speed, wind direction, and road surface grip.

[0043] Following step S105, in step S106, the CPU 11 predicts the average vehicle speed and lateral acceleration for corners based on the vehicle's basic setup, using the trained model 104.

[0044] Following step S106, in step S107, the CPU 11 compares the prediction results using the trained model 104 with the measured data and prompts the user to determine whether tuning of the trained model 104 is necessary. The user's determination is made by inputting it through a predetermined user interface displayed on the display unit 16 by the CPU 11.

[0045] If the user determines that tuning of the trained model 104 is necessary, in step S108, following step S107, the CPU 11 accepts tuning of environmental information such as weather, temperature, humidity, wind speed, wind direction, and road surface grip. Upon accepting the tuning of the environmental information, the CPU 11 returns to step S106 and uses the trained model 104 to predict the average vehicle speed and lateral acceleration of the corner based on the tuned environmental information.

[0046] On the other hand, if the user determines that tuning of the trained model 104 is not necessary, the CPU 11 terminates the series of processes.

[0047] The information processing device 10 can propose an optimal vehicle setup using a machine learning model 104 that has been tuned to the on-site environmental conditions by executing the series of processes shown in Figure 3.

[0048] To propose the optimal vehicle setup, it is necessary not only to suggest a setup that maximizes lap times, but also to correct the handling characteristics at each corner according to the driver's feedback. Correcting the handling characteristics requires considering both simulations using the trained model 104 and feedback from the driver.

[0049] The information processing device 10 according to this embodiment is capable of receiving feedback information from the driver and compares the feedback information from the driver with the handling characteristics in the basic setup proposed by the trained model 104. Through this comparison, the information processing device 10 according to this embodiment can achieve both correction of handling characteristics and improvement of lap times.

[0050] The following is an example of the handling characteristic correction process performed by the optimal setup proposal unit 102. Consider a certain corner a on the course, and assume that the driver has a problem with the handling characteristics for that corner. If the number of predicted cases in the Design of Experiments (DOE) is n, and the handling characteristics predicted by the trained model 104 are g, then considering the handling characteristics, the number of predicted cases is narrowed down as follows.

[0051] The narrowing down of the possibilities when the driver determines that there is oversteer in corner a is expressed by the following formula: g a (i) is the predicted handling characteristics in each prediction case, g a_base This represents the handling characteristics predicted by the trained model 104.

[0052]

number

[0053] On the other hand, if the driver determines that there is understeer in corner a, the narrowing down of options can be expressed by the following formula.

[0054]

number

[0055] The optimal setup suggestion unit 102 performs this narrowing down process for all corners of the course. If the remaining number of cases is n', the optimal setup suggestion unit 102 selects the i that minimizes δ using the following formula. By finding the i that minimizes δ, it is possible to search for the optimal setup that can achieve the fastest time, taking into account the handling characteristics of each corner.

[0056]

number

[0057] Figure 4 is a flowchart illustrating an example of the information processing flow by the information processing device 10. Information processing is performed when the CPU 11 reads an information processing program from the ROM 12 or storage 14, loads it into the RAM 13, and executes it. The flowchart shown in Figure 4 is a flowchart for searching for the optimal setup considering handling characteristics.

[0058] In step S111, the CPU 11 predicts a reference time and handling characteristics using the vehicle's basic setup with the trained model 104.

[0059] Following step S111, in step S112, the CPU 11 narrows down the predicted reference time and handling characteristics based on the changeable parameter range and the narrowed number of predicted cases.

[0060] Following step S112, in step S113, the CPU 11 determines whether it has finished processing all corners. If it has not finished processing all corners, the CPU 11 then determines in step S114 whether there was any feedback (chief complaint) from the driver regarding that corner.

[0061] If there is driver feedback in that corner (step S114; Yes), then in step S115, the CPU 11 determines whether the feedback indicated that the corner was understeer (US).

[0062] If the feedback indicates understeer (step S115; Yes), then in step S116, CPU 11 narrows down the options to those that tend to oversteer (OS) for that corner. On the other hand, if the feedback indicates oversteer (step S115; No), then in step S117, CPU 11 narrows down the options to those that tend to understeer for that corner.

[0063] If, in step S113, processing has been completed for all corners, then in step S118, the CPU 11 extracts the optimal setup from the narrowed-down cases.

[0064] The information processing device 10 can search for the optimal setup that is expected to yield the fastest time by performing a series of processes, taking into account the handling characteristics of each corner. Furthermore, when the information processing device 10 searches for the optimal setup that is expected to yield the fastest time, taking into account the handling characteristics of each corner, it may also search for the optimal setup after receiving feedback from the driver at both the corner entry and exit.

[0065] Figure 5 shows an example of optimal setup extraction by the information processing device 10. Figure 5 shows an example of searching for the optimal setup considering handling characteristics at the entrance and exit of a corner. In the graph of Figure 5, the positive direction on each axis represents an oversteer tendency, and the negative direction represents an understeer tendency. The symbol S1 in Figure 5 is a point plotted to represent the handling characteristics at that setting.

[0066] Suppose the vehicle is set to have handling characteristics corresponding to symbol S1, and the driver provides feedback that there was understeer at the corner entry and oversteer at the corner exit. In this case, the vehicle is constrained to the oversteer direction at the entry, i.e., the positive direction of the X-axis, and to the understeer direction at the exit, i.e., the direction of the Y-axis. Therefore, the information processing device 10 searches for the optimal setup within the range indicated by the pattern in the graph of Figure 5. In the case of Figure 5, the setting indicated by symbol S2 is considered to be the optimal setup.

[0067] If the information processing device 10 does not simply present the setup details but also explain the process by which it determined that the setup was optimal, it will be difficult for the vehicle engineers to actually adopt the optimal setup determined by the information processing device 10.

[0068] Therefore, the information processing device 10 according to this embodiment may not only propose an optimal setup using the trained model 104, but also present the expected time (lap time for one lap, sector time for each sector) based on that optimal setup. Furthermore, the information processing device 10 may present the time trend based on the setup in the form of a scatter plot.

[0069] Figure 6 shows an example of information presentation by the information processing device 10. The horizontal axis of the graph in Figure 6 represents vehicle height, and the vertical axis represents the lap time for one lap. In other words, the graph in Figure 6 plots the relationship between vehicle height and lap time. Figure 6 shows four points S11 to S14 on the graph, each point representing the relationship between vehicle height and lap time in the corresponding vehicle setup.

[0070] The information processing device 10 displays a graph like the one shown in Figure 6, allowing the vehicle engineer to understand what lap times can be achieved at different vehicle heights. In the example in Figure 6, it is shown that the fastest lap time can be achieved when the vehicle is set up to correspond to point S14.

[0071] Furthermore, when the information processing device 10 displays a graph like the one shown in Figure 6, the information displayed on the horizontal or vertical axis may be made variable based on input from the user.

[0072] Vehicle setup may include parameters that significantly affect lap times and parameters that have little effect on lap times. Therefore, the information processing device 10 may calculate and present the contribution of each setup parameter to the lap time.

[0073] Figure 7 shows an example of information presentation by the information processing device 10. The graph shown in Figure 7 is an example of the relationship between each setup parameter and its contribution. By calculating the contribution of each vehicle parameter and presenting it as shown in the graph in Figure 7, the information processing device 10 can provide vehicle engineers with information to help them decide which parameters to prioritize for adjustment.

[0074] Furthermore, the information processing that the CPU reads and executes in each of the above embodiments may be executed by various processors other than the CPU. Examples of such processors include PLDs (Programmable Logic Devices) such as FPGAs (Field-Programmable Gate Arrays) whose circuit configuration can be changed after manufacturing, and dedicated electrical circuits that are processors with circuit configurations specifically designed to execute specific processing, such as ASICs (Application Specific Integrated Circuits). In addition, the information processing may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (for example, multiple FPGAs, and a combination of a CPU and an FPGA). More specifically, the hardware structure of these various processors is an electrical circuit that combines circuit elements such as semiconductor elements.

[0075] Furthermore, while the above embodiments describe a configuration in which the information processing program is pre-stored (installed) in ROM or storage, the invention is not limited to this. The program may be provided in a form recorded on a non-transitory recording medium such as a CD-ROM (Compact Disk Read Only Memory), DVD-ROM (Digital Versatile Disk Read Only Memory), or USB (Universal Serial Bus) memory. Alternatively, the program may be provided in a form that is downloaded from an external device via a network. [Explanation of Symbols]

[0076] 10 Information Processing Devices 101 Acquisition Department 102 Optimal Setup Proposal Department 103 Model Update Section 104 Pre-trained models

Claims

1. Equipped with a processor, The aforementioned processor, Information about the course the vehicle will travel, setup information about the vehicle's setup, and feedback information from the driver operating the vehicle are input into the trained model. Using the aforementioned trained model, the lap time and handling characteristics at each corner included in the course are predicted for multiple prediction cases based on the setup information. In accordance with the evaluation of handling characteristics input for each corner as feedback information from the driver, the plurality of predicted cases are narrowed down to the predicted case having handling characteristics consistent with the evaluation. From the narrowed-down prediction cases, the setup that results in the shortest lap time is proposed as the optimal setup for the vehicle to drive on the course. Information processing device.

2. The aforementioned optimal setup is a setup that takes into account the handling characteristics of the vehicle according to the driver, The information processing apparatus according to claim 1, wherein the feedback information includes information relating to the handling characteristics of the vehicle according to the driver.

3. The processor, Information about the course the vehicle will travel, setup information about the vehicle's setup, and feedback information from the driver operating the vehicle are input into the trained model. Using the aforementioned trained model, the lap time and handling characteristics at each corner included in the course are predicted for multiple prediction cases based on the setup information. In accordance with the evaluation of handling characteristics input for each corner as feedback information from the driver, the plurality of predicted cases are narrowed down to the predicted case having handling characteristics consistent with the evaluation. From the narrowed-down prediction cases, the setup that results in the shortest lap time is proposed as the optimal setup for the vehicle to drive on the course. An information processing method that executes a process.

Images