Information processing equipment, vehicles, and programs

Abstract

To provide an information processing device, a vehicle and a program that are able to analyze, during travel, influence of factors such as air resistance and / or friction that occur when an autonomous vehicle travels on a road.SOLUTION: An information processing device 1 of the present disclosure comprises: an information acquisition unit 10 that can acquire a plurality of information items relating to a vehicle; an inference unit 20 that uses deep learning to infer a plurality of index values from the plurality of information items acquired by the information acquisition unit; and an operation control unit 30 that performs operation control for the vehicle on the basis of the plurality of index values.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to an information processing apparatus, a vehicle, and a program that include multivariate analysis using deep learning. [Background Art]

[0002] Patent Document 1 describes a vehicle having an automatic driving function. [Prior Art Literature] [Patent Literature]

[0003] [Patent Document 1] Japanese Unexamined Patent Publication No. 2022-035198 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] In conventional autonomous driving vehicles, it has been difficult to analyze the influence of factors such as air resistance and friction that occur when driving on a road while the vehicle is traveling.

[0005] The technology of the present disclosure provides an information processing apparatus, a vehicle, and a program that can analyze the influence of factors such as air resistance and / or friction that occur when an autonomous driving vehicle travels on a road while the vehicle is traveling. [Means for Solving the Problem]

[0006] According to one embodiment of the present disclosure, there is provided an information processing apparatus including: an information acquisition unit capable of acquiring a plurality of pieces of information related to a vehicle; an inference unit that infers a plurality of index values from the plurality of pieces of information acquired by the information acquisition unit using deep learning; and a driving control unit that executes driving control of the vehicle based on the plurality of index values.

[0007] According to one embodiment of the present disclosure, in the information processing device described above, the inference unit infers the plurality of index values ​​from the plurality of information by multivariate analysis using the integration method with deep learning.

[0008] According to one embodiment of the present disclosure, in the information processing apparatus, the information acquisition unit acquires the plurality of pieces of information in units of one billionth of a second, and the inference unit and the driving control unit use the plurality of pieces of information acquired in units of one billionth of a second to perform inference of the plurality of index values ​​and driving control of the vehicle in units of one billionth of a second.

[0009] According to one embodiment of the present disclosure, the information processing device further includes a strategy setting unit for setting a driving strategy for the vehicle until it reaches a destination, the driving strategy including at least one theoretical value of the optimal route to the destination, driving speed, tilt, and braking, and the driving control unit includes a strategy updating unit for updating the driving strategy based on the difference between the plurality of index values ​​and the theoretical values.

[0010] According to one embodiment of the present disclosure, in the information processing device, the information acquisition unit includes a sensor provided on the underside of the vehicle that can detect the temperature, material, and tilt of the ground under which the vehicle is traveling.

[0011] According to one embodiment of the present disclosure, in the information processing device, the plurality of index values ​​include a first index value relating to a first distance, which includes the stopping distance required for the vehicle to stop without colliding with an obstacle in the direction of travel of the vehicle, the driving control includes driving speed control, and the driving speed control is control of the driving speed of the vehicle and is performed based on the first index value.

[0012] According to one embodiment of the present disclosure, in the information processing device, the driving speed control includes control to drive the vehicle at the maximum speed at which the vehicle does not collide with the obstacle, and the maximum speed is calculated based on the first index value.

[0013] According to one embodiment of the present disclosure, in the information processing device described above, the maximum speed is a maximum speed within a range of legal speed limits and / or within a range of forward vehicle speed limits, and the forward vehicle speed is the travel speed of another vehicle traveling in front of the vehicle.

[0014] According to one embodiment of the present disclosure, in the information processing device described above, the first distance is the sum of the stopping distance and the margin distance.

[0015] According to one embodiment of the present disclosure, a vehicle equipped with the above-mentioned information processing device is provided.

[0016] According to one embodiment of the present disclosure, a program is provided for causing a computer to function as the information processing device.

[0017] It should be noted that the above summary of the invention does not enumerate all the necessary features of the present invention. Furthermore, subcombinations of these features may also constitute an invention. [Brief explanation of the drawing]

[0018] [Figure 1] This is a schematic diagram showing an example of a vehicle equipped with Central Brain. [Figure 2] This is a block diagram showing an example of an information processing device according to the first embodiment of the present disclosure. [Figure 3] This is a block diagram showing an example of an information processing device according to the second embodiment of the present disclosure. [Figure 4] This is a conceptual diagram showing an example of the configuration of an inference unit included in an information processing device according to the third embodiment of this disclosure. [Figure 5] This is a conceptual diagram showing an example of the processing content of the information acquisition unit, inference unit, and operation control unit included in the information processing apparatus according to the third embodiment of this disclosure. [Figure 6] This flowchart shows an example of the flow of the driving speed control process according to the third embodiment of this disclosure. [Figure 7]It is a block diagram schematically illustrating an example of the hardware configuration of a computer that functions as an information processing apparatus. DETAILED DESCRIPTION OF THE INVENTION

[0019] Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. Furthermore, not all combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0020] The information processing apparatus of the present disclosure may calculate an index value necessary for driving control with high accuracy based on a large amount of information related to vehicle control. Accordingly, the information processing apparatus of the present disclosure may be at least partially mounted on a vehicle to realize vehicle control.

[0021] Furthermore, the information processing apparatus of the present disclosure can realize Autonomous Driving in real time at Level 6 based on data obtained from AI / multivariate analysis / goal seeking / strategy planning / optimal probability solution / optimal speed solution / optimal course management / input from various sensors at the edge, and can provide a traveling system adjusted based on a delta optimal solution.

[0022] FIG. 1 is a schematic diagram illustrating an example of a vehicle equipped with a Central Brain. The Central Brain may be an example of the information processing apparatus 1 according to the present embodiment. As shown in FIG. 1, a plurality of Gate Ways may be communicably connected to the Central Brain. The Central Brain according to the present embodiment can realize Level 6 autonomous driving based on a plurality of pieces of information acquired via the Gate Ways.

[0023] "Level 6" represents an autonomous driving level, and is even higher than Level 5, which represents fully autonomous driving. Although Level 5 represents fully autonomous driving, it is equivalent to human driving, and there is still a probability of accidents occurring. Level 6 represents a level higher than Level 5, and is equivalent to a level where the probability of accidents occurs is lower than at Level 5.

[0024] The computing power required to achieve Level 6 (i.e., the computing power used to implement Level 6) is approximately 1000 times greater than the computing power required to achieve Level 5 (i.e., the computing power used to implement Level 5). Therefore, high-performance operational control that was not possible with Level 5 is achievable.

[0025] Figure 2 is a block diagram showing an example of an information processing device according to the first embodiment of the present disclosure. The information processing device 1 according to this embodiment includes at least an information acquisition unit 10 capable of acquiring a plurality of pieces of information related to a vehicle, an inference unit 20 that infers a plurality of index values ​​from the plurality of pieces of information acquired by the information acquisition unit 10, and a driving control unit 30 that performs driving control of the vehicle based on the plurality of index values.

[0026] The information acquisition unit 10 is capable of acquiring various types of information related to the vehicle. This information acquisition unit 10 may include, for example, communication means for acquiring information that can be obtained via a network from sensors attached to various parts of the vehicle, or from servers (not shown). Examples of sensors included in the information acquisition unit 10 include radar, LiDAR, high-resolution, telephoto, ultra-wide-angle, 360-degree, and high-performance cameras, vision recognition, micro-sound sensors, ultrasonic sensors, vibration sensors, infrared sensors, ultraviolet sensors, electromagnetic wave sensors, temperature sensors, humidity sensors, spot AI weather forecasting, high-precision multi-channel GPS, and / or low-altitude satellite information. Alternatively, it may include long-tail incident AI data. Long-tail incident AI data refers to trip data from vehicles equipped with Level 5 (i.e., vehicles equipped with devices capable of achieving Level 5 computing power (here, as an example, the information processing device 1)).

[0027] Information that can be acquired by multiple types of sensors includes the temperature and material of the ground (e.g., road), ambient temperature, ground tilt, road freezing conditions and moisture content, the material and wear status of each tire, air pressure, road width, whether overtaking is prohibited, presence or absence of oncoming vehicles, vehicle type information of vehicles in front and behind, cruising status of those vehicles, and / or surrounding conditions (birds, animals, soccer balls, accident vehicles, earthquakes, fires, wind, typhoons, heavy rain, light rain, blizzards, and / or fog). In this embodiment, by utilizing Level 6 computing power, these detections can be performed every one billionth of a second (nanosecond).

[0028] It is particularly important to note that the information acquisition unit 10 described above includes a vehicle underbody sensor located beneath the vehicle that can detect the temperature, material, and tilt of the ground under which the vehicle is traveling. This vehicle underbody sensor can be used to perform independent smart tilt.

[0029] The inference unit 20 may be capable of inferring indexed values ​​related to vehicle control from multiple pieces of information acquired by the information acquisition unit 10 using machine learning, or more specifically, deep learning. In other words, the inference unit 20 can be composed of AI (Artificial Intelligence).

[0030] The inference unit 20 uses the computing power used to achieve Level 6 (hereinafter also referred to as "Level 6 computing power") to perform multivariate analysis using the integral method shown in equation (1) below (see, for example, equation (2)) on nanosecond-by-nanosecond data and long-tail incident AI data collected by the information acquisition unit 10 from a large group of sensors, etc., thereby obtaining accurate index values. More specifically, by calculating the integral values ​​of the delta values ​​of various Ultra High Resolution sensors using Level 6 computing power, the inference unit 20 can obtain the indexed values ​​of each variable at the edge level and in real time, and obtain the results that occur in the next nanosecond (i.e., the indexed values ​​of each variable, which are the indexed values) with the highest probability. To achieve this, for example, the delta value (for example, the change in a small time interval) of a function that can identify each variable (for example, multiple pieces of information acquired by the information acquisition unit 10), such as air resistance, road resistance, road elements (for example, debris), and slip coefficient, is integrated over time and input into the deep learning model of the inference unit 20 (for example, a trained model obtained by performing deep learning on a neural network). The deep learning model of the inference unit 20 outputs an index value (for example, the index value of the highest confidence level (i.e., evaluation value)) corresponding to the input integral value. The output of the index value is done in nanoseconds.

[0031]

number

[0032]

number

[0033] For example, in equation (1), “f(A)” is a simplified representation of a function that shows the behavior of various variables such as air resistance, road resistance, road elements (e.g., debris), and slip coefficient. Also, for example, equation (1) is an equation that shows the time integral v of “f(A)” from time a to time b. In the equation, DL stands for deep learning (for example, a deep learning model optimized by performing deep learning on a neural network), and dA n / dt represents the delta value of f(A,B,C,D,···,N), where A,B,C,D,···,N represent air resistance, road resistance, road elements (e.g., debris), and slip coefficient, and f(A,B,C,D,···,N) represents a function that shows the behavior of A,B,C,D,···,N, V n This indicates the value (i.e., the index value) output from a deep learning model that has been optimized by performing deep learning on a neural network.

[0034] Here, we have given an example of a configuration in which the integral value obtained by integrating the delta value of a function over time is input to the deep learning model of the inference unit 20, but this is merely one example. For example, the integral value obtained by integrating the delta value of a function that represents the behavior of each variable such as air resistance, road resistance, road elements, and slip coefficient over time (for example, the result that will occur in the next nanosecond) may be inferred by the deep learning model of the inference unit 20, and as an inference result, the integral value with the highest confidence level (i.e., evaluation value) may be obtained by the inference unit 20 every nanosecond.

[0035] Furthermore, while examples of inputting integral values ​​into a deep learning model and outputting integral values ​​from a deep learning model are given here, these are merely examples, and the technology of this disclosure can be implemented without using integral values. For example, deep learning may be performed on a neural network using training data where values ​​corresponding to A, B, C, D, ..., N are used as example data and values ​​corresponding to at least one index value (for example, the result that occurs in the next nanosecond) are used as ground truth data, so that at least one index value is inferred by an optimized deep learning model.

[0036] The indexed values ​​(i.e., index values) of each variable obtained by the inference unit 20 can be further refined by increasing the number of Deep Learning iterations. For example, more accurate index values ​​can be calculated using vast amounts of data such as tire and motor rotation, steering angle, road material, weather, the effects of debris and quadratic deceleration, slippage, and steering and speed control methods for balance loss and recovery, as well as long-tail incident AI data.

[0037] The driving control unit 30 may perform vehicle driving control based on a plurality of index values ​​identified by the inference unit 20. This driving control unit 30 may be capable of realizing automatic vehicle driving control. Specifically, the result occurring in the next nanosecond can be obtained from the plurality of index values ​​with the highest probability value, and vehicle driving control can be performed taking this probability value into consideration. That is, the driving control unit 30 may obtain the index value with the highest confidence level (i.e., evaluation value) as the result occurring in the next nanosecond from the plurality of index values, and perform vehicle driving control according to the obtained index value.

[0038] According to the information processing device 1 with the configuration described above, it is possible to perform information analysis and inference using Level 6 computing power, which is far greater than Level 5 computing power, thus enabling a level of sophistication incomparable to before. This makes it possible to control vehicles for safe autonomous driving. Furthermore, the multivariate analysis by the above AI can create a value difference of 1000 times compared to the world of Level 5.

[0039] Figure 3 is a block diagram showing an example of an information processing device according to a second embodiment of the present disclosure. The information processing device 1A according to this embodiment differs from the information processing device 1 according to the first embodiment described above in that, in addition to the information processing device 1, it includes a strategy setting unit 40 for setting a driving strategy until the vehicle reaches its destination.

[0040] The strategy setting unit 40 may set a driving strategy from the current location to the destination based on destination information entered by the vehicle occupants, traffic information between the current location and the destination, etc. In doing so, it may take into account the information at the time the strategy setting is calculated, that is, the data currently acquired by the information acquisition unit 10. This is to calculate a more realistic theoretical value by taking into account the surrounding conditions at that moment, rather than just calculating a simple route to the destination. The driving strategy may consist of the optimal route to the destination (strategic route), driving speed, tilt, and at least one theoretical value of braking (i.e., the theoretical value of driving speed, the theoretical value of tilt, and / or the theoretical value of brake control value (in other words, the parameter that controls the braking system)). Preferably, the driving strategy can consist of all of the theoretical values ​​of the optimal route, driving speed, tilt, and braking mentioned above (i.e., the theoretical value of driving speed, the theoretical value of tilt, and the theoretical value of brake control value).

[0041] Multiple theoretical values ​​constituting the driving strategy set in the strategy setting unit 40 can be used for automatic driving control in the driving control unit 30. In addition, it is preferable that the driving control unit 30 includes a strategy update unit 31 that can update the driving strategy based on the difference between multiple index values ​​inferred by the inference unit 20 (for example, an index value indicating driving speed, an index value indicating tilt, and an index value indicating brake control value) and each theoretical value set in the strategy setting unit 40 (for example, a theoretical value for driving speed, a theoretical value for tilt, and a theoretical value for brake control value).

[0042] The index value inferred by the inference unit 20 is based on information acquired during vehicle operation, specifically detected during actual driving. For example, it is inferred based on the coefficient of friction. Therefore, by considering this index value, the strategy update unit 31 can respond to the moment-to-moment changes during travel along the strategic route. Specifically, the strategy update unit 31 can derive the optimal solution again and re-formulate the strategic route by calculating the difference (delta value) between the theoretical value and the index value included in the driving strategy. The first example of the optimal solution is the index value used in place of the theoretical value. The second example of the optimal solution is the adjusted index value used in place of the theoretical value. The third example of the optimal solution is the solution obtained by performing regression analysis using at least one theoretical value and at least one index value. The fourth example of the optimal solution is the statistical value obtained from the theoretical value and the index value (for example, the median and / or mean). Whether the strategy update unit 31 derives the optimal solution from the first to fourth examples may be determined, for example, according to the magnitude of the difference. Furthermore, the optimal solution may be obtained by other methods, not just the first to fourth examples.

[0043] In this way, the strategy update unit 31 derives the optimal solution again, making it possible to achieve, for example, automated driving control that is just within the limits of preventing slippage. That is, if automated driving control is performed according to theoretical values ​​only, the vehicle will slip, but if automated driving control is performed according to index values ​​only, the vehicle will not slip with a safety margin. In this case, the adjusted index value obtained by subtracting the margin is used as the theoretical value by the driving control unit 30, thereby achieving automated driving control that is just within the limits of preventing vehicle slippage. Furthermore, since the computational power of Level 6 described above can be used during such update processing, it becomes possible to correct and fine-tune in units of one billionth of a second, enabling more precise driving control.

[0044] In addition, if the information acquisition unit 10 has the aforementioned under-vehicle sensor, this sensor also detects the temperature and material of the ground, making it possible to respond to the moment-to-moment changes when traveling along the strategic route. When calculating the driving course included in the driving strategy, independent smart tilt can also be implemented. Furthermore, even if other information is detected (flying tires, debris, animals, etc.), by responding to the moment-to-moment changes when traveling along the strategic route, the optimal driving course can be recalculated at each moment, enabling optimal course management.

[0045] Figure 4 is a conceptual diagram showing an example of the configuration of the inference unit 20 included in the information processing device 1B according to the third embodiment of this disclosure.

[0046] In the example shown in Figure 4, the information processing device 1B is mounted on the vehicle 48. The inference unit 20 included in the information processing device 1B has a deep learning model 20A. The deep learning model 20A is a trained model optimized by performing deep learning on a neural network using multiple training data 50. The inference unit 20 infers multiple index values ​​from environmental information 56 (see Figure 5) using the deep learning model 20A.

[0047] The training data 50 is a dataset having example data 52 and correct answer data 54. The example data 52 has example environmental information 52A. The example environmental information 52A is information that assumes environmental information 56 (see Figure 5) acquired by the information acquisition unit 10. For example, the example environmental information 52A includes information such as the distance between vehicle obstacles 52A1, driving speed 52A2, air resistance 52A3, road resistance 52A4, road elements 52A5, and ground inclination 52A6. Here, air resistance 52A3 corresponds to the air resistance exemplified in the first embodiment, road resistance 52A4 corresponds to the road resistance exemplified in the first embodiment, road elements 52A5 corresponds to the road elements exemplified in the first embodiment, and ground inclination 52A6 corresponds to the tilt exemplified in the first embodiment. Furthermore, the vehicle-to-obstacle distance 52A1 is the distance between vehicle 48 and an obstacle in the direction of vehicle 48's travel (in the example shown in Figure 4, the vehicle 53 directly ahead of vehicle 48). The travel speed 52A2 is the travel speed of vehicle 48.

[0048] The correct answer data 54 is the correct answer data (i.e., annotation) for the example data 52. The correct answer data 54 has a correct distance 54A. The correct distance 54A is an example of the "first distance" relating to the technology of this disclosure.

[0049] The correct stopping distance 54A is the sum of the required stopping distance 54A1 and the margin distance 54A2. The required stopping distance 54A1 is the distance required for vehicle 48 to stop without colliding with vehicle 53 between vehicle 48 and vehicle 53. Vehicle 53 is an obstacle in the direction of travel of vehicle 48 and is traveling in front of vehicle 48. In the example shown in Figure 4, vehicle 53 traveling in front of vehicle 48 is illustrated, but the technology of this disclosure is not limited to this, and may also be a vehicle 53 stopped in front of vehicle 48, or a pedestrian etc. located in front of vehicle 48, as long as it is an obstacle in the direction of travel of vehicle 48.

[0050] The margin distance 54A2 is an extra distance (for example, a few meters) set to increase the certainty of avoiding a collision between vehicle 48 and vehicle 53.

[0051] Figure 5 is a conceptual diagram showing an example of the processing contents of the information acquisition unit 10, inference unit 20, and operation control unit 30 included in the information processing device 1B according to the third embodiment.

[0052] The information acquisition unit 10 acquires environmental information 56 in the same manner as in the first embodiment described above. The environmental information 56 includes information such as the distance between vehicle obstacles 56A, driving speed 56B, air resistance 56C, road resistance 56D, road elements 56E, and ground inclination 56F.

[0053] The inference unit 20 inputs the environmental information 56 acquired by the information acquisition unit 10 to the deep learning model 20A. As a result, the deep learning model 20A outputs an index value 58 corresponding to the environmental information 56 (i.e., an index value related to the correct distance 54A corresponding to the environmental information 56). The inference unit 20 acquires the index value 58 output from the deep learning model 20A. The index value 58 is an index value inferred by the deep learning model 20A as the non-collision distance. The non-collision distance refers to, for example, the distance at which a vehicle 48 does not collide with an obstacle in the direction of travel of the vehicle 48 (vehicle 53 in the example shown in Figure 4). The index value 58 may be an index value obtained by performing multivariate analysis by the integral method described in the first embodiment above. Note that the index value 58 is an example of the "first index value" related to the technology of this disclosure.

[0054] The driving control unit 30 uses the driving speed calculation formula 60 to calculate the maximum speed 62 at which the vehicle 48 will not collide with an obstacle in the direction of travel (for example, a vehicle or pedestrian in front of the vehicle 48) from the index value 58 obtained by the inference unit 20. The driving speed calculation formula 60 is a formula in which the index value 58 is the independent variable and the maximum speed 62 is the dependent variable. The maximum speed 62 is the maximum speed within the range of legal speed limits and the speed of the vehicle ahead. The speed of the vehicle ahead is the speed of another vehicle traveling in front of the vehicle 48 (for example, the vehicle directly ahead of the vehicle 48 in the direction of travel). For example, the speed of the vehicle ahead is obtained by the information acquisition unit 10, etc. The driving control unit 30 calculates the maximum speed 62 by referring to the speed of the vehicle ahead obtained by the information acquisition unit 10, etc.

[0055] The driving control unit 30 performs driving control of the vehicle based on a plurality of index values ​​inferred by the inference unit 20. Driving control includes speed control. Speed ​​control is the control of the speed of the vehicle 48 and is performed based on the index value 58. Speed ​​control includes control to make the vehicle 48 run at a maximum speed 62. That is, the driving control unit 30 controls the drive system of the vehicle 48 (for example, the power source that transmits power to the wheels) to make the vehicle 48 run at a maximum speed 62 calculated based on the index value 58.

[0056] Figure 6 is a flowchart showing an example of the flow of the driving speed control process performed by the information processing device 1B.

[0057] In the speed control process shown in Figure 6, first, in step ST10, the information acquisition unit 10 determines whether or not a timing defined in nanoseconds has arrived (for example, whether or not one billionth of a second has elapsed). If the timing defined in nanoseconds has not arrived in step ST10, the determination is denied, and the speed control process proceeds to step ST22. If the timing defined in nanoseconds has arrived in step ST10, the determination is affirmed, and the speed control process proceeds to step ST12.

[0058] In step ST12, the information acquisition unit 10 acquires environmental information 56. After the processing in step ST12 is completed, the driving speed control process proceeds to step ST14.

[0059] In step ST14, the inference unit 20 inputs the environmental information 56 acquired by the information acquisition unit 10 in step ST12 to the deep learning model 20A. In response, the deep learning model 20A outputs an index value 58 corresponding to the input environmental information 56. After the processing in step ST14 is completed, the driving speed control process moves to step ST16.

[0060] In step ST16, the inference unit 20 obtains the index value 58 output from the deep learning model 20A. After the processing in step ST16 is completed, the driving speed control process moves on to step ST18.

[0061] In step ST18, the driving control unit 30 calculates the maximum speed 62 using the driving speed calculation formula 60 from the index value 58 obtained by the inference unit 20 in step ST16. After the processing in step ST18 is completed, the driving speed control process moves on to step ST20.

[0062] In step ST20, the driving control unit 30 controls the drive system of the vehicle 48 to drive the vehicle 48 at the maximum speed 62 calculated in step ST18. After the processing in step ST20 is completed, the driving speed control process moves on to step ST22.

[0063] In step ST22, the driving control unit 30 determines whether the conditions for terminating the driving speed control process have been met. An example of a condition for terminating the driving speed control process is that an instruction to terminate the driving speed control process has been given to the information processing device 1B. If the conditions for terminating the driving speed control process are not met in step ST22, the determination is denied, and the driving speed control process proceeds to step ST10. If the conditions for terminating the driving speed control process are met in step ST22, the determination is affirmed, and the driving speed control process terminates.

[0064] As described above, in this third embodiment, the inference unit 20 infers an index value 58 related to the correct distance 54A, which includes the stopping distance 54A1 required for the vehicle 48 to stop without colliding with an obstacle in the direction of travel of the vehicle 48. Then, the driving control unit 30 controls the driving speed of the vehicle 48 based on the index value 58. Therefore, the vehicle 48 can be driven to the destination safely and in a short amount of time.

[0065] Furthermore, in this third embodiment, the index value 58 is inferred in nanoseconds, and the maximum speed 62 is calculated based on the index value 58. The maximum speed 62 is the maximum speed at which the vehicle 48 will not collide with an obstacle, and the drive system of the vehicle 48 is controlled by the driving control unit 30 to drive the vehicle 48 at the maximum speed 62. Therefore, the vehicle 48 can be driven to its destination safely and in the shortest possible time.

[0066] Furthermore, in this third embodiment, the maximum speed 62 is calculated within a range that is below the legal speed limit and below the speed of the vehicle ahead. Therefore, the vehicle 48 can be driven to its destination safely and in the shortest possible time while adhering to the legal speed limit.

[0067] Furthermore, in this third embodiment, the correct distance 54A is the sum of the stopping distance 54A1 and the margin distance 54A2. Therefore, compared to the case where only the stopping distance 54A1 is used as the correct distance 54A, the possibility of collision between vehicle 48 and vehicle 53 can be reduced.

[0068] In the third embodiment described above, an example of the index value 58 was given as an index value inferred as the non-collision distance by the deep learning model 20A, but the technology of this disclosure is not limited thereto. For example, the index value 58 may be an index value indicating the maximum speed 62 inferred by the deep learning model 20A. In this case, for example, the drive system of the vehicle 48 may be controlled by the driving control unit 30 to drive the vehicle 48 at the maximum speed 62 indicated by the index value 58.

[0069] Furthermore, although the third embodiment described above explained an example in which the maximum speed 62 is calculated, this is merely an example, and a speed that is faster than the specified speed and slower than the maximum speed 62 may be calculated. Alternatively, instead of speed, the rotational spin rate of the wheels may be calculated, and information related to speed (i.e., parameters used to control the speed of the vehicle 48) may be calculated.

[0070] Furthermore, in the third embodiment described above, the correct distance 54A was given as the sum of the stopping distance 54A1 and the margin distance 54A2. However, this is merely an example, and the stopping distance 54A1 alone may also be used as the correct distance 54A.

[0071] Figure 7 schematically shows an example of the hardware configuration of a computer 1200 that functions as the information processing device (Central Brain) described above. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to each embodiment described above, or to cause the computer 1200 to execute operations associated with the device according to each embodiment or such one or more "parts", and / or to cause the computer 1200 to execute a process or a stage of such process according to each embodiment. Such a program may be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0072] The computer 1200 according to each embodiment may include a CPU 1212, RAM 1214, and a graphics controller 1216, which may be interconnected by a host controller 1210. The computer 1200 may also include input / output units such as a communication interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which may be connected to the host controller 1210 via an input / output controller 1220. The DVD drive may be a DVD-ROM drive and a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive and a solid-state drive, etc. The computer 1200 may also include legacy input / output units such as a ROM 1230 and a keyboard, which may be connected to the input / output controller 1220 via an input / output chip 1240.

[0073] The CPU 1212 can control each unit by operating according to programs stored in the ROM 1230 and RAM 1214. The graphics controller 1216 can acquire image data generated by the CPU 1212 and store it in a frame buffer provided in RAM 1214 or within itself, so that the image data can be displayed on the display device 1218.

[0074] The communication interface 1222 can communicate with other electronic devices via a network. The storage device 1224 can store programs and data used by the CPU 1212 in the computer 1200. The DVD drive can read programs or data from a DVD-ROM or the like and provide them to the storage device 1224. The IC card drive can read programs and data from an IC card and / or write programs and data to an IC card.

[0075] The ROM 1230 can store boot programs and / or hardware-dependent programs of the computer 1200, which are executed by the computer 1200 when activated. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0076] The program may be provided on a computer-readable storage medium such as a DVD-ROM or IC card. This program may be read from the computer-readable storage medium and installed in a storage device 1224, RAM 1214, or ROM 1230, which are examples of computer-readable storage media, and executed by the CPU 1212. The information processing described within these programs may be read by the computer 1200, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to implement information operations or processing in accordance with the use of the computer 1200.

[0077] For example, when communication is performed between a computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into RAM 1214 and, based on the processing described in the communication program, instruct the communication interface 1222 to perform communication processing. Under the control of the CPU 1212, the communication interface 1222 can read transmission data stored in a transmission buffer area provided in a recording medium such as RAM 1214, storage device 1224, DVD-ROM, or IC card, transmit the read transmission data to the network, or write received data received from the network to a receive buffer area or the like provided on the recording medium.

[0078] Furthermore, the CPU 1212 may read all or necessary parts of a file or database stored on an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), or an IC card into the RAM 1214, and perform various types of processing on the data in the RAM 1214. The CPU 1212 may then write the processed data back to the external recording medium.

[0079] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and subjected to information processing. The CPU 1212 may perform various types of processing on the data read from RAM 1214, including various types of operations, information processing, conditional judgments, conditional branching, unconditional branching, information retrieval / replacement, etc., as described throughout this disclosure and specified by the program instruction sequence, and may write the results back to RAM 1214. The CPU 1212 may also retrieve information in files, databases, etc., within the recording medium. For example, if multiple entries are stored in the recording medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 1212 may search among the multiple entries for an entry that matches the specified condition for the attribute value of the first attribute, read the attribute value of the second attribute stored in that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies the predetermined condition.

[0080] The program or software module described above may be stored on or near the computer 1200 in a computer-readable storage medium. Alternatively, a recording medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the program to the computer 1200 via the network.

[0081] In this embodiment, blocks in the flowchart and block diagram may represent a stage in a process in which an operation is performed or a "part" of a device that has the role of performing an operation. A particular stage and "part" may be implemented by a dedicated circuit, a programmable circuit supplied with computer-readable instructions stored on a computer-readable storage medium, and / or a processor supplied with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuit may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuit may include reconfigurable hardware circuits, such as field-programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), which include logical AND, logical OR, exclusive OR, negated AND, negated OR, and other logical operations, flip-flops, registers, and memory elements.

[0082] A computer-readable storage medium may include any tangible device capable of storing instructions to be executed by a suitable device, and as a result, a computer-readable storage medium having instructions stored therein will comprise a product that includes instructions that can be executed to create means for performing operations specified in a flowchart or block diagram. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital multipurpose disc (DVD), Blu-ray® disc, memory stick, integrated circuit card, etc.

[0083] Computer-readable instructions may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, Java®, C++, and traditional procedural programming languages ​​such as the C programming language or similar programming languages.

[0084] Computer-readable instructions may be provided to a general-purpose computer, a special-purpose computer, or a programmable circuit, either locally or via a wide area network (WAN) such as a local area network (LAN) or the internet, so that the computer-readable instructions may be executed by the processor or programmable circuit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, in order to generate means for performing operations specified in a flowchart or block diagram. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, and the like.

[0085] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0086] It should be noted that the execution order of operations, procedures, steps, and stages in the apparatus, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before" or "prior to," and that these can be implemented in any order unless the output of a previous process is used in a later process. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," and "next," for convenience, this does not mean that it is essential to perform the operations in that order.

[0087] In this specification, "α and / or β" is synonymous with "at least one of α and β." That is, "α and / or β" may be α alone, β alone, or a combination of α and β. Furthermore, in this specification, the same concept as "α and / or β" applies when expressing three or more things linked by "and / or." [Explanation of Symbols]

[0088] 10 Information acquisition department 20 Reasoning section 20A Deep Learning Model 30 Operation Control Unit 31. Strategy Update Department 40. Strategy Setting Department 48,53 vehicles 50 training data 52 Example Data 52A Example environment information 52A1, 56A Vehicle-to-obstacle distance 52A2, 56B Running speed 52A3, 56C Air resistance 52A4,56D Road resistance 52A5, 56E Road elements 52A6,56F Ground slope 54 Correct Data 54A Correct distance 54A1 Required stopping distance 54A2 Margin distance 58 Index Values 60. Formula for calculating travel speed 62 maximum speed 1200 Computers 1210 Host Controller 1212 CPU 1214 RAM 1216 Graphics Controller 1218 Display Devices 1220 Input / Output Controller 1222 Communication Interface 1224 Storage device 1230 ROM 1240 Input / Output Chip

Claims

1. An information acquisition unit capable of acquiring multiple pieces of information related to the vehicle, An inference unit that uses deep learning to infer multiple index values ​​from the multiple pieces of information acquired by the information acquisition unit, The vehicle comprises a driving control unit that performs driving control of the vehicle based on the plurality of index values, The plurality of index values ​​include a first index value relating to a first distance, which includes the stopping distance required for the vehicle to stop without colliding with an obstacle in the direction of travel of the vehicle. The aforementioned driving control includes speed control, which is the control of the vehicle's travel speed. The aforementioned travel speed control is performed based on the first index value. Information processing device.

2. The inference unit infers the multiple index values ​​from the multiple pieces of information by performing multivariate analysis using the integration method with deep learning. The information processing apparatus according to claim 1.

3. The information acquisition unit acquires the plurality of pieces of information in units of one billionth of a second, and the inference unit and the driving control unit use the plurality of pieces of information acquired in units of one billionth of a second to perform inference of the plurality of index values ​​and driving control of the vehicle in units of one billionth of a second. The information processing apparatus according to claim 1.

4. The vehicle further comprises a strategy setting unit that sets a driving strategy until the vehicle reaches its destination. The aforementioned driving strategy includes the driving course from the current location to the destination, the driving speed, the slope of the ground being driven on, and at least one theoretical value of a brake control value which is a parameter for controlling the operation of the brakes. The operation control unit includes a strategy update unit that updates the driving strategy based on the difference between the plurality of index values ​​and the theoretical value. The information processing apparatus according to claim 1.

5. The information acquisition unit is provided with a sensor located beneath the vehicle that can detect the temperature, material, and incline of the ground it is traveling on. The information processing apparatus according to claim 1.

6. The aforementioned speed control includes control that causes the vehicle to travel at the maximum speed at which it does not collide with the obstacle, The information relating to the maximum speed is calculated based on the first index value. The information processing apparatus according to claim 1.

7. The aforementioned maximum speed is the maximum speed within the range of the legal speed limit and / or within the range of the speed of the vehicle ahead. The aforementioned forward vehicle speed is the speed of other vehicles traveling in front of the vehicle in question. The information processing apparatus according to claim 6.

8. The first distance is the sum of the stopping distance and the margin distance. The information processing apparatus according to claim 1.

9. The information processing device comprises the information processing device described in any one of claims 1 to 8. vehicle.

10. A program for causing a computer to function as an information processing device according to any one of claims 1 to 8.

Images