Intelligent driving method and system for automobile

Abstract

The invention provides an intelligent driving method and system for an automobile. The intelligent driving method comprises the steps that sample data of the automobile under different road conditions are collected; performing data cleaning and normalization processing on the sample data to form a training sample; inputting the training sample into a neural network for training to obtain an engine torque accurate control model under different road conditions; a vehicle-mounted laser radar on the target automobile is used for sending a laser signal to the road surface, and the driving road condition of the automobile is determined based on the laser echo signal; and the engine torque accurate control model under the corresponding road condition is used for completing torque control of the target automobile. According to the invention, the vehicle-mounted laser radar sends the laser signal and determines the driving road condition of the automobile, and at the same time, various data samples are collected and analyzed as training data to complete the training of the engine torque precise control model, so that the acceleration performance, steering flexibility and fuel efficiency of the automobile can be improved, the automobile can adapt to different road conditions, and the driving experience of the automobile is improved. And the driving safety and stability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automotive drive, and more particularly, to an intelligent drive method and system for an automobile. Background Art

[0002] Currently, the torque control of an automotive engine is usually adjusted based on parameters such as the driver's throttle pedal input and the engine's intake air volume. However, this method does not fully consider the impact of driving conditions, ambient temperature, and other factors on the engine torque demand, resulting in the inability to optimize the driving performance and fuel economy of the vehicle under different road conditions. Summary of the Invention

[0003] To solve the above problems, an object of the present invention is to provide an intelligent drive method and system for an automobile.

[0004] An intelligent drive method for an automobile includes:

[0005] Step 1: Collect sample data of the automobile under different road conditions; the sample data includes vehicle speed, ambient temperature, coolant temperature, oil temperature, fuel consumption, road adhesion coefficient, driving force at the wheels, and the corresponding engine torque output;

[0006] Step 2: Perform data cleaning and normalization processing on the sample data to form training samples;

[0007] Step 3: Input the training samples into a neural network for training to obtain an accurate engine torque control model under different road conditions;

[0008] Step 4: Use the on-vehicle lidar on the target vehicle to send laser signals to the road surface, and determine the driving road conditions of the vehicle based on the laser echo signals;

[0009] Step 5: Use the accurate engine torque control model under the corresponding road conditions to complete the torque control of the target vehicle.

[0010] Preferably, in Step 1, the fuel consumption is calculated through the following steps:

[0011] Determine the fuel consumption of the engine according to the steady-state fuel consumption rate corresponding to different engine speeds; wherein, the fuel consumption calculation formula of the engine is:

[0012]

[0013] In the formula, represents the transient fuel consumption gain coefficient, A m represents the first regression coefficient, ω e represents the engine speed, B m represents the second regression coefficient, Cm Represents the third regression coefficient, D m Represents the fourth regression coefficient, E m Represents the constant term Represents the engine speed conversion rate, T e Represents the engine torque Represents the engine torque conversion rate Represents the fuel consumption of the engine, b fs Represents the fuel consumption rate of the engine at steady state, ρ represents the fuel density, T ei Represents the indicated torque, Φ represents the throttle opening

[0014] Preferably, in the said step 1, the driving force at the wheel is calculated through the following steps:

[0015] Step 1.1: Determine the driving resistance according to the vehicle condition during the vehicle operation

[0016] Step 1.2: Determine the driving force at the wheel according to the magnitude of the driving resistance; wherein, the calculation formula of the driving force at the wheel is:

[0017]

[0018] In the formula, F r Represents the driving resistance, F d Represents the driving force at the wheel, m represents the mass of the vehicle, g represents the acceleration due to gravity, α represents the ramp angle, ρ represents the air density, C D Represents the air resistance coefficient, A represents the frontal area of the vehicle, v represents the vehicle speed, δ represents the conversion coefficient of the rotating mass, t represents the time

[0019] Preferably, in the said step 4: Use the on-vehicle lidar on the target vehicle to send laser signal points to the road surface, and determine the driving condition of the vehicle based on the laser echo signal, including:

[0020] Step 4.1: Calculate the average distance between each laser signal point and a preset number of adjacent laser signal points

[0021] Step 4.2: Calculate the distance parameter based on the average distance between each laser signal point

[0022] Step 4.3: Determine the credibility radius of the laser signal point based on the said distance parameter

[0023] Step 4.4: Obtain the number of all laser signal points under the corresponding credibility radius for each laser signal point

[0024] Step 4.5: When the number of all laser signal points is less than the preset value, remove the corresponding laser signal points as isolated points to obtain the laser signal points after removing the isolated points

[0025] Step 4.6: Construct a training sample using the laser signal points after removing the isolated points, and input it into the neural network model for training to obtain a driving road condition detection model;

[0026] Step 4.7: Use the driving road condition detection model to determine the driving road condition of the current vehicle.

[0027] Preferably, in Step 4.2: calculating the distance parameter based on the average distance between each laser signal point, including:

[0028] Using the formula:

[0029]

[0030] Calculate the distance parameter; where, represents the distance parameter, n represents the number of all laser signal points, represents the average distance between the i-th laser signal point and k adjacent laser signal points, d ij represents the Euclidean distance between the i-th laser signal point and the j-th adjacent laser signal point, represents the sum of the average distances between all laser signal points and their corresponding k adjacent laser signal points.

[0031] Preferably, in Step 4.3: determining the credibility radius of the laser signal point based on the distance parameter, including:

[0032] Step 4.3.1: Calculate the standard deviation based on the Euclidean distance and the average distance between adjacent laser signal points;

[0033] Step 4.3.2: Determine the credibility radius of the laser signal point using the standard deviation and the distance parameter; where, the credibility radius calculation formula is:

[0034]

[0035] where, σ is the standard deviation, and r represents the credibility radius.

[0036] Preferably, in Step 4.6: constructing a training sample using the laser signal points after removing the isolated points, and inputting it into the neural network model for training to obtain a driving road condition detection model, including:

[0037] Use the power of the laser echo signal of each laser signal point as a training sample, and input it into the neural network model for training to obtain a driving road condition detection model.

[0038] Preferably, in Step 4.6, the power calculation formula of the laser echo signal is:

[0039]

[0040] Among them, P r represents the power of the laser echo signal, R represents the detection distance, D r represents the receiver aperture, β t represents the laser beam width, η atm represents the influence factor of the laser echo signal during atmospheric transmission, η sys represents the lidar system attenuation factor, ρ represents the reflectivity of the laser, θ represents the laser incident angle, Ω represents the laser scattering angle, A s represents the contact area of the laser signal point.

[0041] The present invention also provides an intelligent driving system for an automobile, including:

[0042] A data acquisition module for collecting sample data of the automobile under different road conditions; the sample data includes vehicle speed, ambient temperature, coolant temperature, oil temperature, fuel consumption, road adhesion coefficient, driving force at the wheels, and the corresponding engine torque output;

[0043] A data preprocessing module for performing data cleaning and normalization processing on the sample data to form training samples;

[0044] A training module for inputting the training samples into a neural network for training to obtain an accurate engine torque control model under different road conditions;

[0045] A driving road condition determination module for sending a laser signal to the road surface using an on-vehicle lidar of the target vehicle and determining the driving road condition of the vehicle based on the laser echo signal;

[0046] A torque control module for using the accurate engine torque control model under the corresponding road condition to complete the torque control of the target vehicle.

[0047] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above-mentioned intelligent driving method for an automobile are implemented.

[0048] The beneficial effects of the intelligent driving method and system for an automobile provided by the present invention are as follows: Compared with the prior art, the present invention sends a laser signal through an on-vehicle lidar to determine the driving road condition of the vehicle, and at the same time completes the training of the accurate engine torque control model by collecting and analyzing various data samples as training data, which can improve the acceleration performance, steering flexibility and fuel efficiency of the vehicle, enable the vehicle to adapt to different road conditions, and improve the driving safety and stability.

[0049] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following provides preferred embodiments in conjunction with the accompanying drawings and describes them in detail as follows. Description of the Drawings

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0051] Figure 1 Shows a flowchart of an intelligent driving method for an automobile provided by an embodiment of the present invention;

[0052] Figure 2 Shows a schematic diagram of an intelligent driving system for an automobile provided by an embodiment of the present invention. Detailed Embodiments

[0053] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0054] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0055] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0056] Please refer to Figure 1, an intelligent driving method for automobiles, comprising:

[0057] Step 1: Collect sample data of the automobile under different road conditions; the sample data includes vehicle speed, ambient temperature, coolant temperature, oil temperature, fuel consumption, road adhesion coefficient, driving force at the wheels, and corresponding engine torque output;

[0058] In practical applications, it is necessary to drive the test vehicle on different road conditions (rainy asphalt road, dry asphalt road, dry dirt road, wet dirt road, gravel road, etc.), install corresponding sensors to collect relevant sample data, and use the expert analysis method to calibrate the optimal industrial control of the automobile under different road conditions.

[0059] In the above Step 1, the fuel consumption is calculated through the following steps:

[0060] Determine the fuel consumption of the engine according to the steady-state fuel consumption rate corresponding to different engine speeds; wherein, the fuel consumption calculation formula of the engine is:

[0061]

[0062] In the formula, represents the transient fuel consumption gain coefficient, A m represents the first regression coefficient, ω e represents the engine speed, B m represents the second regression coefficient, C m represents the third regression coefficient, D m represents the fourth regression coefficient, E m represents the constant term, represents the engine speed conversion rate, T e represents the engine torque, represents the engine torque conversion rate, represents the fuel consumption of the engine, b fs represents the fuel consumption rate of the engine at steady state, ρ represents the fuel density, T ei represents the indicated torque, Φ represents the throttle opening.

[0063] It should be noted that the present invention can use the least squares method to perform regression fitting on the transient fuel consumption gain coefficient under different road conditions to obtain each regression coefficient under each road condition, and then calculate the fuel consumption of the automobile driving under different road conditions.

[0064] In the above Step 1, the driving force at the wheels is calculated through the following steps:

[0065] Step 1.1: Determine the driving resistance according to the vehicle condition during the vehicle operation;

[0066] Step 1.2: Determine the driving force at the wheels according to the magnitude of the driving resistance.

[0067] Further, the present invention can calculate the driving force at the wheels according to Newton's laws of motion and the principles of aerodynamics:

[0068]

[0069] In the formula, F r represents the driving resistance, F d represents the driving force at the wheels, m represents the mass of the vehicle, g represents the acceleration due to gravity, α represents the ramp angle, ρ represents the air density, C D represents the air resistance coefficient, A represents the frontal area of the vehicle, v represents the vehicle speed, δ represents the conversion coefficient of the rotating mass, and t represents time.

[0070] Step 2: Perform data cleaning and normalization on the sample data to form training samples.

[0071] By performing data cleaning and normalization on the sample data, the present invention can help remove noise and outliers in the data, improve the quality and accuracy of the data, and at the same time, performing normalization on it can unify the data ranges of different features to the same scale, which helps to speed up the training speed of the model.

[0072] Step 3: Input the training samples into a neural network for training to obtain an accurate control model of the engine torque under different road conditions.

[0073] Step 4: Use the on-vehicle lidar on the target vehicle to send laser signals to the road surface, and determine the driving road condition of the vehicle based on the laser echo signals.

[0074] Further, Step 4 includes:

[0075] Step 4.1: Calculate the average distance between each laser signal point and a preset number of adjacent laser signal points.

[0076] Step 4.2: Calculate the distance parameter based on the average distance between each laser signal point; using the formula:

[0077]

[0078] Calculate the distance parameter; where represents the distance parameter, n represents the number of all laser signal points, represents the average distance between the i-th laser signal point and k adjacent laser signal points, d ij represents the Euclidean distance between the i-th laser signal point and the j-th adjacent laser signal point, represents the sum of the average distances between all laser signal points and their corresponding k adjacent laser signal points;

[0079] Step 4.3: Determine the credibility radius of the laser signal points based on the distance parameter;

[0080] Further, the step 4.3 includes:

[0081] Step 4.3.1: Calculate the standard deviation based on the Euclidean distance and the average distance between adjacent laser signal points;

[0082] Step 4.3.2: Determine the credibility radius of the laser signal points using the standard deviation and the distance parameter; where the formula for the credibility radius is:

[0083]

[0084] where σ is the standard deviation and r represents the credibility radius.

[0085] Step 4.4: Obtain the number of all laser signal points under the corresponding credibility radius for each laser signal point;

[0086] Step 4.5: When the number of all laser signal points is less than the preset value, remove the corresponding laser signal points as isolated points to obtain the laser signal points after removing isolated points;

[0087] In a laser point cloud, it is usually necessary to remove isolated point cloud data points. This is because isolated point cloud data points may be noise points caused by sensor errors, environmental interference, or other factors, which will affect subsequent point cloud processing and analysis. Removing isolated point cloud data points can improve the quality and accuracy of point cloud data, which is beneficial to subsequent point cloud processing and analysis work. Based on statistical principles, the present invention can find isolated laser signal points with a large distance from neighboring laser points, which can avoid the influence of noise points on the determination of the driving road condition of the vehicle.

[0088] Step 4.6: Use the laser signal points after removing isolated points to construct a training sample and input it into a neural network model for training to obtain a driving road condition detection model;

[0089] Since the materials and smoothness of different road surfaces are different, the reflectivity of laser light will also be different. There is a direct relationship between the reflectivity of laser light and the power of the laser. When a laser beam irradiates the surface of an object, a part of the laser energy will be absorbed by the object surface and a part will be reflected. Therefore, the higher the reflectivity, the greater the laser power reflected by the object surface. On the contrary, the lower the reflectivity, the smaller the reflected laser power. Generally speaking, there is a positive correlation between the reflectivity of laser light and the power of the laser, that is, the higher the reflectivity, the greater the reflected laser power.

[0090] Therefore, the present invention uses the power of the laser echo signal of each laser signal point as a training sample and inputs it into a neural network model for training to obtain a driving road condition detection model, which can reflect information such as the material and smoothness of the road surface. This information is very important for real-time driving road condition detection. The neural network model can learn this information to achieve a fast response and accurate judgment of the real-time road condition.

[0091] Among them, the power calculation formula of the laser echo signal is:

[0092]

[0093] Among them, P r represents the power of the laser echo signal, R represents the detection distance, D r represents the receiver aperture, β t represents the laser beam width, η atm represents the influence factor of the laser echo signal during atmospheric transmission, η sys represents the attenuation factor of the lidar system, ρ represents the reflectivity of the laser, θ represents the laser incident angle, Ω represents the laser scattering angle, A s represents the contact area of the laser signal point.

[0094] Step 4.7: Use the driving road condition detection model to determine the driving road condition of the current vehicle.

[0095] Step 5: Use the engine torque precise control model under the corresponding road condition to complete the torque control of the target vehicle.

[0096] The present invention sends laser signals through an in-vehicle lidar and determines the driving road condition of the vehicle. At the same time, by collecting and analyzing various data samples as training data, the training of the engine torque precise control model is completed, which can improve the acceleration performance, steering flexibility and fuel efficiency of the vehicle, enable the vehicle to adapt to different road conditions, and improve driving safety and stability.

[0097] Please refer to Figure 2 , the present invention also provides an intelligent drive system for a vehicle, including:

[0098] A data acquisition module for collecting sample data of the vehicle under different road conditions; the sample data includes vehicle speed, ambient temperature, coolant temperature, oil temperature, fuel consumption, road adhesion coefficient, driving force at the wheel, and the corresponding engine torque output;

[0099] A data preprocessing module for performing data cleaning and normalization processing on the sample data to form a training sample;

[0100] A training module for inputting the training samples into a neural network for training to obtain an accurate engine torque control model under different road conditions;

[0101] A driving road condition determination module for sending laser signals to the road surface using an on-vehicle lidar on a target vehicle and determining the driving road condition of the vehicle based on the laser echo signals;

[0102] A torque control module for using the accurate engine torque control model under the corresponding road condition to complete the torque control of the target vehicle.

[0103] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned intelligent driving method for an automobile are implemented.

[0104] Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as those of the above-mentioned intelligent driving method for an automobile, and will not be elaborated here.

[0105] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of the technical solutions of changes or substitutions within the technical scope disclosed by the present invention, and all of them should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An intelligent driving method for an automobile, characterized in that, Including: Step 1: Collect sample data of the vehicle under different road conditions; the sample data includes vehicle speed, ambient temperature, coolant temperature, oil temperature, fuel consumption, road adhesion coefficient, driving force at the wheels, and the corresponding engine torque output. Step 2: Perform data cleaning and normalization on the sample data to form training samples. Step 3: Input the training samples into a neural network for training to obtain an accurate engine torque control model under different road conditions. Step 4: Use the on-vehicle lidar on the target vehicle to send laser signals to the road surface, and determine the driving road conditions of the vehicle based on the laser echo signals. Step 5: Use the accurate engine torque control model under the corresponding road conditions to complete the torque control of the target vehicle.

2. The intelligent driving method for an automobile according to claim 1, wherein In Step 1, the fuel consumption is calculated through the following steps: Determine the fuel consumption of the engine according to the steady-state fuel consumption rate corresponding to different engine speeds; where the formula for calculating the fuel consumption of the engine is: In the formula, is expressed as the transient fuel consumption gain coefficient, A m is expressed as the first regression coefficient, ω e is expressed as the engine speed, B m is expressed as the second regression coefficient, C m is expressed as the third regression coefficient, D m is expressed as the fourth regression coefficient, E m is expressed as the constant term, is expressed as the engine speed conversion rate, T e is expressed as the engine torque, is expressed as the engine torque conversion rate, is expressed as the fuel consumption of the engine, b fs is expressed as the fuel consumption rate of the engine at steady state, ρ represents the fuel density, T ei is expressed as the indicated torque, Φ represents the throttle opening.

3. An intelligent driving method for an automobile according to claim 2, characterized in that, In Step 1, the driving force at the wheels is calculated through the following steps: Step 1.1: Determine the driving resistance according to the vehicle condition during vehicle operation. Step 1.2: Determine the driving force at the wheels according to the magnitude of the driving resistance; where the formula for calculating the driving force at the wheels is: Where F r represents the driving resistance, F d represents the driving force at the wheels, m represents the mass of the vehicle, g represents the acceleration due to gravity, α represents the ramp angle, ρ represents the air density, C D represents the air resistance coefficient, A represents the frontal area of the vehicle, v represents the vehicle speed, δ represents the conversion coefficient of the rotating mass, and t represents time.

4. An intelligent driving method for an automobile according to claim 3, characterized in that, Step 4: Use the on-vehicle lidar on the target vehicle to send laser signal points to the road surface, and determine the driving road conditions of the vehicle based on the laser echo signals, including: Step 4.1: Calculate the average distance between each laser signal point and a preset number of adjacent laser signal points. Step 4.2: Calculate the distance parameter based on the average distances between the laser signal points. Step 4.3: Determine the credibility radius of the laser signal points based on the distance parameter. Step 4.4: Obtain the number of all laser signal points under the corresponding credibility radius for each laser signal point. Step 4.5: When the number of all laser signal points is less than a preset value, remove the corresponding laser signal points as isolated points to obtain the laser signal points after removing isolated points. Step 4.6: Use the laser signal points after removing isolated points to construct training samples, and input them into a neural network model for training to obtain a driving road condition detection model. Step 4.7: Use the driving road condition detection model to determine the current driving road conditions of the vehicle.

5. The intelligent driving method for an automobile according to claim 4, wherein Step 4.2: Calculate the distance parameter based on the average distances between the laser signal points, including: Using the formula: Calculate the distance parameter; among them, represents the distance parameter, n represents the number of all laser signal points, represents the average distance between the i-th laser signal point and k adjacent laser signal points, d ij represents the Euclidean distance between the i-th laser signal point and the j-th adjacent laser signal point, represents the sum of the average distances between all laser signal points and their corresponding k adjacent laser signal points.

6. The intelligent driving method for an automobile according to claim 5, characterized in that, Step 4.3: Determine the credibility radius of the laser signal points based on the distance parameter, including: Step 4.3.1: Calculate the standard deviation based on the Euclidean distance and the average distance between adjacent laser signal points. Step 4.3.2: Determine the credibility radius of the laser signal points using the standard deviation and the distance parameter; where the formula for the credibility radius is: Where σ is the standard deviation and r represents the credibility radius.

7. An intelligent driving method for an automobile according to claim 6, characterized in that, Step 4.6: Use the laser signal points after removing isolated points to construct training samples, and input them into a neural network model for training to obtain a driving road condition detection model, including: Take the power of the laser echo signal of each laser signal point as a training sample and input it into a neural network model for training to obtain a driving road condition detection model.

8. An intelligent driving method for an automobile according to claim 7, characterized in that, In step 4.6, the power calculation formula of the laser echo signal is: Among them, P r represents the power of the laser echo signal, R represents the detection distance, D r represents the receiver aperture, β t represents the laser beam width, η atm represents the influence factor of the laser echo signal during atmospheric transmission, η sys represents the lidar system attenuation factor, ρ represents the reflectivity of the laser, θ represents the laser incident angle, Ω represents the laser scattering angle, A s represents the contact area of the laser signal point.

9. An intelligent drive system for an automobile, characterized in that, Including: A data acquisition module for collecting sample data of the vehicle under different road conditions; the sample data includes vehicle speed, ambient temperature, coolant temperature, oil temperature, fuel consumption, road surface adhesion coefficient, driving force at the wheels, and the corresponding engine torque output; A data preprocessing module for cleaning and normalizing the sample data to form a training sample; A training module for inputting the training sample into a neural network for training to obtain an engine torque precise control model under different road conditions; A driving road condition determination module for sending a laser signal to the road surface using a vehicle-mounted lidar on the target vehicle and determining the driving road condition of the vehicle based on the laser echo signal; A torque control module for using the engine torque precise control model under the corresponding road condition to complete the torque control of the target vehicle.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps in an intelligent driving method for a vehicle as described in any one of claims 1-8.

Images