Automobile light self-adaptive control method and system based on machine learning and medium

Abstract

The invention discloses an automobile light adaptive control method and system based on machine learning and a medium, and the method comprises the steps: obtaining vehicle state data, external environment information and GPS positioning information of a target vehicle, and the external environment information comprises illumination intensity information, road condition information and weather condition information; determining an illumination intensity change rate, a road surface reflection coefficient and a visibility index according to the external environment information and the GPS positioning information, and performing feature fusion on the illumination intensity change rate, the road surface reflection coefficient and the visibility index to obtain external environment feature data; inputting the external environment characteristic data and the vehicle state data into a pre-trained vehicle external lamp brightness prediction model to obtain a target external lamp brightness level; and adjusting and controlling the outer lamp brightness of the target vehicle according to the target outer lamp brightness level. The driving experience and the driving safety of the user are improved, and the method can be widely applied to the technical field of vehicle control.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a method, system and medium for adaptively controlling automobile lighting based on machine learning. Background Art

[0002] As a common means of transportation, cars have become indispensable in human life. Existing vehicle headlight control systems are mostly fixed lighting. When the owner turns on the vehicle's headlights, the light intensity is uniform and cannot be adjusted according to the real-time environment. It is impossible to achieve personalized lighting, which affects the user's driving experience. In the case of insufficient light, there are certain safety hazards to vehicle driving, affecting driving safety. Summary of the invention

[0003] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0004] To this end, an object of an embodiment of the present invention is to provide a method for adaptively controlling automobile lighting based on machine learning, which improves the user's driving experience and driving safety.

[0005] Another object of an embodiment of the present invention is to provide an automobile lighting adaptive control system based on machine learning.

[0006] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0007] In a first aspect, an embodiment of the present invention provides a method for adaptively controlling automobile lighting based on machine learning, comprising the following steps:

[0008] Acquire vehicle status data, external environment information, and GPS positioning information of the target vehicle, wherein the external environment information includes light intensity information, road condition information, and weather condition information;

[0009] Determine the light intensity change rate, the road surface reflection coefficient and the visibility index according to the external environment information and the GPS positioning information, perform feature fusion on the light intensity change rate, the road surface reflection coefficient and the visibility index, and obtain external environment feature data;

[0010] Inputting the external environment characteristic data and the vehicle status data into a pre-trained automobile exterior light brightness prediction model to obtain a target exterior light brightness level;

[0011] The exterior light brightness of the target vehicle is adjusted and controlled according to the target exterior light brightness level.

[0012] Further, in one embodiment of the present invention, the step of obtaining vehicle status data, external environment information and GPS positioning information of the target vehicle specifically includes:

[0013] Acquiring the vehicle status data through a vehicle body controller, wherein the vehicle status data includes the speed and steering angle of the target vehicle;

[0014] The light intensity information is obtained by monitoring the light intensity around the target vehicle in real time through an ambient light sensor;

[0015] Monitor the road conditions around the target vehicle in real time by using a camera and / or a radar to obtain the road condition information;

[0016] Monitor the weather conditions around the target vehicle in real time through a rain sensor and a humidity sensor to obtain the weather condition information;

[0017] The GPS positioning information is obtained through a positioning module.

[0018] Further, in one embodiment of the present invention, the determining of the light intensity change rate, the road surface reflection coefficient and the visibility index according to the external environment information and the GPS positioning information specifically includes:

[0019] Determining the light intensity change rate according to the light intensity information;

[0020] Determine the road surface slipperiness and the water and snow accumulation state according to the road surface state information, and determine the road surface reflection coefficient according to the road surface slipperiness and the water and snow accumulation state;

[0021] The real-time weather information of the vehicle's geographical location is acquired according to the GPS positioning information, and the visibility index is determined according to the real-time weather information and the weather condition information.

[0022] Furthermore, in one embodiment of the present invention, the light intensity change rate, the road surface reflectance coefficient and the visibility index are subjected to feature fusion to obtain external environment feature data, which specifically includes:

[0023] Performing data standardization and vectorization processing on the illumination intensity change rate, the road surface reflection coefficient, and the visibility index to obtain an illumination intensity feature vector, a road surface reflection feature vector, and a visibility feature vector;

[0024] The light intensity feature vector, the road surface reflection feature vector and the visibility feature vector are vector-joined to obtain the external environment feature data.

[0025] Furthermore, in one embodiment of the present invention, the automobile exterior light brightness prediction model is trained by the following steps:

[0026] Obtaining the external environment feature sample data and vehicle status sample data of the test vehicle, and determining the corresponding exterior light brightness level label through manual labeling;

[0027] Determine a training sample according to the external environment feature sample data and the vehicle state sample data;

[0028] Inputting the training samples into a pre-built deep learning neural network to obtain exterior light brightness prediction results;

[0029] Determine a loss value according to the exterior light brightness prediction result and the exterior light brightness level label;

[0030] The parameters of the deep learning neural network are updated according to the loss value to obtain a trained vehicle exterior light brightness prediction model.

[0031] Further, in one embodiment of the present invention, the step of adjusting and controlling the brightness of the exterior lights of the target vehicle according to the target exterior light brightness level specifically includes:

[0032] generating an RLS signal adjustment instruction according to the target exterior light brightness level and a preset safety and energy-saving strategy;

[0033] The RLS signal adjustment instruction is sent to a vehicle light control unit, so that the vehicle light control unit gradually adjusts the brightness of the exterior light LED array of the target vehicle to the target exterior light brightness level.

[0034] Furthermore, in one embodiment of the present invention, after adjusting and controlling the brightness of the exterior lights of the target vehicle according to the target exterior light brightness level, the method further includes the following steps:

[0035] In response to a manual adjustment operation of an exterior light of a driver of the target vehicle, obtaining a corresponding manually adjusted brightness level;

[0036] A feedback sample is generated according to the external environment characteristic data, the vehicle status data and the manually adjusted brightness level, and the automobile exterior light brightness prediction model is optimized according to the feedback sample.

[0037] In a second aspect, an embodiment of the present invention provides an automobile lighting adaptive control system based on machine learning, comprising:

[0038] A data acquisition module is used to acquire vehicle status data, external environment information and GPS positioning information of the target vehicle, wherein the external environment information includes light intensity information, road condition information and weather condition information;

[0039] A feature fusion module is used to determine the light intensity change rate, the road surface reflection coefficient and the visibility index according to the external environment information and the GPS positioning information, and perform feature fusion on the light intensity change rate, the road surface reflection coefficient and the visibility index to obtain external environment feature data;

[0040] An exterior light brightness prediction module, used to input the external environment feature data and the vehicle status data into a pre-trained automobile exterior light brightness prediction model to obtain a target exterior light brightness level;

[0041] The exterior light brightness control module is used to adjust and control the exterior light brightness of the target vehicle according to the target exterior light brightness level.

[0042] In a third aspect, an embodiment of the present invention provides a vehicle lighting adaptive control device based on machine learning, comprising:

[0043] at least one processor;

[0044] at least one memory for storing at least one program;

[0045] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method for adaptive control of automobile lights based on machine learning.

[0046] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores a program executable by a processor, and the program executable by the processor is used to execute the above-mentioned method of adaptive control of automobile lights based on machine learning when executed by the processor.

[0047] The advantages and beneficial effects of the present invention will be partly given in the following description, partly become apparent from the following description, or be understood through the practice of the present invention:

[0048] The embodiment of the present invention obtains vehicle status data, external environment information and GPS positioning information of a target vehicle, the external environment information includes light intensity information, road condition information and weather condition information, determines the light intensity change rate, road surface reflection coefficient and visibility index according to the external environment information and GPS positioning information, performs feature fusion on the light intensity change rate, road surface reflection coefficient and visibility index to obtain external environment feature data, inputs the external environment feature data and the vehicle status data into a pre-trained automobile exterior light brightness prediction model to obtain a target exterior light brightness level, and adjusts and controls the exterior light brightness of the target vehicle according to the target exterior light brightness level. The embodiment of the present invention acquires the vehicle status data, external environment information and GPS positioning information of the vehicle in real time, determines the light intensity change rate, road surface reflection coefficient and visibility index according to the external environment information and GPS positioning information, obtains the external environment feature data through feature fusion, inputs the external environment feature data and the vehicle status data into a pre-trained automobile exterior light brightness prediction model, obtains the target exterior light brightness level, and thus can adjust and control the exterior light brightness of the target vehicle according to the target exterior light brightness level, which can not only enhance the lighting and improve the driving vision at night or in bad weather, but also appropriately reduce the brightness during the day or when there is sufficient light, thereby achieving energy saving and consumption reduction, and improving the user's driving experience and driving safety; in addition, through continuous learning and optimization, the embodiment of the present invention can gradually adapt to different driving habits and environments, and provide users with a more personalized, safe and environmentally friendly driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solution in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solution of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 A flowchart of a method for adaptively controlling automobile lighting based on machine learning provided by an embodiment of the present invention;

[0051] Figure 2 A structural block diagram of an automobile lighting adaptive control system based on machine learning provided by an embodiment of the present invention;

[0052] Figure 3 A structural block diagram of a vehicle lighting adaptive control device based on machine learning provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limitations of the present invention. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0054] In the description of the present invention, the meaning of "a plurality" is two or more than two. If there is a description of "a first" or "a second", it is only used for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features. In addition, unless otherwise defined, all technical and scientific terms used in this document have the same meaning as those commonly understood by those skilled in the art.

[0055] Reference Figure 1 The embodiment of the present invention provides a method for adaptively controlling automobile lighting based on machine learning, which specifically includes the following steps:

[0056] S101, obtaining vehicle status data, external environment information and GPS positioning information of a target vehicle, wherein the external environment information includes light intensity information, road condition information and weather condition information;

[0057] S102, determining the illumination intensity change rate, the road surface reflection coefficient, and the visibility index according to the external environment information and the GPS positioning information, and performing feature fusion on the illumination intensity change rate, the road surface reflection coefficient, and the visibility index to obtain external environment feature data;

[0058] S103, inputting the external environment feature data and the vehicle status data into a pre-trained automobile exterior light brightness prediction model to obtain a target exterior light brightness level;

[0059] S104: adjusting and controlling the brightness of the exterior lights of the target vehicle according to the target exterior light brightness level.

[0060] The embodiment of the present invention realizes intelligent control of exterior light brightness and RLS (Road Lighting System) signal mode based on machine learning algorithm. In specific implementation, firstly, the driving environment data such as light intensity, road conditions, weather conditions, etc. are collected in real time through the vehicle-mounted sensor, and combined with the vehicle status data (vehicle speed, steering angle) and GPS positioning information, and input into the machine learning model for comprehensive analysis to obtain the optimal exterior light brightness level, and then generate RLS signal adjustment instructions in combination with the preset safety and energy-saving strategies, and then drive the lighting system to perform the adjustment.

[0061] It can be recognized that the embodiment of the present invention acquires the vehicle status data, external environment information and GPS positioning information of the vehicle in real time, determines the light intensity change rate, road surface reflection coefficient and visibility index according to the external environment information and GPS positioning information, obtains the external environment feature data through feature fusion, inputs the external environment feature data and the vehicle status data into a pre-trained automobile exterior light brightness prediction model, obtains the target exterior light brightness level, and thus can adjust and control the exterior light brightness of the target vehicle according to the target exterior light brightness level, which can not only enhance lighting and improve driving vision at night or in bad weather, but also appropriately reduce brightness during the day or when there is sufficient light, thereby achieving energy saving and consumption reduction, and improving the user's driving experience and driving safety; in addition, through continuous learning and optimization, the embodiment of the present invention can gradually adapt to different driving habits and environments, and provide users with a more personalized, safe and environmentally friendly driving experience.

[0062] As an optional implementation, the vehicle status data, external environment information and GPS positioning information of the target vehicle are obtained, which specifically includes:

[0063] S1011, acquiring vehicle status data through a vehicle body controller, where the vehicle status data includes a speed and a steering angle of the target vehicle;

[0064] S1012, monitoring the light intensity around the target vehicle in real time through an ambient light sensor to obtain light intensity information;

[0065] S1013, monitoring the road conditions around the target vehicle in real time through a camera and / or a radar to obtain road condition information;

[0066] S1014, monitoring the weather conditions around the target vehicle in real time through a rain sensor and a humidity sensor to obtain weather condition information;

[0067] S1015. Obtain GPS positioning information through a positioning module.

[0068] Specifically, the real-time speed and steering angle are obtained through the body controller to obtain vehicle status data; the light intensity around the vehicle, including natural light, street lights, tunnel lights, etc., is monitored in real time through photosensitive sensors (such as ambient light sensors) to obtain light intensity information; the wetness, water accumulation, snow accumulation and other conditions of the road are identified using cameras, millimeter-wave radars or laser radars (LiDAR), and the degree of vehicle bumps is judged in combination with acceleration sensors to obtain road condition information; rainfall, haze, dust and other weather conditions are judged through rainfall sensors, humidity sensors and camera image analysis (such as raindrop detection algorithms) to obtain weather condition information; the vehicle's geographic location (such as urban roads, highways, tunnels) and local time (day and night, seasonal changes) are obtained in combination with GPS to supplement light prediction information.

[0069] In some optional embodiments, after acquiring multi-source sensor data, it is also necessary to align the sensor data's timestamps to eliminate the time difference between devices. In addition, the sensor data needs to be cleaned to remove outliers (such as camera reflection interference) and noise filtering (such as radar signal interference).

[0070] In some optional embodiments, Kalman filtering or deep learning models (such as Transformer) are used to fuse multi-source data, for example, combining camera images and radar point clouds to enhance the accuracy of road condition recognition.

[0071] As an optional implementation, the light intensity change rate, road surface reflection coefficient and visibility index are determined according to the external environment information and GPS positioning information, which specifically includes:

[0072] S1021. Determine the light intensity change rate according to the light intensity information;

[0073] S1022, determining the road surface slipperiness and the state of water and snow accumulation according to the road surface state information, and determining the road surface reflection coefficient according to the road surface slipperiness and the state of water and snow accumulation;

[0074] S1023. Acquire real-time meteorological information of the vehicle's geographical location according to the GPS positioning information, and determine a visibility index according to the real-time meteorological information and weather condition information.

[0075] Specifically, the rate of change of light intensity (such as the instantaneous change in darkness when entering a tunnel) is determined based on the light intensity at multiple consecutive moments. The road surface slipperiness and the state of water and snow accumulation are determined based on the road surface condition information. The road surface reflection coefficient (the scattering effect of a wet and slippery road surface on light) is determined based on the road surface slipperiness and the state of water and snow accumulation. The GPS positioning is matched with the weather API data to obtain real-time meteorological information of the vehicle's geographic location. The visibility index (corresponding to the light penetration requirements in rainy and foggy days) is comprehensively judged based on the real-time meteorological information and weather condition information.

[0076] As an optional implementation, feature fusion is performed on the light intensity change rate, road surface reflectance coefficient and visibility index to obtain external environment feature data, which specifically includes:

[0077] S1024, performing data standardization and vectorization processing on the illumination intensity change rate, the road surface reflection coefficient, and the visibility index to obtain an illumination intensity feature vector, a road surface reflection feature vector, and a visibility feature vector;

[0078] S1025. Perform vector concatenation on the light intensity feature vector, the road surface reflection feature vector, and the visibility feature vector to obtain external environment feature data.

[0079] Specifically, data of different dimensions (such as light units in lux and road humidity in percentage) are converted into a unified numerical range and then vectorized to obtain light intensity feature vectors, road surface reflection feature vectors, and visibility feature vectors. The light intensity feature vectors, road surface reflection feature vectors, and visibility feature vectors are vector-concatenated to obtain external environment feature data.

[0080] As an optional implementation, the vehicle exterior light brightness prediction model is trained by the following steps:

[0081] S201, obtaining external environment feature sample data and vehicle status sample data of the test vehicle, and determining corresponding exterior light brightness level labels through manual labeling;

[0082] S202, determining training samples according to the external environment feature sample data and the vehicle state sample data;

[0083] S203, inputting the training samples into a pre-built deep learning neural network to obtain a prediction result of the exterior light brightness;

[0084] S204, determining a loss value according to the exterior light brightness prediction result and the exterior light brightness level label;

[0085] S205. Update the parameters of the deep learning neural network according to the loss value to obtain a trained vehicle exterior light brightness prediction model.

[0086] Specifically, the input data of the automobile exterior light brightness prediction model includes vehicle status data and external environment feature data. The model architecture can adopt a deep learning neural network, and the model output is a discrete brightness level (such as 0-100%). The external environment feature sample data and vehicle status sample data of the test vehicle are obtained, and the most appropriate exterior light brightness level label is determined through manual labeling. Then, the external environment feature sample data and vehicle status sample data of the test vehicle are used as training samples and input into the deep learning neural network for training.

[0087] After inputting the training samples into the initialized deep learning neural network, the recognition results output by the model, i.e., the prediction results of the exterior light brightness, can be obtained. The accuracy of the model prediction can be evaluated based on the prediction results of the exterior light brightness and the aforementioned labels of the exterior light brightness levels, thereby updating the parameters of the model. For the automobile exterior light brightness prediction model, the accuracy of the model prediction results can be measured by the loss function. The loss function is defined on a single training data and is used to measure the prediction error of a training data. Specifically, the loss value of the training data is determined by the label of a single training data and the prediction results of the model for the training data. In actual training, a training data set has a lot of training data, so the cost function is generally used to measure the overall error of the training data set. The cost function is defined on the entire training data set and is used to calculate the average value of the prediction errors of all training data, which can better measure the prediction effect of the model. For general machine learning models, the aforementioned cost function, plus the regularization term that measures the complexity of the model, can be used as the objective function of the training. Based on this objective function, the loss value of the entire training data set can be calculated. There are many types of commonly used loss functions, such as 0-1 loss function, square loss function, absolute loss function, logarithmic loss function, cross entropy loss function, etc., which can all be used as loss functions of machine learning models, which will not be elaborated here one by one. In an embodiment of the present invention, any loss function can be selected to determine the loss value of training. Based on the loss value of training, the back propagation algorithm is used to update the parameters of the model, and a trained automobile exterior light brightness prediction model can be obtained after several rounds of iteration. The specific number of iterations can be pre-set, or the training is considered to be completed when the test set meets the accuracy requirements.

[0088] By inputting the external environment feature data and vehicle status data of the target vehicle into the automobile exterior light brightness prediction model, the optimal target exterior light brightness level inferred by the model can be obtained. For example, medium brightness is used to balance energy consumption and visibility in a cloudy city environment at night, and high brightness and high-frequency flashing are used in heavy rain scenes on highways to enhance penetration and warn following vehicles.

[0089] As a further optional implementation, the brightness of the exterior lights of the target vehicle is adjusted and controlled according to the target exterior light brightness level, which specifically includes:

[0090] S1041, generating an RLS signal adjustment instruction according to the target exterior light brightness level and the preset safety and energy-saving strategy;

[0091] S1042: Send an RLS signal adjustment instruction to a vehicle light control unit, so that the vehicle light control unit gradually adjusts the brightness of the exterior light LED array of the target vehicle to a target exterior light brightness level.

[0092] Specifically, the preset safety strategy (such as ISO 22179 standard) and energy-saving strategy (such as low power mode) are used as constraints, and the corresponding RLS signal adjustment instructions are determined according to the target exterior light brightness level. The instructions are sent to the headlight control unit (ECU) through the CAN bus to adjust the current of the LED array or the projection area of ​​the matrix headlights. Gradual adjustment is also supported (to avoid sudden changes in brightness affecting the driver's adaptation).

[0093] As an optional implementation, after adjusting and controlling the exterior light brightness of the target vehicle according to the target exterior light brightness level, the following steps are further included:

[0094] S105, in response to the manual adjustment operation of the exterior lights of the target vehicle by the driver, obtaining a corresponding manually adjusted brightness level;

[0095] S106: Generate feedback samples according to the external environment feature data, the vehicle status data, and the manually adjusted brightness level, and optimize the automobile exterior light brightness prediction model according to the feedback samples.

[0096] Specifically, after adjusting and controlling the brightness of the target vehicle's exterior lights, the effect of the adjustment can be monitored in real time, for example, by verifying through a camera whether the actual lighting range matches expectations. At the same time, if the driver manually intervenes (such as the user turns up the brightness), feedback samples are generated based on the external environment characteristic data, vehicle status data, and manually adjusted brightness levels. The vehicle exterior light brightness prediction model is optimized based on the feedback samples to further improve the accuracy of the model prediction.

[0097] The method steps of the embodiment of the present invention are described above. It can be understood that the embodiment of the present invention obtains the vehicle status data, external environment information and GPS positioning information of the vehicle in real time, determines the light intensity change rate, road surface reflection coefficient and visibility index according to the external environment information and GPS positioning information, obtains the external environment feature data through feature fusion, inputs the external environment feature data and vehicle status data into the pre-trained automobile exterior light brightness prediction model, obtains the target exterior light brightness level, and thus can adjust and control the exterior light brightness of the target vehicle according to the target exterior light brightness level, which can not only enhance the lighting and improve the driving vision at night or in bad weather, but also moderately reduce the brightness during the day or when there is sufficient light, so as to achieve energy saving and consumption reduction, and improve the user's driving experience and driving safety; in addition, through continuous learning and optimization, the embodiment of the present invention can gradually adapt to different driving habits and environments, and provide users with a more personalized, safe and environmentally friendly driving experience.

[0098] Reference Figure 2 , an embodiment of the present invention provides an automobile lighting adaptive control system based on machine learning, comprising:

[0099] A data acquisition module is used to acquire vehicle status data, external environment information and GPS positioning information of the target vehicle, the external environment information includes light intensity information, road condition information and weather condition information;

[0100] A feature fusion module is used to determine the light intensity change rate, road surface reflection coefficient and visibility index according to the external environment information and GPS positioning information, and to perform feature fusion on the light intensity change rate, road surface reflection coefficient and visibility index to obtain external environment feature data;

[0101] The exterior light brightness prediction module is used to input the external environment feature data and the vehicle status data into the pre-trained automobile exterior light brightness prediction model to obtain the target exterior light brightness level;

[0102] The exterior light brightness control module is used to adjust and control the exterior light brightness of the target vehicle according to the target exterior light brightness level.

[0103] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0104] Reference Figure 3 , an embodiment of the present invention provides a vehicle lighting adaptive control device based on machine learning, comprising:

[0105] at least one processor;

[0106] at least one memory for storing at least one program;

[0107] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method for adaptive control of automobile lights based on machine learning.

[0108] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0109] An embodiment of the present invention further provides a computer-readable storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to execute the above-mentioned method for adaptive control of automobile lights based on machine learning.

[0110] A computer-readable storage medium of an embodiment of the present invention can execute a method for adaptive control of automobile lights based on machine learning provided by an embodiment of the method of the present invention, can execute any combination of implementation steps of the method embodiment, and has the corresponding functions and beneficial effects of the method.

[0111] The embodiment of the present invention also discloses a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 1 The method shown.

[0112] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0113] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified to the contrary, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0114] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0115] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0116] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the above-mentioned program is printed, since the above-mentioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in other suitable ways as necessary, and then stored in a computer memory.

[0117] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0118] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0119] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0120] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for adaptive control of automobile lighting based on machine learning, characterized in that: The following steps are involved: Acquire vehicle status data, external environment information, and GPS positioning information of the target vehicle, wherein the external environment information includes light intensity information, road condition information, and weather condition information; Determine the light intensity change rate, the road surface reflection coefficient and the visibility index according to the external environment information and the GPS positioning information, perform feature fusion on the light intensity change rate, the road surface reflection coefficient and the visibility index, and obtain external environment feature data; Inputting the external environment characteristic data and the vehicle status data into a pre-trained automobile exterior light brightness prediction model to obtain a target exterior light brightness level; The exterior light brightness of the target vehicle is adjusted and controlled according to the target exterior light brightness level.

2. The method for adaptively controlling automobile lighting based on machine learning according to claim 1, characterized in that: The acquisition of vehicle status data, external environment information and GPS positioning information of the target vehicle specifically includes: Acquiring the vehicle status data through a vehicle body controller, wherein the vehicle status data includes the speed and steering angle of the target vehicle; The light intensity information is obtained by monitoring the light intensity around the target vehicle in real time through an ambient light sensor; Monitor the road conditions around the target vehicle in real time by using a camera and / or a radar to obtain the road condition information; Monitor the weather conditions around the target vehicle in real time through a rain sensor and a humidity sensor to obtain the weather condition information; The GPS positioning information is obtained through a positioning module.

3. The method for adaptively controlling automobile lighting based on machine learning according to claim 1, characterized in that: The determining of the light intensity change rate, the road surface reflection coefficient and the visibility index according to the external environment information and the GPS positioning information specifically includes: Determining the light intensity change rate according to the light intensity information; Determine the road surface slipperiness and the water and snow accumulation state according to the road surface state information, and determine the road surface reflection coefficient according to the road surface slipperiness and the water and snow accumulation state; The real-time weather information of the vehicle's geographical location is acquired according to the GPS positioning information, and the visibility index is determined according to the real-time weather information and the weather condition information.

4. The method for adaptively controlling automobile lighting based on machine learning according to claim 1, characterized in that: The feature fusion of the light intensity change rate, the road surface reflectance coefficient and the visibility index to obtain external environment feature data specifically includes: Performing data standardization and vectorization processing on the illumination intensity change rate, the road surface reflection coefficient, and the visibility index to obtain an illumination intensity feature vector, a road surface reflection feature vector, and a visibility feature vector; The light intensity feature vector, the road surface reflection feature vector and the visibility feature vector are vector-joined to obtain the external environment feature data.

5. The method for adaptively controlling automobile lighting based on machine learning according to claim 1, characterized in that: The vehicle exterior light brightness prediction model is trained by the following steps: Obtaining the external environment feature sample data and vehicle status sample data of the test vehicle, and determining the corresponding exterior light brightness level label through manual labeling; Determine a training sample according to the external environment feature sample data and the vehicle state sample data; Inputting the training samples into a pre-built deep learning neural network to obtain exterior light brightness prediction results; Determine a loss value according to the exterior light brightness prediction result and the exterior light brightness level label; The parameters of the deep learning neural network are updated according to the loss value to obtain a trained vehicle exterior light brightness prediction model.

6. The method for adaptively controlling automobile lighting based on machine learning according to claim 1, characterized in that: The step of adjusting and controlling the exterior light brightness of the target vehicle according to the target exterior light brightness level specifically includes: generating an RLS signal adjustment instruction according to the target exterior light brightness level and a preset safety and energy-saving strategy; The RLS signal adjustment instruction is sent to a vehicle light control unit, so that the vehicle light control unit gradually adjusts the brightness of the exterior light LED array of the target vehicle to the target exterior light brightness level.

7. A method for adaptively controlling automobile lighting based on machine learning according to any one of claims 1 to 6, characterized in that: After the exterior light brightness of the target vehicle is adjusted and controlled according to the target exterior light brightness level, the following steps are also included: In response to a manual adjustment operation of an exterior light of a driver of the target vehicle, obtaining a corresponding manually adjusted brightness level; A feedback sample is generated according to the external environment characteristic data, the vehicle status data and the manually adjusted brightness level, and the automobile exterior light brightness prediction model is optimized according to the feedback sample.

8. An adaptive control system for automobile lighting based on machine learning, characterized in that: include: A data acquisition module is used to acquire vehicle status data, external environment information and GPS positioning information of the target vehicle, wherein the external environment information includes light intensity information, road condition information and weather condition information; A feature fusion module is used to determine the light intensity change rate, the road surface reflection coefficient and the visibility index according to the external environment information and the GPS positioning information, and perform feature fusion on the light intensity change rate, the road surface reflection coefficient and the visibility index to obtain external environment feature data; An exterior light brightness prediction module, used to input the external environment feature data and the vehicle status data into a pre-trained automobile exterior light brightness prediction model to obtain a target exterior light brightness level; The exterior light brightness control module is used to adjust and control the exterior light brightness of the target vehicle according to the target exterior light brightness level.

9. A vehicle lighting adaptive control device based on machine learning, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle lighting adaptive control method based on machine learning as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to execute the vehicle lighting adaptive control method based on machine learning as described in any one of claims 1 to 7 when executed by the processor.

Images