Integrated digital intelligent cockpit domain system

Abstract

The invention discloses an integrated digital intelligent cockpit domain system, and relates to the technical field of intelligent automobiles, the cockpit domain system comprises an environment sensing module, a decision planning module, a control execution module, an early warning and auxiliary driving module and a man-machine interaction and information display module; the environment sensing module is used for acquiring and analyzing the landform, curve and gradient information of the mountain road in real time, and environment data of pedestrians, vehicles, obstacles and road edges around the vehicle. The cockpit domain system has the advantages that the cockpit domain system monitors the surrounding environment of a vehicle in real time through the environment sensing module, front collision early warning and lane keeping assistance are achieved, traffic accidents are effectively prevented, the driving safety is improved, the early warning and auxiliary driving module can detect behaviors of a driver, the driving state of the driver is monitored in real time, and the driving safety is improved. Fatigue driving, distracted driving and violation operation can be found and reminded in time, and the safety, convenience and comfort of driving are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent automobile technology, and in particular to an integrated digital intelligent cockpit domain system. Background Art

[0002] With the rapid development of intelligent driving technology, the cockpit domain system, as a core component of vehicle intelligence and automation, has become increasingly important. Traditional cockpit systems often have single functions and are difficult to achieve autonomous driving and intelligent management under complex road conditions. Especially in complex terrains such as mountain roads, traditional systems are difficult to effectively cope with terrain, curves, slope changes, and various obstacles in the surrounding environment, resulting in reduced driving safety and poor driving experience.

[0003] At present, intelligent driving systems mainly rely on the comprehensive application of multiple technical means such as sensor technology, image recognition technology, intelligent algorithms and human-computer interaction technology. However, the existing systems still have many shortcomings in terms of integration, data processing capabilities, path planning efficiency and decision-making execution accuracy. Existing systems often use a certain sensor alone for environmental perception and lack effective fusion of multi-sensor data, resulting in inaccurate construction of environmental models and failure to fully reflect the complex environment around the vehicle. Traditional systems often only consider a single factor when planning paths, while ignoring the comprehensive influence of multiple factors such as safety, compliance with traffic rules, and obstacle avoidance, resulting in unreasonable planned paths. After receiving planning instructions, existing systems often have execution delays or inaccurate execution problems, and cannot respond to driving needs under complex road conditions in a timely manner, affecting driving safety. Traditional systems are often limited to simple information display and voice command reception in terms of human-computer interaction, lack intelligent interaction methods, and cannot provide drivers with a more convenient and efficient driving experience. In this regard, we propose an integrated digital intelligent cockpit domain system. Summary of the invention

[0004] The present invention aims at the technical problems existing in the prior art and provides an integrated digital intelligent cockpit domain system.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] An integrated digital intelligent cockpit domain system, the cockpit domain system comprising:

[0007] Environmental perception module, decision-making and planning module, control execution module, warning and assisted driving module, and human-computer interaction and information display module;

[0008] The environmental perception module is used to obtain and analyze the terrain, curves and slope information of mountain roads in real time, as well as the environmental data of pedestrians, vehicles, obstacles and road edges around the vehicle;

[0009] The decision-making and planning module is electrically connected to the environment perception module, and the decision-making and planning module is used to use intelligent algorithms to perform road recognition, obstacle detection and path planning based on the environment perception data to formulate an optimal driving strategy;

[0010] The control execution module is electrically connected to the decision-making and planning module, and the control execution module is used to automatically adjust vehicle parameters and execute operations to adapt to the road conditions of the mountain road through chassis control and braking and driving according to the instructions of the decision-making and planning module;

[0011] The warning and assisted driving module is electrically connected to the environmental perception module, and the warning and assisted driving module is used for forward collision warning, lane keeping assistance and driver behavior monitoring;

[0012] The human-computer interaction and information display module is electrically connected to the environmental perception module, decision-making and planning module, control execution module and warning and assisted driving module. The human-computer interaction and information display module is used to display the vehicle status, navigation information and road conditions to the driver through a display screen, and use an intelligent voice recognition system to receive and execute the driver's voice commands.

[0013] Preferably, the method for the environment perception module to obtain information and data is:

[0014] Obtain road information and vehicle location information in real time through high-precision maps and real-time positioning technology, the road information including: terrain, curves and slopes;

[0015] Use laser radar to perform three-dimensional space scanning to obtain three-dimensional image information of the vehicle's surrounding environment, including road edges and obstacles. Use millimeter-wave radar to obtain distance, speed and direction information, use cameras to capture images around and in front of the vehicle, and combine image processing technology to identify pedestrians, vehicles and traffic signs;

[0016] Clean and preprocess the acquired information and data, and process the preprocessed data through image recognition technology and object detection technology;

[0017] The processed data is fused to build an environmental model.

[0018] Preferably, the method for constructing the environment model is:

[0019] Based on the preprocessed data, the target distance and speed information detected by the millimeter-wave radar is used to search for the corresponding point set in the laser radar point cloud data;

[0020] Extract feature information from the lidar point cloud and camera image, and establish a corresponding relationship between the two data through a feature matching algorithm. The calculation method of the feature matching algorithm is:

[0021]

[0022] Where D A,B represents the Euclidean distance between vectors A and B, n represents the dimension of the vector, A i and B i Represent the value of the i-th dimension of vectors A and B respectively;

[0023] By calculating the corresponding position of the target in the point cloud data, the target position information detected by the millimeter-wave radar is mapped to the point cloud data of the laser radar, and the speed information of the millimeter-wave radar is attached to the corresponding point cloud data to form enhanced point cloud data containing position and speed information;

[0024] By converting the three-dimensional point cloud data into two-dimensional image data, the point cloud data of the laser radar is projected onto the image plane of the camera to form a point cloud image, and the point cloud image is superimposed with the original image of the camera to form a composite image containing depth information and visual information;

[0025] Extract feature information of each sensor and fuse it at the feature level;

[0026] After each sensor completes the perception task independently, the respective perception results are integrated at the decision-making level;

[0027] Use point cloud map data structure to store and represent environmental information, and build a three-dimensional environmental model based on the fused data.

[0028] Preferably, the method for the decision-making planning module to formulate a driving strategy is:

[0029] Data based on the environment perception module;

[0030] Using high-precision maps and real-time positioning technology, combined with image data from LiDAR and cameras, the vehicle can identify the type of road and specific road conditions it is currently on, and the road edge can be identified and tracked through image processing technology and object detection technology.

[0031] Utilize the three-dimensional space scanning capability of the laser radar, combined with the distance, speed and direction information of the millimeter wave radar, to detect obstacles around the vehicle, including: static obstacles and dynamic obstacles;

[0032] Based on the results of road recognition and obstacle detection, multiple driving paths are planned taking into account the vehicle's current position, target position, road conditions, traffic rules, and obstacle distribution;

[0033] Evaluate each path and select the best driving path;

[0034] According to the selected optimal path, a driving strategy is formulated in combination with the current status of the vehicle.

[0035] Preferably, the method for planning multiple driving paths is:

[0036] Based on the preprocessed data and road and obstacle identification, a number of paths are randomly generated, each path consists of a series of path points;

[0037] The fitness of each path is evaluated by considering its length, safety, degree of compliance with traffic rules and ability to avoid obstacles;

[0038] Use the roulette wheel selection strategy to select excellent individuals from a number of paths as the parents of the next generation, perform crossover operations on the selected parent individuals to generate new offspring individuals, and randomly change a node in a single path to perform mutation operations on the offspring individuals;

[0039] The new individuals generated after crossover and mutation are merged with some excellent parent individuals to form a new path;

[0040] The individual with the highest fitness is selected from the final several paths as the optimal driving path.

[0041] Preferably, the calculation method for fitness evaluation is:

[0042] F(p)=α·L(p)+β·S(p)+γ·M(p)+δ·C(p)

[0043] Where p represents the path, F(p) represents the fitness function of path p, L(p) represents the length of path p, S(p) represents the safety of path p, M(p) represents the stability of path p, C(p) represents the degree of compliance with traffic rules of path p, and α, β, γ, and δ represent the weight coefficients of path length, path safety, path stability, and the degree of compliance with path traffic rules, respectively.

[0044] Preferably, the method for controlling the execution module to adapt to the road conditions of mountain roads is:

[0045] The control execution module receives the driving strategy instruction from the decision planning module;

[0046] The vehicle's suspension system is adjusted according to the slope and curve information of the mountain road, and the posture of the vehicle body is adjusted actively to cope with complex road conditions on the mountain road;

[0047] When deceleration or parking is required, the control execution module automatically adjusts the braking force and distribution;

[0048] According to the driving strategy, the engine's output power and torque are adjusted to match the current mountain road conditions.

[0049] Preferably, the method for controlling the execution module to adjust the output power and torque of the engine to match the current mountain road conditions is:

[0050] Obtain the vehicle's real-time speed, driving force, current acceleration data and throttle opening information;

[0051] Obtain the slope information where the vehicle is located through the environment perception module;

[0052] Calculate the current vehicle weight data of the vehicle according to the acquired data information;

[0053] Determine the target acceleration based on the corresponding relationship between the vehicle weight, throttle opening, current vehicle speed and the target acceleration;

[0054] Determine whether power compensation and torque compensation are required based on the current acceleration and the target acceleration.

[0055] Preferably, the formula for calculating the current vehicle weight is:

[0056]

[0057] Where Q represents the current vehicle weight, T represents the motor drive torque, e represents the total transmission ratio of the gearbox, η represents the transmission system efficiency, r represents the tire rolling radius, G represents the wind resistance coefficient, J represents the frontal area, v represents the current vehicle speed, x represents the acceleration of gravity, u represents the rolling resistance coefficient, σ represents the ramp angle, y represents the current acceleration, O represents the moment of inertia, W represents the wheel, U represents the drive motor, and O represents the current acceleration. W represents the wheel moment of inertia, O U Indicates the rotational inertia of the drive motor.

[0058] Preferably, the method for the warning and assisted driving module to implement forward collision warning, lane keeping assistance and driver behavior detection is:

[0059] Forward collision warning: The environment perception module monitors the road environment ahead in real time. When an object is detected ahead, it will be displayed in the human-computer interaction and information display module, and an audible warning will be given;

[0060] Lane Keeping Assist: The environment perception module monitors the vehicle's position on the road in real time. When it detects that the vehicle is about to deviate from the current lane, it will give a sound warning through slight adjustments of the steering wheel and display in the human-computer interaction and information display module;

[0061] Driver behavior detection, the environmental perception module monitors the driver's driving status in real time through the camera unit and sensor unit installed in the car, collects the driver's image and video data in real time through the camera unit and sensor unit, processes and analyzes the collected data through image recognition technology and data analysis algorithm, and defines a series of abnormal driver behaviors according to safe driving specifications and relevant regulations. The abnormal behaviors include fatigue driving, distracted driving and illegal operations. The processed data is compared with the preset abnormal behavior pattern, and the driver's behavior is judged by building an abnormal behavior model. When the driver exhibits abnormal behavior, the driver will be reminded through sound warning information and automatically slow down.

[0062] The beneficial effects of the present invention are: the cockpit domain system monitors the vehicle's surrounding environment in real time through the environmental perception module, realizes forward collision warning and lane keeping assistance, effectively prevents traffic accidents, and improves driving safety. The warning and assisted driving module can also detect driver behavior, and through real-time monitoring of the driver's driving status, promptly discover and remind fatigue driving, distracted driving and illegal operations, further ensure driving safety, use intelligent algorithms for road recognition, obstacle detection and path planning, formulate the best driving strategy, provide the driver with accurate driving assistance, improve driving convenience and comfort, automatically adjust vehicle parameters and execute operations through chassis control and braking and driving, adapt to various complex road conditions, realize comprehensive perception of the vehicle's surrounding environment and intelligent decision-making planning, and improve driving safety, convenience and comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is the structural framework diagram of the integrated digital intelligent cockpit domain system. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0065] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0066] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0067] An integrated digital intelligent cockpit domain system, the cockpit domain system comprising:

[0068] Environmental perception module, decision-making and planning module, control execution module, warning and assisted driving module, and human-computer interaction and information display module;

[0069] The environmental perception module uses a variety of sensors to monitor the terrain around the vehicle and the mountain road in real time. It can accurately capture the ups and downs of the terrain, the curvature of the curve, the change of slope, and the subtle differences of surrounding pedestrians, vehicles, static obstacles and even the edge of the road, ensuring that the vehicle can grasp and adapt to complex road conditions in real time.

[0070] The decision-making and planning module uses intelligent algorithms to formulate the optimal driving strategy based on the environmental perception data. Based on the rich data provided by the environmental perception module, the algorithm is used for calculation and analysis to identify the road type, obstacle location and the behavior of other traffic participants, and formulate the optimal driving strategy to ensure the safety and efficiency of vehicle driving;

[0071] The control execution module automatically adjusts vehicle parameters and executes operations to adapt to road conditions according to the decision-making planning instructions. Through the sophisticated chassis control system and advanced braking and driving systems, it can achieve precise control of vehicle parameters. Under complex mountain road conditions, it can automatically adjust the vehicle posture and optimize the driving trajectory according to the instructions of the decision-making planning module to ensure that the vehicle passes every curve and slope stably and safely.

[0072] The warning and assisted driving module provides forward collision warning, lane keeping assist and driver behavior detection to enhance driving safety. Through the integrated forward collision warning system, lane keeping assist system and driver behavior monitoring system, it monitors the potential dangers in front of the vehicle in real time, keeps the vehicle stable in the lane, and evaluates the driver's driving status. Once an abnormal situation is found, the module will immediately warn the driver;

[0073] The human-computer interaction and information display module displays vehicle information and receives driver instructions through the display screen and intelligent voice recognition system, realizing convenient human-computer interaction.

[0074] Furthermore, the method for the environment perception module to obtain information and data is:

[0075] As the core of intelligent driving, the environmental perception module integrates high-precision maps, real-time positioning, lidar, millimeter-wave radar and high-definition cameras to comprehensively obtain information about the vehicle's surrounding environment. Through three-dimensional scanning, distance measurement and image recognition, it accurately constructs road and obstacle models. After data cleaning and preprocessing, it integrates information from various sources to form a dynamic environmental model, providing a solid foundation for intelligent driving decisions and ensuring driving safety and comfort.

[0076] Furthermore, the method of constructing the environment model is:

[0077] In the process of building the environmental model, the environmental perception module uses multi-sensor fusion technology to match, enhance and project the data of millimeter-wave radar, lidar and camera to form a composite image. Subsequently, information fusion is performed at the feature level and decision level, and the point cloud map data structure is used to store and represent the three-dimensional environmental model containing static and dynamic information, so as to achieve real-time adaptation and accurate understanding of complex traffic environments.

[0078] Furthermore, the method for the decision-making planning module to formulate a driving strategy is:

[0079] The decision-making planning module builds a comprehensive environmental cognition framework based on the data transmitted in real time by the environmental perception module. These data include but are not limited to road type, road condition information, vehicle location, and obstacle distribution, providing a solid foundation for subsequent decision-making;

[0080] The module uses high-precision maps and real-time positioning technology to accurately determine the type of road and specific road conditions the vehicle is currently on. By combining the image data of the laser radar and camera, the module uses image processing technology and object detection technology to accurately identify and continuously track the edge of the road, helping the vehicle to clarify the driving boundary and providing a strong guarantee for its stable driving under complex road conditions.

[0081] The module fully utilizes the three-dimensional spatial scanning capability of the laser radar and combines the distance, speed and direction information provided by the millimeter-wave radar to comprehensively detect obstacles around the vehicle. These obstacles include static trees, buildings, and shoulders, as well as dynamic pedestrians and other vehicles. By comprehensively analyzing this information, the type, location, speed and movement trajectory of the obstacles can be accurately determined, providing an important reference for subsequent path planning.

[0082] After obtaining the results of road identification and obstacle detection, the decision-making planning module plans the driving path. It plans multiple driving paths based on the vehicle's current position, target position, road conditions, traffic rules, and obstacle distribution, taking safety and efficiency into consideration. These paths not only take into account the vehicle's own driving capabilities, but also fully consider the interaction with other traffic participants to ensure smooth and safe driving.

[0083] The module evaluates each planned path. During the evaluation process, the module will comprehensively consider the path length, driving time, safety, and compliance with traffic rules. The module calculates the score of each path through an algorithm and selects the path with the highest score as the optimal driving path.

[0084] Based on the selected optimal path, the decision-making planning module formulates specific driving strategies based on the current status of the vehicle. These strategies include but are not limited to acceleration, deceleration, steering, and obstacle avoidance, aiming to guide the vehicle to drive safely and efficiently along the optimal path to the target location. At the same time, the module will dynamically adjust and optimize the driving strategy based on changes in real-time road conditions and vehicle status to ensure a smooth and comfortable driving process.

[0085] Further, the method of planning multiple driving paths is:

[0086] Based on the preprocessed data and road and obstacle identification, a number of paths are randomly generated, each path consists of a series of path points;

[0087] The fitness of each path is evaluated by considering its length, safety, degree of compliance with traffic rules and ability to avoid obstacles;

[0088] Use the roulette wheel selection strategy to select excellent individuals from a number of paths as the parents of the next generation, perform crossover operations on the selected parent individuals to generate new offspring individuals, and randomly change a node in a single path to perform mutation operations on the offspring individuals;

[0089] The new individuals generated after crossover and mutation are merged with some excellent parent individuals to form a new path;

[0090] The individual with the highest fitness is selected from the final several paths as the optimal driving path.

[0091] Furthermore, the calculation method for fitness evaluation is:

[0092] F(p)=α·L(p)+β·S(p)+γ·M(p)+δ·C(p)

[0093] Where p represents the path, F(p) represents the fitness function of path p, L(p) represents the length of path p, S(p) represents the safety of path p, M(p) represents the stability of path p, C(p) represents the degree of compliance with traffic rules of path p, α, β, γ, δ represent the weight coefficients of path length, path safety, path stability, and the degree of compliance with path traffic rules respectively;

[0094] Furthermore, the method of controlling the execution module to adapt to the road conditions of the mountain road is:

[0095] As the end executor of the entire intelligent driving system, the control execution module accurately receives driving strategy instructions from the decision-making and planning module. These instructions are based on comprehensive environmental perception and precise path planning, providing clear guidance for the vehicle's driving in the current mountain road environment.

[0096] After receiving the command, the control execution module immediately adjusts the vehicle's suspension system according to the road condition information of the mountain road. Through the active suspension system, the vehicle can respond to the ups and downs, bumps and rolls on the mountain road in the best posture, thereby improving the vehicle's stability and comfort, ensuring good contact between the tires and the ground, and improving the vehicle's handling and grip.

[0097] During driving, when encountering a situation where deceleration or parking is required, the control execution module will automatically adjust the braking force and distribution according to the driving strategy. By accurately controlling the braking force of each wheel, the module can achieve a smooth deceleration and parking process to avoid vehicle deviation or tail swinging caused by uneven braking force. At the same time, the module will also dynamically adjust the braking strategy according to the specific conditions of the mountain road to ensure the optimization of the braking effect;

[0098] According to the driving strategy, the engine's output power and torque are adjusted to match the current mountain road conditions.

[0099] Furthermore, the method for controlling the execution module to adjust the output power and torque of the engine to match the current mountain road conditions is as follows:

[0100] Obtain the vehicle's real-time speed, driving force, current acceleration data and throttle opening information;

[0101] Obtain the slope information where the vehicle is located through the environment perception module;

[0102] Calculate the current vehicle weight data based on the acquired data information.

[0103] Determine the target acceleration based on the corresponding relationship between the vehicle weight, throttle opening, current vehicle speed and the target acceleration;

[0104] Determine whether power compensation and torque compensation are required based on the current acceleration and the target acceleration.

[0105] Furthermore, the formula for calculating the current vehicle weight is:

[0106]

[0107] Where Q represents the current vehicle weight, T represents the motor drive torque, e represents the total transmission ratio of the gearbox, η represents the transmission system efficiency, r represents the tire rolling radius, G represents the wind resistance coefficient, J represents the frontal area, v represents the current vehicle speed, x represents the acceleration of gravity, u represents the rolling resistance coefficient, σ represents the ramp angle, y represents the current acceleration, O represents the moment of inertia, W represents the wheel, U represents the drive motor, and O represents the current acceleration. W represents the wheel moment of inertia, O U Indicates the rotational inertia of the drive motor.

[0108] Furthermore, the method for the warning and assisted driving module to realize forward collision warning, lane keeping assistance and driver behavior detection is as follows:

[0109] The warning and assisted driving module is the key to the intelligent driving system. It integrates multiple sensors and intelligent technologies to achieve forward collision warning, lane keeping assist and driver behavior detection. Forward collision warning monitors the environment ahead, assesses collision risks and issues warnings. Lane keeping assist automatically adjusts the vehicle position and reminds the driver to stay in the lane by identifying lane markings. Driver behavior detection monitors the driver's status through cameras and sensor units, identifies abnormal behavior and issues warnings, and automatically takes measures when necessary to improve driving safety and comfort.

[0110] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0112] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An integrated digital intelligent cockpit domain system, characterized in that: The cockpit domain system includes: Environmental perception module, decision-making and planning module, control execution module, warning and assisted driving module, and human-computer interaction and information display module; The environmental perception module is used to obtain and analyze the terrain, curves and slope information of mountain roads in real time, as well as the environmental data of pedestrians, vehicles, obstacles and road edges around the vehicle; The decision-making and planning module is electrically connected to the environment perception module, and the decision-making and planning module is used to use intelligent algorithms to perform road recognition, obstacle detection and path planning based on the environment perception data to formulate an optimal driving strategy; The control execution module is electrically connected to the decision-making and planning module, and the control execution module is used to automatically adjust vehicle parameters and execute operations to adapt to the road conditions of the mountain road through chassis control and braking and driving according to the instructions of the decision-making and planning module; The warning and assisted driving module is electrically connected to the environmental perception module, and the warning and assisted driving module is used for forward collision warning, lane keeping assistance and driver behavior monitoring; The human-computer interaction and information display module is electrically connected to the environmental perception module, decision-making and planning module, control execution module and warning and assisted driving module. The human-computer interaction and information display module is used to display the vehicle status, navigation information and road conditions to the driver through a display screen, and use an intelligent voice recognition system to receive and execute the driver's voice commands.

2. The integrated digital intelligent cockpit domain system according to claim 1, characterized in that: The method for the environmental perception module to obtain information and data is: Obtain road information and vehicle location information in real time through high-precision maps and real-time positioning technology, the road information including: terrain, curves and slopes; Use laser radar to perform three-dimensional space scanning to obtain three-dimensional image information of the vehicle's surrounding environment, including road edges and obstacles. Use millimeter-wave radar to obtain distance, speed and direction information, use cameras to capture images around and in front of the vehicle, and combine image processing technology to identify pedestrians, vehicles and traffic signs; Clean and preprocess the acquired information and data, and process the preprocessed data through image recognition technology and object detection technology; The processed data is fused to build an environmental model.

3. The integrated digital intelligent cockpit domain system according to claim 2, characterized in that: The method to build the environment model is: Based on the preprocessed data, the target distance and speed information detected by the millimeter-wave radar is used to search for the corresponding point set in the laser radar point cloud data; Extract feature information from the lidar point cloud and camera image, and establish a corresponding relationship between the two data through a feature matching algorithm. The calculation method of the feature matching algorithm is: Where D A,B represents the Euclidean distance between vectors A and B, n represents the dimension of the vector, A i and B i Represent the value of the i-th dimension of vectors A and B respectively; By calculating the corresponding position of the target in the point cloud data, the target position information detected by the millimeter-wave radar is mapped to the point cloud data of the laser radar, and the speed information of the millimeter-wave radar is attached to the corresponding point cloud data to form enhanced point cloud data containing position and speed information; By converting the three-dimensional point cloud data into two-dimensional image data, the point cloud data of the laser radar is projected onto the image plane of the camera to form a point cloud image, and the point cloud image is superimposed with the original image of the camera to form a composite image containing depth information and visual information; Extract feature information of each sensor and fuse it at the feature level; After each sensor completes the perception task independently, the respective perception results are integrated at the decision-making level; Use point cloud map data structure to store and represent environmental information, and build a three-dimensional environmental model based on the fused data.

4. The integrated digital intelligent cockpit domain system according to claim 1, characterized in that: The method for the decision-making planning module to formulate driving strategies is: Data based on the environment perception module; Using high-precision maps and real-time positioning technology, combined with image data from LiDAR and cameras, the vehicle can identify the type of road and specific road conditions it is currently on, and the road edge can be identified and tracked through image processing technology and object detection technology. Utilize the three-dimensional space scanning capability of the laser radar, combined with the distance, speed and direction information of the millimeter wave radar, to detect obstacles around the vehicle, including: static obstacles and dynamic obstacles; Based on the results of road recognition and obstacle detection, multiple driving paths are planned taking into account the vehicle's current position, target position, road conditions, traffic rules, and obstacle distribution; Evaluate each path and select the best driving path; According to the selected optimal path, a driving strategy is formulated in combination with the current status of the vehicle.

5. The integrated digital intelligent cockpit domain system according to claim 4, characterized in that: The method of planning multiple driving paths is: Based on the preprocessed data and road and obstacle identification, a number of paths are randomly generated, each path consists of a series of path points; The fitness of each path is evaluated by considering its length, safety, degree of compliance with traffic rules and ability to avoid obstacles; Use the roulette wheel selection strategy to select excellent individuals from a number of paths as the parents of the next generation, perform crossover operations on the selected parent individuals to generate new offspring individuals, and randomly change a node in a single path to perform mutation operations on the offspring individuals; The new individuals generated after crossover and mutation are merged with some excellent parent individuals to form a new path; The individual with the highest fitness is selected from the final several paths as the optimal driving path.

6. The integrated digital intelligent cockpit domain system according to claim 4 is characterized in that in, The calculation method for fitness evaluation is: F(p)=α·L(p)+β·S(p)+γ·M(p)+δ·C(p); Where p represents the path, F(p) represents the fitness function of path p, L(p) represents the length of path p, S(p) represents the safety of path p, M(p) represents the stability of path p, C(p) represents the degree of compliance with traffic rules of path p, and α, β, γ, and δ represent the weight coefficients of path length, path safety, path stability, and the degree of compliance with path traffic rules, respectively.

7. The integrated digital intelligent cockpit domain system according to claim 1, characterized in that: The method of controlling the execution module to adapt to the road conditions of mountain roads is: The control execution module receives the driving strategy instruction from the decision planning module; The vehicle's suspension system is adjusted according to the slope and curve information of the mountain road, and the posture of the vehicle body is adjusted actively to cope with complex road conditions on the mountain road; When deceleration or parking is required, the control execution module automatically adjusts the braking force and distribution; According to the driving strategy, the engine's output power and torque are adjusted to match the current mountain road conditions.

8. The integrated digital intelligent cockpit domain system according to claim 7, characterized in that: The method for controlling the execution module to adjust the engine output power and torque to match the current mountain road conditions is as follows: Obtain the vehicle's real-time speed, driving force, current acceleration data and throttle opening information; Obtain the slope information where the vehicle is located through the environment perception module; Calculate the current vehicle weight data of the vehicle according to the acquired data information; Determine the target acceleration based on the corresponding relationship between the vehicle weight, throttle opening, current vehicle speed and the target acceleration; Determine whether power compensation and torque compensation are required based on the current acceleration and the target acceleration.

9. The integrated digital intelligent cockpit domain system according to claim 8, characterized in that: The formula for calculating the vehicle's current vehicle weight is: Where Q represents the current vehicle weight, T represents the motor drive torque, e represents the total transmission ratio of the gearbox, η represents the transmission system efficiency, r represents the tire rolling radius, G represents the wind resistance coefficient, J represents the frontal area, v represents the current vehicle speed, x represents the acceleration of gravity, u represents the rolling resistance coefficient, σ represents the ramp angle, y represents the current acceleration, O represents the moment of inertia, W represents the wheel, U represents the drive motor, and O represents the current acceleration. W represents the wheel moment of inertia, O U Indicates the driving motor's rotational inertia.

10. The integrated digital intelligent cockpit domain system according to claim 1, characterized in that: The method by which the warning and assisted driving module implements forward collision warning, lane keeping assistance and driver behavior detection is as follows: Forward collision warning: The environment perception module monitors the road environment ahead in real time. When an object is detected ahead, it will be displayed in the human-computer interaction and information display module, and an audible warning will be given; Lane Keeping Assist: The environment perception module monitors the vehicle's position on the road in real time. When it detects that the vehicle is about to deviate from the current lane, it will give a sound warning through slight adjustments of the steering wheel and display in the human-computer interaction and information display module; Driver behavior detection, the environmental perception module monitors the driver's driving status in real time through the camera unit and sensor unit installed in the car, collects the driver's image and video data in real time through the camera unit and sensor unit, processes and analyzes the collected data through image recognition technology and data analysis algorithm, and defines a series of abnormal driver behaviors according to safe driving specifications and relevant regulations. The abnormal behaviors include fatigue driving, distracted driving and illegal operations. The processed data is compared with the preset abnormal behavior pattern, and the driver's behavior is judged by building an abnormal behavior model. When the driver exhibits abnormal behavior, the driver will be reminded through sound warning information and automatically slow down.

Images