Vehicle control method and device, computer readable storage medium and vehicle

Abstract

The invention discloses a vehicle control method and device, a computer readable storage medium and a vehicle, and the vehicle control method comprises the steps: obtaining a visual image and an expected driving track of a road section around the vehicle; predicting a pavement terrain corresponding to the vehicle driving track according to the visual image and the expected driving track; and control parameters of the vehicle are adjusted according to the road topography corresponding to the vehicle driving track. According to the method and the device, automatic identification of the pavement terrain can be realized, the terrain of the vehicle driving path is predicted, the vehicle control parameters are adjusted in advance, and the adaptability and the safety of the vehicle under different pavement conditions are improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a vehicle control method, a vehicle control device, a computer-readable storage medium and a vehicle. Background Art

[0002] In the related art, there are two main methods for identifying terrain changes during vehicle driving: using the suspension system for terrain identification and using a camera for terrain identification. Among them, for the solution of using a camera for terrain identification, it is usually based on the collected image information of the current road surface on which the vehicle is currently driving, and image processing is performed through an image processing algorithm to identify the current road surface terrain, and then control the vehicle. However, it is impossible to predict the road surface conditions of the vehicle's driving path, and it is impossible to adjust the vehicle parameters in advance to adapt to the road surface terrain. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, one purpose of the present invention is to provide a vehicle control method, which can realize automatic recognition of road terrain, and predict the terrain of the vehicle's driving path to adjust the vehicle control parameters in advance, thereby improving the adaptability and safety of the vehicle under different road conditions.

[0004] A second object of the present invention is to provide a vehicle control device.

[0005] A third object of the present invention is to provide a computer-readable storage medium.

[0006] A fourth objective of the present invention is to provide a vehicle.

[0007] In order to achieve the above-mentioned purpose, the vehicle control method of the first aspect of the embodiment of the present invention includes: acquiring a visual image of the road section around the vehicle and an expected driving trajectory; predicting the road topography corresponding to the vehicle's driving trajectory based on the visual image and the expected driving trajectory; and adjusting the control parameters of the vehicle based on the road topography corresponding to the vehicle's driving trajectory.

[0008] According to the vehicle control method of the embodiment of the present invention, by acquiring the visual image and expected driving trajectory of the vehicle, the road terrain corresponding to the current vehicle driving trajectory can be automatically identified. This method of comprehensively utilizing the visual image and the expected driving trajectory can avoid the shortcomings of relying solely on a single sensor for terrain recognition, and can predict the road terrain of the vehicle's driving path. The vehicle's control parameters can be adjusted in advance according to the road terrain corresponding to the vehicle's driving trajectory, so that the vehicle can better adapt to various road terrain changes and maintain a stable driving state, thereby improving the vehicle's adaptability and safety under different road conditions.

[0009] In some embodiments, predicting the road topography corresponding to the vehicle driving trajectory based on the expected driving trajectory and the visual image includes: obtaining the area covered by the expected driving trajectory in the visual image to obtain an image containing the driving trajectory; extracting terrain features from the image containing the driving trajectory; and solving the terrain data of the road surface at each wheel position along the driving trajectory based on the extracted terrain features.

[0010] In some embodiments, the vehicle control method further includes: determining the confidence of the terrain data according to the data integrity and recognition result of the terrain data.

[0011] In some embodiments, the vehicle control method also includes: obtaining actual road terrain data of the road on which the vehicle is currently traveling; comparing the actual road terrain data with the road terrain data identified in the corresponding driving area; if the deviation between the actual road terrain data and the road terrain data identified in the corresponding driving area exceeds a preset threshold, marking the identified road terrain data as under-fitting data; and sending the under-fitting data to the cloud to optimize the algorithm for identifying the road terrain based on the under-fitting data.

[0012] In some embodiments, the vehicle control method further includes: obtaining an algorithm for identifying the road terrain that is optimized according to the underfitting data to perform road terrain recognition.

[0013] In some embodiments, the control parameters of the vehicle are adjusted according to the road terrain corresponding to the vehicle's driving trajectory, including: pre-controlling at least one of the vehicle's driving force, braking force, steering angle, and suspension system parameters according to the road terrain corresponding to the vehicle's driving trajectory and the vehicle's actual driving state.

[0014] In some embodiments, the vehicle control method further includes: adjusting the control intensity of at least one of the driving force, braking force, steering angle, and suspension system parameters of the vehicle according to the confidence level of the terrain data.

[0015] In some embodiments, the vehicle control method further includes: acquiring actual road terrain data of the road on which the vehicle is currently traveling; and performing closed-loop control of at least one of the vehicle's drive system, braking system, steering system and suspension according to the actual road terrain data.

[0016] In some embodiments, the vehicle control method also includes: obtaining feedforward control data based on the road terrain corresponding to the vehicle's driving trajectory; acquiring actual road terrain data of the road on which the vehicle is currently driving, and obtaining feedback control data based on the actual road terrain data; obtaining ideal target control data based on the feedforward control data and the feedback control data; and controlling the vehicle based on the ideal target control data.

[0017] In some embodiments, obtaining actual road terrain data of the road on which the vehicle is currently traveling includes: obtaining vehicle status data and wheel status data; obtaining the vehicle's actual body inclination angle and the absolute height of each wheel based on the vehicle status data and the wheel status data; and obtaining the actual road terrain data based on the actual body inclination angle and the absolute height of each wheel.

[0018] In order to achieve the above-mentioned purpose, the second aspect of the embodiment of the present invention proposes a vehicle control device, including: an acquisition module, used to acquire a visual image of the road section around the vehicle and an expected driving trajectory; a prediction module, used to predict the road terrain corresponding to the vehicle's driving trajectory based on the visual image and the expected driving trajectory; a control module, used to adjust the control parameters of the vehicle according to the road terrain corresponding to the vehicle's driving trajectory.

[0019] According to the vehicle control device of the embodiment of the present invention, the acquisition module acquires the visual image and expected driving trajectory of the vehicle, and the prediction module can automatically identify the road terrain corresponding to the current vehicle driving trajectory. This method of comprehensively utilizing the visual image and the expected driving trajectory can avoid the shortcomings of relying on only a single sensor for terrain recognition, and can predict the road terrain of the vehicle's driving path. The vehicle's control parameters can be adjusted in advance according to the road terrain corresponding to the vehicle's driving trajectory, so that the vehicle can better adapt to various road terrain changes and maintain a stable driving state, thereby improving the adaptability and safety of the vehicle under different road conditions.

[0020] In order to achieve the above-mentioned purpose, the vehicle control device of the third aspect embodiment of the present invention includes: at least one processor; a memory communicatively connected to the at least one processor; a computer program is stored in the memory, and when the at least one processor executes the computer program, the vehicle control method described in the above embodiment is implemented.

[0021] The vehicle control device according to the embodiment of the present invention implements the vehicle control method described in the above embodiment when the processor executes the computer program. By comprehensively utilizing visual images and expected driving trajectories, the function of automatically identifying road terrain and adjusting vehicle control parameters is realized. This comprehensive terrain recognition and parameter adjustment capability enables the vehicle to adapt to changes in different road terrains more accurately, thereby improving the vehicle's adaptability and driving safety under different road conditions.

[0022] In order to achieve the above-mentioned purpose, a computer-readable storage medium of an embodiment of the fourth aspect of the present invention stores a computer program thereon, and when the computer program is executed, the vehicle control method described in the above embodiment is implemented.

[0023] According to the computer-readable storage medium of an embodiment of the present invention, by executing the vehicle control method described in the above embodiment, the visual image and the expected driving trajectory of the vehicle are comprehensively utilized to automatically identify the road terrain corresponding to the vehicle's driving trajectory. This method of comprehensively utilizing the visual image and the expected driving trajectory can avoid the shortcomings of relying solely on a single sensor for terrain recognition, and can predict the road terrain of the vehicle's driving path. The vehicle's control parameters can be adjusted in advance according to the road terrain corresponding to the vehicle's driving trajectory, so that the vehicle can better adapt to various road terrain changes and maintain a stable driving state, thereby improving the vehicle's adaptability and safety under different road conditions.

[0024] In order to achieve the above-mentioned purpose, the vehicle of the fifth aspect of the embodiment of the present invention includes: a visual system for collecting visual images of the vehicle; and the vehicle control device described in the above embodiments, wherein the vehicle control device is connected to the visual system.

[0025] According to the vehicle of the embodiment of the present invention, the vehicle control device analyzes and processes the images obtained from the visual system and the expected driving trajectory by adopting the vehicle control method described in the above embodiment, and can automatically identify the road terrain corresponding to the current driving trajectory of the vehicle, and automatically adjust the control parameters of the vehicle according to these identification results, so that the vehicle can better adapt to various road terrain changes and maintain a stable driving state, thereby improving the adaptability and safety of the vehicle under different road conditions.

[0026] In some embodiments, the vehicle further includes: a communication device, which is connected to the vehicle control device and is used to send underfitting data and receive an algorithm for identifying road terrain that is optimized based on the underfitting data.

[0027] In some embodiments, the vehicle further includes a wheel height sensor, a wheel speed sensor, and a vehicle body inertial navigation sensor.

[0028] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0030] Figure 1 is a schematic diagram of the structure of a vehicle data interaction system according to an embodiment of the present invention;

[0031] Figure 2 is a flow chart of a vehicle control method according to an embodiment of the present invention;

[0032] Figure 3 is a functional architecture diagram of a terrain automatic control system according to an embodiment of the present invention;

[0033] Figure 4 is a working scene diagram of a feature recognition and classification module according to an embodiment of the present invention;

[0034] Figure 5 is a graph showing the relationship between the longitudinal displacement of the left front wheel and the vertical height of the wheel from the horizontal ground according to an embodiment of the present invention;

[0035] Figure 6 is a schematic diagram of the principle of a four-wheel terrain parsing module according to an embodiment of the present invention;

[0036] Figure 7 is a block diagram of a vehicle control device according to an embodiment of the present invention;

[0037] Figure 8 is a block diagram of a vehicle control device according to still another embodiment of the present invention.

[0038] Reference numerals:

[0039] Terrain automatic control system 100; Vehicle data interaction system 200;

[0040] Vehicle 1; Communication network 2; Cloud server 3;

[0041] Vehicle control device 10; visual system 20; communication device 30; wheel height sensor 40; wheel speed sensor 50; vehicle body inertial navigation sensor 60;

[0042] Automatic terrain recognition module 110; terrain analysis control module 120; feedback control module 130; four-wheel terrain analysis module 140; acquisition module 11; prediction module 12; control module 13;

[0043] Driving trajectory prediction module 111; visual processing module 112; data online update module 113; feature recognition and classification module 114; feedforward control module 121; ideal target calculation module 122;

[0044] The ground where the vehicle is currently located 141; the coordinate system 142 corresponding to the ground where the vehicle is currently located; the horizontal plane 143; the coordinate system 144 corresponding to the horizontal plane; the schematic body of the vehicle 145; the center of mass of the vehicle 146; the coordinate system 147 corresponding to the plane where the chassis of the vehicle is located; the wheel 148;

[0045] Processor 101; Memory 102. DETAILED DESCRIPTION

[0046] Embodiments of the present invention are described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. Embodiments of the present invention are described in detail below.

[0047] In the related art, only the suspension system is used for terrain perception, or only visual sensors such as cameras are used to identify terrain, which may have certain limitations in accuracy and comprehensiveness, resulting in the vehicle being unable to fully adapt to complex road surface changes. In response to this problem, the present invention proposes a vehicle control method, which can provide more comprehensive and accurate terrain recognition capabilities, realize automatic recognition of road surface terrain, enable the vehicle to better adapt to different road surface terrains, and improve the adaptability and safety of the vehicle under different road conditions.

[0048] In order to facilitate the description of the technical solution, the vehicle according to the embodiment of the present invention will be described below.

[0049] Figure 1 FIG. 1 is a schematic diagram of a vehicle data interaction system according to an embodiment of the present invention. Figure 1 As shown, the vehicle data interaction system 200 includes: a communication network 2, a cloud server 3 and a vehicle 1.

[0050] The communication network 2 may be composed of various network infrastructures, such as base stations, satellites, optical cables, etc. The communication network 2 may perform data transmission with the communication device 30 equipped on the vehicle 1 or the cloud server 3 based on a specific communication protocol.

[0051] The cloud server 3 is a powerful computing resource located in the cloud computing center. It can store data uploaded by all vehicles 1 equipped with terrain automatic control systems and be used to train and iterate visual algorithms. Through the cloud server 3, the visual recognition algorithm trained with the latest big data can be updated and optimized online, and the latest version of the software data can be sent to the vehicle 1 through the communication network 2.

[0052] The vehicle 1 may be a vehicle equipped with an automatic terrain control system. The vehicle 1 may be connected to the communication network 2 via the communication device 30 , and finally establish communication with the cloud server 3 .

[0053] In some embodiments, the vehicle 1 includes: a vision system 20 , a vehicle control device 10 , a communication device 30 , a wheel height sensor 40 , a wheel speed sensor 50 , and a vehicle body inertial navigation sensor 60 .

[0054] Among them, the visual system 20 can be used to collect visual images of the vehicle 1. In an embodiment, the visual system 20 may include two or more cameras for capturing terrain information of the road section around the vehicle 1. These cameras provide images from different perspectives and can obtain multiple visual angles of the same terrain area. In addition, the visual system 20 may also include other detection methods, such as laser radar or ultrasonic radar, to provide additional physical information. This physical information can assist in calculation when the subsequent vehicle control device 10 processes the image to provide a more comprehensive terrain recognition function.

[0055] In some embodiments, the vehicle control device 10 is connected to the visual system 20. The road surface topography corresponding to the vehicle driving trajectory is identified by using the image information and the expected driving trajectory acquired by the visual system 20, and the control parameters of the vehicle 1 are adjusted according to the road surface topography corresponding to the vehicle driving trajectory. This enables the vehicle 1 to adapt to different road surface topography changes and improves adaptability and safety under different road conditions.

[0056] In some embodiments, the vehicle control device 10 includes a controller, which is the core computing and processing unit of the terrain automatic control system 100. The controller can process data from visual signals and sensor signals, and automatically judge the terrain conditions corresponding to the current terrain and the path ahead based on these data. Finally, the controller will send requests to the drive, brake, steering and suspension systems according to these judgment results, so that the whole vehicle automatically operates in a control mode adapted to the current terrain. The controller can exchange data with the communication device 30. The controller may include any variety of electronic processing devices, storage devices, input / output (I / O) devices, and / or other known components.

[0057] In some embodiments, the controller may include multiple internal modules, such as an internal μC module, an internal storage module, an internal communication module, and an internal sensor module. These internal modules cooperate with each other to enable the controller to process and analyze data, realize terrain recognition and vehicle control, so that the vehicle 1 can adapt to different road terrain changes.

[0058] The internal μC module may include an electronic processing device such as a microprocessor 101, a microcontroller, an application-specific integrated circuit (ASIC), etc., which is responsible for executing instructions such as software, firmware, programs, algorithms, scripts, etc. stored in the internal storage module. This module is the core part of the controller, which enables the controller to process and analyze the collected data.

[0059] The internal storage module can be used to store various sensor readings, visual images, lookup tables or other data structures, algorithms, etc. The internal storage module provides the controller with the ability to store and retrieve data for terrain recognition and control parameter adjustment.

[0060] The internal communication module can connect to other vehicle devices, modules and systems and exchange data when needed. The internal communication module enables the controller to coordinate and exchange information with other vehicle components to achieve higher-level functions.

[0061] The internal sensor module may be a sensor integrated inside the controller, or may include other sensor circuits such as power supply voltage and current monitoring. The internal sensor module is used to collect various parameters and status information inside the vehicle 1 so that the controller can make corresponding decisions and adjustments.

[0062] In some embodiments, the communication device 30 is connected to the vehicle control device 10 to realize information transmission between the vehicle data and the communication network 2. The communication device 30 has multiple communication interfaces, such as CAN, Ethernet, WIFI, 4G / 5G, etc. The communication device 30 obtains update data from the cloud server 3 through the communication network 2. These data may include map information, new software versions, etc., which are used to update the software modules inside the vehicle 1. The communication device 30 is responsible for transmitting these data to the internal system of the vehicle 1 for corresponding iteration and update.

[0063] In addition, the communication device 30 is also used to send underfitting data and receive an algorithm for identifying road terrain that is optimized based on the underfitting data. Specifically, when the vehicle control device 10 identifies that the vision and sensor deviation is too large, the communication device 30 uploads the corresponding underfitting data to the cloud server 3. These data can be used for algorithm optimization training in the cloud to improve the terrain recognition function of the vehicle 1.

[0064] In some embodiments, the wheel height sensor 40 is used to sense the relative height between each wheel 148 and the vehicle body, and generally there are at least four sensors, which are usually arranged on the suspension between the wheel 148 and the vehicle body. The controller can obtain the signals of these sensors to better understand the posture and suspension state of the vehicle 1, so as to make corresponding adjustments and controls.

[0065] In some embodiments, the wheel speed sensor 50 is used to monitor the rotation speed of each wheel 148. Generally, there are at least four sensors, which are usually arranged on the wheel hub. The controller can obtain the signals of these sensors to monitor the rotation speed of the wheel 148 and the motion state of the vehicle 1 in real time, and provide necessary information for the system.

[0066] In some embodiments, the vehicle body inertial navigation sensor 60 is used to detect the motion information of the vehicle body in various directions, including six dimensions such as longitudinal acceleration, lateral acceleration, vertical acceleration, yaw angular velocity, pitch angular velocity, and roll angular velocity. These sensors can directly obtain pitch angle and sideslip angle information, which can be used to simplify the algorithms of some modules, provide more accurate vehicle posture information, and reference data of vehicle motion status.

[0067] Reference below Figure 2-Figure 6 A vehicle control method according to an embodiment of the present invention is described.

[0068] Figure 2 is a flow chart of a vehicle control method according to an embodiment of the present invention. Figure 2 As shown, the vehicle control method at least includes steps S1-S3, which are specifically as follows.

[0069] S1, obtains the visual image of the road section around the vehicle and the expected driving trajectory.

[0070] In some embodiments, the vehicle can continuously capture visual images of the surrounding environment through an equipped visual system, such as a camera, radar, or other sensing device. These devices can be located in different positions such as the front, rear, left, right, and top of the vehicle to obtain a full range of vision. The visual images may include elements such as roads, surroundings, obstacles, traffic signs, and other vehicles. These visual images are presented in the form of digital images and may contain information such as color, brightness, and texture.

[0071] The expected driving trajectory can be a theoretical driving path derived from the vehicle's navigation system, map data, and planning algorithms. This path describes the route the vehicle is expected to follow, including turns, straight driving, acceleration, and deceleration. The expected driving trajectory can take into account factors such as traffic regulations, destinations, and optimization of routes.

[0072] S2, predicting the road topography corresponding to the vehicle's driving trajectory based on the visual image and the expected driving trajectory.

[0073] Specifically, the vehicle obtains surrounding image information through the visual system. Through image processing technology and visual recognition algorithms based on image big data, features in the image, such as road texture, edges, and colors, can be extracted. At the same time, the expected driving trajectory provides the vehicle's expected path. By comparing and analyzing the expected driving trajectory with the road features in the image, the system can predict the road terrain corresponding to the vehicle's driving trajectory. Pre-trained visual recognition algorithms can improve recognition accuracy and efficiency.

[0074] In some embodiments, the road surface terrain can be of various types, including but not limited to: paved roads (such as asphalt roads, concrete roads, etc.), unpaved roads (such as dirt roads, gravel roads, etc.), uneven roads (such as bumps, potholes, and uneven sections), flat roads and ramps (such as uphill, downhill, side slopes, and other different slopes), etc. By analyzing the image, the system can identify the inclination, texture, curvature and other characteristics of the road surface. For example, for unpaved roads, the color and texture of gravel or soil may be seen in the image. For ramps, it may be possible to determine whether there is an inclination by the change in perspective in the image. In addition, information about the expected driving trajectory can also help the system infer the terrain conditions that the vehicle is about to pass. For example, if the expected driving trajectory shows that the vehicle will enter a curve, the system can identify the road surface terrain based on the curve features in the image.

[0075] In some embodiments, the system can also determine the undulation of the road surface by using sensors such as lidar or ultrasonic radar to judge the height change of the ground with the help of the strength and time of the reflected signal to predict different types of road terrain.

[0076] S3, adjusting the control parameters of the vehicle according to the road topography corresponding to the vehicle's driving trajectory.

[0077] Specifically, based on the road terrain information corresponding to the vehicle's driving trajectory, the vehicle control device automatically adjusts various control parameters of the vehicle in advance, including driving force, braking force, steering angle or power strength, and suspension stiffness or damping. These adjustments can achieve optimal control for different terrains to provide better vehicle stability, suspension adjustment, brake distribution and other functions. For example, when the road terrain is identified as uneven or with obstacles, the system may reduce the vehicle speed and increase the damping of the suspension to reduce the bumps of the vehicle body. If the road terrain is flat and open, the system may optimize the vehicle's power distribution and improve driving performance.

[0078] For example, on unpaved roads, the system can reduce the stiffness of the suspension to reduce vibration and provide a more comfortable driving experience. On steep slopes, the system can adjust the braking force and power distribution to ensure that the vehicle maintains a safe speed when going up and down the slope.

[0079] In some embodiments, the system may also consider the current driving mode, such as cruise mode, sport mode, etc., to adjust the control parameters. In addition, the system may also combine the actual dynamic data of the vehicle, such as vehicle speed, acceleration, etc., to further optimize the adjustment of the parameters.

[0080] According to the vehicle control method of the embodiment of the present invention, by acquiring the visual image and expected driving trajectory of the vehicle, the road terrain corresponding to the current vehicle driving trajectory can be automatically identified. This method of comprehensively utilizing the visual image and the expected driving trajectory can avoid the shortcomings of relying solely on a single sensor for terrain recognition, and can predict the terrain of the vehicle's driving path. The vehicle's control parameters can be adjusted in advance according to the road terrain corresponding to the vehicle's driving trajectory, so that the vehicle can better adapt to various road terrain changes and maintain a stable driving state, thereby improving the vehicle's adaptability and safety under different road conditions.

[0081] In some embodiments, predicting the road terrain corresponding to the vehicle driving trajectory based on the expected driving trajectory and the visual image includes: obtaining the expected driving trajectory coverage area in the visual image to obtain an image containing the driving trajectory. Extracting terrain features from the image containing the driving trajectory. According to the extracted terrain features, solving the terrain data of the road surface at each wheel position along the driving trajectory.

[0082] Specifically, based on the expected driving trajectory of the vehicle and the current position of the vehicle, the system can determine the coverage area of ​​the expected driving trajectory in the visual image. Then, from the visual images acquired by the vehicle, an image covering the expected driving trajectory area is selected. This step ensures that the selected image contains the road section where the vehicle is about to travel.

[0083] Further, the selected image will be processed for terrain feature extraction. This can use image processing and computer vision techniques to extract terrain-related information from the image. For example, edge detection, texture analysis and other methods can be used to identify road boundaries, color changes, texture features, etc.

[0084] Furthermore, by matching these features with the expected driving trajectory, terrain data at different positions along the vehicle's driving trajectory can be calculated. These terrain data may include height change curves, driving trajectories, vectors, coordinates, terrain pitch angle changes, terrain roll angle changes, yaw angle changes, etc.

[0085] Among them, the height change curve can describe the ups and downs of the road surface. The driving trajectory can describe the vehicle's travel path. The vector can represent the direction and speed of the vehicle's movement. The coordinates can identify the location information of different positions on the vehicle's driving trajectory. The terrain pitch angle change can describe the up and down tilt of the road surface. The terrain roll angle change can describe the lateral tilt of the road surface. The yaw angle change can describe the lateral swing of the vehicle.

[0086] In general, in practical applications, these steps work together to enable the system to obtain detailed road terrain information based on the expected driving trajectory and terrain features extracted from visual images. This information will be output to the cruise system or the driver to assist in planning a more appropriate driving route and driving speed, setting a more appropriate drive torque distribution method, etc., to adapt to different terrain conditions and improve vehicle stability and performance.

[0087] In some embodiments, the system not only identifies the road terrain corresponding to the vehicle's driving trajectory, but also evaluates the terrain data obtained to determine its credibility or confidence. Specifically, the system can evaluate the data integrity of the terrain data obtained from the visual image and the expected driving trajectory. This can include checking whether there are missing, noisy or other inaccurate factors in the data. The system will then evaluate the previous recognition steps to determine how well the recognized terrain matches the actual terrain. This can be achieved by comparing the extracted terrain features with the actual terrain features.

[0088] Furthermore, based on the completeness of the data and the recognition results, the system can calculate the confidence of the terrain data. If the data is complete and the recognition results match the actual terrain height, the confidence will be high. On the contrary, if the data is incomplete or the recognition results are inaccurate, the confidence will be low.

[0089] In some embodiments, the system may also consider multiple other factors to determine the confidence of the terrain data. For example, the system may adjust the calculation of the confidence based on factors such as the vehicle's speed, driving state (acceleration, braking, steering, etc.), and sensor stability. In addition, the system may also introduce historical data, such as previous recognition results of similar terrain, to further improve the confidence of the terrain data.

[0090] In some embodiments, the system not only focuses on the identification of the road terrain corresponding to the expected driving trajectory, but can also compare the actual road terrain data with the road terrain data identified in the corresponding driving area to detect whether there is an underfitting situation, that is, the actual terrain is inconsistent with the identified terrain.

[0091] Specifically, during the driving process of the vehicle, the system can use various sensors to obtain the actual terrain data of the road the vehicle is currently driving on. These data may include information such as ground height change, slope, roll angle, etc.

[0092] Furthermore, the acquired actual road terrain data is compared with the road terrain data identified in the corresponding driving area, and the system can determine whether the deviation between them exceeds a preset threshold. If the deviation between the actual road terrain data and the identified terrain data exceeds the preset threshold, the system can mark these identified terrain data as underfitting data. This means that the recognition algorithm performs poorly in these areas and needs to be further optimized.

[0093] Furthermore, the road terrain data marked as underfitting data can be sent to the cloud to optimize the road terrain recognition algorithm. In the cloud, the algorithm can analyze the underfitting data, find out the problem, and optimize it. This optimization process can involve adjusting the algorithm parameters, training machine learning or deep learning models, etc. The accuracy of the algorithm is optimized through continuous iteration and training.

[0094] In some embodiments, the system can record the difference between the recognized terrain data and the actual terrain data while marking the underfitting data. This information can be used to further analyze the improvement direction of the algorithm. In addition, the system can also dynamically adjust the preset threshold according to different road types, driving conditions and other factors to adapt to different actual situations.

[0095] In addition, when optimizing in the cloud, the system can analyze the common characteristics of underfit data to improve the performance of the algorithm. For example, if multiple vehicles report underfit data on the same road section, the system can centrally process these cases in the cloud and further optimize the algorithm to achieve better performance in road terrain recognition in that area.

[0096] In some embodiments, after optimization in the cloud, the system can obtain an algorithm for identifying road terrain that is optimized based on the underfitting data, and this optimized algorithm is the result of training and improvement based on the previously collected underfitting data. By using the optimized algorithm, the system can more accurately identify the road terrain corresponding to the vehicle's driving trajectory based on the visual image and the expected driving trajectory during the actual driving of the vehicle.

[0097] Through the above steps, the system can more accurately identify road terrain based on the optimized algorithm, improving the adaptability and safety of the vehicle under different terrain conditions. This real-time application optimization method can continuously improve the performance of the system and enable the vehicle to better adapt to the changing road environment.

[0098] In some embodiments, adjusting the control parameters of the vehicle according to the road surface topography corresponding to the vehicle driving trajectory includes: pre-controlling at least one of the driving force, braking force, steering angle, and suspension system parameters of the vehicle according to the road surface topography corresponding to the vehicle driving trajectory and the actual driving state of the vehicle. The suspension system parameters may include suspension damping, suspension stiffness, and suspension height. These adjustments are intended to optimize the stability, comfort, and performance of the vehicle.

[0099] The driving force may refer to the power output by the vehicle engine, which is used to propel the vehicle forward. In advance control, the system can adjust the output power of the engine according to the terrain of the road the vehicle is about to pass and the actual driving state of the vehicle, thereby changing the acceleration performance of the vehicle. For example, on an uphill road, the system can increase the driving force in advance to ensure that the vehicle can go uphill smoothly.

[0100] Braking force can refer to the deceleration force generated by the braking system, which is used to slow down the vehicle or stop it. In advance control, the system can adjust the braking force distribution of the braking system in advance according to the expected driving trajectory and road terrain information. For example, when the vehicle is about to pass a steep downhill section, the system can increase the braking force to control the speed of the vehicle and avoid excessive speed.

[0101] The steering angle may refer to the deflection angle of the wheel relative to the vehicle's forward direction. In advance control, the system can adjust the steering system in advance according to the expected driving trajectory and curve angle to make the vehicle more adaptable to the curve. For example, when entering a curve, the system can adjust the steering angle in advance so that the vehicle can turn more smoothly.

[0102] Suspension system parameters may refer to the adjustment of the damping, stiffness, and height of the suspension in the suspension system. In advance control, the system can adjust the suspension system parameters in advance according to the changes in the road topography and the actual driving state of the vehicle. For example, on an uneven road surface, the system can reduce the damping of the suspension in advance to provide a better shock absorption effect.

[0103] In some embodiments, the vehicle control method further includes: adjusting the control strength of at least one of the vehicle's driving force, braking force, steering angle, and suspension system parameters according to the confidence level of the terrain data. This adjustment can achieve more sophisticated vehicle control according to the confidence level of the terrain data to adapt to terrain recognition results with different confidence levels.

[0104] Among them, the confidence of terrain data can refer to the degree of trust in the identified road terrain information. This can be evaluated based on the reliability of the recognition algorithm, the accuracy of the sensor, etc. The confidence can be expressed as a value, such as a percentage or a range of 0 to 1, reflecting the reliability of the data. According to the confidence of the terrain data, the weights of control parameters such as driving force, braking force, steering angle and suspension system can be adjusted. For terrain data with high confidence, the system can increase the weight of the corresponding control parameters to respond more actively to terrain changes. For terrain data with low confidence, the system can reduce the weight of the corresponding control parameters to reduce the impact on vehicle control.

[0105] In some embodiments, when adjusting the control parameter strength, a smooth approach may be considered to avoid the impact of sudden control changes on the vehicle. For example, the control parameters may be gradually adjusted according to the confidence level to make the control transition of the vehicle smoother.

[0106] Therefore, the actual vehicle response is compared with the expected response, and the intensity of the control parameters is adjusted based on the actual effect feedback. Through continuous real-time adjustments, the vehicle control is more adapted to the current terrain and driving conditions. This method makes full use of the confidence information of the terrain data to adjust the vehicle control parameters in a more intelligent and adaptive way, thereby improving the vehicle's stability, suspension adjustment, brake distribution and overall driving performance.

[0107] In some embodiments, the vehicle control method further includes: acquiring actual road terrain data of the road on which the vehicle is currently traveling, and performing closed-loop control on at least one of the vehicle's driving system, braking system, steering system, and suspension system according to the actual road terrain data.

[0108] Among them, closed-loop control can be a feedback control mechanism, in which the system can continuously measure the actual state, compare this information with the desired state, and then adjust the control input to make the actual state gradually approach the desired state. In an embodiment of the present invention, the vehicle's drive system, braking system, steering system and suspension system can be closed-loop controlled so as to make appropriate adjustments according to changes in the actual road surface topography. Such closed-loop control can adjust the vehicle's control parameters in real time according to the actual road surface topography to ensure the stability and performance of the vehicle under different terrains.

[0109] Specifically, the vehicle can obtain the actual terrain data of the current road through various sensors (such as lidar, camera, ultrasonic sensor, etc.). This data may include information such as road height changes, bumps, potholes, curvature, and road type (paved road, unpaved road, etc.).

[0110] Furthermore, the acquired actual road surface terrain data is processed and analyzed to extract key terrain features. This may involve filtering, smoothing, feature extraction and other processing of the terrain data to obtain effective information about the terrain. Based on the actual road surface terrain data obtained by analysis, the vehicle control system can adjust the control parameters of at least one of the drive system, brake system, steering system and suspension system in real time. For example, when driving on an uneven road section, the control system can increase the damping of the suspension to reduce the bumps of the vehicle. When driving uphill, the output of the drive system can be adjusted to ensure sufficient power.

[0111] Furthermore, the control system implements closed-loop control based on the actual road terrain data. This means that the vehicle's sensors are not only used to obtain the actual road terrain data, but also to monitor the vehicle's status in real time. The control system can compare the actual status with the desired status and adjust the control parameters according to the changes in the actual terrain to maintain the stability and performance of the vehicle.

[0112] In this way, the vehicle can perform closed-loop control based on actual road terrain data, allowing the vehicle to maintain stable and efficient operation on different terrains. This helps improve driving comfort, safety and overall driving performance.

[0113] In some embodiments, the vehicle control method further includes: obtaining feedforward control data according to the road terrain corresponding to the vehicle driving trajectory; obtaining actual road terrain data of the road on which the vehicle is currently driving, and obtaining feedback control data according to the actual road terrain data; obtaining ideal target control data according to the feedforward control data and the feedback control data; and controlling the vehicle according to the ideal target control data.

[0114] Specifically, based on the road topography corresponding to the vehicle's driving trajectory, the system can predict the terrain changes that the vehicle may encounter in the future. Based on these predictions, the system generates feedforward control data. These data include adjustments to control parameters such as driving force, braking force, steering angle, etc. based on the expected terrain changes, so that the vehicle can remain stable under the expected terrain changes.

[0115] Furthermore, the system obtains the actual terrain data of the current driving road through the sensors equipped by the vehicle. These data may include information such as ground height, slope, unevenness, etc. Based on these actual terrain data, the system generates feedback control data. The feedback control data is used to dynamically adjust the control parameters of the vehicle according to the changes in the actual terrain to maintain the stability and performance of the vehicle.

[0116] Furthermore, the feedforward control data and the feedback control data are combined to generate ideal target control data. These data define the optimal control parameters of the vehicle under expected terrain changes and actual terrain changes. The ideal target control data can be generated through mathematical models, control algorithms, etc. to achieve smooth operation of the vehicle under various terrain conditions.

[0117] Further, based on the generated ideal target control data, the vehicle's control system adjusts various control parameters of the vehicle. This may include adjusting driving force, braking force, steering angle, suspension system parameters, etc. Through the synergy of feedforward control and feedback control, the vehicle can maintain good stability, comfort and performance under different terrains.

[0118] In general, the combination of feedforward control and feedback control gives full play to the advantages of both control methods. Feedforward control enables the system to make adjustments in advance by visually predicting the terrain, thus enhancing the timeliness of control. Feedback control ensures the accuracy of the final control and the robustness of the entire system. The combination of the two gives the system better control performance and stability.

[0119] In some embodiments, obtaining actual road terrain data of the road on which the vehicle is currently traveling includes: obtaining vehicle status data and wheel status data. Obtaining the actual vehicle body inclination angle and the absolute height of each wheel according to the vehicle status data and the wheel status data. Obtaining actual road terrain data according to the actual vehicle body inclination angle and the absolute height of each wheel.

[0120] Specifically, data related to the vehicle status and wheel status are obtained through sensors installed on the vehicle, where the vehicle status data may include information such as the vehicle's speed, acceleration, and posture, while the wheel status data may include information such as the position, rotation speed, and displacement of the suspension system of each wheel.

[0121] Furthermore, the actual body inclination of the vehicle and the absolute height of each wheel can be calculated using the vehicle state data and the wheel state data. The actual body inclination may refer to the inclination angle between the vehicle body and the horizontal plane, and the absolute height of the wheel may refer to the vertical distance between the wheel and the reference position.

[0122] Furthermore, based on the calculated actual body inclination angle and the absolute height of the wheels, the terrain of the road the vehicle is currently on can be inferred. For example, by comparing the absolute heights of the wheels, it can be determined whether the vehicle is traveling on an uneven road. By using the actual body inclination angle, it can be estimated whether the vehicle is traveling on a slope and the size of the slope.

[0123] Figure 3 is a functional architecture diagram of a terrain automatic control system according to an embodiment of the present invention, such as Figure 3As shown, the terrain automatic control system 100 includes an automatic terrain recognition module 110 , a terrain analysis control module 120 , a feedback control module 130 and a four-wheel terrain parsing module 140 .

[0124] The automatic terrain recognition module 110 includes a driving trajectory prediction module 111 , a visual processing module 112 , a data online update module 113 and a feature recognition and classification module 114 .

[0125] In some embodiments, the driving trajectory prediction module 111 may input a gear signal, a driver throttle signal, a driver brake signal, a steering wheel angle signal, and a cruise command signal. Among them, the gear signal may indicate the current gear of the vehicle, such as forward gear, reverse gear, etc. The driver throttle signal may reflect the driver's current accelerator pedal input, that is, the intensity with which the driver expects the vehicle 1 to accelerate. The driver brake signal may reflect the driver's current brake pedal input, that is, the intensity with which the driver expects the vehicle 1 to decelerate or stop. The steering wheel angle signal may indicate the current angle of the steering wheel, that is, the steering angle that the driver wants the vehicle 1 to turn. The cruise command signal may include information such as a virtual throttle, a braking target intensity, a target acceleration and deceleration, a target vehicle speed, and a target angle, which is used to indicate the cruise target of the vehicle 1.

[0126] The driving trajectory prediction module 111 can also combine vehicle parameters, such as the mass, suspension stiffness, and power performance of the vehicle 1, to estimate the expected driving trajectory of the vehicle 1 in a future driving range. The output can be a moving vector curve of the vehicle's center of mass, or information such as the trajectory radius of the current vehicle 1. These predicted trajectory information will be used for subsequent terrain recognition and control strategy formulation.

[0127] In some embodiments, the data online update module 113 is a functional module for uploading the underfitting data identified by the system to the cloud server 3, and obtaining the latest version of the visual algorithm from the cloud server 3 to update the feature learning module. When the automatic terrain recognition module 110 finds that there is a large deviation between the visual image recognition result and the actual terrain, these underfitting data are marked and uploaded to the cloud server 3 through the communication network 2. On the cloud server 3, these underfitting data will be used to optimize the training of the visual algorithm and improve the recognition accuracy. At the same time, the cloud server 3 can regularly update the feature learning module and transmit the latest version of the visual algorithm to the vehicle control device 10 of the terrain automatic control system 100. Through online data updates, the system can continuously improve the terrain recognition algorithm and maintain its accuracy and robustness.

[0128] In some embodiments, the feature recognition and classification module 114 can send out marked data when needed, which can be captured by the online data update module 113 and packaged into data packets of rated size according to the amount of data, and then stored in the erasable non-volatile part of the data storage module. The online data update module 113 can select one or more of the following methods to upload these data packets to the cloud backend according to different strategies:

[0129] First, periodic update, the system can set a time interval, for example, to upload data every certain period of time (i.e. every few minutes or hours).

[0130] Second, event-based update: whenever there is a deviation between vision and measurement, the data online update module 113 can immediately start uploading data until the deviation no longer exceeds the specified range.

[0131] Third, resource planning type update, when the usage rate of the storage space allocated to the marked data reaches a certain level (for example, greater than 90%), the data online update module 113 starts uploading.

[0132] Fourth, manual update: vehicle operators such as drivers or testers can actively request the system to upload data through specific operations.

[0133] Furthermore, after each data packet is successfully uploaded to the cloud server 3 , the online data update module 113 may remove the uploaded data from the storage space to release the storage space for subsequent data recording.

[0134] Further, when the cloud backend uses a large amount of underfitting data, the visual algorithm is trained and strengthened to confirm the improvement of recognition efficiency. After the visual algorithm optimization is completed in the cloud backend, the new version of the algorithm software can be pushed to the terminal. After the data online update module 113 receives a request from the cloud server 3 or the vehicle-side operator, the new version of the software unit can be updated to the feature recognition classification module 114. These updates can include decision trees, random forests, deep convolutional neural networks, combinations of deep convolutional neural networks and recursive neural networks and their variants, or combinations of deep convolutional neural networks and conditional random fields. These algorithms will be used for the identification and classification of terrain features, and then assist the terrain automatic control system 100 to make corresponding control strategies, and improve the driving performance and safety of the vehicle 1 on unpaved roads. By continuously updating and optimizing algorithms, the terrain automatic control system 100 can continuously improve and improve its recognition and control performance.

[0135] In some embodiments, the visual processing module 112 can pre-process the image transmitted from the camera. The pre-processing includes clarity inspection, camera selection, binocular image depth information extraction, image frame extraction, etc., to obtain an image library of the terrain of interest, and based on the trajectory information input by the driving trajectory prediction module 111, select the predicted trajectory coverage area in the image, combine the trajectory information with the depth image, obtain image data containing trajectory information and depth information, perform image cropping processing according to the trajectory coverage module, further process the image into a form more suitable for feature recognition and classification, and then input it to the feature recognition and classification module 114.

[0136] In some embodiments, the feature recognition and classification module 114 uses a pre-trained visual recognition algorithm to perform feature recognition and extraction on the depth image containing the track, and corrects the information of the visual image in combination with the terrain where the vehicle 1 is currently located to offset the influence of the vehicle body angle on the camera shooting angle, and then outputs the predicted height change curve of the ground where each wheel is located.

[0137] Furthermore, when performing feature recognition, the feature recognition and classification module 114 can compare the features in the depth image with the pre-trained visual algorithm to identify the features of the terrain, such as changes in ground height, color and texture of the terrain, etc. In addition to using image recognition, the distance or depth data obtained by the radar can also be used to assist in feature recognition and classification. This information helps to more accurately identify the terrain where the current vehicle 1 is located, providing an important basis for the subsequent terrain automatic control strategy.

[0138] Reference below Figure 4 The operation of the feature recognition and classification module of the embodiment of the present invention is described in detail.

[0139] Figure 4 is a working scene diagram of a feature recognition and classification module according to an embodiment of the present invention, such as Figure 4 As shown, based on the calculated expected driving trajectory and the ground distance / depth / height / object size information provided by visual recognition, a scene terrain model can be constructed. By solving the absolute height of the ground where each wheel is located at different positions along the driving trajectory. For example, Figure 4 Taking the left front wheel of vehicle 1 as an example, the relationship curve between the longitudinal displacement of the left front wheel and the vertical height of the wheel 148 to the horizontal is obtained, see the attached Figure 5 .

[0140] In addition to the height curve, the information output by the feature recognition and classification module 114 also includes a variety of terrain information, such as driving trajectory, vector, coordinates, terrain pitch angle change, terrain roll angle change, yaw angle change, etc. At the same time, the feature recognition and classification module 114 can also output the confidence level of this information based on the completeness of the data and the recognition result, and the confidence level will determine the intervention intensity of the feedforward control.

[0141] In some embodiments, the feature recognition and classification module 114 may retain the result of the visual prediction until the vehicle 1 drives to the predicted area for comparison and inspection. When the prediction result of the visual recognition algorithm, that is, the terrain model constructed visually, is compared with the measurement data obtained after the vehicle 1 has driven, if the deviation exceeds a certain range, for example, the longitudinal slope deviation of the vehicle 1 is greater than 3%; the lateral slope deviation is greater than 3%; the longitudinal slope deviation is greater than 2% and the lateral slope deviation is greater than 2%; the absolute height deviation of a single wheel exceeds 0.1m; or the feature recognition and classification module 114 cannot recognize the terrain ahead, etc. The feature recognition and classification module 114 may mark the vehicle driving terrain image and the measured terrain data in the time domain corresponding to the data exceeding the deviation as underfitting data.

[0142] In some embodiments, the terrain analysis control module 120 is an important module of the terrain automatic control system 100, including: a feedforward control module 121 and an ideal target calculation module 122. These functions can be manually selected or turned off by the driver as needed.

[0143] Among them, the feedforward control module 121 intervenes in the driving, braking, steering and suspension systems of the vehicle 1 in advance based on the terrain information output by the feature recognition and classification module 114 and the current driving status of the vehicle 1, so as to adapt to the characteristics of the terrain ahead, optimize the control strategy of the vehicle 1, and ensure the stability and safety of the vehicle 1 on the specific terrain.

[0144] In some embodiments, the feedforward control module 121 selects an appropriate intervention strategy based on the terrain information output by the feature recognition and classification module 114. These intervention strategies include but are not limited to the following:

[0145] First, alarm the driver or limit power output. If the terrain ahead may make it impossible for the vehicle 1 to pass safely, such as mud, deep water, obstacles, pits, cliffs, etc., the feedforward control module 121 can issue an alarm to the driver or limit power output to prevent the vehicle 1 from falling into a dangerous situation.

[0146] Second, request the active suspension system to raise the vehicle height. If the terrain ahead may scrape the vehicle chassis at the current height, the feedforward control module 121 may request the active suspension system to raise the vehicle height to ensure the safe passage of the vehicle chassis.

[0147] Third, request to reduce the intensity or pre-brake. If there is a foreign object or terrain that is not conducive to high-speed driving ahead, the feedforward control module 121 can request the drive system to reduce the intensity or the brake system to pre-brake to ensure that the vehicle 1 can smoothly pass through the specific terrain.

[0148] Fourth, request to increase the steering assist or adjust the suspension stiffness. If the road ahead is rocky or has large ups and downs, the feedforward control module 121 can request the steering system to increase the assist strength or enhance the return stability control strength to improve the handling and stability of the vehicle 1. At the same time, request the active suspension system to raise the vehicle height or reduce the damping of the shock absorber to ensure that the vehicle 1 can adapt to complex terrain.

[0149] Fifth, request the power system to perform pre-processing. If the front may cause some wheels 148 to be vacated, the feedforward control module 121 may request the power system to perform pre-processing, such as switching to four-wheel drive or entering an escape mode, to increase the vehicle's passability. At the same time, it will also request to optimize the recognition threshold of functions such as ABS (Anti-lock Braking System) or TCS (Traction Control System) to improve the control performance of the vehicle 1 on specific terrain.

[0150] In addition, the feedforward control module 121 can also obtain the confidence of the terrain information while obtaining the terrain information. The confidence reflects the reliability of the terrain information of the feature recognition and classification module 114. Based on the confidence, the feedforward control module 121 can adjust the intervention intensity of the control. For example, if the forward visual information is blurred and the terrain cannot be judged, resulting in the confidence being set to 0, the intervention variable output by the feedforward control module 121 will also be adjusted to no intervention to avoid erroneous control interference.

[0151] In some embodiments, the ideal target calculation module 122 calculates the ideal operating target parameters of the vehicle 1 according to the current state of the vehicle, the driver's request and the terrain conditions. These target parameters include the target range of vehicle speed, the target slip range of wheel speed 148, the target height of the vehicle body, the target pitch angle / target roll angle of the vehicle body and the target yaw rate of the vehicle body.

[0152] In some embodiments, the ideal target calculation module 122 includes two modes corresponding to different calculation results. One is based on the terrain recognized by vision for the feedforward control module 121 to calculate reference, and the other is based on the measured terrain obtained after the vehicle 1 has traveled for the feedback control module 130 to calculate reference. Based on the calculation results of the feedforward and feedback, the control logic is calibrated / trained through a large amount of data to improve the accuracy of the judgment and output the ideal control target parameters.

[0153] Furthermore, the target parameters output by the ideal target calculation module 122 will be used for closed-loop control. In closed-loop control, the targets of feedforward control and feedback control will be weighted according to their confidences, i.e., control target = feedforward control confidence + feedback control confidence. Then, they are used to adjust the drive, braking, steering, suspension and other systems of the vehicle 1 to achieve more precise control.

[0154] In some embodiments, the feedback control module 130 performs closed-loop intervention on the vehicle's drive, brake, steering, suspension and other systems based on the actual terrain of the current vehicle 1 output by the four-wheel terrain analysis module 140. In this way, even if the feedforward control leads to pre-control deviation due to the error of visual recognition, the feedback control module 130 can adjust the control strategy in time according to the actual terrain conditions to avoid the accumulation of control deviations and ensure the stability of the vehicle on complex terrain.

[0155] In some embodiments, the four-wheel terrain analysis module 140 is based on a variety of sensor signals and vehicle status, including longitudinal acceleration, lateral acceleration, vertical acceleration signal, pitch angular velocity, roll angular velocity, yaw angular velocity signal, wheel speed, wheel height signal, pitch angle, roll angle, yaw angle and other information. Combined with the vehicle parameters, the module can accurately measure and solve the actual inclination angle of the vehicle body and the absolute height of each wheel, and perform terrain analysis based on this information. The principle of terrain analysis can be referred to Figure 5 Provide explanation.

[0156] Figure 6 Schematic diagram of the principle of a four-wheel terrain parsing module according to an embodiment of the present invention. Figure 6 As shown, the figure describes the current position of the vehicle 1 on the ground and the relationship between the coordinate systems. Through this information, the coordinate system corresponding to the ground where the vehicle 1 is located can be derived, thereby realizing the analysis and measurement of the terrain.

[0157] Among them, the ground 141 where the current vehicle is located can represent the actual ground where the vehicle 1 is currently located, which can be an uneven road surface or other terrain. The coordinate system corresponding to the ground 141 where the current vehicle is located can be a coordinate system relative to the vehicle 1 itself, with the vehicle center of mass 146 as the origin, and has a certain conversion relationship with the body coordinate system. The horizontal plane 143 (parallel to the sea level) can represent a horizontal plane, usually parallel to the sea level of the earth. The coordinate system 144 corresponding to the horizontal plane can be a coordinate system relative to the vehicle 1 itself, with the vehicle center of mass 146 as the origin, and is described on the horizontal plane 143. The vehicle schematic body 145 can be used to identify the overall shape of the vehicle. The vehicle center of mass 146 can be the position of the overall center of gravity of the vehicle 1. The coordinate system 147 corresponding to the plane where the body chassis is located can be a coordinate system relative to the vehicle 1 itself, with the vehicle center of mass 146 as the origin, used to describe the position of the body chassis. The wheel 148 can represent the four wheels 148 of the vehicle 1.

[0158] In some embodiments, by knowing the relationship between the body coordinate system and the horizontal coordinate system, and the relationship between the plane where the body chassis is located and the height of the wheel 148 (Hfl, Hfr, Hrl, Hrr), combined with the vehicle parameters, the coordinate system corresponding to the ground 141 where the current vehicle is located can be solved. In this way, the terrain information such as the height and slope of the ground where the vehicle 1 is located can be accurately measured.

[0159] Based on this terrain analysis principle, the terrain automatic control system 100 can obtain the information of the terrain where the vehicle 1 is located in real time, and provide accurate data for the feedforward control module 121 and the feedback control module 130 to achieve precise adjustment and optimization of the vehicle control strategy. In this way, the vehicle 1 can more intelligently adapt to the driving needs under different terrain conditions, and improve driving safety and adaptability. Figure 7-Figure 8 A vehicle control device according to an embodiment of the present invention is described.

[0160] Figure 7 is a block diagram of a vehicle control device according to an embodiment of the present invention, Figure 7 As shown, the vehicle control device 10 includes: an acquisition module 11; a prediction module 12; and a control module 13.

[0161] The acquisition module is used to acquire the visual image of the road section around the vehicle and the expected driving trajectory. The acquisition module may include sensing devices such as cameras, sensors, radars, etc., which are responsible for capturing information about the vehicle's surrounding environment in real time. The visual image may include elements such as roads, surroundings, obstacles, traffic signs, other vehicles, etc. The expected driving trajectory may be a theoretical driving path derived from the vehicle's navigation system, map data, and planning algorithms.

[0162] The prediction module is used to predict the road terrain corresponding to the vehicle's driving trajectory based on the visual image and the expected driving trajectory. There are many types of road terrain, including but not limited to: paved roads (such as asphalt roads, concrete roads, etc.), unpaved roads (such as dirt roads, gravel roads, etc.), uneven roads (such as bumps, potholes, and uneven sections), flat roads and ramps (such as uphill, downhill, side slopes, etc.). The task of the prediction module is to match the image information and driving trajectory with the terrain type and features for further control adjustment.

[0163] The control module is used to adjust the vehicle's control parameters according to the road terrain corresponding to the vehicle's driving trajectory. These parameters include driving force, braking force, steering force, suspension system, etc. According to the different characteristics of the road terrain, the control module can automatically adjust these parameters to achieve the best vehicle performance and stability. For example, for rough roads, it may increase the damping of the suspension system to reduce bumps; while on flat roads, it can optimize power distribution and improve driving performance.

[0164] According to the vehicle control device of the embodiment of the present invention, the visual image and expected driving trajectory of the vehicle 1 are acquired through the acquisition module, and the prediction module can automatically identify the road terrain corresponding to the current vehicle driving trajectory. This method of comprehensively utilizing the visual image and the expected driving trajectory can avoid the shortcomings of relying on only a single sensor for terrain recognition, and can predict the road terrain of the vehicle's driving path. The control parameters of the vehicle 1 can be adjusted in advance according to the road terrain corresponding to the vehicle's driving trajectory, so that the vehicle 1 can better adapt to various road terrain changes and maintain a stable driving state, thereby improving the adaptability and safety of the vehicle 1 under different road conditions.

[0165] Figure 8 is a block diagram of a vehicle control device according to yet another embodiment of the present invention. Figure 8 As shown, the vehicle control device 10 includes: at least one processor 101 and a memory 102 .

[0166] The processor 101 is used to execute instructions in a computer program. The processor 101 may be a central processing unit (CPU) or other computing devices.

[0167] The memory 102 is connected to the processor 101 for storing computer programs and related data. The memory 102 may include a random access memory (RAM), a read-only memory (ROM), a flash memory, etc.

[0168] The computer program stored in the memory 102 is a series of instructions for implementing the vehicle control method described in the above embodiment. These instructions are executed by the processor 101, thereby implementing the various steps and functions described in the vehicle control method.

[0169] According to the vehicle control device 10 of the embodiment of the present invention, the vehicle control method described in the above embodiment is implemented when the processor 101 executes the computer program. By comprehensively utilizing visual images and expected driving trajectories, the function of automatically identifying road terrain and adjusting vehicle control parameters is realized. This comprehensive terrain recognition and parameter adjustment capability enables the vehicle 1 to adapt to changes in different road terrains more accurately, thereby improving the adaptability and driving safety of the vehicle 1 under different road conditions.

[0170] In some embodiments of the present invention, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed, the vehicle control method of any of the above embodiments is implemented.

[0171] According to the computer-readable storage medium of an embodiment of the present invention, by executing the vehicle control method described in the above embodiment, the visual image and the expected driving trajectory of the vehicle are comprehensively utilized to automatically identify the road terrain corresponding to the vehicle's driving trajectory. This method of comprehensively utilizing the visual image and the expected driving trajectory can avoid the shortcomings of relying solely on a single sensor for terrain recognition, and can predict the road terrain of the vehicle's driving path. According to the road terrain corresponding to the vehicle's driving trajectory, the control parameters of the vehicle 1 can be adjusted in advance, so that the vehicle 1 can better adapt to various road terrain changes and maintain a stable driving state, thereby improving the adaptability and safety of the vehicle 1 under different road conditions.

[0172] The computer-readable storage medium of the embodiments of the present invention may include, but is not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0173] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" 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.

[0174] Although the 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.

Claims

1. A vehicle control method, characterized in that: include: Obtain visual images of the road sections around the vehicle and the expected driving trajectory; Predicting a road surface topography corresponding to the vehicle driving trajectory according to the visual image and the expected driving trajectory; The control parameters of the vehicle are adjusted according to the road topography corresponding to the vehicle's driving trajectory.

2. The vehicle control method according to claim 1, characterized in that: Predicting a road surface terrain corresponding to the vehicle driving trajectory according to the expected driving trajectory and the visual image includes: Obtaining the expected driving track coverage area in the visual image to obtain an image containing the driving track; Extracting terrain features from the image containing the driving track; The terrain data of the road surface at each wheel position is solved along the driving trajectory according to the extracted terrain features.

3. The vehicle control method according to claim 2, characterized in that: The vehicle control method further includes: The confidence level of the terrain data is determined according to the data integrity and the recognition result of the terrain data.

4. The vehicle control method according to claim 1, characterized in that: The vehicle control method further includes: Acquire actual road topography data of the road on which the vehicle is currently traveling; comparing the actual road surface topography data with road surface topography data identified in the corresponding driving area; The deviation between the actual road surface topography data and the road surface topography data identified in the corresponding driving area exceeds a preset threshold, marking the identified road surface topography data as underfitting data; The underfitting data is sent to the cloud to optimize an algorithm for identifying the road terrain according to the underfitting data.

5. The vehicle control method according to claim 4, characterized in that: The vehicle control method further includes: An algorithm for identifying the road surface terrain that is optimized according to the underfitting data is obtained to perform road surface terrain recognition.

6. The vehicle control method according to claim 3, characterized in that: Adjusting the control parameters of the vehicle according to the road topography corresponding to the vehicle driving trajectory includes: At least one of the driving force, braking force, steering angle, and suspension system parameters of the vehicle is pre-controlled according to the road topography corresponding to the vehicle driving trajectory and the actual driving state of the vehicle.

7. The vehicle control method according to claim 6, characterized in that: The vehicle control method further includes: The control intensity of at least one of the driving force, braking force, steering angle, and suspension system parameters of the vehicle is adjusted according to the confidence level of the terrain data.

8. The vehicle control method according to claim 1, characterized in that: The vehicle control method further includes: Acquire actual road topography data of the road on which the vehicle is currently traveling; Closed-loop control is performed on at least one of the vehicle's driving system, braking system, steering system, and suspension according to the actual road topography data.

9. The vehicle control method according to claim 1, characterized in that: The vehicle control method further includes: Obtaining feedforward control data according to the road topography corresponding to the vehicle driving trajectory; Acquiring actual road topography data of the road on which the vehicle is currently traveling, and obtaining feedback control data according to the actual road topography data; Obtaining ideal target control data according to the feedforward control data and the feedback control data; The vehicle is controlled according to the ideal target control data.

10. The vehicle control method according to claim 4, 8 or 9, characterized in that: Acquiring actual road topography data of the road on which the vehicle is currently traveling, including: Obtain vehicle status data and wheel status data; Obtaining an actual body inclination angle of the vehicle and an absolute height of each wheel according to the vehicle state data and the wheel state data; The actual road topography data is obtained according to the actual vehicle body inclination angle and the absolute height of each wheel.

11. A vehicle control device, characterized in that: include: An acquisition module, used to acquire visual images of the road sections around the vehicle and the expected driving trajectory; A prediction module, configured to predict a road surface topography corresponding to the vehicle driving trajectory according to the visual image and the expected driving trajectory; A control module is used to adjust the control parameters of the vehicle according to the road topography corresponding to the vehicle's driving trajectory.

12. A vehicle control device, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores a computer program, and the at least one processor implements the vehicle control method according to any one of claims 1 to 10 when executing the computer program.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the vehicle control method according to any one of claims 1 to 10 is implemented.

14. A vehicle, characterized in that: include: A visual system for collecting visual images of the vehicle; The vehicle control device according to claim 12, wherein the vehicle control device is connected to the visual system.

15. The vehicle according to claim 14, characterized in that The vehicle further comprises: A communication device is connected to the vehicle control device and is used to send underfitting data and receive an algorithm for identifying road topography that is optimized based on the underfitting data.

16. The vehicle according to claim 14, characterized in that The vehicle also includes a wheel height sensor, a wheel speed sensor and a vehicle body inertial navigation sensor.

Images