Self-adaptive control method and device for intelligent vehicle

Abstract

The invention provides a self-adaptive control method and device for an intelligent vehicle, and relates to the technical field of intelligent driving. According to the method, the target area is detected, identification analysis is carried out based on the detected radar data and camera data, terrain features such as the earth surface type, the position coordinates, the elevation and the gradient of the target area are determined, then the three-dimensional terrain model is constructed, and a safe and efficient driving path is planned in combination with performance parameters of the intelligent vehicle. And controlling the intelligent vehicle to realize self-adaptive driving based on the planned path. According to the method, the three-dimensional model is drawn by detecting the topographic features of the field environment, so that the vehicle self-adaptive driving in the field environment is realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to an adaptive control method and device for an intelligent vehicle. Background Art

[0002] With the rapid development of autonomous driving technology, the application of intelligent vehicles in structured environments such as urban roads and highways has gradually matured. However, in the complex and changeable environment of the wild, such as rugged mountains, muddy and wet swamps, soft sand and changeable weather conditions (such as heavy rain, fog, sandstorms, etc.), the realization of autonomous driving still faces great challenges. These unstructured environments require not only that the vehicle has a high degree of environmental perception, but also that it can analyze terrain features in real time and make reasonable driving decisions based on them to ensure the safety and passability of the vehicle.

[0003] Traditional autonomous driving systems mainly rely on high-precision maps and GPS positioning technology, but in the wild environment, due to the complex and changeable terrain and the susceptibility of signals to interference, these technologies often have difficulty in providing stable and reliable support. In addition, the presence of natural obstacles such as trees, rocks, puddles, etc., also increases the uncertainty and risk of vehicle driving. Therefore, it is difficult to achieve autonomous driving in the wild environment. Summary of the invention

[0004] The present invention provides an adaptive control method and device for an intelligent vehicle, which can realize adaptive driving of the intelligent vehicle in a field environment.

[0005] In a first aspect, the present invention provides an adaptive control method for an intelligent vehicle, the method comprising: acquiring detection data of a target area; the detection data comprising radar data and camera data; performing identification and analysis based on the detection data of the target area to determine the terrain features of each point in the target area; the terrain features comprising surface type, location coordinates, elevation and slope; drawing a three-dimensional terrain model of the target area based on the terrain feature data of each point in the target area; determining a planned path through the target area based on the three-dimensional terrain model and performance parameters of the intelligent vehicle; the planned path comprising the terrain features of each section on the path; and controlling the adaptive driving of the intelligent vehicle based on the planned path.

[0006] In one possible implementation, based on a planned path, controlling the adaptive driving of an intelligent vehicle includes: determining the terrain features of key nodes in the planned path based on the planned path; the key nodes include obstacles and turning points; determining the control parameters of the intelligent vehicle at each key node based on the terrain features of the key nodes in the planned path, the control parameters including at least one of the following: vehicle power, vehicle speed, acceleration, tire pressure, steering angle and suspension height; determining the control parameters of the intelligent vehicle at each key node based on the control parameters of the intelligent vehicle and the terrain features of each section of the planned path between each key node; determining the target control parameters of the intelligent vehicle on the planned path based on the control parameters of the intelligent vehicle at each key node and each section; and adaptively controlling the intelligent vehicle based on the target control parameters of the intelligent vehicle on the planned path.

[0007] In one possible implementation, target control parameters of the intelligent vehicle on the planned path are determined based on the control parameters of the intelligent vehicle at each key node and each road section, including: determining the value range of the control parameters of each point on the planned path based on the control parameters of the intelligent vehicle at each key node and each road section; generating multiple groups of control parameter sets based on the value range of the control parameters of each point on the planned path of the intelligent vehicle; calculating the comfort and travel time of each group of control parameter sets; determining the optimal control parameter set based on the comfort and travel time of each group of control parameter sets; and determining the optimal control parameter set as the target control parameters of the intelligent vehicle on the planned path.

[0008] In a possible implementation, based on the target control parameters of the intelligent vehicle on the planned path, the intelligent vehicle is adaptively controlled, including: detecting the real-time control parameters of the intelligent vehicle; calculating the error between the real-time control parameters and the target control parameters; if the error is greater than a set threshold, recording the position point where the error is greater than the set threshold as an abnormal point, and sending a first indication message to the drone, the first indication message is used to instruct the drone to re-detect the remaining planned path and determine the secondary detection data; the remaining planned path is the path between the abnormal point and the destination on the planned path; based on the secondary detection data, the target control parameters are regenerated; based on the regenerated target control parameters, the intelligent vehicle is controlled to travel.

[0009] In a possible implementation, after recording the position point whose error is greater than the set threshold as an outlier, the method further includes: screening the remaining planned paths based on the terrain features of the outlier to determine a plurality of suspected points in the remaining planned paths that have similar terrain features to the outlier;

[0010] Based on the position coordinates of multiple suspicious points, a second indication information is generated and sent to the UAV, and the second indication information is used to instruct the UAV to perform close-range and fine detection of the multiple suspicious points; accordingly, based on the secondary detection data, the target control parameters are regenerated, including: based on the secondary detection data, the fine terrain features of the multiple suspicious points are determined; if the error between the fine terrain features of the multiple suspicious points and the terrain features is greater than the set error, based on the fine terrain features of the multiple suspicious points and the performance parameters of the intelligent vehicle, a verification is performed to determine the passability of the intelligent vehicle; if the intelligent vehicle can pass, the planned path is kept unchanged, and the target control parameters are regenerated based on the fine terrain features of the multiple suspicious points; if the intelligent vehicle cannot pass, the unpassable suspicious points are determined, and the path is replanned based on the secondary detection data, and the target control parameters of the replanned path are determined.

[0011] In a possible implementation, after detecting the real-time control parameters of the smart vehicle, it also includes: if it is detected that the speed of the smart vehicle is zero, sending a third indication information to the drone, the third indication information is used to instruct the drone to detect the area where the smart vehicle is located; receiving detection data of the area where the smart vehicle is located transmitted back by the drone; based on the detection data of the area where the smart vehicle is located and the three-dimensional terrain model, generating a three-dimensional local model of the area where the smart vehicle is located; based on the three-dimensional local model, determining a rescue plan for the smart vehicle.

[0012] In a possible implementation, based on the detection data of the target area, identification analysis is performed to determine the terrain features of each point in the target area, including: based on the radar data of the target area, the position coordinates and elevation of each point in the target area are determined with the vehicle as the coordinate origin; based on the position coordinates and elevation of each point in the target area, the slope and slope direction of each point are calculated; based on the position coordinates, elevation, slope and slope direction of each point in the target area, the key nodes of the target area are detected and the position coordinates, elevation, slope and slope direction of each key node are obtained; based on the camera data, image recognition is performed to determine the image of each key node; based on the position coordinates, elevation, slope and slope direction of each key node, and the image of each key node, image fitting is performed to determine the vector image of the target area; the vector image includes the position coordinates, elevation, slope and slope direction of each point; based on the vector image of the target area, cluster analysis is performed to determine the surface type of each point in the target area, and the surface types include mountains, hills, plains, and basins.

[0013] In a possible implementation, a three-dimensional terrain model of the target area is drawn based on terrain feature data of each point in the target area, including: performing coordinate conversion based on the position coordinates and elevation of each point in the target area to determine the three-dimensional coordinates of each point in the target area; gridding the target area based on the three-dimensional coordinates of each point in the target area to construct three-dimensional grid data of the target area; the three-dimensional grid data includes coordinate data of multiple three-dimensional grids; performing feature mapping based on the surface type and slope, as well as the three-dimensional grid data, to determine an initial three-dimensional model; and rendering the initial three-dimensional model based on the camera data to obtain a three-dimensional terrain model.

[0014] In one possible implementation, a planned path through a target area is determined based on a three-dimensional terrain model and performance parameters of an intelligent vehicle, including: screening multiple initial paths between a starting point and a destination based on the three-dimensional terrain model; determining path screening conditions based on the performance parameters of the intelligent vehicle; the path screening conditions include at least one of the following: maximum slope, minimum load, maximum pit depth, minimum turning radius, cruising range, and braking capability; based on the path screening conditions, screening multiple initial paths to obtain multiple preliminary selected paths; calculating the travel time, risk level, and comfort of each preliminary selected path; and determining the planned path of the target area based on the travel time, risk level, and comfort of each preliminary selected path.

[0015] In a second aspect, an embodiment of the present invention provides an adaptive control device for an intelligent vehicle, the control device comprising: a communication module for acquiring detection data of a target area; the detection data comprising radar data and camera data; a processing module for performing identification and analysis based on the detection data of the target area, and determining the terrain features of each point in the target area; the terrain features comprising surface type, location coordinates, elevation and slope; drawing a three-dimensional terrain model of the target area based on the terrain feature data of each point in the target area; determining a planned path through the target area based on the three-dimensional terrain model and the performance parameters of the intelligent vehicle; the planned path comprising the terrain features of each section on the path; and controlling the adaptive driving of the intelligent vehicle based on the planned path.

[0016] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, the memory storing a computer program, the processor being used to call and run the computer program stored in the memory to perform the steps of the method described in the first aspect and any possible implementation method of the first aspect.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein when the computer program is executed by a processor, the steps of the method described in the first aspect and any possible implementation method of the first aspect are implemented.

[0018] The present invention provides an adaptive control method and device for an intelligent vehicle. The present invention detects a target area, identifies and analyzes the detected radar data and camera data, determines the terrain features such as the surface type, position coordinates, elevation and slope of the target area, and then constructs a three-dimensional terrain model. Combined with the performance parameters of the intelligent vehicle, a safe and efficient driving path is planned, and the intelligent vehicle is controlled based on the planned path to achieve adaptive driving. The present invention detects the terrain features of the outdoor environment and draws a three-dimensional model, thereby achieving adaptive driving of the vehicle in the outdoor environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 is a flow chart of an adaptive control method for an intelligent vehicle provided by an embodiment of the present invention;

[0021] Figure 2 is a schematic structural diagram of an adaptive control device for an intelligent vehicle provided by an embodiment of the present invention;

[0022] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0024] In the description of the present invention, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" and "plurality" refer to two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different.

[0025] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0026] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but may optionally include other steps or modules that are not listed, or may optionally include other steps or modules that are inherent to these processes, methods, products or devices.

[0027] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will be described through specific embodiments in conjunction with the accompanying drawings of the present invention.

[0028] As described in the background technology, the wild environment is complex and changeable, and conventional autonomous driving technology cannot adapt to the wild environment, which makes it difficult to achieve vehicle autonomous driving technology in the wild environment.

[0029] To solve this technical problem, Figure 1 As shown, an embodiment of the present invention provides an adaptive control method for an intelligent vehicle. The method includes steps S101-S105.

[0030] S101: Acquire detection data of a target area.

[0031] In the embodiment of the present application, the detection data includes radar data and camera data.

[0032] Exemplarily, the embodiment of the present invention can send instructions to the drone before the smart vehicle passes through the target area, and the drone can perform radar detection and capture images of the target area to obtain radar data and camera data of the target area.

[0033] In some embodiments, the radar data includes radar detection data of the drone for each location in the target area.

[0034] In some embodiments, the camera data includes multiple images taken by the drone at various locations in the target area, and a captured video of the target area.

[0035] S102: Based on the detection data of the target area, identification analysis is performed to determine the terrain features of each point in the target area.

[0036] In the embodiment of the present application, the terrain features include surface type, location coordinates, elevation and slope.

[0037] As a possible implementation manner, step S102 may be specifically implemented as steps S1021 - S1026 .

[0038] S1021. Based on the radar data of the target area, the position coordinates and elevation of each point in the target area are determined with the vehicle as the coordinate origin.

[0039] S1022. Calculate the slope and slope direction of each point based on the position coordinates and elevation of each point in the target area.

[0040] S1023. Based on the position coordinates, elevation, slope and slope direction of each point in the target area, key nodes of the target area are detected and the position coordinates, elevation, slope and slope direction of each key node are obtained.

[0041] In some embodiments, the key node includes an obstacle. Exemplarily, the obstacle includes a protruding obstacle and a recessed obstacle.

[0042] It should be noted that the embodiments of the present invention can determine whether the intelligent vehicle can pass through the obstacle by analyzing the elevation, slope and slope direction of the obstacle, combined with the performance parameters of the intelligent vehicle. For example, the elevation of a raised obstacle indicates the height of the raised obstacle. The embodiments of the present invention can determine whether the intelligent vehicle can pass through the raised obstacle based on the height and slope of the raised obstacle. For another example, the elevation of a recessed obstacle indicates the depth of the recessed obstacle, that is, the depth of the pit. The embodiments of the present invention can determine whether the intelligent vehicle can pass through the recessed obstacle based on the depth and slope of the recessed obstacle and the area of ​​the pit.

[0043] S1024: Perform image recognition based on the camera data to determine the image of each key node.

[0044] Exemplarily, the embodiment of the present invention can perform image recognition on multiple images in the camera data, identify key nodes, and filter out images with key nodes.

[0045] S1025: Based on the position coordinates, elevation, slope and slope direction of each key node and the image of each key node, image fitting is performed to determine the vector image of the target area.

[0046] In some embodiments, the vector image includes the location coordinates, elevation, slope, and aspect of each point.

[0047] Exemplarily, the embodiments of the present invention may match key nodes obtained by analyzing radar data with key nodes obtained by analyzing camera data, determine the corresponding relationship between the two data, and implement image fitting.

[0048] Afterwards, according to the corresponding relationship between the key nodes obtained by the radar data analysis and the key nodes obtained by the camera data analysis, the vector image of each key node is determined.

[0049] Finally, according to the relative position relationship between the images in the camera image, the corresponding relationship of other areas in the target area except the key nodes is determined to achieve the overall image fitting of the target area and obtain the vector image of the target area.

[0050] S1026. Perform cluster analysis based on the vector image of the target area to determine the surface type of each point in the target area.

[0051] In some embodiments, the land surface types include mountains, hills, plains, and basins.

[0052] Exemplarily, the embodiment of the present invention can divide the target area to determine multiple sub-areas, and calculate the elevation, slope and slope direction of each sub-area based on the vector image of each sub-area; clustering is performed based on the elevation, slope and slope direction of each sub-area to obtain multiple clusters. That is, mountains, hills, plains, and basins. Then, the surface type is determined according to the elevation, slope and slope direction of each cluster.

[0053] For example, the terrain of a mountain is undulating, with steep slopes, high relative height, mostly covered with rocks or soil, and rich but unevenly distributed vegetation.

[0054] For example, the terrain of a hill is undulating, but the relative height is small, the slope is relatively gentle, and it is mostly composed of a mixture of soil and rocks, with good vegetation coverage.

[0055] For example, a plain has a flat or minimally undulating terrain, low relative height, fertile soil, is a major area of ​​agricultural activity, and has abundant and evenly distributed vegetation.

[0056] For example, a basin is surrounded by mountains or hills on all sides, with a relatively low middle part, shaped like a basin, and may contain water bodies such as lakes and rivers. The climate and vegetation vary depending on the geographical location.

[0057] S103: Draw a three-dimensional terrain model of the target area based on the terrain feature data of each point in the target area.

[0058] As a possible implementation manner, step S103 may be specifically implemented as steps S1031 - S1034 .

[0059] S1031. Based on the position coordinates and elevation of each point in the target area, coordinate conversion is performed to determine the three-dimensional coordinates of each point in the target area.

[0060] S1032. Divide the target area into grids based on the three-dimensional coordinates of each point in the target area, and construct three-dimensional grid data of the target area.

[0061] In some embodiments, the three-dimensional mesh data includes coordinate data of a plurality of three-dimensional meshes.

[0062] S1033. Based on the surface type and slope, as well as the three-dimensional grid data, feature mapping is performed to determine an initial three-dimensional model.

[0063] S1034: Render the initial three-dimensional model based on the camera data to obtain a three-dimensional terrain model.

[0064] S104: Determine a planned path through the target area based on the three-dimensional terrain model and the performance parameters of the intelligent vehicle.

[0065] In the embodiment of the present application, the planned path includes the terrain features of each section on the path.

[0066] As a possible implementation manner, step S104 may be specifically implemented as steps S1041 - S1045 .

[0067] S1041. Filter multiple initial paths between a starting point and a destination based on a three-dimensional terrain model.

[0068] S1042. Determine path screening conditions based on performance parameters of the intelligent vehicle.

[0069] In some embodiments, the path screening condition includes at least one of the following: maximum slope, minimum load, maximum pit depth, minimum turning radius, cruising range, and braking capacity.

[0070] S1043. Based on the path screening condition, multiple initial paths are screened to obtain multiple preliminary selected paths.

[0071] S1044. Calculate the travel time, risk level, and comfort of each primary selected path.

[0072] Exemplarily, the embodiment of the present invention may determine the travel time of each preliminary selected path based on the length of each preliminary selected path and the vehicle speed.

[0073] Exemplarily, the embodiment of the present invention may determine the risk level of each preliminary selected path based on the number, elevation and slope of obstacles on each preliminary selected path.

[0074] It should be noted that the number of obstacles directly affects the traffic capacity and safety of the path. The more obstacles there are, the longer the number and distance that vehicles or pedestrians may need to detour, and the risk of collision will also increase. The embodiment of the present invention can quantify the number of obstacles, such as setting a certain risk value corresponding to each obstacle (such as increasing the risk value by 1 unit for each obstacle), and then accumulating to obtain the total risk value of the entire path.

[0075] Paths with large elevation changes may bring greater difficulty in passing and safety risks. At the same time, steep slopes may also increase the risk of vehicles or pedestrians slipping. The embodiment of the present invention can be classified according to the elevation of the area passed by the path, such as low elevation (safety), medium elevation (general risk), high elevation (high risk), etc. Alternatively, it is also possible to directly analyze the elevation value of each point in the path, and judge the steepness of the slope by comparing the elevation difference between adjacent points, so as to assess the risk.

[0076] Slope is an important factor affecting the safety and traffic capacity of a path. The greater the slope, the more difficult it is for vehicles or pedestrians to go up and down the slope, and the risk of slipping may also increase. The embodiment of the present invention can be graded according to the specific value of the slope, such as less than 5% for low slope (low risk), 5%-15% for medium slope (general risk), greater than 15% for high slope (high risk), etc. On the basis of the grade division, the specific risks of each slope section can be further analyzed. For example, for a long-distance high-slope section, a higher risk assessment value may be required.

[0077] Finally, the embodiment of the present invention can assign different weights to the number of obstacles, elevation and slope when determining the risk level of each path. A risk assessment model is established, and the quantitative values ​​of the number of obstacles, elevation and slope and their respective weights are substituted into the model for calculation to obtain the total risk value of each path.

[0078] Exemplarily, the embodiment of the present invention can determine the comfort of each preliminary selected path according to the number of obstacles, elevation, slope, vehicle speed, acceleration, number of turns, and turning radius on each preliminary selected path.

[0079] Among them, the more obstacles there are, the more frequently the vehicle needs to avoid or slow down, affecting driving smoothness and passenger comfort. Larger elevation changes mean steeper uphill and downhill slopes, which increase the mechanical burden on the vehicle and may affect passenger comfort. The size of the slope directly affects the vehicle's traction and braking force requirements, as well as the perceived comfort of passengers. Too high or too low a speed may affect passenger comfort. Too high a speed may cause passengers to feel nervous, while too low a speed may increase travel time. Acceleration: Frequent acceleration and deceleration not only affects the vehicle's fuel economy, but may also cause discomfort to passengers. Number of turns: The more turns there are, the worse the vehicle's driving stability is, and passengers may be more likely to feel motion sickness. Turning radius: Too small a turning radius may cause the vehicle to tilt, affecting passenger comfort.

[0080] The embodiment of the present invention can set a corresponding weight for each influencing factor, and determine the comfort of each preliminary selected route based on the specific data of each influencing factor on each preliminary selected route and the corresponding weight.

[0081] S1045. Determine the planned path for the target area based on the travel time, risk level, and comfort of each initially selected path.

[0082] Exemplarily, the embodiment of the present invention may directly determine the preliminary selected path with the shortest travel time, the lowest risk level, or the highest comfort level as the planned path.

[0083] As another example, an embodiment of the present invention may standardize travel time, risk level, and comfort, convert each indicator into a value between 0 and 1, set a corresponding weight value for each indicator, calculate a comprehensive score for each preliminary path, and determine a planned path based on the comprehensive score.

[0084] The embodiment of the present invention can also modify the weight value of each indicator to meet the user's preference settings and improve the user experience.

[0085] S105: Based on the planned path, control the intelligent vehicle to drive adaptively.

[0086] As a possible implementation manner, step S105 may be specifically implemented as steps S1051 - S1055 .

[0087] S1051. Based on the planned path, determine the terrain features of key nodes in the planned path.

[0088] In some embodiments, key nodes include obstacles and corner points.

[0089] S1052. Determine control parameters of the intelligent vehicle at each key node based on the terrain characteristics of the key nodes in the planned path.

[0090] In some embodiments, the control parameter includes at least one of the following: vehicle power, vehicle speed, acceleration, tire pressure, steering angle, and suspension height.

[0091] S1053: Determine the control parameters of the intelligent vehicle at each road section based on the control parameters of the intelligent vehicle at each key node and the terrain characteristics of each road section between the key nodes of the planned path.

[0092] S1054: Determine target control parameters of the intelligent vehicle on the planned path based on the control parameters of the intelligent vehicle at each key node and each road section.

[0093] Exemplarily, step S1054 may be specifically implemented as steps A1-A5.

[0094] A1. Based on the control parameters of the intelligent vehicle at each key node and each road section, determine the value range of the control parameters of the intelligent vehicle at each point on the planned path.

[0095] A2. Generate multiple sets of control parameter sets based on the value range of the control parameters of each point on the planned path of the intelligent vehicle.

[0096] A3. Calculate the comfort and travel time of each set of control parameters.

[0097] A4. Determine the optimal control parameter set based on the comfort level and travel time of each control parameter set.

[0098] A5. Determine the optimal control parameter set as the target control parameters of the intelligent vehicle on the planned path.

[0099] In this way, after determining the planned path, the embodiment of the present invention can fine-tune the control parameters of the intelligent vehicle on the planned path to the optimal control parameters that meet the user's needs.

[0100] S1055. Adaptively control the intelligent vehicle based on the target control parameters of the intelligent vehicle on the planned path.

[0101] Exemplarily, the target control parameters include vehicle power, vehicle speed, acceleration, tire pressure, steering angle, and suspension height.

[0102] The embodiment of the present invention can control the vehicle to drive adaptively according to the control parameters to adapt to the terrain of the target area and improve the speed of travel while ensuring comfort. For example, the vehicle acceleration and steering can be controlled, the tire pressure can be increased or decreased, and the suspension height of the vehicle can be raised or lowered.

[0103] Exemplarily, step S1055 may be specifically implemented as steps B1-B5.

[0104] B1. Detect the real-time control parameters of intelligent vehicles.

[0105] B2. Calculate the error between the real-time control parameter and the target control parameter.

[0106] B3. If the error is greater than the set threshold, the location point where the error is greater than the set threshold is recorded as an abnormal point, and a first indication message is sent to the drone.

[0107] In some embodiments, the first indication information is used to instruct the drone to re-detect the remaining planned path and determine the secondary detection data; the remaining planned path is the path between the abnormal point on the planned path and the destination.

[0108] B4. Regenerate target control parameters based on the secondary detection data.

[0109] B5. Based on the regenerated target control parameters, control the driving of the intelligent vehicle.

[0110] In this way, the embodiment of the present invention can monitor the control parameters of the intelligent vehicle in real time and compare them with the target control parameters. If the error is large, it means that there is a difference between the detected terrain and the actual terrain, resulting in a deviation in the control of the vehicle. The embodiment of the present invention can perform secondary precision measurement based on the drone and regenerate the target control parameters to ensure that the intelligent vehicle passes through the target area smoothly and safely.

[0111] Exemplarily, the adaptive control method for an intelligent vehicle provided by an embodiment of the present invention further includes steps C1-C5 after recording a position point where the error is greater than a set threshold as an abnormal point.

[0112] C1. Based on the terrain features of the outlier, the remaining planned paths are screened to determine multiple suspicious points in the remaining planned paths that have terrain features similar to those of the outlier.

[0113] C2. Based on the position coordinates of the multiple suspicious points, generate and send second indication information to the drone.

[0114] In some embodiments, the second instruction information is used to instruct the drone to perform close-range and precise detection of multiple suspicious points.

[0115] Correspondingly, step B4 can be specifically implemented as steps C3-C6.

[0116] C3. Based on the secondary detection data, determine the fine terrain features of multiple suspicious points.

[0117] C4. If the error between the fine terrain features and the terrain features of multiple suspicious points is greater than the set error, a calibration is performed based on the fine terrain features of the multiple suspicious points and the performance parameters of the intelligent vehicle to determine the passability of the intelligent vehicle.

[0118] C5. If the intelligent vehicle can pass, the planned path is kept unchanged, and the target control parameters are regenerated based on the fine terrain features of multiple suspicious points.

[0119] C6. If the intelligent vehicle cannot pass, the suspected point that cannot be passed is determined, and the path is replanned based on the secondary detection data, and the target control parameters of the replanned path are determined.

[0120] In this way, the embodiment of the present invention can focus on detecting suspicious points similar to abnormal points during the secondary precision measurement process, avoid the occurrence of similar errors, and ensure the accuracy of autonomous driving control.

[0121] Exemplarily, the adaptive control method for an intelligent vehicle provided by an embodiment of the present invention further includes steps D1-D5 after detecting the real-time control parameters of the intelligent vehicle.

[0122] D1. If it is detected that the speed of the smart vehicle is zero, a third instruction message is sent to the drone.

[0123] In some embodiments, the third indication information is used to instruct the drone to detect the area where the smart vehicle is located.

[0124] D2. Receive the detection data of the area where the smart vehicle is located sent back by the drone.

[0125] D3. Based on the detection data of the area where the intelligent vehicle is located and the three-dimensional terrain model, a three-dimensional local model of the area where the intelligent vehicle is located is generated.

[0126] D4. Determine the rescue plan for the smart vehicle based on the three-dimensional local model.

[0127] In some embodiments, the rescue scheme includes increasing tire pressure, decreasing tire pressure, rope dragging, raising suspension height, manual pushing, dragging direction, etc.

[0128] In this way, the embodiment of the present invention can provide users with auxiliary rescue solutions by establishing a local model after the vehicle encounters an unexpected stop or difficulty, thereby improving the success rate of the vehicle passing through the target area and the safety of the vehicle.

[0129] The present invention provides an adaptive control method for an intelligent vehicle, which detects a target area, identifies and analyzes the detected radar data and camera data, determines the terrain features such as the surface type, position coordinates, elevation and slope of the target area, and then constructs a three-dimensional terrain model. Combined with the performance parameters of the intelligent vehicle, a safe and efficient driving path is planned, and the intelligent vehicle is controlled based on the planned path to achieve adaptive driving. The present invention realizes adaptive driving of vehicles in a field environment by detecting the terrain features of the field environment and drawing a three-dimensional model.

[0130] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0131] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0132] Figure 2 The schematic diagram of the structure of an adaptive control device for an intelligent vehicle provided by an embodiment of the present invention is shown. The control device 200 includes a communication module 201 and a processing module 202 .

[0133] Communication module 201, used to obtain detection data of the target area; the detection data includes radar data and camera data;

[0134] The processing module 202 is used to perform identification and analysis based on the detection data of the target area to determine the terrain characteristics of each point in the target area; the terrain characteristics include surface type, location coordinates, elevation and slope; based on the terrain characteristic data of each point in the target area, draw a three-dimensional terrain model of the target area; based on the three-dimensional terrain model and the performance parameters of the intelligent vehicle, determine the planned path through the target area; the planned path includes the terrain characteristics of each section on the path; based on the planned path, control the intelligent vehicle to adaptively drive.

[0135] Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, the electronic device 300 includes: a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301. When the processor 301 executes the computer program 303, the steps in the above-mentioned method embodiments are implemented, for example Figure 1 Alternatively, when the processor 301 executes the computer program 303, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 2 The functions of the communication module 201 and the processing module 202 are shown.

[0136] Exemplarily, the computer program 303 may be divided into one or more modules / units, which are stored in the memory 302 and executed by the processor 301 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments that can implement specific functions, and the instruction segments are used to describe the execution process of the computer program 303 in the electronic device 300. For example, the computer program 303 may be divided into Figure 2The communication module 201 and the processing module 202 are shown.

[0137] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0138] The memory 302 may be an internal storage unit of the electronic device 300, such as a hard disk or memory of the electronic device 300. The memory 302 may also be an external storage device of the electronic device 300, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 300. Further, the memory 302 may also include both an internal storage unit of the electronic device 300 and an external storage device. The memory 302 is used to store the computer program and other programs and data required by the terminal. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0139] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. An adaptive control method for an intelligent vehicle, characterized in that: include: Acquire detection data of the target area; the detection data includes radar data and camera data; Based on the detection data of the target area, identification and analysis are performed to determine the terrain features of each point in the target area; the terrain features include surface type, location coordinates, elevation and slope; Based on the terrain feature data of each point in the target area, a three-dimensional terrain model of the target area is drawn; Based on the three-dimensional terrain model and the performance parameters of the intelligent vehicle, determining a planned path through the target area; the planned path includes terrain features of each section on the path; Based on the planned path, the intelligent vehicle is controlled to drive adaptively.

2. The adaptive control method of an intelligent vehicle according to claim 1, characterized in that: The step of controlling the intelligent vehicle to adaptively travel based on the planned path includes: Based on the planned path, determining terrain features of key nodes in the planned path; the key nodes include obstacles and corner points; Determining control parameters of the intelligent vehicle at each key node based on the terrain features of the key nodes in the planned path, wherein the control parameters include at least one of the following: vehicle power, vehicle speed, acceleration, tire pressure, steering angle, and suspension height; Determine the control parameters of the intelligent vehicle at each road section based on the control parameters of the intelligent vehicle at each key node and the terrain characteristics of each road section between each key node of the planned path; Determining target control parameters of the intelligent vehicle on the planned path based on the control parameters of the intelligent vehicle at each key node and each road section; The intelligent vehicle is adaptively controlled based on the target control parameters of the intelligent vehicle on the planned path.

3. The adaptive control method of an intelligent vehicle according to claim 2, characterized in that: The step of determining target control parameters of the intelligent vehicle on the planned path based on the control parameters of the intelligent vehicle at each key node and each road section includes: Determine the value range of the control parameters of the intelligent vehicle at each point on the planned path based on the control parameters of the intelligent vehicle at each key node and each road section; Generate multiple sets of control parameter sets based on the value range of the control parameters of each point on the planned path of the intelligent vehicle; Calculate the comfort and travel time of each set of control parameters; Determine the optimal control parameter set based on the comfort level and travel time of each control parameter set; The optimal control parameter set is determined as the target control parameters of the intelligent vehicle on the planned path.

4. The adaptive control method of an intelligent vehicle according to claim 2, characterized in that: The method of adaptively controlling the intelligent vehicle based on the target control parameter of the intelligent vehicle on the planned path includes: Detecting real-time control parameters of the intelligent vehicle; Calculating an error between the real-time control parameter and the target control parameter; If the error is greater than a set threshold, the position point where the error is greater than the set threshold is recorded as an abnormal point, and a first indication message is sent to the drone, wherein the first indication message is used to instruct the drone to re-detect the remaining planned path to determine secondary detection data; the remaining planned path is the path between the abnormal point and the destination on the planned path; regenerating target control parameters based on the secondary detection data; Based on the regenerated target control parameters, the intelligent vehicle is controlled to travel.

5. The adaptive control method of an intelligent vehicle according to claim 4, characterized in that: After recording the position point where the error is greater than the set threshold as an abnormal point, the method further includes: Based on the terrain features of the outlier point, the remaining planned paths are screened to determine a plurality of suspicious points in the remaining planned paths that are similar to the terrain features of the outlier point; Based on the position coordinates of the multiple suspicious points, second instruction information is generated and sent to the drone, where the second instruction information is used to instruct the drone to perform close-range and precise detection of the multiple suspicious points; Accordingly, based on the secondary detection data, the target control parameters are regenerated, including: Based on the secondary detection data, determining fine terrain features of the plurality of suspicious points; If the error between the fine terrain features of the multiple suspicious points and the terrain features is greater than a set error, a check is performed based on the fine terrain features of the multiple suspicious points and the performance parameters of the smart vehicle to determine the passability of the smart vehicle; If the intelligent vehicle can pass, the planned path is kept unchanged, and target control parameters are regenerated based on the fine terrain features of the multiple suspicious points; If the intelligent vehicle cannot pass, the suspected point that cannot pass is determined, and the path is replanned based on the secondary detection data, and the target control parameters of the replanned path are determined.

6. The adaptive control method of an intelligent vehicle according to claim 4, characterized in that: After detecting the real-time control parameters of the intelligent vehicle, the method further includes: If it is detected that the speed of the smart vehicle is zero, a third indication message is sent to the drone, where the third indication message is used to instruct the drone to detect the area where the smart vehicle is located; Receiving detection data of the area where the intelligent vehicle is located transmitted back by the drone; Generate a three-dimensional local model of the area where the smart vehicle is located based on the detection data of the area where the smart vehicle is located and the three-dimensional terrain model; Based on the three-dimensional local model, a rescue plan for the intelligent vehicle is determined.

7. The adaptive control method of an intelligent vehicle according to claim 1, characterized in that: The identification and analysis based on the detection data of the target area to determine the terrain features of each point in the target area includes: Based on the radar data of the target area, the position coordinates and elevation of each point in the target area are determined with the vehicle as the coordinate origin; Calculate the slope and slope direction of each point based on the position coordinates and elevation of each point in the target area; Based on the position coordinates, elevation, slope and slope direction of each point in the target area, key nodes of the target area are detected and the position coordinates, elevation, slope and slope direction of each key node are obtained; Based on the camera data, image recognition is performed to determine the image of each key node; Based on the position coordinates, elevation, slope and slope direction of each key node and the image of each key node, image fitting is performed to determine the vector image of the target area; the vector image includes the position coordinates, elevation, slope and slope direction of each point; Based on the vector image of the target area, cluster analysis is performed to determine the surface type of each point in the target area, and the surface types include mountains, hills, plains, and basins.

8. The adaptive control method for an intelligent vehicle according to claim 1, characterized in that: Drawing a three-dimensional terrain model of the target area based on the terrain feature data of each point in the target area includes: Based on the position coordinates and elevation of each point in the target area, coordinate conversion is performed to determine the three-dimensional coordinates of each point in the target area; Based on the three-dimensional coordinates of each point in the target area, the target area is divided into grids to construct three-dimensional grid data of the target area; the three-dimensional grid data includes coordinate data of multiple three-dimensional grids; Based on the surface type and slope, and the three-dimensional grid data, feature mapping is performed to determine an initial three-dimensional model; Based on the camera data, the initial three-dimensional model is rendered to obtain the three-dimensional terrain model.

9. The adaptive control method for an intelligent vehicle according to claim 1, characterized in that: Determining a planned path through the target area based on the three-dimensional terrain model and the performance parameters of the intelligent vehicle includes: Based on the three-dimensional terrain model, screening multiple initial paths between a starting point and a destination; Determine a path screening condition based on the performance parameters of the intelligent vehicle; the path screening condition includes at least one of the following: maximum slope, minimum load, maximum pit depth, minimum turning radius, cruising range and braking capacity; Based on the path screening condition, the multiple initial paths are screened to obtain multiple preliminary selected paths; Calculate the travel time, risk level and comfort of each of the primary selected routes; Based on the travel time, risk level and comfort of each of the initially selected paths, a planned path for the target area is determined.

10. An adaptive control device for an intelligent vehicle, characterized in that: include: A communication module, used to obtain detection data of the target area; the detection data includes radar data and camera data; A processing module is used to identify and analyze the detection data of the target area to determine the terrain features of each point in the target area; the terrain features include surface type, location coordinates, elevation and slope; based on the terrain feature data of each point in the target area, draw a three-dimensional terrain model of the target area; based on the three-dimensional terrain model and the performance parameters of the intelligent vehicle, determine a planned path through the target area; the planned path includes the terrain features of each section on the path; Based on the planned path, the intelligent vehicle is controlled to drive adaptively.

Images