Vehicle control method and device and readable storage medium
By acquiring and analyzing the size, type, cargo and dynamic characteristics of vehicles around autonomous driving vehicles, and using deep learning models to identify dangerous vehicles and update their driving paths, the problem of low accuracy in identification of dangerous vehicles in the prior art is solved, and the safety and intelligence of autonomous driving vehicles are improved.
Patent Information
- Application Number
- CN202510850458.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-24
- Publication Date
- 2025-08-15
AI Technical Summary
The existing autonomous driving and assisted driving systems have low recognition accuracy when identifying dangerous vehicles, especially oil tankers, cement trucks or trucks loaded with abnormal cargo, which may lead to collision risks.
By obtaining the size, type, cargo and dynamic characteristics of other vehicles within the preset range, use deep learning models to identify dangerous vehicles and update the driving path according to distance to avoid target vehicles.
It improves the accuracy of identification of dangerous vehicles by autonomous driving vehicles, improves operational safety and intelligence, and expands application scenarios.
Smart Images
Figure CN120482092A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of new energy vehicle technology, and in particular to a vehicle control method, device, and readable storage medium. Background Art
[0002] Current autonomous and assisted driving technologies typically rely on sensor and radar data to determine the type of surrounding vehicles and their distance from the vehicle to determine collision risk. However, this ignores the driver's subjective awareness of danger and the type of cargo loaded. When nearby vehicles like tankers, cement trucks, or trucks carrying unusual cargo (such as overlong or tilting cargo) are present, the system may misidentify them as normal vehicles due to perception limitations and continue to maintain a close, safe distance, potentially causing a sense of crisis in the driver and potentially leading to a collision. This suggests that existing vehicle control methods suffer from technical issues such as low accuracy in identifying dangerous vehicles. Summary of the Invention
[0003] The embodiments of the present application provide a vehicle control method, device, and readable storage medium, which are used to solve technical problems such as low accuracy in identifying dangerous vehicles in the prior art.
[0004] In a first aspect of an embodiment of the present application, a vehicle control method is provided, the method comprising:
[0005] When the first vehicle is traveling along the first route, the first vehicle is controlled to obtain a plurality of vehicle feature sets of a plurality of second vehicles within a preset range, each vehicle feature set including a first size feature, a first type feature, a first cargo feature, and a first dynamic feature of the second vehicle;
[0006] determining a target vehicle among the plurality of second vehicles based on the first size characteristic, the first type characteristic, the first cargo characteristic, and the first dynamic characteristic of each second vehicle;
[0007] Obtaining a preset distance threshold corresponding to the target vehicle, and when the distance between the first vehicle and the target vehicle is greater than the preset distance threshold, updating the first path so that the first path is updated to the second path;
[0008] The first vehicle is controlled to travel along the second path so that the first vehicle avoids the target vehicle.
[0009] In some embodiments, the first vehicle includes a camera and a radar sensor, and controlling the first vehicle to obtain a plurality of vehicle feature sets of a plurality of second vehicles within a preset range includes:
[0010] Control the camera to collect image data within a preset range;
[0011] performing vehicle recognition processing on the image data to determine a plurality of second vehicles within a preset range;
[0012] The radar sensor is controlled to collect the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle to obtain a plurality of vehicle feature sets.
[0013] In some embodiments, determining a target vehicle among the plurality of second vehicles based on the first size characteristic, the first type characteristic, the first cargo characteristic, and the first dynamic characteristic of each second vehicle includes:
[0014] Inputting the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle into a preset first vehicle identification model to obtain a plurality of first vehicle labels output by the first vehicle identification model, wherein the plurality of first vehicle labels correspond one-to-one to the plurality of second vehicles;
[0015] By comparing the plurality of first vehicle tags with the first preset tag, determining a first target tag that is the same as the first preset tag among the plurality of first vehicle tags;
[0016] Among the plurality of second vehicles, a second vehicle corresponding to the first target tag is determined as a target vehicle.
[0017] In some embodiments, the method further comprises:
[0018] Acquire multiple preset vehicles, and perform labeling processing on each preset vehicle to obtain multiple second vehicle labels of the multiple preset vehicles;
[0019] determining a second size characteristic, a second type characteristic, a second cargo load characteristic, and a second driving characteristic of each predetermined vehicle to obtain a plurality of second size characteristics, a plurality of second type characteristics, a plurality of second cargo load characteristics, and a plurality of second driving characteristics;
[0020] storing a plurality of second vehicle labels, a plurality of second size features, a plurality of second type features, a plurality of second cargo features, and a plurality of second driving features as a model training dataset;
[0021] A model training process is performed based on the model training data set to establish a first vehicle recognition model.
[0022] In some embodiments, determining a target vehicle among the plurality of second vehicles based on the first size characteristic, the first type characteristic, the first cargo characteristic, and the first dynamic characteristic of each second vehicle includes:
[0023] Obtain environmental characteristics within a preset range;
[0024] A target vehicle among the plurality of second vehicles is determined based on the environmental feature and the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle.
[0025] In some embodiments, determining a target vehicle among the plurality of second vehicles based on the environmental feature and the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle includes:
[0026] Inputting the environmental feature and the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle into a preset second vehicle recognition model to obtain a plurality of third vehicle labels output by the second vehicle recognition model, wherein the plurality of third vehicle labels correspond one-to-one to the plurality of second vehicles;
[0027] By comparing the plurality of third vehicle tags with the second preset tag, determining a second target tag that is identical to the second preset tag among the plurality of third vehicle tags;
[0028] Among the plurality of second vehicles, a second vehicle corresponding to the second target tag is determined as the target vehicle.
[0029] In some embodiments, the first vehicle includes a distance sensor. After obtaining a preset distance threshold corresponding to the target vehicle, the method further includes:
[0030] Controlling the distance sensor to obtain a first distance and a second distance between the first vehicle and the target vehicle, wherein the first distance is a distance in a first direction, and the second distance is a distance in a second direction, and the first direction and the second direction are perpendicular to each other;
[0031] Data processing is performed on the first distance and the second distance to determine the distance between the first vehicle and the target vehicle.
[0032] The vehicle control method in this embodiment accurately determines a dangerous target vehicle among multiple second vehicles through data information of multiple dimensions such as the first size feature, the first type feature, the first cargo feature, and the first dynamic feature, and updates the driving path of the first vehicle based on the distance between the first vehicle and the target vehicle, thereby improving the recognition accuracy of the autonomous driving vehicle for dangerous vehicles and enhancing the operating safety of the autonomous driving vehicle.
[0033] According to a second aspect of the present application, a vehicle control device is provided, the device comprising:
[0034] a control unit, configured to control the first vehicle to obtain, while the first vehicle is traveling along the first path, a plurality of vehicle feature sets of a plurality of other second vehicles within a preset range, each vehicle feature set including a first size feature, a first type feature, a first cargo feature, and a first dynamic feature of the second vehicle;
[0035] a processing unit for determining a target vehicle among the plurality of second vehicles based on the first size characteristic, the first type characteristic, the first cargo characteristic, and the first dynamic characteristic of each second vehicle;
[0036] The processing unit is further configured to obtain a preset distance threshold corresponding to the target vehicle, and when the distance between the first vehicle and the target vehicle is greater than the preset distance threshold, update the data of the first path so that the first path is updated to the second path;
[0037] The processing unit is further configured to control the first vehicle to travel along the second path so that the first vehicle avoids the target vehicle.
[0038] The vehicle control device in this embodiment accurately determines a dangerous target vehicle among multiple second vehicles through data information of multiple dimensions such as the first size feature, the first type feature, the first cargo feature and the first dynamic feature, and updates the driving path of the first vehicle based on the distance between the first vehicle and the target vehicle, thereby improving the recognition accuracy of the autonomous driving vehicle for dangerous vehicles and enhancing the operational safety of the autonomous driving vehicle.
[0039] A third aspect of the present application provides another vehicle control device, comprising a processor and a memory, wherein the memory stores a computer program that, when executed by the processor, implements the steps of the vehicle control method described in any of the aforementioned embodiments. Therefore, this vehicle control device possesses all the beneficial effects of the vehicle control method described in any of the aforementioned embodiments, and further description thereof is omitted.
[0040] A fourth aspect of the present application provides a readable storage medium having a program or instructions stored thereon. When executed by a processor, the program or instructions implement the steps of the vehicle control method described in any of the aforementioned embodiments. Therefore, the readable storage medium possesses all the beneficial effects of the vehicle control method described in any of the aforementioned embodiments, and further description thereof is omitted. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0042] Figure 1 A flow chart of a vehicle control method provided in an embodiment of the present application;
[0043] Figure 2 A functional schematic diagram of a vehicle control method provided in an embodiment of the present application;
[0044] Figure 3 A functional module block diagram of a vehicle control device provided in an embodiment of the present application;
[0045] Figure 4 This is a structural block diagram of the vehicle control device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0046] In order to better understand the technical solutions provided by the embodiments of this specification, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.
[0047] In this article, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also include elements inherent to such process, method, article or equipment. In the absence of further restrictions, the elements defined by the statement "comprising a ..." do not exclude the presence of other identical elements in the process, method, article or equipment comprising the elements. The term "two or more" includes two or more than two cases.
[0048] In some embodiments, as Figure 1 As shown, an embodiment of the present application provides a vehicle control method, including:
[0049] Step S101, while a first vehicle is traveling along a first route, controlling the first vehicle to obtain a plurality of vehicle feature sets of a plurality of other second vehicles within a preset range;
[0050] Step S102, determining a target vehicle among the plurality of second vehicles based on the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle;
[0051] Step S103, obtaining a preset distance threshold corresponding to the target vehicle, and when the distance between the first vehicle and the target vehicle is greater than the preset distance threshold, updating the data of the first path so that the first path is updated to the second path;
[0052] Step S104: Control the first vehicle to travel along the second path so that the first vehicle avoids the target vehicle.
[0053] In this embodiment, a vehicle control method is proposed, which is applied to a first vehicle. During the process of automatic driving and assisted driving of the first vehicle, the first vehicle can be controlled to identify large dangerous vehicles nearby and replan the path to ensure that the first vehicle avoids large dangerous vehicles, thereby improving the driving safety of the first vehicle.
[0054] Exemplarily, the first vehicle is an unmanned vehicle.
[0055] For example, the first vehicle may be a vehicle that is following the vehicle.
[0056] After the first vehicle starts the automatic driving function, a first path of the first vehicle is planned, and the first vehicle is controlled to travel along the first path, wherein the first path is an initial driving path of the first vehicle.
[0057] Exemplarily, after the first vehicle starts the automatic driving function, path planning is performed based on the current position and destination position of the first vehicle to obtain a first path.
[0058] A preset range that needs to be monitored for the first vehicle is determined, wherein the preset range is an area that needs to be monitored for the first vehicle.
[0059] For example, the preset range may be a circular area with a radius of 30 meters and the first vehicle as the center.
[0060] For example, the user can customize the preset range.
[0061] For example, the first vehicle may monitor road signs, vehicles, and obstacles within a preset range.
[0062] During the process of the first vehicle traveling along the first path, the first vehicle is controlled to obtain multiple vehicle feature sets of multiple other second vehicles within a preset range, wherein the second vehicles are other traveling vehicles within the preset range, the multiple second vehicles correspond one-to-one to the multiple vehicle feature sets, and the vehicle feature set is a data set of feature information of the second vehicles.
[0063] Exemplarily, a perception sensor is provided on the first vehicle, and a plurality of vehicle feature sets of a plurality of other second vehicles within a preset range can be acquired through the perception sensor.
[0064] Each vehicle feature set includes a first size feature, a first type feature, a first cargo feature and a first dynamic feature of the second vehicle, wherein the first size feature represents the size physical feature of the second vehicle, the first type feature represents the vehicle type of the second vehicle, the first cargo feature represents the cargo type of the second vehicle, and the first dynamic feature represents parameters such as the speed of the second vehicle.
[0065] For example, the first size characteristic may include parameters such as length, height, and width of the second vehicle.
[0066] For example, the first size characteristic may include a 3D boundary characteristic parameter of the second vehicle.
[0067] For example, the first type feature may include a type feature of the second vehicle, such as a special vehicle, a tanker truck, a cement truck, and the like.
[0068] For example, the first cargo characteristics may include characteristics such as the material, length, and height of the cargo in the second vehicle, such as steel bars, ultra-high foam boards, and the like.
[0069] For example, the first dynamic characteristics may include parameters such as the speed, lateral acceleration, and lateral and longitudinal distances of the second vehicle from the own vehicle.
[0070] A target vehicle among the plurality of second vehicles is determined based on the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle, wherein the target vehicle is a vehicle among the plurality of second vehicles that poses a danger to the first vehicle.
[0071] Exemplarily, the target vehicle may be a large dangerous vehicle.
[0072] For example, the target vehicle may be a special vehicle, a tanker truck, or a cement truck.
[0073] Obtain a preset distance threshold corresponding to the target vehicle, wherein the preset distance threshold is a safety distance threshold corresponding to the target vehicle.
[0074] Exemplarily, when the target vehicle is a special vehicle, the preset distance threshold is 5 meters.
[0075] Exemplarily, when the target vehicle is a tanker truck, the preset distance threshold is 10 meters.
[0076] Exemplarily, when the target vehicle is a cement truck, the preset distance threshold is 10 meters.
[0077] The first vehicle is controlled to determine a distance between the first vehicle and a target vehicle. When the distance between the first vehicle and the target vehicle is greater than a preset distance threshold, data of the first path is updated so that the first path is updated to a second path, wherein the second path is the updated driving path of the first vehicle.
[0078] For example, when the distance between the first vehicle and the target vehicle is greater than a preset distance threshold, it indicates that the target vehicle poses a safety hazard to the first vehicle, and the first path needs to be updated to the second path so that the first vehicle avoids the target vehicle.
[0079] The first vehicle is controlled to travel along the second path so that the first vehicle avoids the target vehicle.
[0080] For example, when the distance between the first vehicle and the target vehicle is less than a preset distance threshold, it indicates that the target vehicle poses no safety hazard to the first vehicle, and the first path does not need to be updated. The first vehicle can be controlled to continue traveling along the first path.
[0081] It should be noted that this embodiment is based on data information of multiple dimensions such as the first size feature, the first type feature, the first cargo feature and the first dynamic feature, and can accurately determine the dangerous target vehicle among multiple second vehicles, thereby ensuring the accuracy of identifying the target vehicle, and further ensuring that the first vehicle can avoid the target vehicle in time, thereby improving the driving safety of the first vehicle.
[0082] It should also be noted that this embodiment can update the driving path of the first vehicle in real time based on the distance between the first vehicle and the target vehicle, thereby improving the initiative and intelligence of the first vehicle and further expanding the application scenarios of the first vehicle.
[0083] The vehicle control method in this embodiment accurately determines a dangerous target vehicle among multiple second vehicles through data information of multiple dimensions such as the first size feature, the first type feature, the first cargo feature, and the first dynamic feature, and updates the driving path of the first vehicle based on the distance between the first vehicle and the target vehicle, thereby improving the recognition accuracy of the autonomous driving vehicle for dangerous vehicles and enhancing the operating safety of the autonomous driving vehicle.
[0084] In some embodiments, an embodiment of the present application provides a vehicle control method for controlling a first vehicle to obtain multiple vehicle feature sets of multiple second vehicles within a preset range, including:
[0085] Step S201, controlling the camera to collect image data within a preset range;
[0086] Step S202, performing vehicle recognition processing on the image data to determine a plurality of second vehicles within a preset range;
[0087] Step S203 : Controlling the radar sensor to collect the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle to obtain a plurality of vehicle feature sets.
[0088] In this embodiment, a camera and a radar sensor are provided on the first vehicle.
[0089] Exemplarily, the camera may be a two-dimensional camera for collecting two-dimensional image data within a preset range.
[0090] Exemplarily, the radar sensor may be a millimeter wave radar and a lidar.
[0091] When the first vehicle travels along the first path, the camera is started and controlled to collect image data of a preset range, wherein the image data is a real-time image of the preset range.
[0092] Exemplarily, the image data may be a three-dimensional panoramic image of a preset range.
[0093] Exemplarily, the image data may be a real-time panoramic video of a preset range.
[0094] Vehicle recognition processing is performed on the image data to determine a plurality of second vehicles within a preset range.
[0095] Exemplarily, a target recognition algorithm is used to identify vehicle targets in the image data to determine a plurality of second vehicles within a preset range.
[0096] The radar sensor is controlled to collect the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle to obtain a plurality of vehicle feature sets.
[0097] Exemplarily, the radar sensor is controlled to collect point cloud data of each second vehicle, and based on the point cloud data of each second vehicle, the first size feature, the first type feature, the first cargo feature and the first dynamic feature of each second vehicle can be determined.
[0098] Illustratively, the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle are integrated to obtain a plurality of vehicle feature sets.
[0099] In some embodiments, an embodiment of the present application provides a vehicle control method, which determines a target vehicle among a plurality of second vehicles based on a first size feature, a first type feature, a first cargo feature, and a first dynamic feature of each second vehicle, including:
[0100] Step S301: Inputting the first size feature, first type feature, first cargo feature, and first dynamic feature of each second vehicle into a preset first vehicle recognition model to obtain a plurality of first vehicle labels output by the first vehicle recognition model, wherein the plurality of first vehicle labels correspond one-to-one to the plurality of second vehicles;
[0101] Step S302, by comparing the plurality of first vehicle tags with the first preset tag, determining a first target tag that is the same as the first preset tag among the plurality of first vehicle tags;
[0102] Step S303: Determine, among the plurality of second vehicles, the second vehicle corresponding to the first target tag as the target vehicle.
[0103] In this embodiment, a first vehicle recognition model for identifying a vehicle is established, wherein the first vehicle recognition model is a deep learning model for identifying a vehicle type.
[0104] Exemplarily, the first vehicle recognition model may be a deep learning model that recognizes multiple dimensional data such as size, type, cargo load, and dynamic parameters.
[0105] The first size feature, first type feature, first cargo feature and first dynamic feature of each second vehicle are input into the first vehicle identification model to obtain multiple first vehicle labels output by the first vehicle identification model, wherein the multiple first vehicle labels correspond one-to-one to the multiple second vehicles, and the first vehicle label is a label indicating the degree of danger of the second vehicle.
[0106] For example, the plurality of first vehicle tags may include tags such as large vehicle tags, dangerous vehicle tags, regular vehicle tags, and unconventional vehicle tags.
[0107] A first preset tag is obtained, wherein the first preset tag is a vehicle tag preset by a user.
[0108] Exemplarily, the first preset label may specifically be a dangerous vehicle label.
[0109] For example, the first preset label may be a vehicle label input and set by a user on the first vehicle.
[0110] By comparing the plurality of first vehicle tags with the first preset tag, a first target tag identical to the first preset tag among the plurality of first vehicle tags is determined, wherein the first target tag is the vehicle tag identical to the first preset tag.
[0111] Exemplarily, when the first preset tag is a dangerous vehicle tag, the first target tag is a dangerous vehicle tag among the multiple first vehicle tags.
[0112] Exemplarily, when the first preset tag is a dangerous vehicle tag, the first target tag may include multiple dangerous vehicle tags among the multiple first vehicle tags.
[0113] Among the plurality of second vehicles, a second vehicle corresponding to the first target tag is determined as a target vehicle.
[0114] Exemplarily, under the condition that the first target tag includes a plurality of dangerous vehicle tags, a plurality of target vehicles among the plurality of second vehicles may be determined.
[0115] In some embodiments, an embodiment of the present application provides a vehicle control method, the method further comprising:
[0116] Step S401: Acquire multiple preset vehicles, and perform labeling processing on each preset vehicle to obtain multiple second vehicle labels of the multiple preset vehicles;
[0117] Step S402, determining a second size characteristic, a second type characteristic, a second cargo load characteristic, and a second driving characteristic of each preset vehicle to obtain a plurality of second size characteristics, a plurality of second type characteristics, a plurality of second cargo load characteristics, and a plurality of second driving characteristics;
[0118] Step S403, storing the plurality of second vehicle labels, the plurality of second size features, the plurality of second type features, the plurality of second cargo features, and the plurality of second driving features as a model training data set;
[0119] Step S404: performing a model training process based on the model training data set to establish a first vehicle recognition model.
[0120] In this embodiment, multiple preset vehicles are obtained, and each preset vehicle is labeled to obtain multiple second vehicle labels of the multiple preset vehicles, wherein the preset vehicles are preset alternative vehicles, the multiple second vehicle labels correspond one-to-one to the multiple preset vehicles, and the second vehicle labels are vehicle labels of the preset vehicles.
[0121] Exemplarily, image data of a plurality of preset vehicles may be acquired, and based on the image data of the plurality of preset vehicles, labeling processing may be performed on each preset vehicle to obtain a plurality of second vehicle labels.
[0122] Exemplarily, video data of a plurality of preset vehicles may be acquired, and based on the video data of the plurality of preset vehicles, labeling processing is performed on each preset vehicle to obtain a plurality of second vehicle labels.
[0123] The second size characteristic, the second type characteristic, the second cargo characteristic, and the second driving characteristic of each preset vehicle are identified to obtain a plurality of second size characteristics, a plurality of second type characteristics, a plurality of second cargo characteristics, and a plurality of second driving characteristics.
[0124] Among them, the second size feature represents the size physical feature of the preset vehicle, the second type feature represents the vehicle type of the preset vehicle, the second cargo feature represents the cargo type of the preset vehicle, and the second dynamic feature represents parameters such as the speed of the preset vehicle.
[0125] A plurality of second vehicle labels, a plurality of second size features, a plurality of second type features, a plurality of second cargo features, and a plurality of second driving features are stored as a model training dataset, wherein the model training dataset is a dataset used to train the first vehicle recognition model.
[0126] A model training process is performed based on the model training data set to establish a first vehicle recognition model.
[0127] Exemplarily, there is a one-to-one correspondence between the stored multiple second vehicle labels, multiple second size features, multiple second type features, multiple second cargo features, and multiple second driving features. Based on the correspondence between the stored multiple second vehicle labels, multiple second size features, multiple second type features, multiple second cargo features, and multiple second driving features, the multiple second vehicle labels, multiple second size features, multiple second type features, multiple second cargo features, and multiple second driving features are integrated into a model training data set.
[0128] In some embodiments, an embodiment of the present application provides a vehicle control method, which determines a target vehicle among a plurality of second vehicles based on a first size feature, a first type feature, a first cargo feature, and a first dynamic feature of each second vehicle, including:
[0129] Step S501, obtaining environmental characteristics within a preset range;
[0130] Step S502 : determining a target vehicle among the plurality of second vehicles based on the environmental characteristics and the first size characteristic, the first type characteristic, the first cargo characteristic, and the first dynamic characteristic of each second vehicle.
[0131] In this embodiment, the environmental conditions within a preset range are monitored to obtain environmental characteristics within the preset range, wherein the environmental characteristics represent the environmental conditions within the preset range.
[0132] For example, environmental characteristics may include information such as weather (wind speed, precipitation), road slope, etc.
[0133] A target vehicle among the plurality of second vehicles is determined based on the environmental feature and the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle.
[0134] For example, a weather sensing device may be provided on the vehicle, through which the current weather conditions and thus the environmental characteristics may be determined.
[0135] In some embodiments, embodiments of the present application provide a vehicle control method, which determines a target vehicle among a plurality of second vehicles based on environmental characteristics and a first size characteristic, a first type characteristic, a first cargo characteristic, and a first dynamic characteristic of each second vehicle, including:
[0136] Step S601: Inputting the environmental characteristics and the first size characteristic, the first type characteristic, the first cargo characteristic, and the first dynamic characteristic of each second vehicle into a preset second vehicle recognition model to obtain a plurality of third vehicle labels output by the second vehicle recognition model, wherein the plurality of third vehicle labels correspond one-to-one to the plurality of second vehicles;
[0137] Step S602, by comparing the plurality of third vehicle tags with the second preset tag, determining a second target tag that is the same as the second preset tag among the plurality of third vehicle tags;
[0138] Step S603: Determine, among the plurality of second vehicles, a second vehicle corresponding to the second target tag as a target vehicle.
[0139] In this embodiment, a second vehicle recognition model is established for identifying vehicles, wherein the second vehicle recognition model is a deep learning model for identifying vehicle types.
[0140] Exemplarily, the second vehicle recognition model may be a deep learning model that recognizes multiple dimensional data such as environment, size, type, cargo, and dynamic parameters.
[0141] The environmental characteristics and the first size characteristics, first type characteristics, first cargo characteristics and first dynamic characteristics of each second vehicle are input into a preset second vehicle identification model to obtain multiple third vehicle labels output by the second vehicle identification model, wherein the multiple third vehicle labels correspond one-to-one to the multiple second vehicles, and the third vehicle labels are labels output by the second vehicle identification model.
[0142] For example, the plurality of third vehicle tags may include tags such as large vehicle tags, dangerous vehicle tags, regular vehicle tags, and unconventional vehicle tags.
[0143] A second preset tag is obtained, wherein the second preset tag is a vehicle tag preset by a user.
[0144] Exemplarily, the second preset label may specifically be a dangerous vehicle label.
[0145] For example, the second preset label may be a vehicle label input and set by the user on the second vehicle.
[0146] By comparing the plurality of third vehicle tags with the second preset tag, a second target tag identical to the second preset tag among the plurality of third vehicle tags is determined, wherein the second target tag is the vehicle tag identical to the second preset tag.
[0147] Exemplarily, when the second preset tag is a dangerous vehicle tag, the second target tag is a dangerous vehicle tag among the plurality of third vehicle tags.
[0148] Exemplarily, when the second preset tag is a dangerous vehicle tag, the second target tag may include multiple dangerous vehicle tags among the multiple third vehicle tags.
[0149] Among the plurality of second vehicles, a second vehicle corresponding to the second target tag is determined as the target vehicle.
[0150] Exemplarily, under the condition that the second target tag includes a plurality of dangerous vehicle tags, a plurality of target vehicles among the plurality of second vehicles may be determined.
[0151] In some embodiments, an embodiment of the present application provides a vehicle control method. After obtaining a preset distance threshold corresponding to a target vehicle, the method further includes:
[0152] Step S701: Control the distance sensor to obtain a first distance and a second distance between the first vehicle and the target vehicle, where the first distance is the distance in a first direction and the second distance is the distance in a second direction, and the first direction and the second direction are perpendicular to each other.
[0153] Step S702 : Processing the first distance and the second distance to determine the distance between the first vehicle and the target vehicle.
[0154] In this embodiment, the first vehicle further includes a distance sensor, which is a sensor for detecting distance.
[0155] The distance sensor is controlled to obtain a first distance and a second distance between the first vehicle and the target vehicle, wherein the first distance is a distance in a first direction, the second distance is a distance in a second direction, and the first direction and the second direction are perpendicular to each other.
[0156] For example, the first direction may be a longitudinal direction of the first vehicle, and the second direction may be a lateral direction of the first vehicle.
[0157] Data processing is performed on the first distance and the second distance to determine the distance between the first vehicle and the target vehicle.
[0158] For example, the distance between the first vehicle and the target vehicle may be determined by performing a square sum operation on the first distance and the second distance.
[0159] For example, Figure 2 As shown, the first vehicle may include a perception and recognition module, a vehicle marking module, a dangerous vehicle database module, and a vehicle avoidance module.
[0160] The perception and recognition module primarily includes cameras and radar, including but not limited to millimeter-wave radar and lidar. This combination of cameras and radar can output information about the road, vehicles, and obstacles surrounding the vehicle to the IVI. This outputted vehicle information should include vehicle type, length, width, lateral distance, longitudinal distance, and other information.
[0161] The vehicle identification module includes an IVI (In-Vehicle Infotainment) display system and a user confirmation system.
[0162] IVI display system: The HMI will display the current road, obstacles, and vehicle information on the perception interface.
[0163] User confirmation system: When the driver clicks on the target, the system will mark the target in red and pop up a window to ask the driver. When the driver clicks to confirm, the system will list the vehicle as a "dangerous vehicle" and output it to the next module.
[0164] The dangerous vehicle database is mainly used to judge the multi-dimensional model of "dangerous vehicles". The system will extract the following characteristics of the target:
[0165] Physical features: including 3D boundary features such as the vehicle's length, height, and width.
[0166] Type characteristics: Contains the type characteristics of vehicles, such as special vehicles, tank trucks, cement trucks, etc.
[0167] Cargo characteristics: including the material, length, height and other characteristics of the cargo in the vehicle, such as steel bars, ultra-high foam boards, etc.
[0168] Dynamic behavior characteristics: including the target vehicle’s speed, lateral acceleration, and lateral and longitudinal distances from the ego vehicle.
[0169] Environmental characteristics: including current weather (wind speed, precipitation), road slope, etc.
[0170] The system will fuse all features through deep learning to obtain a multi-dimensional model of a "dangerous vehicle". All subsequent vehicles similar to this model will be uniformly labeled as "dangerous vehicles". The feature library is continuously updated and optimized. Whenever a user marks a new dangerous vehicle or when the features of an existing dangerous vehicle change, the database will automatically adjust.
[0171] The vehicle avoidance module includes a dynamic safety distance calculation system, a personalized distance adjustment system, and a collaborative braking system.
[0172] The initial safety distance calculation system contains an initial value that integrates the dangerous vehicle distance threshold, the lateral and longitudinal distances, and the relative speed. When it is detected that the lateral and longitudinal distances between the two vehicles exceed the threshold and there is no collision risk around, avoidance will be performed.
[0173] Dynamic distance adjustment system: When the user intervenes in the avoidance action, the system will calculate the intervention conditions and bind the conditions to the identified model. Subsequently, all identified targets similar to the model will be avoided according to the new threshold to achieve personalized avoidance effect.
[0174] The safety avoidance system is associated with the actuator. When it is confirmed that avoidance is required, it outputs steering or braking instructions to the associated parts to achieve a safe avoidance result.
[0175] In some embodiments, as Figure 3 As shown, an embodiment of the present application provides a vehicle control device 800, including:
[0176] A control unit 802 is configured to control the first vehicle to obtain, while the first vehicle is traveling along the first route, a plurality of vehicle feature sets of a plurality of second vehicles within a preset range, each vehicle feature set including a first size feature, a first type feature, a first cargo feature, and a first dynamic feature of the second vehicle;
[0177] a processing unit 804 for determining a target vehicle among the plurality of second vehicles based on the first size characteristic, the first type characteristic, the first cargo characteristic, and the first dynamic characteristic of each second vehicle;
[0178] The processing unit 804 is further configured to obtain a preset distance threshold corresponding to the target vehicle, and when the distance between the first vehicle and the target vehicle is greater than the preset distance threshold, update the data of the first path so that the first path is updated to the second path;
[0179] The processing unit 804 is further configured to control the first vehicle to travel along the second path so that the first vehicle avoids the target vehicle.
[0180] The vehicle control device 900 in this embodiment accurately determines a dangerous target vehicle among multiple second vehicles through data information of multiple dimensions such as the first size feature, the first type feature, the first cargo feature and the first dynamic feature, and updates the driving path of the first vehicle based on the distance between the first vehicle and the target vehicle, thereby improving the recognition accuracy of the autonomous driving vehicle for dangerous vehicles and enhancing the operating safety of the autonomous driving vehicle.
[0181] In some embodiments, an embodiment of the present application provides a vehicle control device 800, including:
[0182] A control unit 802 is used to control the camera to collect image data within a preset range;
[0183] a control unit 802 for performing vehicle recognition processing on the image data to determine a plurality of second vehicles within a preset range;
[0184] The control unit 802 is configured to control the radar sensor to collect the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle to obtain a plurality of vehicle feature sets.
[0185] In some embodiments, an embodiment of the present application provides a vehicle control device 800, including:
[0186] a processing unit 804 configured to input the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle into a preset first vehicle identification model to obtain a plurality of first vehicle labels output by the first vehicle identification model, wherein the plurality of first vehicle labels correspond one-to-one to the plurality of second vehicles;
[0187] The processing unit 804 is configured to determine a first target tag that is the same as the first preset tag among the plurality of first vehicle tags by comparing the plurality of first vehicle tags with the first preset tag;
[0188] The processing unit 804 is configured to determine, among the plurality of second vehicles, a second vehicle corresponding to the first target tag as a target vehicle.
[0189] In some embodiments, an embodiment of the present application provides a vehicle control device 800, including:
[0190] The processing unit 804 is configured to obtain a plurality of preset vehicles and perform labeling processing on each preset vehicle to obtain a plurality of second vehicle labels for the plurality of preset vehicles;
[0191] The processing unit 804 is configured to determine a second size characteristic, a second type characteristic, a second cargo characteristic, and a second driving characteristic of each predetermined vehicle to obtain a plurality of second size characteristics, a plurality of second type characteristics, a plurality of second cargo characteristics, and a plurality of second driving characteristics;
[0192] a processing unit 804 configured to store the plurality of second vehicle labels, the plurality of second size features, the plurality of second type features, the plurality of second cargo features, and the plurality of second driving features as a model training dataset;
[0193] The processing unit 804 is configured to perform a model training process based on the model training data set to establish a first vehicle recognition model.
[0194] In some embodiments, an embodiment of the present application provides a vehicle control device 800, including:
[0195] Processing unit 804, used to obtain environmental characteristics within a preset range;
[0196] The processing unit 804 is configured to determine a target vehicle among the plurality of second vehicles based on the environmental feature and the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle.
[0197] In some embodiments, an embodiment of the present application provides a vehicle control device 800, including:
[0198] a processing unit 804 configured to input the environmental feature and the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle into a preset second vehicle identification model to obtain a plurality of third vehicle labels output by the second vehicle identification model, wherein the plurality of third vehicle labels correspond one-to-one to the plurality of second vehicles;
[0199] The processing unit 804 is configured to determine a second target tag that is identical to the second preset tag among the plurality of third vehicle tags by comparing the plurality of third vehicle tags with the second preset tag;
[0200] The processing unit 804 is configured to determine, among the plurality of second vehicles, a second vehicle corresponding to the second target tag as a target vehicle.
[0201] In some embodiments, an embodiment of the present application provides a vehicle control device 800, including:
[0202] The processing unit 804 is configured to control the distance sensor to obtain a first distance and a second distance between the first vehicle and the target vehicle, where the first distance is a distance in a first direction and the second distance is a distance in a second direction, and the first direction and the second direction are perpendicular to each other;
[0203] The processing unit 804 is configured to perform data processing on the first distance and the second distance to determine the distance between the first vehicle and the target vehicle.
[0204] In some embodiments, as Figure 4 As shown, a vehicle control device 900 is provided. The vehicle control device 900 includes a processor 902 and a memory 904. The memory 904 stores a computer program. When executed by the processor 902, the computer program implements the steps of the vehicle control method described in any of the above-mentioned embodiments. Therefore, the vehicle control device 900 has all the advantages of the vehicle control method described in any of the above-mentioned embodiments, and will not be further described here.
[0205] In some embodiments, a readable storage medium is provided on which a program is stored. When the program is executed by a processor, the steps of the vehicle control method in any of the above embodiments are implemented, thereby having all the beneficial technical effects of the vehicle control method in any of the above embodiments.
[0206] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.
[0207] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-readable program code.
[0208] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0209] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.
[0210] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.
[0211] An embodiment of the present application further provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of the vehicle control method.
[0212] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).
[0213] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0214] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.
[0215] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.
[0216] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.
[0217] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0218] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these 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 application.
[0219] Although the preferred embodiments of this specification have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of this specification.
[0220] Obviously, those skilled in the art may make various changes and modifications to this specification without departing from the spirit and scope of this specification. Thus, if such changes and modifications fall within the scope of the claims of this specification and their equivalents, this specification is intended to include such changes and modifications.
Claims
1. A vehicle control method, characterized in that: The method comprises: During a process in which a first vehicle travels along a first route, controlling the first vehicle to obtain a plurality of vehicle feature sets of a plurality of second vehicles within a preset range, each of the vehicle feature sets including a first size feature, a first type feature, a first cargo feature, and a first dynamic feature of the second vehicle; determining a target vehicle among the plurality of second vehicles based on the first size characteristic, the first type characteristic, the first cargo characteristic, and the first dynamic characteristic of each second vehicle; Obtaining a preset distance threshold corresponding to the target vehicle, and when the distance between the first vehicle and the target vehicle is greater than the preset distance threshold, updating data on the first path so that the first path is updated to a second path; The first vehicle is controlled to travel along the second path so that the first vehicle avoids the target vehicle.
2. The method according to claim 1, characterized in that The first vehicle includes a camera and a radar sensor, and controlling the first vehicle to obtain multiple vehicle feature sets of multiple second vehicles within a preset range includes: Controlling the camera to collect image data within the preset range; performing vehicle recognition processing on the image data to determine a plurality of second vehicles within the preset range; The radar sensor is controlled to collect the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle to obtain a plurality of vehicle feature sets.
3. The method according to claim 1, characterized in that The determining of a target vehicle among the plurality of second vehicles based on the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle comprises: Inputting the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle into a preset first vehicle identification model to obtain a plurality of first vehicle labels output by the first vehicle identification model, wherein the plurality of first vehicle labels correspond one-to-one to the plurality of second vehicles; By comparing the plurality of first vehicle tags with a first preset tag, determining a first target tag that is identical to the first preset tag among the plurality of first vehicle tags; Among the plurality of second vehicles, the second vehicle corresponding to the first target tag is determined as the target vehicle.
4. The method according to claim 3, characterized in that The method further comprises: Acquire a plurality of preset vehicles, and perform labeling processing on each of the preset vehicles to obtain a plurality of second vehicle labels for the plurality of preset vehicles; determining a second size characteristic, a second type characteristic, a second cargo-carrying characteristic, and a second driving characteristic of each of the preset vehicles to obtain a plurality of the second size characteristics, a plurality of the second type characteristics, a plurality of the second cargo-carrying characteristics, and a plurality of the second driving characteristics; storing a plurality of the second vehicle labels, a plurality of the second size features, a plurality of the second type features, a plurality of the second cargo features, and a plurality of the second driving features as a model training dataset; A model training process is performed based on the model training data set to establish the first vehicle recognition model.
5. The method according to claim 1, characterized in that The determining of a target vehicle among the plurality of second vehicles based on the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle comprises: Acquire environmental characteristics within the preset range; A target vehicle among the plurality of second vehicles is determined based on the environmental characteristics and the first size characteristic, the first type characteristic, the first cargo characteristic, and the first dynamic characteristic of each second vehicle.
6. The method according to claim 5, characterized in that The determining a target vehicle among the plurality of second vehicles based on the environmental feature and the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle includes: Inputting the environmental feature and the first size feature, the first type feature, the first cargo feature, and the first dynamic feature of each second vehicle into a preset second vehicle recognition model to obtain a plurality of third vehicle labels output by the second vehicle recognition model, wherein the plurality of third vehicle labels correspond one-to-one to the plurality of second vehicles; By comparing the plurality of third vehicle tags with the second preset tags, determining a second target tag that is the same as the second preset tag among the plurality of third vehicle tags; Among the plurality of second vehicles, the second vehicle corresponding to the second target tag is determined as the target vehicle.
7. The method according to any one of claims 1 to 6, characterized in that The first vehicle includes a distance sensor. After obtaining the preset distance threshold corresponding to the target vehicle, the method further includes: Controlling a distance sensor to obtain a first distance and a second distance between the first vehicle and the target vehicle, wherein the first distance is a distance in a first direction, and the second distance is a distance in a second direction, and the first direction and the second direction are perpendicular to each other; Data processing is performed on the first distance and the second distance to determine a distance between the first vehicle and the target vehicle.
8. A vehicle control device, characterized in that: The device comprises: a control unit, configured to control the first vehicle to obtain, while the first vehicle is traveling along the first path, a plurality of vehicle feature sets of a plurality of second vehicles within a preset range, each of the vehicle feature sets comprising a first size feature, a first type feature, a first cargo feature, and a first dynamic feature of the second vehicle; a processing unit configured to determine a target vehicle among the plurality of second vehicles based on the first size characteristic, the first type characteristic, the first cargo characteristic, and the first dynamic characteristic of each second vehicle; The processing unit is further configured to obtain a preset distance threshold corresponding to the target vehicle, and when the distance between the first vehicle and the target vehicle is greater than the preset distance threshold, update the data of the first path so that the first path is updated to a second path; The processing unit is further configured to control the first vehicle to travel along the second path so that the first vehicle avoids the target vehicle.
9. A vehicle control device, characterized in that: include: processor; A memory, wherein a program or instruction is stored in the memory, and when the processor executes the program or instruction in the memory, the steps of the vehicle control method according to any one of claims 1 to 7 are implemented.
10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the vehicle control method according to any one of claims 1 to 7 are implemented.