Method and device for detecting actual speed of unmanned vehicle and unmanned vehicle

Abstract

The present application discloses a method, device and unmanned vehicle for detecting the actual speed of an unmanned vehicle, and belongs to the field of unmanned driving. The detection method includes: first identifying the motion scene of the unmanned vehicle, and when the motion scene of the unmanned vehicle is identified as a short-distance start, controlling to enter the vehicle speed fusion mode, and then in the vehicle fusion mode, determining the actual vehicle speed based on the first vehicle speed and the second vehicle speed, wherein the first vehicle speed is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned vehicle, and the second vehicle speed is the movement speed of the unmanned vehicle in the spatial coordinate system obtained by the sensor of the unmanned vehicle. That is, when starting a short distance, the actual vehicle speed is determined by the first vehicle speed and the second vehicle speed, which can solve the problem of poor accuracy in detecting the actual vehicle speed of the vehicle in the related art.

Description

Technical Field

[0001] The present application relates to the field of unmanned driving technology, and in particular, to a method and device for detecting the actual speed of an unmanned vehicle and an unmanned vehicle. Background Art

[0002] In the field of autonomous driving, in order to ensure driving safety, it is necessary to accurately obtain the actual speed of the driverless vehicle. The relevant technologies all determine the actual speed by positioning the vehicle speed, which is the vehicle speed obtained by the sensor as the actual speed. However, the positioning speed sometimes deviates greatly from the actual speed, resulting in inaccurate vehicle control based on the positioning speed. Summary of the invention

[0003] In order to overcome the shortcomings of the related art, the present application provides a method, device and unmanned vehicle for detecting the actual speed of an unmanned vehicle, so as to solve the problem in the related art that when the actual speed is determined only based on the positioned speed, the positioned speed sometimes deviates greatly from the actual speed, resulting in inaccurate vehicle control based on the positioned speed.

[0004] The technical solution adopted by this application to solve its technical problem is:

[0005] In a first aspect, a method for detecting an actual speed of an unmanned vehicle is provided, comprising:

[0006] Identify motion scenes of unmanned vehicles;

[0007] When it is identified that the movement scene of the unmanned vehicle is a short-distance start, control is performed to enter a vehicle speed fusion mode, wherein the vehicle speed fusion mode is a mode in which an actual vehicle speed is obtained by fusing a first vehicle speed and a second vehicle speed, wherein the first vehicle speed is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned vehicle, and the second vehicle speed is the movement speed of the unmanned vehicle in a spatial coordinate system obtained by a sensor of the unmanned vehicle;

[0008] In the vehicle speed fusion mode, an actual vehicle speed is determined based on the first vehicle speed and the second vehicle speed.

[0009] Furthermore, when it is recognized that the motion scene of the unmanned vehicle is a short-distance start, controlling the vehicle to enter the vehicle speed fusion mode includes:

[0010] detecting a vehicle speed difference between the first vehicle speed and the second vehicle speed;

[0011] When it is identified that the movement scene of the unmanned vehicle is a short-distance start and the vehicle speed difference is greater than a difference threshold, the control enters a vehicle speed fusion mode.

[0012] Further, determining the actual vehicle speed based on the first vehicle speed and the second vehicle speed includes:

[0013] detecting a vehicle speed difference between the first vehicle speed and the second vehicle speed;

[0014] Based on the vehicle speed difference, determining a first weight coefficient for the first vehicle speed and a second weight coefficient for the second vehicle speed respectively;

[0015] Based on the first weight coefficient and the first vehicle speed, and the second weight coefficient and the second vehicle speed, weighted processing is performed to obtain the actual vehicle speed.

[0016] Further, the determining, based on the vehicle speed difference, a first weight coefficient for the first vehicle speed and a second weight coefficient for the second vehicle speed respectively comprises:

[0017] The first weight coefficient is calculated by the following objective function:

[0018]

[0019] in, represents the first weight coefficient, represents the specified coefficient, represents the vehicle speed difference;

[0020] The value obtained by subtracting the first weight coefficient from 1 is used as the second weight coefficient.

[0021] Furthermore, the first weight coefficient is also related to at least the following parameters:

[0022] Hardware parameters of the gearbox;

[0023] Hardware parameters of the sensor;

[0024] The positioning signal parameters of the unmanned vehicle.

[0025] Furthermore, the method further comprises:

[0026] Acquire multiple sample data collected by the unmanned driving sample vehicle, the sample data including a first speed sample, a second speed sample and an actual vehicle speed sample, wherein the first speed sample is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned driving sample vehicle, and the second speed sample is the movement speed of the unmanned driving sample vehicle in the spatial coordinate system acquired by the sensor of the unmanned driving sample vehicle;

[0027] The designated function is trained using the plurality of sample data to obtain the designated coefficients, wherein the designated function at least includes the target function.

[0028] Furthermore, the identifying the motion scene of the unmanned vehicle includes:

[0029] Identifying a motion scene of the unmanned vehicle according to a current vehicle state of the unmanned vehicle and a trajectory plan issued by a planning module of the unmanned vehicle;

[0030] Among them, when the current vehicle state is a parking state and the trajectory planning is less than a corresponding threshold, the movement scene of the unmanned vehicle is identified as a short-distance start.

[0031] Furthermore, it also includes:

[0032] When the handbrake of the driverless vehicle is in a pulled-up state and the current gear position of the driverless vehicle is the N gear, it is determined that the current vehicle state is a parking state.

[0033] Furthermore, it also includes:

[0034] In the case where the trajectory planning is a parking distance, when the parking distance is less than a first preset distance, the trajectory planning is less than a corresponding threshold;

[0035] And / or, in a case where the trajectory planning is a starting distance, when the starting distance is less than a second preset distance, the trajectory planning is less than a corresponding threshold.

[0036] Furthermore, it also includes:

[0037] When it is recognized that the motion scene of the unmanned vehicle is not a short-distance start, controlling to enter a first vehicle speed detection mode, wherein the first vehicle speed detection mode is used to determine an actual vehicle speed based on a specified vehicle speed, wherein the specified vehicle speed includes the second vehicle speed and does not include the first vehicle speed;

[0038] In the first vehicle speed detection mode, the actual vehicle speed is determined based on the designated vehicle speed.

[0039] Furthermore, it also includes:

[0040] When a preset condition is met, the vehicle speed fusion mode is exited, and the preset condition includes at least one of the following:

[0041] The actual vehicle speed is greater than the preset vehicle speed;

[0042] The duration of entering the vehicle speed fusion mode exceeds the preset duration;

[0043] The vehicle is detected to be stopped.

[0044] In a second aspect, a device for determining an actual speed of an unmanned vehicle is provided, comprising:

[0045] A scene recognition module, used to identify the motion scenes of unmanned vehicles;

[0046] a mode control module, configured to control the vehicle to enter a vehicle speed fusion mode when it is identified that the movement scene of the unmanned vehicle is a short-distance start; wherein the vehicle speed fusion mode is a mode in which an actual vehicle speed is obtained by fusing a first vehicle speed and a second vehicle speed, wherein the first vehicle speed is used to represent the rotation speed of the wheels connected to the gearbox of the unmanned vehicle, and the second vehicle speed is the movement speed of the unmanned vehicle in a spatial coordinate system obtained by a sensor of the unmanned vehicle;

[0047] The vehicle speed determination module is used to determine the actual vehicle speed based on the first vehicle speed and the second vehicle speed in the vehicle speed fusion mode.

[0048] In a third aspect, a computer-readable storage medium is provided, on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the steps of the method for detecting the actual speed of an unmanned vehicle provided by the technical solution of the first aspect are implemented.

[0049] In a fourth aspect, an electronic device is provided, including:

[0050] at least one processor and at least one memory;

[0051] The memory stores executable instructions of the processor;

[0052] The processor is configured to execute the method for detecting the actual speed of the unmanned vehicle provided by the technical solution of the first aspect.

[0053] In a fifth aspect, an unmanned vehicle is provided, which uses the method for detecting the actual speed of the unmanned vehicle provided by the technical solution of the first aspect.

[0054] Beneficial effects:

[0055] The technical solution of the present application provides a method, device and unmanned vehicle for detecting the actual speed of an unmanned vehicle. The detection method includes: firstly identifying the motion scene of the unmanned vehicle, and when the motion scene of the unmanned vehicle is identified as a short-distance start, controlling the vehicle to enter the vehicle speed fusion mode, and then in the vehicle fusion mode, determining the actual vehicle speed based on the first vehicle speed and the second vehicle speed, wherein the first vehicle speed is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned vehicle, and the second vehicle speed is the motion speed of the unmanned vehicle in the spatial coordinate system obtained by the sensor of the unmanned vehicle. That is, when starting in a short distance, the actual vehicle speed is determined by the first vehicle speed and the second vehicle speed. Compared with only using the second vehicle speed as the actual vehicle speed, it can effectively solve the problem of excessive deviation between the second vehicle speed and the actual vehicle speed, and obtain an accurate actual vehicle speed, thereby realizing accurate control of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 This is a flow chart of a method for detecting the actual speed of an unmanned vehicle provided in an embodiment of the present application;

[0058] Figure 2 is a curve of a first weight coefficient and a vehicle speed difference when K=1 provided in an embodiment of the present application;

[0059] Figure 3 is a curve of the first weight coefficient and the vehicle speed difference when K=3 provided in an embodiment of the present application;

[0060] Figure 4 is a curve of the first weight coefficient and the vehicle speed difference when K=5 provided in an embodiment of the present application;

[0061] Figure 5 It is a schematic diagram of the structure of a device for detecting the actual speed of an unmanned vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application is described in detail below in conjunction with the accompanying drawings and embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other implementation methods obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0063] In the field of autonomous driving, in order to ensure driving safety, it is necessary to accurately obtain the actual speed of the unmanned vehicle. The relevant technology generally determines the actual speed by positioning the vehicle speed. However, the positioning speed sometimes deviates greatly from the actual speed, resulting in inaccurate vehicle control based on the positioning speed.

[0064] Therefore, in order to solve the above technical problems, the present application provides a solution that integrates the transmission speed and the positioning speed when starting from a short distance, such as Figure 1 As shown, the present application provides a method for detecting the actual speed of an unmanned vehicle, comprising:

[0065] S11: Identify the movement scene of the unmanned vehicle; that is, first identify whether the unmanned vehicle is starting from a short distance, because when it is not starting from a short distance, even if there is a delay in positioning the vehicle speed, due to the long planned distance, it can be adjusted later and will not exceed the planned distance.

[0066] It should be emphasized that short-distance starting refers to the vehicle starting from a stationary state to a short distance; optionally, short-distance starting can be the state in which the vehicle returns to a stationary state after starting from a stationary state with a short distance; optionally, short-distance starting can be the state in which the vehicle continues to move after starting from a stationary state with a short distance. The short-distance starting in this application can be the previous stage in this situation (i.e. the stage in which the vehicle starts from a stationary state through a short distance and reaches a certain speed threshold), and the latter stage can be acceleration, deceleration or constant speed driving based on the speed threshold, which is not specifically limited in this application. The short distance is determined according to the actual situation.

[0067] As a preferred implementation method of the embodiment of the present application, identifying the motion scene of the unmanned vehicle includes:

[0068] According to the current vehicle state of the unmanned vehicle and the trajectory planning issued by the planning module of the unmanned vehicle, the movement scene of the unmanned vehicle is identified; wherein, when the current vehicle state is a parking state and the trajectory planning is less than the corresponding threshold, the movement scene of the unmanned vehicle is identified as a short-distance start. It should be noted that the trajectory planning is the trajectory of the accurate driving of the unmanned vehicle. The trajectory can only include the route (i.e., direction and distance), or a speed limit can be added on the basis of the route.

[0069] Preferably, when the handbrake of the driverless vehicle is in a pulled-up state and the current gear position of the driverless vehicle is N gear, it is determined that the current vehicle state is a parking state.

[0070] Alternatively, when the first vehicle speed and the second vehicle speed are both 0 or when the first vehicle speed and the second vehicle speed are both 0 for a preset period of time, it is determined that the current vehicle state is a parking state, the first vehicle speed is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned vehicle (i.e., the gearbox speed), and the second vehicle speed is the movement speed of the unmanned vehicle in the spatial coordinate system obtained by the sensor of the unmanned vehicle (i.e., the positioning speed).

[0071] In addition, when the trajectory planning is a parking distance, when the parking distance is less than a first preset distance, the trajectory planning is less than a corresponding threshold; the parking distance is the moving distance of the unmanned vehicle after starting from a parking state to being in a parking state again.

[0072] And / or, in the case where the trajectory planning is a starting distance, when the starting distance is less than a second preset distance, the trajectory planning is less than a corresponding threshold. The starting distance is the moving distance when the unmanned vehicle starts from a parking state and reaches a preset motion state, where the preset motion state can be reaching a preset speed or reaching a preset location.

[0073] S12: When it is identified that the movement scene of the unmanned vehicle is a short-distance start, control is performed to enter a vehicle speed fusion mode, wherein the vehicle speed fusion mode is a mode in which an actual vehicle speed is obtained by fusing a first vehicle speed and a second vehicle speed.

[0074] That is, in this embodiment, when it is determined that the movement scene of the unmanned vehicle is a short-distance start, the vehicle speed fusion mode is directly entered. However, in actual situations, when the difference between the first vehicle speed and the second vehicle speed is not large, it is not meaningful to perform vehicle speed fusion, and the quality of the final fused vehicle speed will be affected by the disturbance of the gearbox (such as motor damping, etc.).

[0075] Therefore, as another optional implementation method of the embodiment of the present application, the speed difference between the first speed and the second speed is detected; when it is identified that the movement scene of the unmanned vehicle is a short-distance start and the speed difference is greater than the difference threshold, the control enters the speed fusion mode. That is, in the case of a short-distance start, the speed fusion mode is entered only when the speed difference is greater than the difference threshold. In the case of a short-distance start, if the speed difference is less than or equal to the difference threshold, the second speed is directly used as the actual speed, or the second speed is processed in a certain way and used as the actual speed. The processing may include taking the average of the second speed within a certain period of time as the actual speed. Alternatively, it is determined whether the current second speed is greater than a preset threshold. If it is, the second speed at the previous moment is used as the actual speed or the preset threshold is used as the actual speed.

[0076] S13: In the vehicle speed fusion mode, determining an actual vehicle speed based on the first vehicle speed and the second vehicle speed.

[0077] As a preferred implementation of the embodiment of the present application, determining the actual vehicle speed based on the first vehicle speed and the second vehicle speed includes:

[0078] Detect the speed difference between the first vehicle speed and the second vehicle speed; determine a first weight coefficient for the first vehicle speed and a second weight coefficient for the second vehicle speed based on the speed difference; perform weighted processing based on the first weight coefficient and the first vehicle speed, and the second weight coefficient and the second vehicle speed to obtain the actual vehicle speed.

[0079] Wherein, based on the vehicle speed difference, respectively determining a first weight coefficient for the first vehicle speed and a second weight coefficient for the second vehicle speed comprises:

[0080] The first weight coefficient is calculated by the following objective function:

[0081]

[0082] in, represents the first weight coefficient, represents the specified coefficient, represents the vehicle speed difference;

[0083] The value obtained by subtracting the first weight coefficient from 1 is used as the second weight coefficient.

[0084] Actual vehicle speed = first weight coefficient * first vehicle speed + second weight coefficient * second vehicle speed.

[0085] Due to different designated coefficients, the first weight coefficient is different for the same vehicle speed difference. Figure 2-Figure 4 As shown in FIG. 1 , the curves of the first weight coefficient and the vehicle speed difference when K=1, K=3 and K=5 are respectively given. Among them, Figure 2-Figure 4 The horizontal axis is the vehicle speed difference, and the vertical axis is the first weight coefficient.

[0086] Therefore, when determining the actual vehicle speed, it is necessary to determine the value of the specified coefficient. In one embodiment, the first weight coefficient is also related to at least the following parameters:

[0087] Hardware parameters of the gearbox;

[0088] Hardware parameters of the sensor; exemplarily, hardware parameters of an inertial navigation system;

[0089] The positioning signal parameters of the unmanned vehicle.

[0090] The first weight coefficient is directly determined based on the above parameters, or a specified coefficient is determined based on the above parameters.

[0091] In another embodiment, it also includes:

[0092] Acquire multiple sample data collected by the unmanned driving sample vehicle, the sample data including a first speed sample, a second speed sample and an actual vehicle speed sample, wherein the first speed sample is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned driving sample vehicle, and the second speed sample is the movement speed of the unmanned driving sample vehicle in the spatial coordinate system obtained by the sensor of the unmanned driving sample vehicle; use the multiple sample data to train a specified function to obtain the specified coefficient, wherein the specified function at least includes the target function.

[0093] That is, the first speed sample, the second speed sample and the actual speed sample of the unmanned driving sample vehicle are collected in advance, and then the objective function is trained based on the actual test to obtain the value of the specified coefficient.

[0094] It should be noted that the objective function in the embodiment of the present application is a function with a good fitting effect obtained in actual testing. Based on the same method, other functions with a good fitting effect can also be used. That is, the specified function can be a function of the corresponding relationship between the vehicle speed difference and the first weight coefficient (or the second weight coefficient) obtained by fitting based on actual testing. In this way, when the vehicle speed difference is known, the first weight coefficient (or the second weight coefficient) can be obtained by the specified coefficient.

[0095] Alternatively, the specified function may be a function obtained based on the corresponding relationship between the first vehicle speed and the second vehicle speed and the actual vehicle speed, that is, when the first vehicle speed and the second vehicle speed are known, the actual vehicle speed can be directly obtained through the specified function.

[0096] It should be noted that, when it is identified that the motion scene of the unmanned vehicle is not a short-distance start, the control enters the first vehicle speed detection mode, wherein the first vehicle speed detection mode is used to determine the actual vehicle speed based on the specified vehicle speed, and the specified vehicle speed includes the second vehicle speed and does not include the first vehicle speed; in the first vehicle speed detection mode, the actual vehicle speed is determined based on the specified vehicle speed. Exemplarily, the second vehicle speed is directly used as the actual vehicle speed. Alternatively, the second vehicle speed is processed as the actual vehicle speed, and the processing may include taking the average of the second vehicle speed within a certain time period as the actual vehicle speed. Alternatively, it is determined whether the current second vehicle speed is greater than a preset threshold. If it is, the second vehicle speed at the previous moment is used as the actual vehicle speed or the preset threshold is used as the actual vehicle speed.

[0097] As a preferred implementation method of the embodiment of the present application, it also includes:

[0098] When a preset condition is met, the vehicle speed fusion mode is exited, and the preset condition includes at least one of the following:

[0099] The actual vehicle speed is greater than the preset vehicle speed; because when starting in a short distance, the vehicle speed will not be too high, but will be within a certain range. Therefore, when the actual vehicle speed is greater than the preset vehicle speed, it means that it is no longer a short distance start, so it is necessary to exit the vehicle speed fusion mode.

[0100] The duration of entering the vehicle speed fusion mode exceeds the preset duration; because the moving distance of a short-distance start is limited, the duration of the vehicle speed fusion mode is destined not to be too long. Therefore, when the duration of entering the vehicle speed fusion mode exceeds the preset duration, even if the actual vehicle speed is not greater than the preset speed, the vehicle speed fusion mode will be exited at this time.

[0101] The vehicle is detected to be stopped. When the vehicle stops, it means that the short-distance start has ended and there is no need to determine the actual vehicle speed. The vehicle is detected to be stopped by detecting that the handbrake of the vehicle is pulled up again and the current gear is N gear, or the first speed and the second speed are both 0, or the first speed and the second speed are both 0 for a preset time.

[0102] The detection method of the actual speed of the unmanned vehicle provided in the embodiment of the present application first identifies the motion scene of the unmanned vehicle, and when the motion scene of the unmanned vehicle is identified as a short-distance start, the control enters the vehicle speed fusion mode, and then in the vehicle fusion mode, the actual vehicle speed is determined based on the first vehicle speed and the second vehicle speed, wherein the first vehicle speed is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned vehicle, and the second vehicle speed is the motion speed of the unmanned vehicle in the spatial coordinate system obtained by the sensor of the unmanned vehicle. That is, when starting in a short distance, the actual vehicle speed is determined by the first vehicle speed and the second vehicle speed. Compared with only using the second vehicle speed as the actual vehicle speed, it can effectively solve the problem of excessive deviation between the positioning vehicle speed and the actual vehicle speed, and obtain an accurate actual vehicle speed, thereby realizing accurate control of the vehicle.

[0103] In order to more clearly illustrate the solution of this application, a specific implementation method is provided below, which is divided into two main processes, namely, vehicle speed fusion scene recognition and vehicle speed fusion algorithm design:

[0104] 1. Vehicle speed fusion scene recognition:

[0105] Taking into account the characteristics of the current transmission speed (i.e. the first speed) and the positioning speed (i.e. the second speed), delays are more likely to occur in the case of short-distance starting. In other working conditions, the positioning speed has the advantages of high precision and accuracy compared to the transmission speed, so speed fusion needs to be limited to short-distance starting.

[0106] Identifying short-distance starts is mainly based on the current vehicle status and the trajectory issued by the autonomous vehicle planning module. The specific rules are as follows:

[0107] {Pull up the handbrake}&&{Shift to N gear}&&{(parking distance < 2m)||(total length of planned trajectory < 4m)}.

[0108] If the above rules are met, it is judged as a short-distance start, which requires the transmission speed and positioning speed to be integrated.

[0109] The exit condition of vehicle speed fusion is the end of the short-distance start process. The specific rules are as follows:

[0110] {The vehicle speed is greater than a certain threshold}||{The vehicle speed fusion time exceeds a certain threshold}||{(The vehicle is shifted into N gear again)&&(The handbrake is pulled)}.

[0111] 2. Vehicle speed fusion algorithm design:

[0112] Because the delay of the positioning speed has a greater impact mainly when starting, the overall speed fusion strategy is to prefer the one with a greater speed between the transmission speed and the positioning speed.

[0113] When the vehicle starts a short distance, take the difference between the transmission speed and the positioning speed (in kilometers per hour, km / h), and then multiply it by the specified coefficient , imported into the objective function. The output of the objective function is used as the weight coefficient to update the actual speed value. The following is the specific update rule:

[0114] (1)

[0115] in,

[0116] It is the difference between the transmission speed and the positioning speed, that is, the speed difference;

[0117] is the transmission speed;

[0118] is the positioning vehicle speed;

[0119] (2)

[0120] in,

[0121] is the first weight coefficient;

[0122] are the specified coefficients of the objective function;

[0123] (3)

[0124] in,

[0125] is the actual vehicle speed used in the control algorithm;

[0126] In the short-distance start Will always be updated according to the above algorithm and weights, with the following exceptions:

[0127] The difference between the positioning speed and the transmission speed is less than a certain threshold. At this time, according to formulas (1) and (2), we can know that the weights of the positioning speed and the transmission speed should be around 0.5. At this time, it is meaningless to do fusion, and the quality of the final fusion speed will be affected by the disturbance of the transmission (such as motor damping, etc.). Therefore, the positioning speed is directly used as the actual speed.

[0128] like Figure 2-Figure 4 As shown (where Figure 2-Figure 4 The horizontal axis is the speed difference , the ordinate is the first weight coefficient ), the larger the specified coefficient K is, the faster the objective function converges, which means that under the same speed difference, the actual speed used will tend to be the speed with a larger value. When the specified coefficient K is 5, assuming that the speed difference (i.e. ) is 1km / h, and the higher speed has a weight of more than 99%. Therefore, it is necessary to select the appropriate specified coefficient according to the characteristics of the actual transmission speed and positioning speed.

[0129] Based on the same inventive concept, Figure 5 As shown, the present application provides a device 50 for detecting the actual speed of an unmanned vehicle, comprising:

[0130] The scene recognition module 51 is used to recognize the motion scene of the unmanned vehicle.

[0131] Identifying the motion scene of the unmanned vehicle includes:

[0132] Identifying a motion scene of the unmanned vehicle according to a current vehicle state of the unmanned vehicle and a trajectory plan issued by a planning module of the unmanned vehicle;

[0133] Among them, when the current vehicle state is a parking state and the trajectory planning is less than a corresponding threshold, the movement scene of the unmanned vehicle is identified as a short-distance start.

[0134] It should be noted that, when the handbrake of the driverless vehicle is in a pulled-up state and the current gear position of the driverless vehicle is the N gear, it is determined that the current vehicle state is a parking state.

[0135] In the case where the trajectory planning is a parking distance, when the parking distance is less than a first preset distance, the trajectory planning is less than a corresponding threshold;

[0136] And / or, in a case where the trajectory planning is a starting distance, when the starting distance is less than a second preset distance, the trajectory planning is less than a corresponding threshold.

[0137] The mode control module 52 is used to control the vehicle to enter a vehicle speed fusion mode when it is identified that the movement scene of the unmanned vehicle is a short-distance start; wherein the vehicle speed fusion mode is a mode in which an actual vehicle speed is obtained by fusing a first vehicle speed and a second vehicle speed, wherein the first vehicle speed is used to represent the rotation speed of the wheels connected to the gearbox of the unmanned vehicle, and the second vehicle speed is the movement speed of the unmanned vehicle in a spatial coordinate system obtained by a sensor of the unmanned vehicle;

[0138] In another embodiment, when it is identified that the movement scene of the unmanned vehicle is a short-distance start, controlling entry into the vehicle speed fusion mode includes: detecting the speed difference between the first vehicle speed and the second vehicle speed; when it is identified that the movement scene of the unmanned vehicle is a short-distance start and the speed difference is greater than a difference threshold, controlling entry into the vehicle speed fusion mode.

[0139] It should be noted that, when it is identified that the motion scene of the unmanned vehicle is not a short-distance start, the control enters the first vehicle speed detection mode, wherein the first vehicle speed detection mode is used to determine the actual vehicle speed based on the specified vehicle speed, and the specified vehicle speed includes the second vehicle speed and does not include the first vehicle speed;

[0140] In the first vehicle speed detection mode, the actual vehicle speed is determined based on the designated vehicle speed.

[0141] The vehicle speed determination module 53 is configured to determine the actual vehicle speed based on the first vehicle speed and the second vehicle speed in the vehicle speed fusion mode.

[0142] Determining the actual vehicle speed based on the first vehicle speed and the second vehicle speed includes:

[0143] Detect the speed difference between the first vehicle speed and the second vehicle speed; determine a first weight coefficient for the first vehicle speed and a second weight coefficient for the second vehicle speed based on the speed difference; perform weighted processing based on the first weight coefficient and the first vehicle speed, and the second weight coefficient and the second vehicle speed to obtain the actual vehicle speed.

[0144] Wherein, based on the vehicle speed difference, respectively determining a first weight coefficient for the first vehicle speed and a second weight coefficient for the second vehicle speed comprises:

[0145] The first weight coefficient is calculated by the following objective function:

[0146]

[0147] in, represents the first weight coefficient, represents the specified coefficient, represents the vehicle speed difference;

[0148] The value obtained by subtracting the first weight coefficient from 1 is used as the second weight coefficient.

[0149] In one embodiment, the first weight coefficient is also related to at least the following parameters:

[0150] Hardware parameters of the gearbox;

[0151] Hardware parameters of the sensor;

[0152] The positioning signal parameters of the unmanned vehicle.

[0153] In another embodiment, it also includes:

[0154] Acquire multiple sample data collected by the unmanned driving sample vehicle, the sample data including a first speed sample, a second speed sample and an actual vehicle speed sample, wherein the first speed sample is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned driving sample vehicle, and the second speed sample is the movement speed of the unmanned driving sample vehicle in the spatial coordinate system acquired by the sensor of the unmanned driving sample vehicle;

[0155] The designated function is trained using the plurality of sample data to obtain the designated coefficients, wherein the designated function at least includes the target function.

[0156] In addition, the vehicle speed fusion mode is exited when a preset condition is met, and the preset condition includes at least one of the following:

[0157] The actual vehicle speed is greater than the preset vehicle speed;

[0158] The duration of entering the vehicle speed fusion mode exceeds the preset duration;

[0159] The vehicle is detected to be stopped.

[0160] The detection device for the actual speed of the unmanned vehicle provided in the embodiment of the present application first identifies the movement scene of the unmanned vehicle, and when the movement scene of the unmanned vehicle is identified as a short-distance start, controls the vehicle to enter the vehicle speed fusion mode, and then in the vehicle fusion mode, determines the actual vehicle speed based on the first vehicle speed and the second vehicle speed, wherein the first vehicle speed is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned vehicle, and the second vehicle speed is the movement speed of the unmanned vehicle in the spatial coordinate system obtained by the sensor of the unmanned vehicle. That is, when starting in a short distance, the actual vehicle speed is determined by the first vehicle speed and the second vehicle speed. Compared with only using the second vehicle speed as the actual vehicle speed, it can effectively solve the problem of excessive deviation between the positioning vehicle speed and the actual vehicle speed, and obtain an accurate actual vehicle speed, thereby realizing accurate control of the vehicle.

[0161] Based on the same inventive concept, the present application provides a computer-readable storage medium having a computer program or instruction stored thereon. When the computer program or instruction is executed by a processor, the steps of the method for detecting the actual speed of an unmanned vehicle provided in the above embodiment are implemented.

[0162] Based on the same inventive concept, the present application provides an electronic device, including:

[0163] at least one processor and at least one memory;

[0164] The memory stores executable instructions of the processor;

[0165] The processor is configured to execute the method for detecting the actual speed of the unmanned vehicle provided in the above embodiment.

[0166] Based on the same inventive concept, the present application provides an unmanned vehicle, and applies the method for detecting the actual speed of the unmanned vehicle provided by the above embodiment.

[0167] The unmanned vehicle provided in the embodiment of the present application, by applying the detection method of the actual speed of the unmanned vehicle provided in the above embodiment, first identifies the motion scene of the unmanned vehicle, and when the motion scene of the unmanned vehicle is identified as a short-distance start, controls the vehicle to enter the vehicle speed fusion mode, and then in the vehicle fusion mode, determines the actual vehicle speed based on the first vehicle speed and the second vehicle speed, wherein the first vehicle speed is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned vehicle, and the second vehicle speed is the motion speed of the unmanned vehicle in the spatial coordinate system obtained by the sensor of the unmanned vehicle. That is, when starting in a short distance, the actual vehicle speed is determined by the first vehicle speed and the second vehicle speed. Compared with only using the second vehicle speed as the actual vehicle speed, it can effectively solve the problem of excessive deviation between the positioning vehicle speed and the actual vehicle speed, and obtain an accurate actual vehicle speed, thereby achieving accurate control of the vehicle.

[0168] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0169] It should be noted that, in the description of this application, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0170] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0171] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0172] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0173] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0174] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0175] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0176] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for detecting the actual speed of an unmanned vehicle, characterized in that: include: Identify motion scenes of unmanned vehicles; When it is identified that the movement scene of the unmanned vehicle is a short-distance start, control is performed to enter a vehicle speed fusion mode, wherein the vehicle speed fusion mode is a mode in which an actual vehicle speed is obtained by fusing a first vehicle speed and a second vehicle speed, wherein the first vehicle speed is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned vehicle, and the second vehicle speed is the movement speed of the unmanned vehicle in a spatial coordinate system obtained by a sensor of the unmanned vehicle; In the vehicle speed fusion mode, the actual vehicle speed is determined based on the first vehicle speed and the second vehicle speed; wherein the actual vehicle speed is determined by the difference between the first vehicle speed and the second vehicle speed. A first weight coefficient for the first vehicle speed and a second weight coefficient for the second vehicle speed are determined respectively, and weighted processing is performed according to the first weight coefficient, the first vehicle speed, the second weight coefficient and the second vehicle speed; wherein the second weight coefficient is obtained by subtracting the first weight coefficient from 1, and the first weight coefficient It is calculated by the following formula: , Indicates the specified coefficient.

2. The method according to claim 1, characterized in that When the movement scene of the unmanned vehicle is identified as a short-distance start, controlling the vehicle to enter the vehicle speed fusion mode includes: detecting a vehicle speed difference between the first vehicle speed and the second vehicle speed; When it is identified that the movement scene of the unmanned vehicle is a short-distance start and the vehicle speed difference is greater than a difference threshold, the control enters a vehicle speed fusion mode.

3. The method according to claim 1 or 2, characterized in that: Determining the actual vehicle speed based on the first vehicle speed and the second vehicle speed includes: detecting a vehicle speed difference between the first vehicle speed and the second vehicle speed; Based on the vehicle speed difference, determining a first weight coefficient for the first vehicle speed and a second weight coefficient for the second vehicle speed respectively; Based on the first weight coefficient and the first vehicle speed, and the second weight coefficient and the second vehicle speed, weighted processing is performed to obtain the actual vehicle speed.

4. The method according to claim 3, characterized in that The determining, based on the vehicle speed difference, a first weight coefficient for the first vehicle speed and a second weight coefficient for the second vehicle speed respectively comprises: The first weight coefficient is calculated by the following objective function: in, represents the first weight coefficient, represents the specified coefficient, represents the vehicle speed difference; The value obtained by subtracting the first weight coefficient from 1 is used as the second weight coefficient.

5. The method according to claim 3, characterized in that: The first weight coefficient is also related to at least the following parameters: Hardware parameters of the gearbox; Hardware parameters of the sensor; The positioning signal parameters of the unmanned vehicle.

6. The method according to claim 4, characterized in that The method further comprises: Acquire multiple sample data collected by the unmanned driving sample vehicle, the sample data including a first speed sample, a second speed sample and an actual vehicle speed sample, wherein the first speed sample is used to characterize the rotation speed of the wheels connected to the gearbox of the unmanned driving sample vehicle, and the second speed sample is the movement speed of the unmanned driving sample vehicle in a spatial coordinate system acquired by a sensor of the unmanned driving sample vehicle; The designated function is trained using the plurality of sample data to obtain the designated coefficients, wherein the designated function at least includes the target function.

7. The method according to claim 1, characterized in that The identification of the motion scene of the unmanned vehicle includes: Identifying a motion scene of the unmanned vehicle according to a current vehicle state of the unmanned vehicle and a trajectory plan issued by a planning module of the unmanned vehicle; Among them, when the current vehicle state is a parking state and the trajectory planning is less than a corresponding threshold, the movement scene of the unmanned vehicle is identified as a short-distance start.

8. The method according to claim 7, characterized in that Also includes: When the handbrake of the driverless vehicle is in a pulled-up state and the current gear position of the driverless vehicle is the N gear, it is determined that the current vehicle state is a parking state.

9. The method according to claim 7, characterized in that: Also includes: In the case where the trajectory planning is a parking distance, when the parking distance is less than a first preset distance, the trajectory planning is less than a corresponding threshold; And / or, in a case where the trajectory planning is a starting distance, when the starting distance is less than a second preset distance, the trajectory planning is less than a corresponding threshold.

10. The method according to claim 1, characterized in that Also includes: When it is recognized that the motion scene of the unmanned vehicle is not a short-distance start, controlling to enter a first vehicle speed detection mode, wherein the first vehicle speed detection mode is used to determine an actual vehicle speed based on a specified vehicle speed, wherein the specified vehicle speed includes the second vehicle speed and does not include the first vehicle speed; In the first vehicle speed detection mode, the actual vehicle speed is determined based on the designated vehicle speed.

11. The method according to claim 1 or 10, characterized in that: Also includes: When a preset condition is met, the vehicle speed fusion mode is exited, and the preset condition includes at least one of the following: The actual vehicle speed is greater than the preset vehicle speed; The duration of entering the vehicle speed fusion mode exceeds the preset duration; The vehicle is detected to be stopped.

12. A device for detecting the actual speed of an unmanned vehicle, characterized in that: include: A scene recognition module, used to identify the motion scenes of unmanned vehicles; a mode control module, configured to control the vehicle to enter a vehicle speed fusion mode when it is identified that the movement scene of the unmanned vehicle is a short-distance start; wherein the vehicle speed fusion mode is a mode in which an actual vehicle speed is obtained by fusing a first vehicle speed and a second vehicle speed, wherein the first vehicle speed is used to represent the rotation speed of the wheels connected to the gearbox of the unmanned vehicle, and the second vehicle speed is the movement speed of the unmanned vehicle in a spatial coordinate system obtained by a sensor of the unmanned vehicle; A vehicle speed determination module is used to determine the actual vehicle speed based on the first vehicle speed and the second vehicle speed in the vehicle speed fusion mode; wherein the actual vehicle speed is determined by the difference between the first vehicle speed and the second vehicle speed. A first weight coefficient for the first vehicle speed and a second weight coefficient for the second vehicle speed are determined respectively, and weighted processing is performed according to the first weight coefficient, the first vehicle speed, the second weight coefficient and the second vehicle speed; wherein the second weight coefficient is obtained by subtracting the first weight coefficient from 1, and the first weight coefficient It is calculated by the following formula: , Indicates the specified coefficient.

13. An unmanned vehicle, characterized in that: The method according to any one of claims 1 to 11 is used.

Images