Vehicle speed decision-making method and system, vehicle and equipment

Abstract

The invention discloses a vehicle speed decision-making method and system, a vehicle and equipment. The speed decision-making method of the vehicle comprises the following steps: determining a target obstacle according to a planned path of the vehicle; establishing a longitudinal model of the vehicle; performing forward simulation of the vehicle according to the state information of the vehicle and the state information of the target obstacle to obtain an input acceleration at a first moment; the input acceleration at the first moment is input into the longitudinal model, so that state variables of the vehicle at a second moment are obtained according to the input acceleration at the first moment and the position, speed, acceleration and jerk of the vehicle at the first moment, and the second moment is the next moment of the first moment; and determining a speed planning curve of the vehicle according to the obtained state variable of the vehicle. By adopting the method and the device, the state of the vehicle is updated by applying the vehicle longitudinal model, so that the lane forward simulation is closer to the real state of the kinematics of the vehicle, and the speed decision performance is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a speed decision method and system of a vehicle, a vehicle and equipment. BACKGROUND

[0002] Vehicle speed decision technology is one of the key technologies of automatic driving, and is also a basic problem and necessary condition for researching intelligent vehicles. Vehicle speed decision technology is to calculate a speed curve that meets safety, comfort and feasibility according to the state of the ego vehicle and environmental information. The commonly used speed decision method is a method based on dynamic programming, which samples on the ST graph, calculates all feasible solutions of the entire time in the forward direction, searches for the result with the minimum cost in the reverse direction, and finally outputs the speed curve, that is, the result of speed decision. However, the following disadvantages exist: The speed decision method does not consider the actual vehicle model, and the generated speed curve usually does not conform to the kinematic characteristics of the vehicle; the speed curve algorithm based on dynamic programming is relatively complex and low in efficiency. SUMMARY

[0003] Therefore, it is necessary to provide a speed decision method and system of a vehicle, a vehicle and equipment to solve the above technical problems. The longitudinal model of the vehicle is applied to update the state of the ego vehicle, so that the forward simulation of the lane is closer to the real state of the kinematics of the ego vehicle, and the performance of speed decision is improved. In addition, the speed decision of the embodiments of the present application is fast and efficient, and thus the safety and reliability of the ego vehicle can be improved.

[0004] In a first aspect, a speed decision method of a vehicle is provided, comprising: determining a target obstacle according to a planned path of the vehicle; establishing a longitudinal model of the vehicle, wherein the longitudinal model comprises state variables and control variables, the state variables comprise a position, a speed, an acceleration and a jerk of the vehicle, and the control variables comprise an input acceleration; performing forward simulation of the vehicle according to state information of the vehicle and state information of the target obstacle to obtain an input acceleration at a first time; inputting the input acceleration at the first time into the longitudinal model to obtain state variables of the vehicle at a second time according to the input acceleration at the first time and the position, the speed, the acceleration and the jerk of the vehicle at the first time, wherein the second time is a next time of the first time; determining a speed planning curve of the vehicle according to the obtained state variables of the vehicle.

[0005] In some examples, the determining of the target obstacle according to the planned path of the vehicle comprises: searching for an obstacle on the planned path which has a collision risk with the vehicle according to the planned path of the vehicle; calculating a longitudinal distance between each obstacle and the vehicle after the obstacle which has a collision risk with the vehicle is screened out; determining the target obstacle according to the longitudinal distance between each obstacle and the vehicle.

[0006] In some examples, before the longitudinal model of the vehicle is established, further comprising: obtaining the speed of the target obstacle at the current time and the speed at the previous time; obtaining the acceleration of the target obstacle according to the speed of the target obstacle at the current time and the speed at the previous time.

[0007] In some examples, the longitudinal model of the vehicle is established, comprising: establishing a vehicle longitudinal model in the frequency domain; converting the vehicle longitudinal model in the frequency domain into a time domain model; converting the time domain model into a state control model; performing current discretization processing on the state control model to obtain a discretized model in the time domain, and abstracting the longitudinal model of the vehicle according to the discretized model in the time domain.

[0008] In some examples, the forward simulation of the vehicle is performed according to the state information of the vehicle and the state information of the target obstacle to obtain the input acceleration at the first time, comprising: initializing the longitudinal model of the vehicle according to the state information of the vehicle; calculating a target reference vehicle speed and an expected following distance without obstacles; obtaining an expected acceleration, an economic acceleration, a cruise acceleration and a safe deceleration; obtaining the input acceleration at the first time according to the expected acceleration, the economic acceleration, the cruise acceleration and the safe deceleration.

[0009] In some examples, the input acceleration at the first time is input into the longitudinal model to obtain the state variables of the vehicle at the second time according to the input acceleration at the first time and the position, speed, acceleration and jerk of the vehicle at the first time, comprising: inputting the input acceleration at the first time into the longitudinal model to update the position, speed, acceleration and jerk of the vehicle at the second time through the longitudinal model.

[0010] In some examples, the speed planning curve of the vehicle is determined according to the obtained state variables of the vehicle, comprising: According to the obtained state variable of the vehicle, a speed curve is obtained; The speed curve is smoothed to obtain the speed planning curve.

[0011] In a second aspect, a speed decision system of a vehicle is provided, comprising: A determination module is configured to determine a target obstacle according to a planning path of the vehicle; A building module is configured to build a longitudinal model of the vehicle, wherein the longitudinal model comprises state variables and control variables, the state variables comprise position, speed, acceleration and jerk of the vehicle, and the control variables comprise input acceleration; A forward simulation module is configured to perform forward simulation of the vehicle according to state information of the vehicle and state information of the target obstacle, to obtain input acceleration at a first time; A state variable obtaining module is configured to input the input acceleration at the first time into the longitudinal model, to obtain state variables of the vehicle at a second time according to the input acceleration at the first time and the position, speed, acceleration and jerk of the vehicle at the first time, wherein the second time is a next time of the first time; A speed decision module is configured to determine a speed planning curve of the vehicle according to the obtained state variables of the vehicle.

[0012] In a third aspect, a vehicle is provided, comprising the speed decision system of the vehicle according to the second aspect described above.

[0013] In a fourth aspect, a computer device is provided, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, when the processor executes the program, the steps of the speed decision method of the vehicle according to the first aspect and any possible implementation manner of the first aspect are implemented.

[0014] In a fifth aspect, a computer readable storage medium is provided, which stores a computer program, when the program is executed by a processor, the steps of the speed decision method of the vehicle according to the first aspect and any possible implementation manner of the first aspect are implemented.

[0015] In a sixth aspect, a computer program product is provided, which stores a computer program, when the program is executed by a processor, the steps of the speed decision method of the vehicle according to the first aspect and any possible implementation manner of the first aspect are implemented.

[0016] According to the embodiments of the present application, the target obstacle can be determined according to the planned path of the vehicle, the longitudinal model of the vehicle is established, then the forward simulation of the vehicle is performed according to the state information of the vehicle and the state information of the target obstacle, the input acceleration is obtained, finally, the input acceleration is input into the longitudinal model, so as to predict the state variables of the vehicle at the future time according to the input acceleration and the position, speed, acceleration and jerk of the vehicle, and ultimately, the speed planning curve of the vehicle is determined according to the predicted state variables of the vehicle. Thus, the state of the ego vehicle is updated by applying the longitudinal model of the vehicle, so that the forward simulation of the lane is closer to the real state of the kinematics of the ego vehicle, and the performance of the speed decision is improved. In addition, the speed decision of the embodiments of the present application is fast and efficient, and thus the safety and reliability of the ego vehicle can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] Other features, objects, and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments thereof as read with reference to the accompanying drawings: Figure 1 A flowchart of a speed decision method of a vehicle according to an embodiment of the present application is provided. Figure 2 A schematic diagram of a speed decision scene in a speed decision method of a vehicle according to an embodiment of the present application is provided. Figure 3 A flowchart of a speed decision method of a vehicle according to another embodiment of the present application is provided. Figure 4 A structural block diagram of a speed decision system of a vehicle according to an embodiment of the present application is provided. Figure 5 A structural block diagram of a computer device according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0018] The present application will be further described below in conjunction with embodiments and drawings. It can be understood that the specific embodiments described herein are only used to explain the related application, but not to limit the application. In addition, it should be noted that only parts related to the application are shown in the drawings for the convenience of description.

[0019] It should be noted that the features of the embodiments in the present application, i.e. the features of the embodiments, can be combined with each other without conflict. The present application will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0020] The speed decision method, system, vehicle and device of a vehicle according to the embodiments of the present application will be described in detail below in conjunction with the drawings.

[0021] Figure 1 A flowchart of a speed decision method of a vehicle according to an embodiment of the present application is provided. As shown in FIG. 1, the speed decision method of the vehicle according to the embodiment of the present application includes the following steps. Figure 1As shown, the vehicle speed decision method according to an embodiment of this application includes the following steps: S101: Identify the target obstacle based on the vehicle's planned path.

[0022] In one embodiment of this application, determining a target obstacle based on the vehicle's planned path includes: searching for obstacles on the planned path that pose a collision risk to the vehicle; after filtering out obstacles that pose a collision risk to the vehicle, calculating the longitudinal distance between each obstacle and the vehicle; and determining the target obstacle based on the longitudinal distance between each obstacle and the vehicle.

[0023] like Figure 2 As shown, and in combination Figure 3 The process of identifying target obstacles based on the vehicle's planned path is essentially the process of searching for target obstacles. Specifically, this search involves: based on the vehicle's planned path, searching for obstacles that pose a collision risk along that path, i.e., whether the vehicle's (the vehicle's) geometric bounding box overlaps with that of other obstacles on the planned path. After filtering for obstacles with collision risk, the longitudinal distance of each obstacle from the vehicle's position is calculated. ,in, It can be obtained through the following formula:

[0024] in, The longitudinal position of the vehicle along the arc length on the planned path. This represents the longitudinal position of the vehicle along the planned path, where the arc length is measured.

[0025] After calculating the above distances, all distances are sorted from smallest to largest, and the obstacle with the smallest distance is selected as the target obstacle, such as... Figure 2 As shown, obstacle 3 is the target obstacle.

[0026] S102: Establish a longitudinal model of the vehicle, wherein the longitudinal model includes state variables and control variables, the state variables include the vehicle's position, velocity, acceleration, and jerk, and the control variables include the input acceleration.

[0027] In one embodiment of this application, before establishing the longitudinal model of the vehicle, the method further includes: obtaining the current velocity and the previous velocity of the target obstacle; and obtaining the acceleration of the target obstacle based on the current velocity and the previous velocity.

[0028] Specifically, in order to obtain better safety and comfort, the acceleration of the target obstacle needs to be calculated. Among them, the target obstacle ID at the current time is the same as the target obstacle ID at the last time, that is, when the target obstacle is the same obstacle, then

[0029] Among them, is the acceleration of the target obstacle, is the speed of the target obstacle, is the speed of the target obstacle at the last time, is the time interval. It can be obtained by pre-calibration.

[0030] In order to ensure smoothness, the mean filter is used for the acceleration of the target obstacle, and the filter period is 10 periods for example, then

[0031] Of course, if the obstacle ID at the current time is different from the obstacle ID at the last time, the acceleration of the target obstacle is not calculated, and the target obstacle ID at the last time is updated to the obstacle ID at the current time.

[0032] In an embodiment of the present application, a longitudinal model of a vehicle is established, including: establishing a frequency domain vehicle longitudinal model; converting the frequency domain vehicle longitudinal model into a time domain model; converting the time domain model into a state control model; performing current discretization processing on the state control model to obtain a time domain discretization model, and abstracting the longitudinal model of the vehicle according to the time domain discretization model.

[0033] Specifically, since the vehicle has inertia, after inputting the acceleration control to the vehicle, the vehicle cannot immediately reach the required acceleration. In order to more likely approach the performance of the real vehicle, the frequency domain vehicle longitudinal model is established as follows:

[0034] Among them, is the input acceleration in the frequency domain, is the output acceleration in the frequency domain, is the cut-off frequency, is the damping coefficient, and It can be pre-calibrated according to vehicle data.

[0035] Since the frequency domain model cannot be directly used, the above frequency domain is converted into a time domain model as follows:

[0036] Among them, is the acceleration second derivative of the velocity, i.e. jerk.

[0037] The above model is converted into a state control model, with state variables being (position, velocity, acceleration, jerk), and control variables being (input acceleration), as follows:

[0038] Then, linear discretization is performed, with a time interval of, for example, , to obtain a discrete-time model, as follows:

[0039] Therefore, when the current state of the vehicle is obtained , and then an acceleration instruction at the current time is input , the state of the vehicle after T time can be obtained .

[0040] In the subsequent lane forward simulation, the update of the state of the ego vehicle uses the model, which is abstracted as follows: .

[0041] S103: Perform forward simulation of the vehicle according to the state information of the vehicle and the state information of the target obstacle, to obtain an input acceleration at the first time.

[0042] In an embodiment of the present application, the forward simulation of the vehicle is performed according to the state information of the vehicle and the state information of the target obstacle, to obtain an input acceleration at the first time, including: initializing the longitudinal model of the vehicle according to the state information of the vehicle; calculating a target reference vehicle speed and an expected following distance; obtaining an expected acceleration, an economic acceleration, a cruise acceleration and a safe deceleration; and obtaining the input acceleration at the first time according to the expected acceleration, the economic acceleration, the cruise acceleration and the safe deceleration.

[0043] Specifically, for the forward simulation of the vehicle, including: The state information of the ego vehicle is known as follows: position and , arc length position on the reference line , velocity , acceleration , maximum acceleration and , minimum following safety distance and following time .

[0044] The state information of the target obstacle in front is known as follows: position and arc length position on the reference line velocity and acceleration .

[0045] Initialize vehicle longitudinal model state variables using the ego vehicle's state information .

[0046] Carry out lane forward simulation, total length of time is set to , time interval is set to , at each time, the calculation content is as follows: Calculate the obstacle-free target reference vehicle speed .

[0047] Obtain the map speed limit and obtain the cruise speed .

[0048] Calculate the kinematically feasible minimum speed .

[0049] Obstacle-free target reference vehicle speed .

[0050] Calculate the expected following distance .

[0051] Calculate the expected following distance

[0052] Calculate the minimum expected distance , where is the minimum distance change amount, usually .

[0053] Calculate the maximum expected distance , where is the maximum distance change amount, usually , which can be different from the minimum distance change amount.

[0054] Calculate the economic expected distance and the obstacle target reference vehicle speed : If the obstacle is greater than the maximum expected distance , then , , where is the distance gain coefficient of the reference vehicle speed.

[0055] If the obstacle is less than the minimum expected distance , then , .

[0056] otherwise, , .

[0057] compute the expected acceleration .

[0058] compute the relative distance, .

[0059] compute the distance error, .

[0060] compute the velocity compensation, where is the velocity compensation gain coefficient.

[0061] velocity compensation limit, where and are the maximum and minimum values of the velocity compensation.

[0062] compute the obstacle reference velocity, .

[0063] compute the velocity error upper limit, .

[0064] compute the velocity error, .

[0065] compute the relative velocity, .

[0066] if the relative velocity then compute the relative deceleration: .

[0067] compute the acceleration compensation,

[0068] acceleration compensation limit, where, and are the maximum and minimum values of the acceleration compensation, compute the first acceleration, , compute the acceleration compensation upper limit, , compute the second acceleration, , if the second acceleration is greater than 0, , otherwise, .

[0069] Computing economic acceleration, As above, only replace the expected distance with the economic expected distance, i.e. compute the distance error, .

[0070] Computing cruise acceleration, wherein, is a cruise speed gain coefficient, which can be pre-set according to experience.

[0071] Cruise acceleration minimum limit, wherein is a minimum cruise acceleration.

[0072] Computing safety deceleration: .

[0073] Computing acceleration command .

[0074] If , if , , if , .

[0075] If , if , , if , .

[0076] Cruise check, .

[0077] Safety check, , wherein wherein, is a safety deceleration minimum value.

[0078] S104: input the input acceleration at the first time into the longitudinal model to obtain the state variables of the vehicle at the second time according to the input acceleration at the first time and the position, speed, acceleration and jerk of the vehicle at the first time, wherein the second time is the next time of the first time.

[0079] In an embodiment of the present application, inputting the input acceleration at the first time into the longitudinal model to obtain the state variables of the vehicle at the second time according to the input acceleration at the first time and the position, speed, acceleration and jerk of the vehicle at the first time, comprises: inputting the input acceleration at the first time into the longitudinal model to update the position, speed, acceleration and jerk of the vehicle at the second time through the longitudinal model.

[0080] That is, the acceleration instruction is input to the vehicle longitudinal model as follows: .

[0081] The ego vehicle position is updated as follows: .

[0082] The ego vehicle speed is updated as follows: .

[0083] The ego vehicle acceleration is updated as follows: .

[0084] The obstacle state is updated using the uniform acceleration model as follows: The obstacle position is updated as follows: .

[0085] The obstacle speed is updated as follows: .

[0086] The obstacle acceleration is kept unchanged as follows: .

[0087] S105: According to the obtained state variables of the vehicle, a speed planning curve of the vehicle is determined.

[0088] In an embodiment of the present application, according to the obtained state variables of the vehicle, a speed planning curve of the vehicle is determined, including: obtaining a speed curve according to the obtained state variables of the vehicle; and performing smoothing processing on the speed curve to obtain the speed planning curve. That is, after the lane forward simulation is completed, the state variables (position, speed, acceleration, jerk) of the ego vehicle from 0s to 8s are obtained, which are encapsulated as a speed curve, smoothed, and finally sent to a control module for speed control of the vehicle.

[0089] According to the vehicle speed decision method of the embodiment of the present application, the target obstacle can be determined according to the planning path of the vehicle, the longitudinal model of the vehicle is established, then the forward simulation of the vehicle is performed according to the state information of the vehicle and the state information of the target obstacle, the input acceleration is obtained, finally, the input acceleration is input to the longitudinal model, so as to predict the state variables of the vehicle at a future time according to the input acceleration and the position, speed, acceleration and jerk of the vehicle. Ultimately, according to the predicted state variables of the vehicle, the speed planning curve of the vehicle is determined. Thus, the vehicle longitudinal model is applied to update the state of the ego vehicle, so that the lane forward simulation is closer to the real state of the kinematics of the ego vehicle, and the performance of the speed decision is improved. In addition, the speed decision of the embodiment of the present application is fast and efficient, and thus the safety and reliability of the ego vehicle can be improved.

[0090] Figure 4 ​is a structural block diagram of a speed decision system of a vehicle according to an embodiment of the present application. As shown in Figure 4 The speed decision system of the vehicle according to an embodiment of the present application comprises a determination module 410, a building module 420, a forward simulation module 430, a state variable acquisition module 440 and a speed decision module 450, wherein: The determination module 410 is configured to determine a target obstacle according to a planned path of the vehicle; The building module 420 is configured to build a longitudinal model of the vehicle, wherein the longitudinal model comprises state variables and control variables, the state variables comprise a position, a speed, an acceleration and a jerk of the vehicle, and the control variables comprise an input acceleration; The forward simulation module 430 is configured to perform forward simulation of the vehicle according to state information of the vehicle and state information of the target obstacle, to obtain an input acceleration at a first time; The state variable acquisition module 440 is configured to input the input acceleration at the first time into the longitudinal model, to obtain state variables of the vehicle at a second time according to the input acceleration at the first time and the position, the speed, the acceleration and the jerk of the vehicle at the first time, wherein the second time is a next time of the first time; The speed decision module 450 is configured to determine a speed planning curve of the vehicle according to the obtained state variables of the vehicle.

[0091] The speed decision system of the vehicle according to the embodiment of the present application can determine a target obstacle according to a planned path of the vehicle, build a longitudinal model of the vehicle, then perform forward simulation of the vehicle according to state information of the vehicle and state information of the target obstacle, obtain an input acceleration, finally input the input acceleration into the longitudinal model, to predict state variables of the vehicle at a future time according to the input acceleration and the position, the speed, the acceleration and the jerk of the vehicle, and ultimately determine a speed planning curve of the vehicle according to the predicted state variables of the vehicle. Thus, the longitudinal model of the vehicle is applied to update the state of the ego vehicle, so that the forward simulation of the lane is closer to the real state of the kinematics of the ego vehicle, and the performance of the speed decision is improved. In addition, the speed decision of the embodiment of the present application is fast and efficient, and thus the safety and reliability of the ego vehicle can be improved.

[0092] The specific limitation of the speed decision system of the vehicle can refer to the limitation of the speed decision method of the vehicle in the above, which will not be repeated here. The modules of the speed decision system of the vehicle can be realized by software, hardware and their combinations in whole or in part. The modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the modules.

[0093] Further, a vehicle is provided, comprising the vehicle speed decision system according to any one of the above embodiments. The vehicle can determine a target obstacle according to a planned path, establish a longitudinal model of the vehicle, then perform a forward simulation of the vehicle according to state information of the vehicle and state information of the target obstacle, obtain an input acceleration, finally input the input acceleration into the longitudinal model to predict state variables of the vehicle at a future time according to the input acceleration and the position, speed, acceleration and jerk of the vehicle, and finally determine a speed planning curve of the vehicle according to the predicted state variables of the vehicle. Thus, the longitudinal model of the vehicle is applied to update the state of the ego vehicle, so that the forward simulation of the lane is closer to the real state of the kinematics of the ego vehicle, and the performance of the speed decision is improved. In addition, the speed decision of the embodiments of the present application is fast and efficient, and thus the safety and reliability of the ego vehicle can be improved.

[0094] In addition, other configurations and effects of the vehicle according to the embodiments of the present application are known to those skilled in the art, and are not described here.

[0095] In one embodiment, a computer device is provided. Figure 5 For the structural block diagram of the computer device provided in the embodiments of the present application, reference is made to Figure 5 . The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned vehicle speed decision method embodiments when executing the computer program. For example, it is executed: determining a target obstacle according to a planned path of a vehicle; establishing a longitudinal model of the vehicle, wherein the longitudinal model includes state variables and control variables, the state variables include the position, speed, acceleration and jerk of the vehicle, and the control variables include the input acceleration; performing a forward simulation of the vehicle according to state information of the vehicle and state information of the target obstacle, to obtain an input acceleration at a first time; inputting the input acceleration at the first time into the longitudinal model to obtain state variables of the vehicle at a second time according to the input acceleration at the first time and the position, speed, acceleration and jerk of the vehicle at the first time, wherein the second time is the next time of the first time; determining a speed planning curve of the vehicle according to the obtained state variables of the vehicle.

[0096] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the processor implements the above-mentioned vehicle speed decision method embodiments when executing the computer program. For example, it is executed: determining a target obstacle according to a planned path of a vehicle; Establish a longitudinal model of the vehicle, wherein the longitudinal model includes state variables and control variables, the state variables include the vehicle's position, velocity, acceleration and jerk, and the control variables include input acceleration; Based on the vehicle's state information and the target obstacle's state information, a forward simulation of the vehicle is performed to obtain the input acceleration at the first moment. The input acceleration at the first moment is input into the longitudinal model to obtain the vehicle's state variables at the second moment based on the input acceleration at the first moment and the vehicle's position, velocity, acceleration, and jerk at the first moment, wherein the second moment is the moment following the first moment; Based on the obtained vehicle state variables, the vehicle speed planning curve is determined.

[0097] This application provides a computer program product including instructions that, when executed, cause the method described in this application embodiment to be performed. For example, it can execute... Figure 1 The steps of the vehicle speed decision-making method shown include, for example, identifying the target obstacle based on the vehicle's planned path. Establish a longitudinal model of the vehicle, wherein the longitudinal model includes state variables and control variables, the state variables include the vehicle's position, velocity, acceleration and jerk, and the control variables include input acceleration; Based on the vehicle's state information and the target obstacle's state information, a forward simulation of the vehicle is performed to obtain the input acceleration at the first moment. The input acceleration at the first moment is input into the longitudinal model to obtain the vehicle's state variables at the second moment based on the input acceleration at the first moment and the vehicle's position, velocity, acceleration, and jerk at the first moment, wherein the second moment is the moment following the first moment; Based on the obtained vehicle state variables, the vehicle speed planning curve is determined.

[0098] Those skilled in the art can understand that all or part of the processes in the method for implementing the above embodiments can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above embodiments of the method. In the embodiments provided in the present application, any reference to memory, storage, database or other medium can include at least one of non-volatile and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory. The volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0099] Any combination of the technical features of the above embodiments can be combined. In order to make the description simple, all possible combinations of the technical features of the above embodiments are not described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0100] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the patent scope of the application. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for determining the speed of a vehicle, characterized in that, include: Based on the vehicle's planned path, identify the target obstacle; Establish a longitudinal model of the vehicle, wherein the longitudinal model includes state variables and control variables, the state variables include the vehicle's position, velocity, acceleration, and jerk, and the control variables include the input acceleration; Based on the vehicle's state information and the target obstacle's state information, a forward simulation of the vehicle is performed to obtain the input acceleration at the first moment. The input acceleration at the first moment is input into the longitudinal model to obtain the vehicle's state variables at the second moment based on the input acceleration at the first moment and the vehicle's position, velocity, acceleration, and jerk at the first moment, wherein the second moment is the moment following the first moment; Based on the obtained vehicle state variables, the vehicle speed planning curve is determined.

2. The vehicle speed decision method according to claim 1, characterized in that, The process of determining the target obstacle based on the vehicle's planned path includes: Based on the vehicle's planned path, search for obstacles on the planned path that pose a collision risk to the vehicle; After identifying obstacles that pose a collision risk to the vehicle, the longitudinal distance between each obstacle and the vehicle is calculated. The target obstacles are determined based on the longitudinal distance between each obstacle and the vehicle.

3. The vehicle speed decision method according to claim 1, characterized in that, Before building the longitudinal model of the vehicle, the following steps are also included: Obtain the current velocity and the previous velocity of the target obstacle; The acceleration of the target obstacle is obtained based on its current velocity and its velocity at the previous moment.

4. The vehicle speed decision method according to claim 1, characterized in that, The process of establishing the longitudinal model of the vehicle includes: Establish a longitudinal model of the vehicle in the frequency domain; The longitudinal vehicle model in the frequency domain is converted into a time domain model; The time-domain model is converted into a state control model; The state control model is discretized to obtain a time-domain discretized model, and the longitudinal model of the vehicle is abstracted based on the time-domain discretized model.

5. The vehicle speed decision method according to any one of claims 1-4, characterized in that, The step of performing forward simulation of the vehicle based on the vehicle's state information and the target obstacle's state information to obtain the input acceleration at the first moment includes: The longitudinal model of the vehicle is initialized based on the vehicle's state information; Calculate the reference speed and expected following distance for unobstructed targets; Achieve desired acceleration, economic acceleration, cruising acceleration, and safe deceleration; The input acceleration at the first moment is obtained based on the desired acceleration, economic acceleration, cruise acceleration, and safe deceleration.

6. The vehicle speed decision method according to claim 5, characterized in that, The step of inputting the input acceleration at the first moment into the longitudinal model to obtain the vehicle's state variables at the second moment based on the input acceleration at the first moment and the vehicle's position, velocity, acceleration, and jerk at the first moment includes: The input acceleration at the first moment is input into the longitudinal model to update the vehicle's position, velocity, acceleration, and jerk at the second moment through the longitudinal model.

7. The vehicle speed decision method according to claim 6, characterized in that, The step of determining the vehicle's speed planning curve based on the obtained vehicle state variables includes: Based on the obtained vehicle state variables, the speed curve is obtained; The speed curve is smoothed to obtain the speed planning curve.

8. A vehicle speed decision system, characterized in that, include: The determination module is used to identify target obstacles based on the vehicle's planned path; A module is established to build a longitudinal model of the vehicle, wherein the longitudinal model includes state variables and control variables, the state variables include the vehicle's position, velocity, acceleration, and jerk, and the control variables include the input acceleration; The forward simulation module is used to perform forward simulation of the vehicle based on the vehicle's state information and the target obstacle's state information, and to obtain the input acceleration at the first moment. The state variable acquisition module is used to input the input acceleration at the first moment into the longitudinal model, so as to obtain the state variables of the vehicle at the second moment based on the input acceleration at the first moment and the vehicle's position, velocity, acceleration and jerk at the first moment, wherein the second moment is the moment after the first moment; The speed decision module is used to determine the vehicle's speed planning curve based on the obtained vehicle state variables.

9. A vehicle, characterized in that, include: The vehicle speed decision system according to claim 8.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the vehicle speed decision method according to any one of claims 1-7.

Images