Speed planning method, speed planning device, vehicle and readable storage medium

Abstract

The application discloses a speed planning method, a speed planning device, a vehicle and a readable storage medium. The method comprises the following steps: constructing a speed planning model from a starting point to an ending point according to a state transition equation of a vehicle; planning a first speed curve from a current state to the ending state based on the speed planning model, and judging whether the first speed curve satisfies a speed upper limit constraint; if not, expanding the current state, selecting a target candidate state from candidate states obtained through the expansion as the current state, and returning to the step of planning the first speed curve from the current state to the ending state based on the speed planning model; and if yes, obtaining a speed planning result according to the first speed curve. Through the above process, the speed planning result can be obtained by only recursively starting from the starting point and traversing the path once, the calculation power consumption and time consumption of the speed planning can be reduced, the speed planning can be performed on any scene, and the adaptability of the speed planning is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, and in particular to a speed planning method, a speed planning device, a vehicle and a readable storage medium. BACKGROUND

[0002] Speed planning is one of the important technologies in the field of intelligent driving, which determines the comfort and safety of the vehicle in the state of intelligent driving.

[0003] At present, there are mainly two ways to plan speed. One is to plan based on a predefined parametric speed curve, and to modify the parameters according to online data to obtain the actual speed curve used for control. However, this method can only be optimized and cannot obtain the optimal solution, and is limited by the limited flexibility of the predefined speed curve. This planning technology can only adapt to limited scenarios. The other is an optimization-based speed planning method, which needs to establish a longitudinal motion model of the vehicle, define an optimization objective and set constraint conditions, convert the speed planning problem into a mathematical model for solving an optimization problem, iteratively calculate each node and possibly backtrack, and the calculation complexity is an exponential function of the path length, which consumes a lot of time and computing power.

[0004] In summary, how to improve the adaptability of speed planning and save computing power and time is a technical problem that needs to be solved by the technical personnel in the field at present. SUMMARY

[0005] Therefore, the purpose of the present application is to provide a speed planning method, a speed planning device, a vehicle and a readable storage medium for improving the adaptability of speed planning and saving computing power and time.

[0006] In order to achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0007] A speed planning method comprises: constructing a speed planning model from a starting point to an end point according to a state transition equation of a vehicle; planning a first speed curve from a current state to the end state based on the speed planning model, and judging whether the first speed curve satisfies a speed upper limit constraint; if not, expanding the current state, selecting a target candidate state from the candidate states obtained by expansion as the current state, and returning to the step of planning the first speed curve from the current state to the end state based on the speed planning model; if yes, obtaining a speed planning result according to the first speed curve.

[0008] Optionally, the speed upper limit constraint is a function of the driving distance.

[0009] Optionally, the speed planning model includes a jerk value range.

[0010] The speed planning method further comprises: determining a candidate behavior vector according to the jerk value range, the candidate behavior vector comprising a jerk and a duration of the jerk;

[0011] The expanding of the current state, and selecting a target candidate state from the expanded candidate states as the current state, comprises: expanding the current state according to the candidate behavior vector, planning a second speed curve according to the candidate state, determining the target candidate state according to the second speed curve and the speed upper limit constraint, and determining the target candidate state as the current state.

[0012] Optionally, the determining of the target candidate state according to the second speed curve and the speed upper limit constraint comprises: determining a candidate state corresponding to a candidate behavior vector with the second speed curve satisfying the speed upper limit constraint and the maximum jerk as the target candidate state.

[0013] Optionally, before the determining of the target candidate state as the current state, the method further comprises: determining whether a planned driving distance of the vehicle according to the target candidate state exceeds a terminal driving distance; if yes, obtaining a speed planning result according to the target candidate state; and if no, performing the determining of the target candidate state as the current state.

[0014] Optionally, the candidate behavior vectors are arranged in a descending order of jerk;

[0015] The expanding of the current state according to the candidate behavior vector, the planning of the second speed curve according to the candidate state, and the determining of the target candidate state according to the second speed curve and the speed upper limit constraint, comprises: taking a candidate behavior vector arranged at a first position as a current candidate behavior vector, expanding the current state according to the current candidate behavior vector to obtain a candidate state, planning a second speed curve according to the candidate state and the speed planning model, determining whether the second speed curve satisfies the speed upper limit constraint, if yes, determining the candidate state corresponding to the current candidate behavior vector as the target candidate state, and if no, taking a candidate behavior vector arranged at a next position as the current candidate behavior vector and returning to the expanding of the current state according to the current candidate behavior vector.

[0016] Optionally, after the expanding of the current state according to the current candidate behavior vector, the method further comprises: determining whether the obtained candidate state satisfies the speed upper limit constraint, if yes, performing the planning of the second speed curve according to the candidate state and the speed planning model, and if no, performing the taking of the candidate behavior vector arranged at the next position as the current candidate behavior vector.

[0017] Optionally, when the current candidate behavior vector is the candidate behavior vector arranged at the last, if it is determined that the second speed curve does not satisfy the speed upper limit constraint, further comprising: determining that the planning fails, and outputting a prompt of planning failure.

[0018] Optionally, after constructing the speed planning model from the starting point to the ending point according to the state transition equation of the vehicle, further comprising: constructing a distance boundary constant constraint planning model according to the speed planning model; the distance boundary constant constraint planning model comprises a time shortest objective function, and the constraint conditions of the distance boundary constant constraint planning model comprise the starting point boundary, the ending point boundary, the speed limit, the acceleration limit and the jerk value range, and the speed upper limit in the speed limit is a fixed value.

[0019] Planning the first speed curve from the current state to the ending state based on the speed planning model comprises: planning the first speed curve from the current state to the ending state with the shortest time according to the distance boundary constant constraint planning model.

[0020] Optionally, after constructing the speed planning model from the starting point to the ending point according to the state transition equation of the vehicle, further comprising: constructing a speed boundary constant constraint planning model according to the speed planning model; the speed boundary constant constraint planning model comprises a time shortest objective function, and the constraint conditions of the speed boundary constant constraint planning model comprise the starting point speed, the starting point acceleration, the ending point speed, the ending point acceleration, the acceleration limit and the jerk value range.

[0021] Planning the second speed curve according to the candidate state comprises: planning the second speed curve from the candidate state to the parking state with the shortest time by using the speed boundary constant constraint planning model.

[0022] Optionally, before planning the second speed curve from the candidate state to the parking state with the shortest time by using the speed boundary constant constraint planning model, further comprising: constructing an acceleration boundary speed planning model, solving the acceleration boundary speed planning model to obtain a first solving result; the acceleration boundary speed planning model comprises a time shortest objective function, and the constraint conditions of the acceleration boundary speed planning model comprise the starting point acceleration, the ending point acceleration and the jerk value range, and the starting point acceleration, the ending point acceleration and the upper and lower limits of the jerk are all constants.

[0023] The constant constraint planning model of the speed boundary is solved according to the first solving result to obtain a second solving result, and a second speed curve with the shortest time from the candidate state to a parking state is obtained according to the candidate state and the second solving result.

[0024] Optionally, a first speed curve with the shortest time from the current state to the terminal state is planned according to the constant constraint planning model of the distance boundary, including: solving the constant constraint planning model of the distance boundary according to the second solving result to obtain a third solving result; and obtaining the first speed curve with the shortest time from the current state to the terminal state according to the current state and the third solving result.

[0025] Optionally, the speed planning model is:

[0026]

[0027] wherein A i is the ith action vector, Δt i is the duration of the ith action vector, j i is the jerk of the vehicle in the ith action vector, is a real set, N-1 is the number of action vectors, N is the number of states of the vehicle, j max is the upper limit of the jerk in the speed planning, X i = [t i , s i , v i , a i ] T is the ith state vector of the vehicle, s i is the driving distance of the vehicle at t i , v i is the speed of the vehicle at t i , a i is the acceleration of the vehicle at t i , X i+1 = f(X i , A i ) is the state transition equation of the vehicle, s1, v1, a1 are variables, representing the driving distance, speed and acceleration at the starting point, s S , v S , a S are the driving distance, speed and acceleration determined at the starting point, s N , v N , a Ns, v, a are variables representing the travel distance, speed and acceleration at the end point, s E , v E , a E s, v, a are determined at the end point, 0≤v i ≤v max (s i ) is a speed limit, v max (s i ) is the maximum speed at travel distance s i , a min ≤a i ≤a max a is an acceleration limit, a min a is a minimum acceleration, a max a is a maximum acceleration.

[0028] Optionally, the constant constraint planning model of the distance boundary is:

[0029]

[0030] where t N is the time to reach the end state.

[0031] Optionally, the constant constraint planning model of the speed boundary is:

[0032]

[0033] Optionally, the acceleration boundary speed planning model is:

[0034]

[0035] A speed planning device comprising a memory for storing a computer program, and a processor for implementing the steps of the speed planning method according to any one of the above when executing the computer program.

[0036] A vehicle comprising the speed planning device described above.

[0037] A readable storage medium having a computer program stored therein, the computer program being executed by a processor to implement the steps of the speed planning method according to any one of the above.

[0038] The application provides a speed planning method, a speed planning device, a vehicle and a readable storage medium, wherein the method comprises the following steps: constructing a speed planning model from a starting point to an ending point according to a state transition equation of the vehicle; planning a first speed curve from a current state to the ending state based on the speed planning model, and judging whether the first speed curve satisfies a speed upper limit constraint; if not, expanding the current state, selecting a target candidate state from candidate states obtained through the expansion as the current state, and returning to the step of planning the first speed curve from the current state to the ending state based on the speed planning model; and if yes, obtaining a speed planning result according to the first speed curve.

[0039] The above technical solution disclosed in the application comprises the following steps: constructing a speed planning model from a starting point to an ending point according to a state transition equation of the vehicle; planning a first speed curve from a current state to the ending state based on the speed planning model, and judging whether the first speed curve satisfies a speed upper limit constraint; if not, expanding the current state, selecting a target candidate state from candidate states obtained through the expansion as the current state, and returning to the step of planning the first speed curve from the current state to the ending state based on the speed planning model; and if yes, obtaining a speed planning result according to the first speed curve. Through the above process, only one target candidate state in each expansion layer is determined as the current state, that is, the calculation times of each expansion layer are at most equal to the expansion times of the current state, so that the calculation complexity is a linear function of the path length, thereby reducing the calculation complexity, the calculation time consumption and the calculation power consumption, and facilitating obtaining an accurate speed planning result. If the first speed curve satisfies the speed upper limit constraint, it is determined that the planning is successful, and the speed planning result is obtained according to the first speed curve, so as to greatly reduce the calculation time and the calculation power consumption, and obtain an accurate speed planning result. Through the above process, only the recursion from the starting point is needed, and the smooth speed curve satisfying the smoothness constraint can be obtained through once traversal of the path, so as to reduce the calculation power consumption and the time consumption of the speed planning. Moreover, the above speed planning process does not need to predefine the speed curve, and can plan the speed for any scene, thereby improving the adaptability of the speed planning.

[0040] Additional aspects and advantages of the application will be made apparent by the following description. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 A flowchart of a speed planning method provided for an embodiment of the application;

[0042] Figure 2 A flowchart of another speed planning method provided for an embodiment of the application;

[0043] Figure 3 A flowchart of still another speed planning method provided for an embodiment of the application;

[0044] Figure 4 (a)-(f) are schematic diagrams of speed planning according to the period provided by the embodiments of the application;

[0045] Figure 5 (a)-(e) are schematic diagrams of five solutions of the constant constraint planning model of the speed boundary provided by the embodiments of the application;

[0046] Figure 6 (a)-(c) are schematic diagrams of three solutions of the constant constraint planning model of the distance boundary provided by the embodiments of the application;

[0047] Figure 7 (a)-(b) are schematic diagrams of the speed planning results under the condition of the step speed upper limit provided by the embodiments of the application;

[0048] Figure 8 (a)-(b) are schematic diagrams of the speed planning structure under the condition of the sine speed upper limit provided by the embodiments of the application;

[0049] Figure 9 (a)-(b) are schematic diagrams of the speed planning results under the condition of the random speed upper limit provided by the embodiments of the application. DETAILED DESCRIPTION

[0050] At present, there are mainly two ways to carry out speed planning. One is to carry out planning based on a predefined parametric speed curve, and to modify the parameters according to online data (path length, speed limit, etc.) to obtain an actual speed curve used for control. In this way, the predefined parametric speed curve can only be optimized, and only a feasible solution can be obtained, which leads to poor performance of the planning result and cannot adapt to higher requirement application scenarios. Moreover, due to the limited flexibility of the predefined speed curve, this planning technology can only adapt to limited scenarios and may obtain unusable results in some scenarios that are not considered in advance. The other is an optimization-based speed planning method, which needs to establish a longitudinal motion model of the vehicle, define an optimization objective and set constraint conditions, and convert the speed planning problem into a mathematical model for solving an optimization problem. In this way, iterative calculation needs to be carried out for each node and backtracking calculation may be carried out, and the calculation complexity is an exponential function of the calculation path length, so that the time and computing power consumption are relatively high, and it is difficult to apply to platforms with limited computing power.

[0051] Therefore, the application provides a speed planning method, a speed planning device, a vehicle and a readable storage medium, which are used to improve the adaptability of speed planning and save computing power and time.

[0052] Embodiments of the present application are described below in detail with reference to the accompanying drawings, wherein the same or similar components or components having the same or similar functions are denoted by the same or similar reference numerals throughout the drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application.

[0053] Referring to Figure 1 which shows a flowchart of a speed planning method provided by an embodiment of the present application, the speed planning method provided by an embodiment of the present application can include:

[0054] S11: constructing a speed planning model from a starting point to an ending point according to a state transition equation of a vehicle.

[0055] It should be noted that the speed planning method provided by an embodiment of the present application can be specifically planning a longitudinal motion process of a vehicle driving along a one-dimensional path. In the embodiment of the present application, X=[t,s,v,a] is defined as a state vector, indicating a driving distance s, a vehicle speed v, and an acceleration a of the vehicle driving along a one-dimensional path at a time t. T A=[Δt,j] is defined as a behavior vector, indicating a jerk j of the vehicle and a duration Δt of the jerk. T

[0056] According to the above definition, a subsequent state X' can be obtained by taking a behavior A from a state X, and this process is expressed as an equation form, that is, the state transition equation of the vehicle can be expressed as formula (1):

[0057] X'=f(X,A) (1)

[0058] The driving distance s, the vehicle speed v, and the acceleration a can be calculated according to an integral formula shown in formula (2), where τ is an integral variable for time integration:

[0059]

[0060] It is assumed that the jerk j does not change in the time interval Δt, and then formula (2) can be written as formula (3) as follows:

[0061]

[0062] According to formula (3), the state transition equation in formula (1) can be written as formula (4) as follows:

[0063]

[0064] It can be known from formula (4) that, starting from an initial state X1, if there is a series of behavior vectors A i ​(i = 1, 2,..., N - 1), a series of subsequent states can be recursively derived, i.e., X i = f(X i-1 , A i-1 )(i = 1, 2,..., N), which completely represents the motion state of the vehicle on the one-dimensional path. Wherein, N is the number of states of the vehicle, and N - 1 is the number of behavior vectors.

[0065] On the basis of the state transition equation of the vehicle shown in formula (4), the speed planning problem from the starting point to the ending point can be abstracted and constructed to construct a speed planning model from the starting point to the ending point. Wherein, the speed planning model contains behavior vectors A i (i = 1, 2,..., N - 1, N = 2, 3,...) and constraint conditions, etc.

[0066] The constraint conditions in the constructed speed planning model need to consider the following aspects:

[0067] (1) Longitudinal motion model

[0068] The longitudinal motion of the vehicle needs to satisfy certain rules, and the states of any two periods need to satisfy the relationship in formula (4).

[0069] (2) Boundary conditions

[0070] Starting point boundary and ending point boundary, wherein the starting point boundary specifically contains the driving distance s S , the speed v S , the acceleration a S at the starting point, and the ending point boundary specifically contains the driving distance s E , the speed v E , the acceleration a E at the ending point.

[0071] (3) Speed limit

[0072] The lower limit of the vehicle speed is 0, and the upper limit of the vehicle speed is v max (s), that is, the speed upper limit is a function of the driving distance s.

[0073] (4) Acceleration limit

[0074] Specifically contains the upper limit of acceleration and the lower limit of acceleration.

[0075] (5) Time monotonicity constraint

[0076] The time variable t in the speed planning process must be monotonically increasing, that is, Δt > 0.

[0077] That is, the constraint conditions in the constructed speed planning model contain the state transition equation of the vehicle, the starting point boundary, the ending point boundary, the speed limit (the speed upper limit in the speed limit is vmax (s), i.e. the upper limit of the speed is a function of the travel distance s), acceleration limit and time monotonic constraint.

[0078] Including the jerk in the constructed speed planning model can realize the smoothness of the planned speed, i.e. realize the planning of the smooth speed.

[0079] S12: plan a first speed curve from the current state to the end state based on the speed planning model, and determine whether the first speed curve satisfies the upper limit of the speed constraint. If not, execute step S13, and if yes, execute step S14.

[0080] On the basis of step S11, a first speed curve from the current state to the end state can be planned based on the constructed speed planning model, and when planning the first speed curve, it can be planned according to the fixed upper limit of the speed. Wherein, the first speed curve planned is the curve of the speed about the travel distance, i.e. the horizontal coordinate is the travel distance, and the vertical coordinate is the speed.

[0081] After the first speed curve is planned, it can be determined whether the planned first speed curve satisfies the upper limit of the speed constraint. Specifically, determining whether the first speed curve satisfies the upper limit of the speed constraint can be specifically determining whether the first speed curve intersects with the upper limit of the speed constraint, if intersecting, it is determined that the first speed curve does not satisfy the upper limit of the speed constraint, and if not intersecting, it is determined that the first speed curve satisfies the upper limit of the speed constraint.

[0082] It should be noted that before speed planning or after constructing the speed planning model from the start point to the end point according to the state transition equation of the vehicle, and before planning the first speed curve from the current state to the end state based on the speed planning model for the first time, the start point boundary and the end point boundary can be obtained first, and initialization can be performed to facilitate subsequent solving to obtain the speed planning result. Wherein, the initialization mentioned here can be specifically setting the index p of the expansion layer to 1, setting the index q of the candidate state to 1 (q represents the index of the current expansion layer candidate state) and setting X 11 = [0, s S , v S , a s ] T , s S , v S , a S are the travel distance, speed and acceleration determined at the start point, and X 11 is the state when p = 1 (i.e. the state in the first expansion layer), i.e. the start point state.

[0083] S13: expand the current state, select a target candidate state from the candidate states obtained by expansion as the current state, and return to step S12.

[0084] If it is determined that the planned first speed curve does not satisfy the speed upper limit constraint, the current state (at this time, the current state is contained in the pth expansion layer, and when p = 1, the current state is the starting state) can be expanded to obtain a candidate state (the candidate state can be regarded as existing in the (p + 1)th expansion layer, and is used to determine whether to be used as the current state according to subsequent processing). The number of candidate states obtained by expanding the current state is the same as the expansion times of the current state in the pth expansion layer, that is, one candidate state in the (p + 1)th expansion layer can be obtained for each expansion of the current state in the pth expansion layer.

[0085] Then, one target candidate state can be selected from the plurality of candidate states in the (p + 1)th expansion layer as the current state in the (p + 1)th expansion layer, and the step of planning the first speed curve from the current state to the end state based on the speed planning model is returned to be executed, that is, the step S12 can be returned to be executed. That is, taking the target candidate state as the current state indicates that the target candidate state is a state that has been planned, and the target candidate state can be placed at the end of the state sequence, or the target candidate state (specifically, the driving distance and speed in the candidate state) can be incorporated into the end of the planned speed curve, that is, the driving distance and speed in the starting state are taken as the starting point of the planned speed curve, and the driving distance and speed in the target candidate state can be incorporated into the planned speed curve for each determination of the target candidate state. Wherein, when planning the speed, a state buffer area can be pre-opened to store the selected target candidate state (that is, the target candidate state can be stored in the form of a state sequence or a planned speed curve), so as to facilitate subsequent speed planning based on the stored target candidate state to obtain the speed planning result.

[0086] Through the above process, only one candidate state in each expansion layer is allowed to participate in subsequent speed planning as the current state (that is, only one candidate state in each expansion layer is incorporated into the planned speed curve), and at most m (m is equal to the expansion times of the current state) candidate states in each expansion layer are calculated, so that the calculation complexity is a linear function of the path length. In addition, through the above process, the process can be recursively performed from the starting point backward without backtracking. Therefore, compared with the existing optimization-based speed planning method which adopts a tree structure and calculates each node in each layer of the tree structure (the number of nodes in each layer of the tree structure is in an exponential form with the number of layers, that is, the first layer contains x nodes, each node in the first layer derives k nodes in the next layer, the second layer contains x*k nodes, the third layer contains x*k 2 nodes, and the nth layer contains x*k (n-1)The embodiments of the present application can reduce the calculation complexity of the speed planning, thereby reducing the calculation power consumption and time consumption, reducing the demand for platform calculation power, improving the efficiency of the speed planning, and obtaining an accurate speed planning result. Moreover, the embodiments of the present application do not predefine a speed curve, but directly perform speed planning, and therefore, the optimal speed planning result can be obtained for any scenario, improving the performance of the speed planning and the adaptability to the scenario.

[0087] S14: obtaining a speed planning result according to the first speed curve.

[0088] If it is determined that the planned first speed curve from the current state to the end state satisfies the speed upper limit constraint, it can be determined that the planning is successful, and a speed planning result can be obtained according to the first speed curve. Specifically, if the first speed curve from the current state to the end state is planned with the start state as the current state, and the planned first speed curve satisfies the speed upper limit constraint (i.e., without going through step S12, the first speed curve planned with the start state as the current state satisfies the speed upper limit constraint), the speed planning result is directly obtained according to the first speed curve, and specifically, the first speed curve can be taken as the final speed planning curve (i.e., the form of the speed planning result can be a speed planning curve), and of course, each state (i.e., state vector) corresponding to the first speed curve can be obtained, and the speed planning result can be obtained by arranging the states in sequence (i.e., the form of the speed planning result can be a state sequence). If the first speed curve satisfying the speed upper limit constraint can be planned only by going through step S12, the speed planning result can be obtained according to the target candidate state and the first speed curve, and specifically, the target candidate state can be spliced with the first speed curve in sequence to obtain the speed planning result (i.e., the form is a speed planning curve), that is, the planned speed curve can be spliced with the first speed curve to obtain the final speed planning curve, and of course, each state corresponding to the first speed curve can be obtained, and the target candidate state and each state corresponding to the first speed curve can be arranged in sequence to obtain the speed planning result (i.e., the form is a state sequence).

[0089] After obtaining the speed planning result, a planning success prompt and the speed planning result (i.e., the form of the speed planning result can be a state sequence or a speed planning curve) can be output, so that relevant personnel can determine that the speed planning is successful, and can obtain the corresponding speed planning result, and a vehicle can perform intelligent driving based on the planned speed planning result. The process of planning the first speed curve from the current state to the end state based on the speed planning model, determining that the planning is successful when the planned first speed curve satisfies the speed upper limit constraint, and directly obtaining the speed planning result can achieve speed planning without using a recursive method, greatly reducing the calculation complexity and computing power consumption of speed planning, improving the efficiency of speed planning, and accurately obtaining the speed planning result.

[0090] As can be seen from the above speed planning process, the embodiments of the present application first construct a speed planning model, and then plan a first speed curve from the current state to the end state. If the first speed curve does not satisfy the speed upper limit constraint, the current state is expanded, and a target candidate state is selected from the candidate states contained in the next expansion layer obtained by expansion as the current state to continue planning the first speed curve from the current state to the end state and related processes. If the first speed curve satisfies the speed upper limit constraint, the speed planning result is obtained according to the first speed curve, which only needs to be recursively performed from the starting point, and a smooth speed curve satisfying the smoothness constraint can be obtained by traversing the path once, without using a predefined speed curve or an optimization-based method. Compared with the method of planning speed based on a predefined speed curve, the speed planning method provided by the embodiments of the present application can obtain the optimal speed planning result for any scenario. Compared with the method of planning speed based on optimization, the computational complexity of the embodiments of the present application is only a linear function of the path length, rather than an exponential function, and the calculation time and computing power consumption are greatly reduced

[0091] The above technical solution disclosed by the embodiments of the present application constructs a speed planning model from the starting point to the ending point according to the state transition equation of the vehicle, plans a first speed curve from the current state to the ending state based on the constructed speed planning model, and judges whether the first speed curve satisfies the speed upper limit constraint. If the first speed curve does not satisfy the speed upper limit constraint, the current state is expanded, a target candidate state is selected from the candidate states obtained by the expansion as the current state, and the step of planning the first speed curve is returned to be executed. Through the above process, each expansion layer only corresponds to one target candidate state determined as the current state, that is, the calculation times of each expansion layer are at most equal to the expansion times of the current state, so that the calculation complexity is a linear function of the path length, thereby reducing the calculation complexity, calculation time consumption and algorithm consumption, and facilitating to obtain an accurate speed planning result. If the first speed curve satisfies the speed upper limit constraint, it is determined that the planning is successful, and the speed planning result is obtained directly according to the target candidate state and the first speed curve, so as to greatly reduce the calculation time and algorithm consumption, and obtain an accurate speed planning result. Through the above process, only the recursion from the starting point is needed, and the smooth speed curve satisfying the smoothness constraint can be obtained by traversing the path once, so as to reduce the algorithm consumption and time consumption of speed planning. Moreover, the above speed planning process does not need to predefine the speed curve, and can plan the speed for any scene, thereby improving the adaptability of speed planning.

[0092] The speed planning method provided by the embodiments of the present application has a speed upper limit constraint that is a function of the driving distance.

[0093] In the embodiments of the present application, the speed upper limit constraint can be a function of the driving distance s, that is, the speed upper limit constraint can be expressed as v max (s), that is, the speed upper limit constraint is a dynamic speed upper limit constraint related to the driving distance, and does not need to be approximated or linearized. Compared with the current optimization-based method, the embodiments of the present application can accurately process the dynamic speed upper limit constraint related to the driving distance, so as to prevent the speed planning result from violating the constraint, thereby facilitating to obtain an accurate speed planning result. Moreover, setting the speed upper limit constraint as a function of the driving distance can also enable the embodiments of the present application to implement speed planning oriented to the dynamic speed upper limit, so as to further improve the accuracy of speed planning.

[0094] Correspondingly, when judging whether the first speed curve satisfies the speed upper limit constraint, whether the speed at each driving distance in the first speed curve exceeds the speed upper limit at the corresponding driving distance in the speed upper limit constraint can also be judged. If the speed at a driving distance in the first speed curve exceeds the speed upper limit at the corresponding driving distance in the speed upper limit constraint, it is determined that the first speed curve does not satisfy the speed upper limit constraint. If the speed at each driving distance in the first speed curve does not exceed the speed upper limit at the corresponding driving distance in the speed upper limit constraint, it is determined that the first speed curve satisfies the speed upper limit constraint.

[0095] Through the above process, it can be known that the embodiment of the application is to participate in speed planning with the dynamic speed upper limit constraint related to the driving mileage, without needing to perform approximation or linearization processing. Therefore, the dynamic speed upper limit constraint can be accurately processed to prevent the speed planning result from violating the constraint, so that an accurate speed planning result can be obtained.

[0096] The speed planning method provided in the embodiment of the application includes a jerk value range in the speed planning model.

[0097] The speed planning method can further include:

[0098] The candidate behavior vector is determined according to the jerk value range, and the candidate behavior vector includes the jerk and the duration of the jerk.

[0099] The current state is expanded, and the target candidate state is selected from the candidate states obtained by the expansion as the current state, which can include:

[0100] The current state is expanded according to the candidate behavior vector, the second speed curve is planned according to the obtained candidate state, the target candidate state is determined according to the second speed curve and the speed upper limit constraint, and the target candidate state is determined as the current state.

[0101] In the embodiment of the application, the constructed speed planning model can include a jerk value range, and specifically can include a jerk j i The target function takes the maximum value in the jerk value range. The jerk value range can be specifically {-j max , 0, j 1ax}, and j max is the upper limit of the jerk in the speed planning. That is, the constructed speed planning model can be specifically that, when the jerk j i is the maximum under certain constraint conditions, the corresponding behavior vector A i is obtained. That is, in the constructed speed planning model, the design variable to be solved is the sequence of the behavior vector A i(i = 1, 2, …, N-1, N = 2, 3, …), the rule for solving is to select a larger value in the set jerk value range on the premise of meeting the constraint condition. By including the jerk parameter in the speed planning model, the final speed planning result can be a smooth speed curve, thereby improving the vehicle driving performance.

[0102] On the basis of the above, before the current state is expanded, candidate behavior vectors A can be determined according to the jerk value range. Each candidate behavior vector determined contains a jerk and a duration of the jerk. For example, when the jerk value range is {-j max , 0, j max}, the candidate behavior vector A can specifically contain: A1 = [Δt, j max ] T , A2 = [Δt, 0] T , A3 = [Δt, -j max ] T . And X pq represents the qth candidate state of the pth expansion layer, i p is used to record the selected state of the pth layer.

[0103] Correspondingly, the current state can be expanded according to each candidate behavior vector determined, and specifically, the current state can be expanded by using formula (4) to obtain the candidate states (i.e., candidate state vectors) contained in the next expansion layer. That is, if it is determined that the first speed curve does not meet the speed upper limit constraint, the current state (at this time, the current state is contained in the pth expansion layer) can be expanded according to the candidate behavior vector to obtain the candidate state (the candidate state can be regarded as existing in the pth+1 expansion layer, and is used to determine whether to be the current state according to subsequent processing), at this time, the candidate states contained in the pth+1 expansion layer are at most equal to the number of candidate behavior vectors. Compared with the existing optimization-based method in which the number of nodes to be calculated of each layer increases exponentially, the embodiment of the present application can reduce the number of candidate states of each expansion layer, and reduce the time consumption and computing power consumption of speed planning.

[0104] After the candidate state contained in the p+1th extended layer is obtained, a second speed curve can be planned based on the obtained candidate state contained in the p+1th extended layer and the constructed speed planning model (for example, a parking speed curve with the shortest parking time from the candidate state to a parking state can be planned), so as to determine the target behavior vector to be adopted when the current state of the pth layer is transferred to the next state (i.e., as a new current state) by using the second speed curve and the speed upper limit constraint. Specifically, after the second speed curve is planned, it can be judged whether the second speed curve satisfies the speed upper limit constraint. If the second speed curve does not satisfy the speed upper limit constraint, it indicates that the speed will exceed the speed upper limit when the vehicle is in state transition and motion in the future with the corresponding candidate behavior vector, and therefore the corresponding candidate behavior vector can be discarded. If the second speed curve satisfies the speed upper limit constraint, it indicates that the speed will not exceed the speed upper limit when the vehicle is in state transition and motion in the future with the corresponding candidate behavior vector, and therefore the corresponding candidate behavior vector can be retained, and a target behavior vector can be determined from the retained candidate behavior vectors, and the candidate state corresponding to the target behavior vector is determined as a target candidate state. After the target behavior vector is determined, the target behavior vector A pq (q=i p , i p is recorded and stored, and the target candidate state X pq corresponding to the target behavior vector is recorded and stored. When the target behavior vector A pq and the target candidate state X pq corresponding to the target behavior vector are recorded and stored, they can be recorded in the determined order respectively to form a behavior sequence and a state sequence, that is, X pq and A pq (q=i p ) can be recorded in the order of p=1.

[0105] By the above-mentioned manner, the time and computing power consumed by speed planning can be reduced, and accurate speed planning results can be obtained, so as to improve the driving performance of the vehicle.

[0106] The speed planning method provided by the embodiment of the application can comprise the following steps:

[0107] The candidate state corresponding to the candidate behavior vector with the maximum jerk and satisfying the speed upper limit constraint is determined as the target candidate state.

[0108] In the embodiment of the present application, when the target candidate state is determined according to the second speed curve and the speed upper limit constraint, a candidate behavior vector with the maximum jerk can be selected from the candidate behavior vectors satisfying the speed upper limit constraint of the second speed curve, and a candidate state obtained by extending the current state by using the candidate behavior vector is determined as the target candidate state. That is, the candidate state corresponding to the candidate behavior vector with the maximum jerk and satisfying the speed upper limit constraint of the second speed curve is determined as the target candidate state, so as to obtain an accurate and optimal speed planning result, shorten the driving time, and improve the driving performance.

[0109] On the basis of the above, after the planning is determined to be successful, the recorded target behavior vector and the behavior vector corresponding to the first speed curve can be arranged in sequence to obtain a behavior sequence corresponding to the speed planning result, and the behavior sequence can be output, that is, after the planning is determined to be successful, the recorded X pq and A pq (q=i p ), that is, the state sequence and the behavior sequence obtained by planning are output, so that relevant personnel can obtain more speed planning information.

[0110] Referring to Figure 2 , a flowchart of another speed planning method provided by an embodiment of the present application is shown, and the speed planning method provided by the embodiment of the present application can further include the following steps before the target candidate state is determined as the current state:

[0111] determining whether the planning driving distance of the vehicle exceeds the terminal driving distance according to the target candidate state;

[0112] if yes, obtaining the speed planning result according to the target candidate state;

[0113] if no, performing the step of determining the target candidate state as the current state.

[0114] In the embodiment of the present application, before the target candidate state is determined as the current state, after the target candidate state is determined according to the second speed curve and the speed upper limit constraint, it can be determined whether the planning driving distance of the vehicle exceeds the terminal driving distance according to the target candidate state. Specifically, the driving distance in the target candidate state can be determined as the planning driving distance of the vehicle, and then it is determined whether the planning driving distance of the vehicle exceeds the terminal distance.

[0115] If the planned driving distance of the vehicle exceeds the end point distance, it indicates that the planned driving distance has exceeded the end point driving distance although the end point state has not been reached. At this time, it can also be considered as planning success, and the speed planning result can be obtained according to the target candidate state. Specifically, the speed planning curve can be drawn according to the target candidate state and the target behavior vector corresponding to the target candidate state to obtain the speed planning result, or the target candidate state can be arranged in the order determined by the target candidate state to form a state sequence to obtain the speed planning result. Then, the planning success and the speed planning result (the manifestation can be a candidate state sequence or a speed planning curve) can be output.

[0116] If the planned driving distance of the vehicle does not exceed the end point distance, it is determined that the planning is not successful. At this time, subsequent related steps can be performed, that is, the step of determining the target candidate state as the current state can be returned to execute to continue the speed planning.

[0117] Through the above, the accuracy of determining whether the speed planning is successful can be realized, so as to reduce the additional consumption of computing power and time, and improve the accuracy of speed planning.

[0118] Referring to Figure 3 and Figure 4 (a)-(f), wherein, Figure 3 a flowchart of another speed planning method provided by an embodiment of the present application is shown, Figure 4 (a)-(f) show a schematic diagram of speed planning decomposition by period provided by an embodiment of the present application. The speed planning method provided by an embodiment of the present application can further include:

[0119] arranging the candidate behavior vectors in descending order of jerk;

[0120] extending the current state according to the candidate behavior vector, planning a second speed curve according to the obtained candidate state, and determining the target candidate state according to the second speed curve and the speed upper limit constraint, can include:

[0121] arranging the candidate behavior vector in the first place as the current candidate behavior vector, extending the current state according to the current candidate behavior vector to obtain a candidate state;

[0122] planning a second speed curve according to the candidate state and the speed planning model, and judging whether the second speed curve satisfies the speed upper limit constraint;

[0123] if yes, determining the candidate state corresponding to the current candidate behavior vector as the target candidate state;

[0124] if no, arranging the candidate behavior vector in the next place as the current candidate behavior vector, and returning to execute the step of extending the current state according to the current candidate behavior vector.

[0125] In the embodiments of the present application, when the candidate behavior vector A is set according to the value range of the jerk, the candidate behavior vectors can be arranged in the order of the jerk from large to small according to the size of the jerk contained in each candidate behavior vector, to form a candidate behavior sequence. For example, when the value range of the jerk is {-j max , 0, j max}, and the candidate behavior vector A specifically contains: A1 = [Δt, j max ] T , A2 = [Δt, 0] T , A3 = [Δt, -j max ] T , the order of the three candidate behavior vectors can be A1, A2, A3.

[0126] On the basis described above, for each expansion layer, the specific process of expanding the current state according to the candidate behavior vector, planning the second speed curve according to the candidate state, and determining the target candidate state according to the second speed curve and the speed upper limit constraint can be as follows:

[0127] Step 1: The candidate behavior vector arranged at the first in the candidate behavior sequence is taken as the current candidate behavior vector.

[0128] Step 2: The current state is expanded by using formula (4) according to the current candidate behavior vector, to obtain a candidate state.

[0129] Step 3: The second speed curve is planned according to the candidate state obtained in step 2 and the speed planning model, and it is judged whether the planned second speed curve satisfies the speed upper limit constraint. If the planned second speed curve satisfies the speed upper limit constraint, step 4 is executed, and if the planned second speed curve does not satisfy the speed upper limit constraint, step 5 is executed.

[0130] In the formula, the horizontal coordinate of the second speed curve is the travel distance, and the vertical coordinate is the speed, and when the second speed curve is planned, the speed v E and the acceleration a E of the terminal point can be set as 0, that is, the second speed curve can be a parking speed curve (for example, it can be a parking speed curve with the shortest time), that is, deceleration parking can be performed on the basis of the obtained candidate state in the next expansion layer, it is judged whether the speed lower limit satisfies the speed upper limit constraint during deceleration parking. If it does not satisfy, the speed of the vehicle in other driving conditions is even less likely to satisfy the speed upper limit constraint, at this time, step 5 can be executed, and if it satisfies, the speed of the vehicle in other driving conditions is likely to satisfy the speed upper limit constraint, and further expansion and planning of the second speed curve can be performed on this basis, that is, step 4 can be executed.

[0131] Step 4: If it is determined that the planned second velocity curve satisfies the upper speed limit constraint, then the candidate state obtained in step 2 can be determined as the target candidate state.

[0132] Step 5: If it is determined that the planned second speed curve does not meet the speed upper limit constraint, the next candidate behavior vector in the candidate behavior sequence can be used as the current candidate behavior vector, and then return to execute step 2.

[0133] For example, regarding the above process, such as Figure 4 As shown in (a)-(f), Figure 4 In (a)-(f), the horizontal axis represents the travel distance, and the vertical axis represents the speed. The blue line represents the planned speed curve, the red line represents the speed upper limit constraint, the green line represents the first speed curve from the current state to the destination state, the purple line represents the speed curve corresponding to the candidate state obtained after expanding the current state using candidate behavior vectors, and the black line represents the second speed curve expanded based on the expanded candidate state (specifically, the speed curve that decelerates from the speed curve corresponding to the candidate state to 0). Figure 4 As shown in (a)-(f), each time the process starts from the current state, plans a first velocity curve from the current state to the destination state, and determines whether the planned first velocity curve meets the upper speed limit constraint. If it does not, the current state is expanded according to the candidate behavior vector, and a second velocity curve (i.e., the parking velocity curve) is planned from the expanded state. The decision on whether to accept the expanded point is based on whether the planned second velocity curve meets the upper speed limit constraint. If an expanded state is accepted, the expanded state is used as the current state and the above process is repeated; otherwise, the process switches to the next expanded point.

[0134] like Figure 4 As shown in (a), firstly, a first velocity curve is planned from the end of the planned velocity curve (i.e., the current state) to the final state. It is determined that the planned first velocity curve intersects with the upper speed limit constraint, thus indicating that the planned first velocity curve does not satisfy the upper speed limit constraint. At this point, the end of the first velocity curve is expanded using the candidate behavior vector A1 to obtain the velocity curve corresponding to the expanded candidate state. Based on the expanded velocity curve corresponding to the candidate state, a second velocity curve is planned. It is determined that the planned second velocity curve does not intersect with the upper speed limit constraint, thus indicating that the planned second velocity curve satisfies the upper speed limit constraint. At this point, the velocity curve corresponding to the candidate behavior vector A1 can be merged into the planned velocity curve to obtain... Figure 4 (b) shows the planned speed curve.

[0135] like Figure 4(b) as shown, a first speed curve reaching the terminal state is planned at the end of the planned speed curve, it is determined that the planned first speed curve intersects with the speed upper limit constraint, it is determined that the planned first speed curve does not satisfy the speed upper limit constraint, at this time, the end of the first speed curve is expanded by using the candidate behavior vector A1 to obtain a speed curve corresponding to the expanded candidate state, a second speed curve is planned on the basis of the speed curve corresponding to the expanded candidate state, it is determined that the planned second speed curve intersects with the speed upper limit constraint, it is determined that the second speed curve does not satisfy the speed upper limit constraint. Next, the end of the first speed curve is expanded by using the candidate behavior vector A2 to obtain a speed curve corresponding to the expanded candidate state, a second speed curve is planned on the basis of the speed curve corresponding to the expanded candidate state, it is determined that the planned second speed curve intersects with the speed upper limit constraint, it is determined that the second speed curve does not satisfy the speed upper limit constraint. Next, the end of the first speed curve is expanded by using the candidate behavior vector A3 to obtain a speed curve corresponding to the expanded candidate state, a second speed curve is planned on the basis of the speed curve corresponding to the expanded candidate state, it is determined that the planned second speed curve does not intersect with the speed upper limit constraint, it is determined that the second speed curve satisfies the speed upper limit constraint, at this time, the speed curve corresponding to the candidate behavior vector A3 can be integrated into the planned speed curve.

[0136] It should be noted that, Figure 4 (a)- Figure 4 (f) is in order, but the order may not be immediately next, such as Figure 4 (c) after Figure 4 (b), Figure 4 (d) after Figure 4 (c), but Figure 4 (c) is not immediately next Figure 4 (b) is performed, Figure 5 (d) is not immediately next Figure 5 (c) is performed, some similar steps are omitted in between… finally as Figure 5 (f) as shown, a first speed curve reaching the terminal state is planned at the end of the planned speed curve, it is determined that the planned first speed curve satisfies the speed upper limit constraint, at this time, it can be determined that the planning is successful, and the first speed curve is integrated into the planned speed curve to obtain a final speed planning curve.

[0137] The expansion according to the order of the jerk from large to small can select the most effective candidate behavior vector as the selected behavior vector for each expansion layer, and can make the current state of the expansion layer only need to perform less than m times of expansion calculation (such as only need to perform 1 time, 2 times of expansion calculation, and the current state of the expansion layer at most performs m times of expansion calculation), so as to greatly reduce the calculation complexity and the computing power consumption, and improve the speed planning efficiency.

[0138] Of course, when the current state located in the pth expansion layer is expanded according to the candidate behavior vector, the current state located in the pth expansion layer can also be expanded by using the m candidate behavior vectors at the same time to obtain m candidate states in the (p+1)th layer, plan m second speed curves based on the m candidate states in the (p+1)th layer, select the second speed curve in the m second speed curves that satisfies the speed upper limit constraint and has the maximum jerk in the candidate behavior vectors as the target second speed curve, determine the candidate behavior vector corresponding to the target second speed curve as the target behavior vector, and continue to perform speed planning by taking the target candidate state corresponding to the target behavior vector as the current state located in the (p+1)th expansion layer. This way, m times of calculation are needed for each expansion layer, and the calculation complexity is still a linear function of the path length, so the calculation complexity and the computing power consumption can still be reduced, and the speed planning efficiency can be improved.

[0139] The speed planning method provided in the embodiments of the present application can further include the following steps after the current state is expanded according to the current candidate behavior vector:

[0140] determining whether the candidate state satisfies the speed upper limit constraint;

[0141] if yes, performing the step of planning the second speed curve according to the candidate state and the speed planning model;

[0142] if no, performing the step of taking the candidate behavior vector arranged next as the current candidate behavior vector.

[0143] In the embodiments of the present application, after the current state is expanded according to the current candidate behavior vector to obtain the candidate state, it can be determined whether the obtained candidate state satisfies the speed upper limit constraint, that is, whether the speed in the candidate state exceeds the corresponding speed upper limit in the speed upper limit constraint. If each speed in the candidate state does not exceed the corresponding speed upper limit, it is determined that the obtained candidate state in the next expansion layer satisfies the speed upper limit constraint. If there is a speed in the candidate state that exceeds the corresponding speed upper limit, it is determined that the obtained candidate state in the next expansion layer does not satisfy the speed upper limit constraint.

[0144] If it is determined that the obtained candidate state satisfies the speed upper limit constraint, a step of planning a second speed curve according to the candidate state and the speed planning model can be performed. If it is determined that the obtained candidate state does not satisfy the speed upper limit constraint, a step of taking the candidate behavior vector arranged next as the current candidate behavior vector can be performed.

[0145] The above determination ensures that the target candidate state corresponding to the target behavior vector (i.e., the current state in each expansion layer) does not exceed the speed upper limit constraint, thereby improving the accuracy of speed planning.

[0146] The speed planning method provided in the embodiments of the present application, when the current candidate behavior vector is the candidate behavior vector arranged last, if it is determined that the second speed curve does not satisfy the speed upper limit constraint, can further include:

[0147] Determining that the planning fails, and outputting a prompt of planning failure.

[0148] In the embodiments of the present application, in the process of expanding the current state according to the candidate behavior sequence, when the candidate behavior vector arranged last is taken as the current candidate behavior vector, the current state is expanded according to the current candidate behavior vector, the second speed curve is planned based on the expanded candidate state, and it is determined whether the planned second speed curve satisfies the speed upper limit constraint, if it is determined that the planned second speed curve does not satisfy the speed upper limit constraint, it indicates that the subsequently planned speed will exceed the speed upper limit constraint, therefore, it can be determined that the constraint condition has no solution, at this time, it is determined that the planning fails, and a prompt of planning failure (which can include that the constraint condition has no solution, etc.) can be outputted, so that relevant personnel can perform corresponding processing.

[0149] The speed planning method provided in the embodiments of the present application, after constructing the speed planning model from the starting point to the ending point according to the state transition equation of the vehicle, can further include:

[0150] Constructing a distance boundary constant constraint planning model according to the speed planning model; the distance boundary constant constraint planning model includes a target function of time shortest, and the constraint conditions of the distance boundary constant constraint planning model include the starting point boundary, the ending point boundary, the speed limit, the acceleration limit, and the jerk value range, and the speed upper limit in the speed limit is a fixed value;

[0151] Planning a first speed curve from the current state to the ending state based on the speed planning model can include:

[0152] Planning a first speed curve from the current state to the ending state with the shortest time according to the distance boundary constant constraint planning model.

[0153] In the embodiments of the present application, after constructing the speed planning model from the starting point to the ending point according to the state transition equation of the vehicle, a distance boundary constant constraint planning model can be constructed according to the constructed speed planning model. The distance boundary constant constraint planning model contains a time shortest target function, and the constraint conditions of the distance boundary constant constraint planning model contain the state transition equation, the starting point boundary (specifically containing the driving distance s S , the speed v S , the acceleration a S at the starting point), the ending point boundary (specifically containing the driving distance s E , the speed v E , the acceleration a E at the ending point), the speed limit (the upper limit of the speed in the speed limit is a fixed value), the acceleration limit (specifically containing the upper limit of the acceleration and the lower limit of the acceleration), the time monotonicity constraint and the jerk value range.

[0154] On the basis of constructing the distance boundary constant constraint planning model, a first speed curve from the current state to the ending state with the shortest time can be planned according to the constructed distance boundary constant constraint planning model according to the fixed upper limit of the speed, that is, the first speed curve is specifically to plan a path with the shortest time from the current state to the ending state according to the fixed upper limit of the speed. The time shortest target function in the distance boundary constant constraint planning model is specifically the time shortest target function from the current state to the ending state.

[0155] By planning the first speed curve with the shortest time from the current state to the ending state in the above manner, the speed planning performance can be improved and the intelligent driving time can be shortened.

[0156] The speed planning method provided in the embodiments of the present application can further include the following after constructing the speed planning model from the starting point to the ending point according to the state transition equation of the vehicle:

[0157] constructing a speed boundary constant constraint planning model according to the speed planning model; the speed boundary constant constraint planning model contains a time shortest target function, and the constraint conditions of the speed boundary constant constraint planning model can include the starting point speed, the starting point acceleration, the ending point speed, the ending point acceleration, the acceleration limit and the jerk value range;

[0158] planning the second speed curve according to the candidate state can include:

[0159] planning a second speed curve with the shortest time from the candidate state to the parking state by using the speed boundary constant constraint planning model.

[0160] In the embodiments of the present application, after the speed planning model from the starting point to the ending point is constructed according to the state transition equation of the vehicle, a constant constraint planning model of the speed boundary can be constructed according to the constructed speed planning model to plan a second speed curve by using the constant constraint planning model of the speed boundary. The constant constraint planning model of the speed boundary contains a target function of the shortest time, and the constraint conditions of the constant constraint planning model of the speed boundary contain the state transition equation, the starting point speed, the starting point acceleration, the ending point speed, the ending point acceleration, the acceleration limit, the time monotonicity constraint and the jerk value range, and the starting point speed, the starting point acceleration, the ending point speed and the ending point acceleration are all fixed values (i.e. all given). That is, the second speed curve is a speed planning problem of given starting point speed, starting point acceleration, ending point speed and ending point acceleration, which needs to meet the acceleration upper and lower limits and the jerk upper and lower limits, and requires the shortest travel time.

[0161] On the basis of the above, when planning the second speed curve, the constant constraint planning model of the speed boundary can be used to plan the second speed curve with the shortest time from the candidate state to the parking state, so as to predict whether the speed upper limit constraint will be met in the future by using the speed lower limit, thereby realizing the screening of the candidate behavior vector that may exceed the speed upper limit constraint in the future, avoiding the backtracking of the calculation process, so that only the recursion from the starting point is needed, and the result can be obtained by traversing the path once, thereby reducing the calculation complexity, calculation time consumption and computing power consumption.

[0162] The speed planning method provided in the embodiments of the present application can further include the following before planning the second speed curve with the shortest time from the candidate state to the parking state by using the constant constraint planning model of the speed boundary.

[0163] The acceleration boundary speed planning model is constructed, and the acceleration boundary speed planning model is solved to obtain a first solving result. The acceleration boundary speed planning model contains a target function of the shortest time, and the constraint conditions of the acceleration boundary speed planning model contain the starting point acceleration, the ending point acceleration and the jerk value range, and the starting point acceleration, the ending point acceleration and the jerk upper and lower limits are all constants.

[0164] The second speed curve with the shortest time from the candidate state to the parking state can be planned by using the constant constraint planning model of the speed boundary, which can include the following.

[0165] The constant constraint planning model of the speed boundary is solved according to the first solving result to obtain a second solving result.

[0166] The second speed curve with the shortest time from the candidate state to the parking state is obtained according to the candidate state and the second solving result.

[0167] In the embodiments of the present application, in order to facilitate solving the constant constraint programming model of the speed boundary and the constant constraint programming model of the distance boundary, an acceleration boundary speed planning model can be constructed according to the constructed speed planning model. The acceleration boundary speed planning model contains a time shortest objective function, and the constraint conditions of the acceleration boundary speed planning model contain state transition equations, start point acceleration, end point acceleration, time monotonicity constraints and jerk value range. The start point acceleration, the end point acceleration and the upper and lower limits of the jerk are all constants. Since the acceleration boundary speed planning model contains the jerk, the acceleration boundary speed planning model is a constant constraint S-shaped speed planning problem of the acceleration boundary, specifically referring to: 1) given start point and end point acceleration, 2) upper and lower limits of the jerk are constants, 3) total time shortest as the target, the speed planning problem is carried out.

[0168] After the acceleration boundary speed planning model is constructed, the acceleration boundary speed planning model can be solved to obtain a first solving result. The first solving result can include the value of N and the corresponding target behavior vector.

[0169] On the basis of the above, when planning the second speed curve from the candidate state to the parking state with the shortest time by using the constant constraint programming model of the speed boundary, the constant constraint programming model of the speed boundary can be solved according to the first solving result obtained by solving the acceleration boundary speed planning model to obtain a second solving result, wherein the second solving result can contain the value of N and the corresponding target behavior vector. Then, the second speed curve from the candidate state to the parking state with the shortest time can be obtained according to the candidate state and the second solving result. Specifically, the second speed curve from the candidate state to the parking state with the shortest time can be obtained by using the state transition equation according to the candidate state and the second solving result.

[0170] The speed planning method provided in the embodiments of the present application can include the following steps:

[0171] Solving the constant constraint programming model of the distance boundary according to the second solving result to obtain a third solving result;

[0172] Obtaining the first speed curve from the current state to the end point state with the shortest time according to the current state and the third solving result.

[0173] For planning the first speed curve from the current state to the terminal state with the shortest time according to the distance boundary constant constraint planning model, the acceleration boundary speed planning model can be solved first to obtain a first solving result. Then, the speed boundary constant constraint planning model is solved according to the first solving result to obtain a second solving result. Then, the distance boundary constant constraint planning model is solved according to the second solving result to obtain a third solving result, wherein the third solving result includes the value of N and the corresponding target behavior vector. After obtaining the third solving result, the state transition equation can be used to obtain the first speed curve with the shortest time from the current state to the terminal state according to the current state and the third solving result.

[0174] Through the above, for the static speed upper limit constraint, the optimal solution can be obtained in one calculation, without the need for iterative calculation, and without the need for constraint condition calculation on multiple groups of curve clusters, so that the algorithm consumption can be reduced, and accurate results can be obtained, improving the efficiency and accuracy of speed planning.

[0175] The speed planning method provided by the embodiment of the application has a speed planning model as follows:

[0176]

[0177] Wherein, A i is the ith behavior vector, Δt i is the duration of the ith behavior vector, j i is the jerk of the vehicle in the ith behavior vector, is a real set, N-1 is the number of behavior vectors, N is the number of states of the vehicle, j max is the upper limit of the jerk in the speed planning, X i =[t i , s i , v i , a i ] T is the ith state vector of the vehicle, s i is the driving distance of the vehicle at t i , v i is the speed of the vehicle at t i , a i is the acceleration of the vehicle at t i , X i+1 =f(X i , A i ) is the state transition equation of the vehicle, s1, v1, a1 are variables representing the driving distance, speed and acceleration at the starting point, s S , v S , a S are the driving distance, speed and acceleration determined at the starting point, sN v N a N Let be the variables representing the distance traveled, speed, and acceleration at the destination, s E v E a E Let v be the distance traveled, speed, and acceleration determined at the destination, where 0 ≤ v i ≤v max (s i () represents the speed limit, v max (s i ) represents the distance traveled in s i The maximum speed at time a min ≤a i ≤a max For acceleration limitation, a min For minimum acceleration, a max This is the maximum acceleration.

[0178] In this embodiment of the application, the speed planning model from the starting point to the ending point constructed based on the vehicle's state transition equation (4) can be specifically shown in equation (5):

[0179]

[0180] The design variable to be solved is the sequence A of behavior vectors. i The solution rule is to solve the problem within -j while satisfying the constraints. max , 0, j max Choose the larger of the three values, j max It is the upper limit of jerk in speed planning.

[0181] The constraints of the velocity programming model consider five aspects: longitudinal motion model, boundary conditions, velocity limits, acceleration limits, and time monotonicity constraints. Specifically, in the velocity limits, the lower velocity limit is 0, and the upper velocity limit is v. max (s), since the longitudinal motion model in equation (4) is a recursive equation with time as the independent variable, and v max (s) is a function of the travel distance s, causing this constraint to exhibit significant nonlinearity. Compared to existing methods that cannot directly handle this constraint, or use approximation to convert the dynamic constraint into a fixed constraint, or use local linearization to process it into a linear function, or require updating the constraint in each iteration cycle, the embodiments of this application, through the aforementioned planning of the first speed curve and the second speed curve, correlate the first speed curve and the second speed curve with v. max(s) comparing, determining whether the first speed curve and the second speed curve satisfy the dynamic speed upper limit constraint, and adopting corresponding processing measures based on the determination result to achieve accurate processing of the dynamic speed upper limit constraint related to the driving route, without needing to perform approximate or linearization processing, preventing the speed planning result from violating the constraint, obtaining an accurate result, and making the calculation complexity a linear function of the path length, reducing the complexity of calculation and saving computing power.

[0182] The speed planning method provided in the embodiments of the present application has a constant constraint planning model for distance from the boundary, which is as follows:

[0183]

[0184] In formula (6), t N is the time to reach the terminal state, min.t N is the objective function of the constant constraint planning model for distance from the boundary.

[0185] When the first speed curve considers planning a shortest path to reach the terminal state from the current state at a fixed speed upper limit, the constant constraint planning model for distance from the boundary can be specifically as shown in formula (6) above.

[0186] The speed planning method provided in the embodiments of the present application has a constant constraint planning model for distance from the boundary, which is as follows:

[0187]

[0188] When the second speed curve is a speed planning problem of given starting point speed, starting point acceleration, terminal speed, terminal acceleration, needing to satisfy acceleration upper and lower limit and jerk upper and lower limit constraints, and requiring the shortest driving time, the constant constraint planning model for distance from the boundary can be specifically as shown in formula (7) above.

[0189] The speed planning method provided in the embodiments of the present application has an acceleration boundary speed planning model, which is as follows:

[0190]

[0191] In the embodiments of the present application, in order to facilitate solving formula (6) and formula (7), the acceleration boundary speed planning model shown in formula (8) can be planned, and formula (8) is solved.

[0192] For solving formula (8), it can be seen from formula (8) that the acceleration change between two adjacent states is jΔt, if only the accelerations at the starting point and the terminal point are constrained, j takes the limit of jerk (j max or-j max) will make the required Δt minimum, and only a piece of behavior is needed to reach the end point acceleration, i.e. the solution of equation (8) is specifically shown in equation (9):

[0193]

[0194] According to the behavior in the above equation, the generated speed change is:

[0195]

[0196] The speed planning problem of the second speed curve has been defined in equation (7), compared with the acceleration boundary problem defined in equation (8), the acceleration constraints of the start point and the end point are added, and the upper and lower limit constraints of the acceleration are added, here the speed increment from the start point to the end point is divided into five cases, and the solution of equation (7) has five cases, which are specifically shown in Figure 5 (a)-(e), Figure 5 (a)-(e) shows five solutions of the steady constraint planning model of the speed boundary provided by the embodiment of the application, and the specific results of the five solutions in Figure 5 are given as follows:

[0197] (I)

[0198] Specifically, as shown in Figure 5 (a), it corresponds to the speed, acceleration and jerk distribution when , wherein the horizontal coordinate is time, and the vertical coordinate corresponds to speed, acceleration and jerk.

[0199] When the speed increment from the start point to the end point is greater than the critical value of adjusting the acceleration to a max , a uniform acceleration segment with acceleration a max will be generated, i.e.

[0200]

[0201] (II)

[0202] Specifically, as shown in Figure 5 (b), it corresponds to the speed, acceleration and jerk distribution when , wherein the horizontal coordinate is time, and the vertical coordinate corresponds to speed, acceleration and jerk.

[0203] When the speed increment from the start point to the end point is between the critical value of adjusting the acceleration to a max and the special solution of directly adjusting the acceleration to a E , there is no uniform acceleration segment, only a behavior of increasing acceleration and a behavior of decreasing acceleration, i.e.

[0204]

[0205] (three)

[0206] Specifically as shown in (c), which corresponds to the velocity, acceleration and jerk distribution at the time, wherein the abscissa is time, and the ordinate corresponds to the velocity, acceleration and jerk. Figure 6

[0207] When the velocity increment from the starting point to the end point is less than the critical value of adjusting the acceleration to a min , a uniform deceleration segment with acceleration a min will be generated, that is:

[0208]

[0209]

[0210] Specifically as shown in (d), which corresponds to the velocity, acceleration and jerk distribution at the time, wherein the abscissa is time, and the ordinate corresponds to the velocity, acceleration and jerk. Figure 6

[0211] When the velocity increment from the starting point to the end point is between the critical value of adjusting the acceleration to a min and the special solution of directly adjusting the acceleration to a E , there is no uniform acceleration segment, only a segment of acceleration reduction and a segment of acceleration increase, that is:

[0212]

[0213] (five)

[0214] Specifically as shown in (e), which corresponds to the velocity, acceleration and jerk distribution at the time, wherein the abscissa is time, and the ordinate corresponds to the velocity, acceleration and jerk. Figure 6

[0215] When the velocity increment from the starting point to the end point is exactly equal to the special solution of directly adjusting the acceleration from a S to a E , there is only one segment, that is, the acceleration boundary velocity planning corresponding to formula (9).

[0216] The above five cases are the solution results of formula (7).

[0217] ​​​​​​Next, the solving of equation (6) is performed, and the constant constraint planning model of distance boundary is shown in equation (6) (that is, the S-shaped velocity planning problem of distance boundary is defined in equation (6)), and here, the planning problem of velocity boundary (that is, the model shown in equation (7)) is used as a basis, and the above-mentioned similar idea of solving equation (7) is used to solve equation (6).

[0218] Where, for the next representation, the behavior sequence obtained by solving equation (7) using the above-mentioned algorithm is written as A(v S ,a S ,v E ,a E ), N is represented as N(v S ,a S ,v E ,a E ), and the generated distance increment is represented as Δs(v S ,a S ,v E ,a E ).

[0219] Specifically, the solving result of equation (6) can be divided into three cases, which can be seen from Figure 6 (a)-(c) shown, Figure 6 (a)-(c) shows the schematic diagram of three solutions of the constant constraint planning model of distance boundary provided by the embodiment of the application, and the decomposition conditions and calculation methods of the three solutions are given below.

[0220] (I) Case 1: There is v max uniform speed section

[0221] Specifically, as shown in Figure 6 (a), it is the velocity, acceleration and jerk distribution when there is v max uniform speed section, where the horizontal coordinate is time, and the vertical coordinate corresponds to velocity, acceleration and jerk.

[0222] The critical state of this case is that the duration of v max uniform speed section is 0, that is, this case needs to satisfy the following condition:

[0223] s E -s S >Δs(v S ,a S ,v max ,0)+Δs(v max ,0,v E ,a E ) (15)

[0224] When the condition of equation (15) is satisfied, the behavior sequence is:

[0225]

[0226] (ii) Case 2: There exists a point with v' acceleration of 0

[0227] Specifically as shown in Figures 7-9 (b), which is the velocity, acceleration and jerk distribution when there exists a point with v' acceleration of 0, wherein the horizontal coordinate is time, and the vertical coordinate corresponds to velocity, acceleration and jerk.

[0228] When the condition in equation (15) is not met, the velocity cannot be increased to v max , but only to some intermediate value v' and needs to start deceleration (as shown in Figure 7 (b)), as the distance increment s E -s S gradually decreases, v' will also continue to decline, and the lower limit v0 is:

[0229]

[0230] According to the lower limit of v', case 2 should meet equation (18) under the premise that equation (15) is not met:

[0231] s E -s S ≥ Δs(v S , a S , v0, 0) + Δs(v0, 0, v E , a E ) (18)

[0232] The resulting behavior sequence is:

[0233]

[0234] The v' required to solve the behavior sequence according to equation (19) can be determined by the following equation:

[0235] s E -s S ≥ Δs(v S , a S , v', 0) + Δs(v', 0, v E , a E ) v' ∈ [v0, v max ] (20)

[0236] (iii) Case 3: There is no point with acceleration of 0

[0237] Specifically as shown in Figure 7 (c), which is the velocity, acceleration and jerk distribution when there is no point with acceleration of 0, wherein the horizontal coordinate is time, and the vertical coordinate corresponds to velocity, acceleration and jerk.

[0238] If in case two v' reaches its lower limit, the distance increment s E -s S Further reduction, not satisfying equation (18) but still satisfying equation (21), will lead to case three, i.e. there is no intermediate state with acceleration of 0.

[0239] s E -s S ≥ Δs(v S , a S , v E , a E ) (21)

[0240] At this time, the behavior sequence is:

[0241]

[0242] Where a' is not 0.

[0243] The v' and a' required for equation (22) are determined by solving the equation in:

[0244]

[0245] The above three cases are the results of solving equation (6).

[0246] According to the above-mentioned algorithm of the present application, the time- shortest smooth speed curve satisfying the dynamic speed constraint can be obtained. Specifically, the above-mentioned algorithm of the present application can be verified by three kinds of dynamic speed upper limits, which can be referred to in Figure 7 . Figure 8 (a)-(b) are the speed planning results provided by the embodiment of the present application under the condition of step speed upper limit, wherein, Figure 8 (a) is a schematic diagram of the final speed planning curve and the distribution of step speed upper limit, the horizontal coordinate is the travel distance, and the vertical coordinate is the speed, Figure 8 (b) is a schematic diagram of the distribution of planned speed, acceleration and jerk, the horizontal coordinate is time, and the vertical coordinate corresponds to speed, acceleration and jerk. Figure 9 (a)-(b) are the speed planning results provided by the embodiment of the present application under the condition of step speed upper limit, wherein, Figure 9 (a) is a schematic diagram of the final speed planning curve and the distribution of step speed upper limit, the horizontal coordinate is the travel distance, and the vertical coordinate is the speed, Figure 9 (b) is a schematic diagram of the distribution of planned speed, acceleration and jerk, the horizontal coordinate is time, and the vertical coordinate corresponds to speed, acceleration and jerk. Figures 7-9(a)-(b) are schematic diagrams of the speed planning results in the case of the upper limit of the random speed provided by the embodiments of the present application, wherein, ​ (a) is a schematic diagram of the final speed planning curve and the distribution of the upper limit of the random speed, ​ (b) is a schematic diagram of the distribution of the planned speed, acceleration and jerk, wherein the horizontal coordinate is time and the vertical coordinate corresponds to the speed, acceleration and jerk. ​ It can be seen that the algorithm provided by the present application can plan a smooth speed curve in various cases, and the speed curve in each case is tangent to the upper limit of the speed. The fastest speed curve is successfully planned by using the algorithm provided by the present application.

[0247] The embodiments of the present application also provide a speed planning device, which can include:

[0248] a memory for storing a computer program;

[0249] a processor for implementing the steps of any of the above speed planning methods when executing the computer program.

[0250] The speed planning device can be a vehicle computer, a controller or the like.

[0251] The embodiments of the present application also provide a vehicle including the above speed planning device.

[0252] The embodiments of the present application also provide a readable storage medium, and the readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps of any of the above speed planning methods.

[0253] The description of the related parts of the speed planning device, the vehicle and the readable storage medium provided by the embodiments of the present application can refer to the detailed description of the corresponding parts of the speed planning method provided by the embodiments of the present application, and will not be repeated here.

[0254] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "readable storage medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the readable storage medium could even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0255] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0256] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0257] In addition, the terms "first", "second", etc. are used only for the purpose of description, and should not be understood as indicating or implying relative importance or implying a number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise explicitly and specifically limited.

[0258] In the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting", "fixing" and the like should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or it can be integrated; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the internal communication of two elements or the interaction relationship between two elements, unless otherwise explicitly limited. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0259] 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 limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A speed planning method characterized by, The method comprises the following steps: constructing a speed planning model from a starting point to an ending point according to a state transition equation of a vehicle; the speed planning model comprises a jerk value range; determining a candidate behavior vector according to the jerk value range, the candidate behavior vector comprising a jerk and a duration of the jerk; planning a first speed curve from a current state to the ending state based on the speed planning model, and determining whether the first speed curve satisfies a speed upper limit constraint; if not, expanding the current state, selecting a target candidate state from the expanded candidate states as the current state, and returning to the step of planning the first speed curve from the current state to the ending state based on the speed planning model; expanding the current state, selecting a target candidate state from the expanded candidate states as the current state, comprising: expanding the current state according to the candidate behavior vector, planning a second speed curve according to the candidate state, determining a target candidate state according to the second speed curve and the speed upper limit constraint, and determining the target candidate state as the current state; determining the target candidate state according to the second speed curve and the speed upper limit constraint, comprising: determining a candidate state corresponding to a candidate behavior vector with the largest jerk that satisfies the speed upper limit constraint as the target candidate state; if yes, obtaining a speed planning result according to the first speed curve.

2. The speed planning method of claim 1, wherein, The speed upper limit constraint is a function of a driving distance.

3. The speed planning method of claim 1, wherein, Before determining the target candidate state as the current state, the method further comprises the following steps: determining whether a planned driving distance of the vehicle according to the target candidate state exceeds an ending driving distance; if yes, obtaining a speed planning result according to the target candidate state; if not, executing the step of determining the target candidate state as the current state.

4. The speed schedule method of claim 1, wherein, The method further comprises the following steps: arranging the candidate behavior vectors in descending order of jerk; expanding the current state according to the candidate behavior vector, planning a second speed curve according to the candidate state, and determining a target candidate state according to the second speed curve and the speed upper limit constraint, comprising: arranging the candidate behavior vector at the first position as a current candidate behavior vector, expanding the current state according to the current candidate behavior vector to obtain a candidate state; determining whether the second speed curve satisfies the speed upper limit constraint; if yes, determining the candidate state corresponding to the current candidate behavior vector as the target candidate state; if not, arranging the candidate behavior vector at the next position as the current candidate behavior vector, and returning to the step of expanding the current state according to the current candidate behavior vector.

5. The speed planning method of claim 4, wherein, After expanding the current state according to the current candidate behavior vector, the method further comprises the following steps: determining whether the obtained candidate state satisfies the speed upper limit constraint; if yes, executing the step of planning the second speed curve according to the candidate state and the speed planning model; if not, executing the step of planning the second speed curve according to the candidate state and the speed planning model. If not, the step of arranging the next candidate behavior vector as the current candidate behavior vector is performed.

6. The speed schedule method of claim 4, wherein, When the current candidate behavior vector is the last candidate behavior vector, if it is determined that the second speed curve does not satisfy the speed upper limit constraint, further comprising: determining that the planning fails, and outputting a prompt of planning failure.

7. The speed planning method according to any one of claims 1 to 6, characterized in that, After constructing a speed planning model from the start point to the end point according to a state transition equation of the vehicle, further comprising: constructing a distance boundary constant constraint planning model according to the speed planning model; the distance boundary constant constraint planning model comprises a time shortest objective function, and constraint conditions of the distance boundary constant constraint planning model comprise a start point boundary, an end point boundary, a speed limit, an acceleration limit and a jerk value range, wherein the speed upper limit in the speed limit is a fixed value; planning a first speed curve from a current state to a terminal state based on the speed planning model, comprising: planning a first speed curve from the current state to the terminal state based on the distance boundary constant constraint planning model.

8. The speed planning method of claim 7, wherein, After constructing a speed planning model from the start point to the end point according to a state transition equation of the vehicle, further comprising: constructing a distance boundary constant constraint planning model according to the speed planning model; the distance boundary constant constraint planning model comprises a time shortest objective function, and constraint conditions of the distance boundary constant constraint planning model comprise a start point boundary, an end point boundary, a speed limit, an acceleration limit and a jerk value range, wherein the speed upper limit in the speed limit is a fixed value; planning a first speed curve from a current state to a terminal state based on the speed planning model, comprising: planning a first speed curve from the current state to the terminal state based on the distance boundary constant constraint planning model.

9. The speed scheduling method of claim 8, wherein, Before planning a second speed curve from a candidate state to a parking state based on the speed boundary constant constraint planning model, further comprising: constructing an acceleration boundary speed planning model, and solving the acceleration boundary speed planning model to obtain a first solving result; the acceleration boundary speed planning model comprises a time shortest objective function, and constraint conditions of the acceleration boundary speed planning model comprise a start point acceleration, an end point acceleration and a jerk value range, wherein the start point acceleration, the end point acceleration and the upper and lower limits of the jerk are constants; planning a second speed curve from the candidate state to the parking state based on the speed boundary constant constraint planning model, comprising: solving the speed boundary constant constraint planning model according to the first solving result to obtain a second solving result; obtaining a second speed curve from the candidate state to the parking state based on the candidate state and the second solving result.

10. The speed scheduling method of claim 9, wherein, planning a first speed curve from a current state to a terminal state based on the distance boundary constant constraint planning model, comprising: solving the distance boundary constant constraint planning model according to the second solving result to obtain a third solving result; According to the current state and the third solving result, a first speed curve with the shortest time from the current state to the terminal state is obtained.

11. The speed scheduling method of claim 10, wherein, The speed planning model is: wherein, is the ith behavior vector, is the duration of the ith behavior vector, is the jerk of the vehicle in the ith behavior vector, is the set of real numbers, is the number of behavior vectors, is the number of states of the vehicle, is the upper limit of jerk in speed planning, is the ith state vector of the vehicle, is the travel distance of the vehicle at time , is the speed of the vehicle at time , is the acceleration of the vehicle at time , is the state transition equation of the vehicle, , , is the variable representing the travel distance, speed and acceleration at the start point, , , is the determined travel distance, speed and acceleration at the start point, , , is the variable representing the travel distance, speed and acceleration at the end point, , , is the determined travel distance, speed and acceleration at the end point, is the speed limit, is the maximum speed at travel distance , is the acceleration limit, is the minimum acceleration, is the maximum acceleration.

12. The speed scheduling method of claim 11, wherein, The constant constraint planning model of the distance boundary is: wherein, is the time to reach the end state.

13. The speed scheduling method of claim 11, wherein, The constant constraint planning model of the speed boundary is: 。 14. The speed scheduling method of claim 11, wherein, The acceleration boundary speed planning model is: 。 15. A speed planning device characterized by comprising: Comprising: A memory for storing a computer program; A processor for implementing the steps of the speed planning method according to any one of claims 1 to 14 when executing the computer program.

16. A vehicle characterized by comprising: The speed planning device according to claim 15.

17. A readable storage medium, characterized by, The readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the speed planning method according to any one of claims 1 to 14.

Images