Track planning method and device, electronic equipment and storage medium

Abstract

The invention relates to a trajectory planning method and device, electronic equipment and a storage medium, and the method comprises the steps: taking a current position point of a moving tool as a planning starting point, and determining a plurality of trajectory sampling points according to a preset sampling distance; obtaining a state quantity constraint value of each track sampling point and a motion state quantity of the planning starting point; establishing a state prediction model based on the state quantity constraint value of each track sampling point and the motion state quantity of the planning starting point; and based on the state prediction model, solving the motion state quantity of each trajectory reference point trajectory sampling point to obtain a planned trajectory. According to the scheme provided by the invention, the motion state quantity comprises the transverse state quantity and the longitudinal state quantity, so that a transverse and longitudinal coupled trajectory planning scheme can be realized, the state quantity constraint value of each trajectory sampling point can be accurately obtained through a distance sampling mode, and a more accurate state quantity prediction model is established; and the accuracy and safety of the trajectory planning process are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a trajectory planning method, device, electronic device and storage medium. Background Art

[0002] In the field of intelligent driving, accurate trajectory planning directly impacts the safety of mobile vehicles. In related technologies, trajectory planning is typically divided into two parts: lateral and longitudinal trajectory planning. Traditionally, two trajectory planning schemes have been employed: decoupled lateral and longitudinal trajectory planning and coupled lateral and longitudinal trajectory planning.

[0003] However, decoupled lateral and longitudinal trajectory planning requires separating lateral and longitudinal trajectory planning, which can lead to inconsistent lateral and longitudinal trajectory planning results, affecting the accuracy of trajectory planning. Coupled lateral and longitudinal trajectory planning requires time sampling to obtain lateral and longitudinal state quantities at different moments. However, since time sampling cannot accurately obtain the boundary conditions of the lateral and longitudinal state quantities at different moments, the results of coupled lateral and longitudinal trajectory planning suffer from low accuracy and security. Summary of the Invention

[0004] In order to solve or partially solve the problems existing in the related art, the present application provides a trajectory planning method, device, electronic device and storage medium, which can obtain a more accurate planned trajectory in the horizontal and vertical coupled trajectory planning process.

[0005] A first aspect of the present application provides a trajectory planning method, the method comprising:

[0006] Taking the current position of the mobile tool as the planning starting point, multiple trajectory sampling points are determined according to the preset sampling distance;

[0007] Obtaining a state constraint value of each trajectory sampling point and a motion state value of the planning starting point;

[0008] Establishing a state prediction model based on the state constraint value of each trajectory sampling point and the motion state of the planning starting point; wherein the state prediction model includes an optimization function with the motion state of each trajectory sampling point as the optimization target and the constraint conditions of the optimization target;

[0009] Based on the state prediction model, the motion state quantity of each trajectory sampling point is solved to obtain the planned trajectory; wherein the motion state quantity includes a lateral state quantity and a longitudinal state quantity.

[0010] According to the trajectory planning method provided in the present application, the motion state quantity includes any one or more of the following: driving speed, a speed derivative value related to the driving speed, a sampling time, a lateral position, and a position derivative value related to the lateral position.

[0011] According to the trajectory planning method provided in this application, the process of constructing the optimization function includes:

[0012] Establishing the corresponding relationship between the driving speed and speed derivative value of each trajectory sampling point and the longitudinal speed change state to obtain the first sub-function;

[0013] Establish the corresponding relationship between the sampling time of each trajectory sampling point and the driving efficiency to obtain the second sub-function;

[0014] Establish the corresponding relationship between the lateral position and position derivative value of each trajectory sampling point and the steering state to obtain the third sub-function;

[0015] Establishing the corresponding relationship between the driving speed, speed derivative value, position derivative value and lateral offset state of each trajectory sampling point to obtain the fourth sub-function;

[0016] The first sub-function, the second sub-function, the third sub-function and the fourth sub-function are summed to obtain an optimized function.

[0017] According to the trajectory planning method provided in this application, the process of determining the constraint conditions includes:

[0018] Establish the correlation relationship between the motion state quantities of adjacent trajectory points to obtain the first sub-condition;

[0019] The motion state quantity of the optimization starting point is limited based on the motion state quantity of the planning starting point to obtain a second sub-condition;

[0020] The third sub-condition is obtained by limiting the value range of the motion state quantity of the trajectory sampling point based on the state quantity constraint value;

[0021] The first sub-condition, the second sub-condition and the third sub-condition are used as constraint conditions.

[0022] According to the trajectory planning method provided by the present application, the establishment of the correlation relationship between the motion state quantities of adjacent trajectory points to obtain the first sub-condition includes:

[0023] Establish the correlation relationship between the longitudinal state quantities of adjacent trajectory points and obtain the longitudinal correlation condition;

[0024] Establish the correlation relationship between the lateral state quantities of adjacent trajectory points and obtain the lateral correlation conditions;

[0025] The vertical association condition and the horizontal association condition are used as the first sub-condition.

[0026] According to the trajectory planning method provided by the present application, the state quantity constraint value includes a driving speed constraint value, a derivative constraint value related to the driving speed, a lateral position constraint value, and a derivative constraint value related to the lateral position;

[0027] The third sub-condition is obtained by limiting the value range of the motion state quantity of the trajectory sampling point based on the state quantity constraint value, including:

[0028] Limiting the value range of the longitudinal state quantity of the trajectory sampling point based on the driving speed constraint value and the derivative constraint value related to the driving speed to obtain a longitudinal value condition;

[0029] Limiting the value range of the lateral state quantity of the trajectory sampling point based on the lateral position constraint value and the derivative constraint value related to the lateral position to obtain a lateral value condition;

[0030] The vertical value condition and the horizontal value condition are used as the third sub-condition.

[0031] According to the trajectory planning method provided in this application, the motion state quantity of each trajectory sampling point is solved based on the state prediction model to obtain the planned trajectory, including:

[0032] The state prediction model is input into the solver for optimization and solution to obtain the motion state quantity of each trajectory sampling point;

[0033] All trajectory sampling points with known motion state quantities are used as planning trajectories.

[0034] A second aspect of the present application provides a trajectory planning device, the device comprising:

[0035] The sampling module is used to determine multiple trajectory sampling points according to a preset sampling distance using the current position of the mobile tool as the planning starting point;

[0036] An acquisition module, configured to acquire a state constraint value of each trajectory sampling point and a motion state value of the planning starting point;

[0037] a modeling module for establishing a state prediction model based on the state constraint value of each trajectory sampling point and the motion state value of the planning starting point; wherein the state prediction model includes an optimization function with the motion state value of each trajectory sampling point as an optimization target and the constraint conditions of the optimization target;

[0038] The planning module is used to solve the motion state quantity of each trajectory sampling point based on the state prediction model to obtain a planned trajectory; wherein the motion state quantity includes a lateral state quantity and a longitudinal state quantity.

[0039] A third aspect of the present application provides an electronic device, including:

[0040] processor; and

[0041] The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method described above.

[0042] A fourth aspect of the present application provides a mobile tool, comprising: multiple data sources and the electronic device as described above, wherein the data sources are communicatively connected to the electronic device.

[0043] A fifth aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method described above.

[0044] The technical solution provided by this application may have the following beneficial effects:

[0045] By using distance sampling to determine multiple trajectory sampling points, the state constraint value for each trajectory sampling point can be accurately obtained. Based on the state constraint value for each trajectory sampling point and the motion state of the planning starting point, a state prediction model can be established to solve the motion state of each trajectory sampling point and obtain the planned trajectory. Because the motion state includes both lateral and longitudinal state quantities, a coupled lateral and longitudinal trajectory planning scheme can be implemented. Furthermore, compared to time sampling, distance sampling can accurately obtain the state constraint value for each trajectory sampling point, enabling the establishment of a more precise state prediction model, improving the accuracy and safety of the trajectory planning process.

[0046] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0048] Figure 1 This is one of the flow charts of the trajectory planning method shown in the embodiment of the present application;

[0049] Figure 2 Schematic diagram of the relationship between the lateral position constraint value and the longitudinal position in an embodiment of the present application;

[0050] Figure 3Schematic diagram of the relationship between the driving speed constraint value and the longitudinal position in an embodiment of the present application;

[0051] Figure 4 Schematic diagram of the relationship between the lateral position constraint value and the longitudinal position after adjustment based on the obstacle avoidance decision result in an embodiment of the present application;

[0052] Figure 5 This is the second flow chart of the trajectory planning method shown in the embodiment of the present application;

[0053] Figure 6 Schematic diagram of the structure of the trajectory planning device shown in the embodiment of the present application;

[0054] Figure 7 is a schematic structural diagram of an electronic device shown in an embodiment of the present application;

[0055] Figure 8 It is a structural schematic diagram of a mobile tool shown in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following describes embodiments of the present application in more detail with reference to the accompanying drawings. Although the accompanying drawings illustrate embodiments of the present application, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Rather, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0057] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0058] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0059] This embodiment relates to the field of intelligent driving and can be specifically applied to trajectory planning scenarios for intelligent driving. In traditional trajectory planning scenarios, both horizontally and vertically decoupled trajectory planning solutions and horizontally and vertically coupled trajectory planning solutions suffer from inaccurate and unsafe trajectory planning results.

[0060] In response to the above problems, an embodiment of the present application provides a trajectory planning method that can improve the accuracy and security of trajectory planning results of horizontal and vertical coupling.

[0061] The following combination Figures 1 to 8 The technical solutions of the trajectory planning method, device, electronic device and storage medium provided in the embodiments of the present application are described in detail.

[0062] Figure 1 It is a flow chart of the trajectory planning method shown in an embodiment of the present application.

[0063] See also Figure 1 The trajectory planning method provided in the embodiment of the present application specifically includes:

[0064] Step 101: Taking the current position of the mobile tool as the planning starting point, a plurality of trajectory sampling points are determined according to a preset sampling distance.

[0065] In practical applications, the current location of the mobile tool can be determined first, and then the planning starting point can be determined based on the current location. Specifically, the coordinates of the current location of the mobile tool can be transformed to obtain the planning starting point. Then, starting from the planning starting point, sampling is performed at a preset sampling distance Δs to obtain multiple trajectory sampling points.

[0066] It is understood that the number of trajectory sampling points n can be reasonably set according to the actual scenario requirements. For example, in scenarios with high trajectory planning accuracy requirements, the number of trajectory sampling points n can be set slightly larger. This way, the final planned trajectory contains more trajectory sampling points, making the trajectory more accurate and reliable. For scenarios with low trajectory planning accuracy requirements, the number of trajectory sampling points n can be set slightly smaller. This way, the final planned trajectory contains fewer trajectory sampling points, the trajectory generation process is faster, and thus the trajectory planning efficiency can be improved.

[0067] In a specific implementation, the preset sampling distance Δs may be determined according to the travel speed of the mobile tool at the planning starting point. Specifically, the preset sampling distance Δs may be proportional to the travel speed of the mobile tool at the planning starting point.

[0068] Step 102: Obtain the state constraint value of each trajectory sampling point and the motion state value of the planning starting point.

[0069] In this embodiment, the state constraint values ​​are primarily used to define the driving limit states of the mobile tool at corresponding trajectory sampling points, such as the driving speed limit and the lateral offset limit of the mobile tool. Since the state constraint values ​​are primarily constrained by longitudinal position, they are directly related to longitudinal position.

[0070] In a specific implementation, taking the driving speed constraint value and the lateral position constraint value in the state quantity constraint value as an example, the corresponding relationship between the two and the longitudinal position S can be respectively referred to Figure 2 and Figure 3 . Figure 2 The corresponding relationship between the horizontal position constraint value and the longitudinal position S is shown, where the horizontal coordinate is the longitudinal position S and the vertical coordinate is the maximum value l of the horizontal position max and the minimum horizontal position l min . Figure 3 The corresponding relationship between the driving speed constraint value and the longitudinal position S is shown, where the horizontal axis is the longitudinal position S and the vertical axis is the maximum driving speed v max and the minimum value of the driving speed v min .

[0071] In practical applications, the left and right boundaries of the lateral position can be determined based on the lateral decision results of the static obstacle given by the decision module. max and l min Further adjustments. Figure 4 As shown, based on the decision result made by the decision module to avoid the obstacle obj1 to the right, the maximum lateral position of the corresponding trajectory sampling point is l max Reduce, based on the decision result made by the decision module to avoid the obstacle obj2 to the left, the minimum value l of the lateral position of the corresponding trajectory sampling point min Increase, and finally get the left and right boundaries l of the lateral position at different trajectory sampling points max and l min .

[0072] In this embodiment, the trajectory sampling points are determined based on distance sampling. That is, the longitudinal position of each trajectory sampling point is known, so the state quantity constraint value corresponding to each trajectory sampling point can be determined more accurately.

[0073] It is understandable that the motion state quantity of the planning starting point is a known parameter in the trajectory planning process, which can be collected by a data acquisition device on the mobile tool or manually set before trajectory planning.

[0074] Step 103: Based on the state constraint value of each trajectory sampling point and the motion state value of the planning starting point, a state prediction model is established; wherein the state prediction model includes an optimization function with the motion state value of each trajectory sampling point as the optimization target and the constraint conditions of the optimization target.

[0075] It should be noted that the state prediction model is mainly used to optimize the motion state quantity of each trajectory sampling point. Therefore, the state prediction model consists of two parts: optimization function and constraint conditions. The optimization function is mainly used to characterize the correspondence between the function value J and the motion state quantity of each trajectory sampling point. The constraint conditions are used to constrain the relevant independent variables in the optimization function to ensure that the motion state quantity obtained by the optimization solution is within a certain constraint range.

[0076] Step 104: Based on the state prediction model, the motion state quantity of each trajectory sampling point is solved to obtain the planned trajectory; wherein the motion state quantity includes the lateral state quantity and the longitudinal state quantity.

[0077] By solving the state prediction model, we can obtain the value of the motion state quantity corresponding to the minimum value of the function value J, that is, the optimal value of the motion state quantity of each trajectory sampling point, thereby solving the motion state quantity of each trajectory sampling point and obtaining the planned trajectory.

[0078] The trajectory planning method provided in this embodiment, because the motion state variables include lateral and longitudinal state variables, can achieve coupled processing of the lateral and longitudinal motion state variables through a state prediction model, thus realizing a trajectory planning function that is coupled laterally and longitudinally. This effectively avoids or reduces the problems of inconsistent planned trajectories, poor comfort, and poor economy associated with trajectory planning schemes that are decoupled laterally and longitudinally, thereby improving driving safety, efficiency, and comfort indicators for mobile vehicles. Furthermore, the distance sampling method can obtain more accurate state constraint values, resolving the issues of inaccurate speed limits and static obstacle avoidance caused by temporal sampling in trajectory planning schemes that are coupled laterally and longitudinally, thereby improving the accuracy and safety of planned trajectories.

[0079] In one embodiment, the motion state quantity includes any one or more of the following: driving speed, a speed derivative value related to the driving speed, a sampling time, a lateral position, and a position derivative value related to the lateral position.

[0080] Among them, the driving speed The first-order derivative of the time t used to characterize the travel distance s of the mobile tool along the road direction indicates the travel speed of the mobile tool along the road direction.

[0081] The speed derivative value related to the driving speed includes the driving acceleration of the mobile tool along the road direction and the driving jerk of the mobile tool along the road direction.

[0082] Driving acceleration The second-order derivative of the time-based distance s used to characterize the travel distance of the mobile tool along the road direction represents the travel acceleration of the mobile tool along the road direction.

[0083] Driving jerk The third-order derivative of the time-based method used to characterize the travel distance s of the mobile tool along the road direction represents the travel acceleration of the mobile tool along the road direction.

[0084] The sampling time t is used to represent the timestamp information corresponding to each sampling point (ie, trajectory sampling point).

[0085] The lateral position l is used to represent the lateral offset of the mobile tool relative to the center line of the road.

[0086] The position derivative value related to the lateral position includes the rate at which the lateral position of the mobile tool changes with the distance, and the acceleration at which the lateral position of the mobile tool changes with the distance.

[0087] The rate at which the lateral position of the moving tool changes with distance It is used to characterize the first-order derivative of the lateral position based on the distance s traveled by the mobile tool along the road direction. It indicates the rate at which the lateral position of the mobile tool changes with the distance traveled. When its value is not large, it is approximately equal to the relative heading information in the Frenet coordinate system.

[0088] The acceleration of the mobile tool's lateral position as the distance changes The second-order derivative used to characterize the lateral position based on the travel distance s of the mobile tool along the road direction represents the acceleration of the lateral position of the mobile tool as the distance changes, that is, the curvature information.

[0089] Among the above-mentioned motion state quantities, the driving speed and the speed derivative value related to the driving speed are longitudinal state quantities, the lateral position and the position derivative value related to the lateral position are lateral state quantities, and the sampling time can be classified as either a longitudinal state quantity or a lateral state quantity.

[0090] In one embodiment, the process of constructing the optimization function specifically includes:

[0091] Establishing the corresponding relationship between the driving speed and speed derivative value of each trajectory sampling point and the longitudinal speed change state to obtain the first sub-function;

[0092] Establish the corresponding relationship between the sampling time of each trajectory sampling point and the driving efficiency to obtain the second sub-function;

[0093] Establish the corresponding relationship between the lateral position and position derivative value of each trajectory sampling point and the steering state to obtain the third sub-function;

[0094] Establishing the corresponding relationship between the driving speed, speed derivative value, position derivative value and lateral offset state of each trajectory sampling point to obtain the fourth sub-function;

[0095] The first sub-function, the second sub-function, the third sub-function and the fourth sub-function are summed to obtain an optimized function.

[0096] In the process of establishing the optimization function, multiple optimization items that have a significant impact on the driving efficiency, comfort, and safety of the mobile tool can be comprehensively considered, as follows:

[0097] The smaller the better, that is, the driving speed at the i-th trajectory point The larger the better, as long as the maximum speed constraint is met, which is conducive to improving driving efficiency.

[0098] The smaller the better, that is, the driving acceleration at the i-th trajectory point The smaller, the better the comfort.

[0099] The smaller the better, that is, the driving acceleration at the i-th trajectory point The smaller, the better the comfort.

[0100] t i The smaller the better, the sampling time t at the i-th trajectory point i The smaller it is, the shorter the time it takes for the mobile tool to reach the designated location and the higher the driving efficiency.

[0101] l i The smaller the better, the lateral position l at the i-th trajectory point i The smaller it is, the closer the planned trajectory is to the road centerline and away from the road boundary, and the higher the driving safety of the mobile tool.

[0102] l′ i The smaller the better, the rate l′ of change of the lateral position of the i-th trajectory point with the distance i When the value is small, it is approximately equal to the angle with the center line of the road. The smaller the angle with the center line of the road, the smoother and safer the trajectory. This optimization item mainly works at low speeds.

[0103] l″ i The smaller the better, l″ i It is approximately equal to the curvature of the planned trajectory. A trajectory with a smaller curvature is smoother, which can reduce the amplitude of the steering wheel movement and the amplitude of the speed reduction when turning, which is beneficial to improving driving safety and comfort, improving driving efficiency, and reducing energy consumption and emissions.

[0104] l″′ i The smaller the better, l″′i Approximately equal to the curvature of the planned trajectory based on the rate of change of the road direction distance, the smaller l″′ i The trajectory is smoother, and the steering wheel speed is smaller. This optimization item is beneficial to improving safety and comfort during driving.

[0105] The smaller the better, Represents the lateral deviation velocity of the planned trajectory, which is related to l′ i The difference in the optimization term is that it has a better objective function penalty effect at high speeds.

[0106] The smaller the better, represents the lateral acceleration of the planned trajectory, which is related to l″ i The difference of the optimization item is that it has a better effect at high speeds, achieving a more comfortable and safe planning trajectory.

[0107] The smaller the better, represents the lateral acceleration, which is related to l″′ i The difference of the optimization item is that it has a better effect at high speeds, achieving a more comfortable and safe planning trajectory.

[0108] Based on the above multiple optimization items, a first sub-function, a second sub-function, a third sub-function, and a fourth sub-function can be established. Specifically, the first sub-function can be expressed as follows:

[0109]

[0110] J1 represents the first sub-function, which can also be called the longitudinal sub-optimization target, and is mainly used to achieve the goals of adjusting longitudinal comfort and power. Therefore, the function value J1 can be used to characterize the longitudinal speed change state of the mobile tool.

[0111] The second subfunction can be expressed as follows:

[0112]

[0113] J2 represents the second sub-function, which can also be called the driving efficiency sub-optimization objective, and is mainly used to achieve the goal of adjusting the driving efficiency. Therefore, the function value J2 can be used to characterize the driving efficiency of the mobile tool.

[0114] The third sub-function can be expressed as follows:

[0115]

[0116] J3 represents the third sub-function, which can also be called the lateral sub-optimization objective based on the steering wheel and steering wheel speed. It is mainly used to achieve the goal of adjusting the comfort of human-like driving characteristics at low speeds. Therefore, the function value J3 can be used to characterize the steering state of the mobile tool.

[0117] The fourth subfunction can be expressed as follows:

[0118]

[0119] J4 represents the fourth sub-function, which can also be called the lateral sub-optimization target based on centripetal acceleration and centripetal jerk. It is mainly used to achieve the goal of adjusting lateral comfort at medium and high speeds. Therefore, the function value J4 can be used to characterize the lateral offset state of the mobile tool.

[0120] After adding the above four sub-functions, the resulting optimization function can be expressed as follows:

[0121]

[0122] Where J represents the optimization function, is the driving speed at the i-th trajectory point The weight coefficient of v i_max is the maximum speed limit of the i-th trajectory point; is the driving acceleration at the i-th trajectory point The weight coefficient of is the driving acceleration at the i-th trajectory point The weight coefficient of w t is the sampling time t at the i-th trajectory point i The weight coefficient of w l is the lateral position l at the i-th trajectory point i The weight coefficient of w l′ is the rate l′ at which the lateral position of the i-th trajectory point changes with the distance i The weight coefficient of w l″ is the acceleration l″ of the lateral position of the i-th trajectory point as the distance changes i The weight coefficient of w l″′ is the jerk l″′ of the lateral position at the i-th trajectory point as the distance changes i The weight coefficient of is the horizontal position l i The third-order derivative of the distance s traveled by the mobile tool along the road direction represents the jerk of the mobile tool's lateral position as the distance changes; w i for The weight coefficient of in is the lateral offset velocity of the mobile tool in the Frenet coordinate system; for The weight coefficient of in is the lateral offset acceleration of the moving tool in the Frenet coordinate system; for The weight coefficient of in is the lateral offset jerk of the moving tool in the Frenet coordinate system.

[0123] It can be seen from the expression of the above optimization function that in this embodiment, the rate l′ of change of the lateral position of the i-th trajectory point with the distance is i , the acceleration l″ of the lateral position at the i-th trajectory point as the distance changes i , the lateral position of the i-th trajectory point changes with the distance of the acceleration l″′ i and the lateral offset velocity of the moving tool in the Frenet coordinate system Lateral offset acceleration of the moving tool in the Frenet coordinate system And the lateral offset jerk of the moving tool in the Frenet coordinate system At the same time, as an optimization goal, it can improve the rationality and consistency of trajectory planning at different speeds, reduce the parameter adjustment complexity of the trajectory planning algorithm, and this planning method can take into account both high-speed and low-speed scenarios at the same time, and can solve relatively smooth, comfortable and efficient trajectories in both high-speed and low-speed scenarios.

[0124] In one embodiment, the process of determining the constraint conditions specifically includes:

[0125] Establish the correlation relationship between the motion state quantities of adjacent trajectory points to obtain the first sub-condition;

[0126] The motion state quantity of the optimization starting point is limited based on the motion state quantity of the planning starting point to obtain the second sub-condition;

[0127] The third sub-condition is obtained by limiting the value range of the motion state quantity of the trajectory sampling point based on the state quantity constraint value;

[0128] The first sub-condition, the second sub-condition, and the third sub-condition are taken as constraint conditions.

[0129] In this embodiment, the constraint conditions include equality constraint content, starting point constraint content, and inequality constraint content. Among them, the equality constraint content is the first sub-condition, the starting point constraint content is the second sub-condition, and the inequality constraint content is the third sub-condition.

[0130] Specifically, the equality constraint content is used to limit the continuity of the lateral state quantities and longitudinal state quantities between trajectory points, the starting point constraint content is used to limit the motion state of the optimized starting point by planning the motion state quantity of the starting point, and the inequality constraint content is used to limit the value range of different motion state quantities in the optimization content, which needs to be determined based on the state quantity constraint value.

[0131] In one embodiment, a correlation relationship between motion state quantities of adjacent trajectory points is established to obtain the first sub-condition, which specifically includes:

[0132] The association relationship between the longitudinal state quantities of adjacent trajectory points is established to obtain the longitudinal association condition.

[0133] The correlation relationship between the lateral state quantities of adjacent trajectory points is established to obtain the lateral correlation condition.

[0134] The vertical association condition and the horizontal association condition are taken as the first sub-condition.

[0135] In this embodiment, the first sub-condition, i.e., the equality constraint, includes a longitudinal correlation condition and a transverse correlation condition. The longitudinal correlation condition is used to define the correlation relationship between the longitudinal state quantities of two adjacent trajectory points, while the transverse correlation condition is used to define the correlation relationship between the transverse state quantities of two adjacent trajectory points.

[0136] It should be noted that equality constraints can be understood as continuity constraints for trajectory points. In trajectory planning, certain constraints must be satisfied between consecutive points on a trajectory. These constraints typically include position, velocity, acceleration, and direction. The velocity or position continuity constraint formula is the Taylor expansion formula for the velocity or position near that point.

[0137] Specifically, the vertical association condition can be expressed as follows:

[0138]

[0139]

[0140] in, represents the driving speed at the i+1th trajectory point, represents the driving speed at the i-th trajectory point, represents the driving speed at the i-th trajectory point, t i+1 represents the sampling time of the i+1th trajectory point, t i represents the sampling time of the i-th trajectory point, represents the driving acceleration at the i-th trajectory point, s i+1 represents the travel distance of the mobile tool along the road at the i+1th trajectory point, s iIndicates the travel distance of the mobile tool along the road at the i-th trajectory point.

[0141] The horizontal join condition can be expressed as follows:

[0142]

[0143]

[0144] Among them, l′ i+1 represents the rate at which the lateral position of the i+1th trajectory point changes with the distance, l′ i Indicates the rate at which the lateral position of the i-th trajectory point changes with the distance, l″ i represents the acceleration of the lateral position of the i-th trajectory point as the distance changes, Δs represents the sampling distance, l″′ i Indicates the jerk of the mobile tool's lateral position as it changes with distance.

[0145] In a specific implementation, the starting point constraint content can be specifically expressed as follows:

[0146]

[0147]

[0148] t0=0 (12)

[0149] l0=l init (13)

[0150] l′0=l′ init (14)

[0151] l″0=l″ init (15)

[0152] Among them, v init Indicates the driving speed at the planning starting point, a init represents the driving acceleration at the planning starting point, l init Indicates the horizontal position of the planning starting point in the Frenet coordinate system, l′ init Indicates the rate of change of the lateral position of the planning starting point in the Frenet coordinate system with the distance, l″ init Indicates the acceleration of the lateral position of the planning starting point in the Frenet coordinate system as the distance changes. represents the driving speed at the optimization starting point, represents the driving acceleration of the optimization starting point, t0 is the sampling time of the optimization starting point, l0 represents the lateral position of the optimization starting point, l′0 represents the rate of change of the lateral position of the optimization starting point with the path, and l″0 represents the acceleration of the change of the lateral position of the optimization starting point with the distance.

[0153] In one embodiment, the state quantity constraint values ​​include a driving speed constraint value, a derivative constraint value related to the driving speed, a lateral position constraint value, and a derivative constraint value related to the lateral position.

[0154] Based on the state constraint value, the range of the motion state quantity of the trajectory sampling point is limited, and the third sub-condition is obtained, which specifically includes:

[0155] The longitudinal value condition is obtained by limiting the value range of the longitudinal state quantity of the trajectory sampling point based on the driving speed constraint value and the derivative constraint value related to the driving speed.

[0156] The value range of the lateral state quantity of the trajectory sampling point is limited based on the lateral position constraint value and the derivative constraint value related to the lateral position, and the lateral value condition is obtained.

[0157] The vertical value condition and the horizontal value condition are used as the third sub-condition.

[0158] It can be understood that the third sub-condition, that is, the inequality constraint content, can specifically include velocity inequality, acceleration inequality, jerk inequality, sampling time inequality, lateral position inequality, relative heading angle inequality, curvature inequality, curvature change rate inequality, lateral offset velocity inequality, lateral offset acceleration inequality, lateral offset jerk inequality and other constraint inequalities.

[0159] In this embodiment, the inequality constraint content can be specifically expressed as follows:

[0160]

[0161]

[0162]

[0163] t i <t i+1 , i∈[0,n-2] (19)

[0164] l i_min <l i <l i_max , i∈[0,n-1] (20)

[0165] l′ i_min <l′ i <l′ i_max , i∈[0,n-1] (21)

[0166] l″ i_min -l″ i_ref <l″ i <l″ i_max -l″i_ref , i∈[0,n-1] (22)

[0167]

[0168]

[0169]

[0170]

[0171] Among them, v i_min represents the minimum velocity of the i-th trajectory point, v i_max Represents the maximum speed of the i-th trajectory point. The speed inequality is mainly used to limit the maximum and minimum speeds of each trajectory sampling point to prevent the planned speed from exceeding the road speed limit or being less than 0.

[0172] a i_min Indicates the minimum acceleration of the i-th trajectory point, that is, the maximum deceleration, a i_max represents the maximum acceleration of the i-th trajectory point. The acceleration inequality is used to limit the maximum deceleration and acceleration of each trajectory sampling point. This constraint ensures that the acceleration and deceleration of the planned trajectory do not exceed the limits of the drive and brake actuators.

[0173] j i_min Indicates the minimum acceleration of the i-th trajectory point, that is, the maximum deceleration, j i_max is the maximum jerk of the i-th trajectory point. The jerk inequality is used to limit the maximum deceleration and maximum jerk of each trajectory sampling point. This constraint ensures that the jerk of the planned trajectory does not exceed the limit range of the drive and brake actuators.

[0174] t i+1 represents the sampling time of the i+1th trajectory point, t i represents the sampling time of the i-th trajectory point. The sampling time inequality is mainly used to constrain the increase or decrease of the sampling time. Because the planning speed is greater than 0, the sampling time can only increase, not decrease, as the number of trajectory points increases.

[0175] l i_min represents the minimum lateral position of the i-th trajectory point, l i_max represents the maximum lateral position of the i-th trajectory point. The lateral position inequality can ensure that the planned trajectory does not collide with obstacles and does not exceed the road boundary, thus ensuring the driving safety of the mobile tool.

[0176] l′ i_min is the minimum rate of change of the lateral position of the i-th trajectory point with the distance, that is, the minimum relative heading angle, l′ i_maxis the maximum rate of change of the lateral position of the i-th trajectory point along the path, i.e., the maximum relative heading angle. The relative heading angle inequality can constrain the relative heading of the planned trajectory to a certain range, improving the rationality and safety of the planned trajectory.

[0177] l″ i_ref represents the curvature of the i-th trajectory point on the reference line, l″ i_min is the minimum acceleration of the lateral position at the i-th trajectory point with the distance, that is, the minimum curvature, l″ i_max is the maximum acceleration of the lateral position at the i-th trajectory point along the path, i.e., the maximum curvature. The curvature inequality ensures that the curvature of the planned trajectory is within a certain range, and that the mobile tool does not exceed the maximum turning angle range of the EPS (Electric Power Steering) during tracking.

[0178] l″′ i_min Indicates the speed at which the minimum curvature of the i-th trajectory point changes with distance, l″′ i_max Indicates the speed at which the maximum curvature of the i-th trajectory point changes with distance, l″′ i_ref represents the rate at which the curvature of the i-th trajectory point on the reference line changes with distance. The curvature change rate inequality ensures that the curvature change rate of the planned trajectory is within a certain range and does not exceed the maximum speed range during vehicle tracking.

[0179] represents the minimum lateral offset velocity of the i-th trajectory point, represents the maximum lateral offset velocity of the i-th trajectory point, represents the lateral offset velocity of the i-th trajectory point. This lateral offset velocity inequality can constrain the lateral offset velocity of the mobile tool within a reasonable range to ensure the safety of the planned trajectory.

[0180] represents the minimum lateral offset acceleration of the i-th trajectory point, is the maximum lateral offset acceleration of the i-th trajectory point, is the maximum lateral acceleration of the i-th trajectory point on the reference line. The lateral acceleration inequality can constrain the lateral acceleration of the mobile tool to a reasonable range to ensure the safety of the planned trajectory.

[0181] is the minimum lateral offset jerk of the i-th trajectory point, is the maximum lateral offset jerk of the i-th trajectory point, is the maximum lateral jerk of the i-th trajectory point on the reference line, and Δs represents the sampling distance. The lateral jerk inequality can constrain the lateral jerk of the planned trajectory to a reasonable range to ensure the safety of the planned trajectory.

[0182] In one embodiment, based on the state prediction model, the motion state of each trajectory sampling point is solved to obtain the planned trajectory, which specifically includes:

[0183] The state prediction model is input into the solver for optimization and solution to obtain the motion state quantity of each trajectory sampling point;

[0184] All trajectory sampling points with known motion state quantities are used as planning trajectories.

[0185] In practical applications, nonlinear solvers can be used for optimization. For example, the IPOPT solver can be used to solve the above nonlinear constrained optimization problem containing optimization functions and constraints to obtain the motion state quantities corresponding to different trajectory sampling points, and then obtain the planned trajectory.

[0186] In some embodiments, the above trajectory planning method can be reduced to a process of target optimization solution, see Figure 5 In one embodiment, the specific implementation process of the trajectory planning method can be as follows:

[0187] Step 501: Determine trajectory sampling points and obtain state constraint values ​​of different trajectory sampling points.

[0188] In practical applications, the planning starting point can be determined based on the current position of the mobile tool. Starting from the planning starting point, multiple trajectory sampling points are determined according to the preset sampling distance; the state constraint value corresponding to each trajectory sampling point is obtained, and the motion state value of the planning starting point is obtained.

[0189] Step 502: Determine the motion state quantity of the optimization problem.

[0190] In this embodiment, the motion state quantity may specifically include a driving speed, a speed derivative value related to the driving speed, a sampling time, a lateral position, and a position derivative value related to the lateral position.

[0191] Step 503: Set the optimization goal and establish the optimization function.

[0192] In practical applications, multiple optimization items can be established based on the motion state of each trajectory sampling point, taking into account factors such as the vehicle's driving efficiency, driving comfort, and safety. These optimization items can be used as optimization objectives. In practical applications, the motion state can be used as the independent variable, and the function value J can be used as the dependent variable to establish an optimization function with the motion state as the optimization objective.

[0193] Step 504: Set the equality constraint content.

[0194] In this embodiment, the equality constraint content may be determined based on the correlation of the motion states between the plurality of trajectory sampling points, and the kinematic equality constraint may be established.

[0195] Step 505: Set the initial point constraint content.

[0196] In this embodiment, the initial point constraint content in the constraint condition may be determined based on the motion state quantity of the planning starting point.

[0197] Step 506: Set inequality constraint content.

[0198] The inequality constraint content corresponding to each trajectory sampling point is determined based on the state quantity constraint value corresponding to each trajectory sampling point.

[0199] Step 507: Solve the constrained optimization problem. Input the state prediction model containing the constraint conditions and the optimization function into the solver to solve the function value J of the optimization function. Determine the motion state quantity of each trajectory sampling point corresponding to the minimum function value J. Generate a planned trajectory based on the trajectory sampling points with known motion state quantities.

[0200] In summary, the trajectory planning method provided in this embodiment, which utilizes a horizontally and vertically coupled trajectory planning scheme, can address the issues of inconsistency and poor comfort associated with decoupled horizontally and vertically coupled trajectory planning schemes. Furthermore, determining trajectory sampling points based on distance sampling, compared to time sampling, allows for more convenient and accurate acquisition of state constraint values ​​at each trajectory sampling point, resulting in a more accurate and reliable planned trajectory.

[0201] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides a trajectory planning device, an electronic device and corresponding embodiments.

[0202] Figure 6 It is a structural diagram of a trajectory planning device shown in an embodiment of the present application.

[0203] See also Figure 6 , the trajectory planning device provided in the embodiment of the present application specifically includes:

[0204] The sampling module 601 is used to determine a plurality of trajectory sampling points according to a preset sampling distance using the current position of the mobile tool as the planning starting point;

[0205] An acquisition module 602 is used to obtain the state constraint value of each trajectory sampling point and the motion state value of the planning starting point;

[0206] Modeling module 603, for establishing a state prediction model based on the state constraint value of each trajectory sampling point and the motion state value of the planning starting point; wherein the state prediction model includes an optimization function with the motion state value of each trajectory sampling point as the optimization target and the constraints of the optimization target;

[0207] The planning module 604 is used to solve the motion state quantity of each trajectory sampling point based on the state prediction model to obtain the planned trajectory; wherein the motion state quantity includes the lateral state quantity and the longitudinal state quantity.

[0208] In one embodiment, the motion state quantity may specifically include any one or more of the following: driving speed, a speed derivative value related to the driving speed, a sampling time, a lateral position, and a position derivative value related to the lateral position.

[0209] In one embodiment, within the modeling module 603, the process of constructing the optimization function specifically includes:

[0210] Establishing the corresponding relationship between the driving speed and speed derivative value of each trajectory sampling point and the longitudinal speed change state to obtain the first sub-function;

[0211] Establish the corresponding relationship between the sampling time of each trajectory sampling point and the driving efficiency to obtain the second sub-function;

[0212] Establish the corresponding relationship between the lateral position and position derivative value of each trajectory sampling point and the steering state to obtain the third sub-function;

[0213] Establishing the corresponding relationship between the driving speed, speed derivative value, position derivative value and lateral offset state of each trajectory sampling point to obtain the fourth sub-function;

[0214] The first sub-function, the second sub-function, the third sub-function and the fourth sub-function are summed to obtain an optimized function.

[0215] In one embodiment, the process of determining the constraint conditions in the modeling module 603 specifically includes:

[0216] Establish the correlation relationship between the motion state quantities of adjacent trajectory points to obtain the first sub-condition;

[0217] The motion state quantity of the optimization starting point is limited based on the motion state quantity of the planning starting point to obtain the second sub-condition;

[0218] The third sub-condition is obtained by limiting the value range of the motion state quantity of the trajectory sampling point based on the state quantity constraint value;

[0219] The first sub-condition, the second sub-condition, and the third sub-condition are taken as constraint conditions.

[0220] In one embodiment, in the modeling module 603, a correlation relationship between motion state quantities of adjacent trajectory points is established to obtain a first sub-condition, which specifically includes:

[0221] Establish the correlation relationship between the longitudinal state quantities of adjacent trajectory points and obtain the longitudinal correlation condition;

[0222] Establish the correlation relationship between the lateral state quantities of adjacent trajectory points and obtain the lateral correlation conditions;

[0223] The vertical association condition and the horizontal association condition are taken as the first sub-condition.

[0224] In one embodiment, the state quantity constraint value includes a driving speed constraint value, a derivative constraint value related to the driving speed, a lateral position constraint value, and a derivative constraint value related to the lateral position;

[0225] In the modeling module 603, the range of the motion state quantity of the trajectory sampling point is limited based on the state quantity constraint value, and the third sub-condition is obtained, which specifically includes:

[0226] The longitudinal value condition is obtained by limiting the value range of the longitudinal state quantity of the trajectory sampling point based on the driving speed constraint value and the derivative constraint value related to the driving speed;

[0227] The lateral position constraint value and the derivative constraint value related to the lateral position are used to limit the value range of the lateral state quantity of the trajectory sampling point, thereby obtaining the lateral value condition;

[0228] The vertical value condition and the horizontal value condition are used as the third sub-condition.

[0229] In one embodiment, the planning module 604 calculates the motion state of each trajectory sampling point based on the state prediction model to obtain the planned trajectory, specifically including:

[0230] The state prediction model is input into the solver for optimization and solution to obtain the motion state quantity of each trajectory sampling point;

[0231] All trajectory sampling points with known motion state quantities are used as planning trajectories.

[0232] In summary, the trajectory planning device provided in this embodiment can implement a horizontally and vertically coupled trajectory planning scheme because the motion state quantity includes a horizontal state quantity and a vertical state quantity. At the same time, compared with the time sampling method, the distance sampling method can accurately obtain the state quantity constraint value of each trajectory sampling point, thereby establishing a more accurate state quantity prediction model, thereby improving the accuracy and safety of the trajectory planning process.

[0233] Figure 7 It is a structural diagram of an electronic device shown in an embodiment of the present application.

[0234] See also Figure 7 , the electronic device 700 includes a memory 710 and a processor 720.

[0235] The processor 720 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0236] The memory 710 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 720 or other modules of the computer. The permanent storage device can be a readable and writable storage device. The permanent storage device can be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as the permanent storage device. In other embodiments, the permanent storage device can be a removable storage device (such as a floppy disk, optical drive). The system memory can be a readable and writable storage device or a volatile readable and writable storage device, such as dynamic random access memory. The system memory can store some or all instructions and data required by the processor during operation.

[0237] In addition, the memory 710 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and magnetic disks and / or optical disks may also be used. In some embodiments, the memory 710 may include a removable storage device that is readable and / or writable, such as a compact disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-high-density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0238] The memory 710 stores executable codes. When the executable codes are processed by the processor 720 , the processor 720 may execute part or all of the above-mentioned methods.

[0239] Figure 8 It is a structural schematic diagram of a mobile tool shown in an embodiment of the present application.

[0240] Figure 8 A mobile tool 800 provided in an embodiment of the present application is shown, including: multiple data sources 801 and the electronic device 700 as described above, and the data source 801 is communicatively connected with the electronic device 700.

[0241] It is understood that the mobile tool 800 in this embodiment includes, but is not limited to, vehicles with six autonomous driving technology levels, L0-L5, as defined by the Society of Automotive Engineers International (SAE International) or the Chinese national standard "Automotive Driving Automation Levels." For example, it may be a vehicle device or robotic device having the following various functions:

[0242] (1) Passenger-carrying function, such as family cars and buses;

[0243] (2) Cargo carrying function, such as ordinary trucks, box trucks, trailer trucks, closed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, trucks with special structures, etc.;

[0244] (3) Tool functions, such as logistics delivery vehicles, automated guided vehicles (AGVs), patrol cars, cranes, hoists, excavators, bulldozers, forklifts, rollers, loaders, off-road engineering vehicles, armored engineering vehicles, sewage treatment vehicles, sanitation vehicles, vacuum trucks, floor scrubbers, sprinkler trucks, sweeping robots, food delivery robots, shopping guide robots, lawn mowers, golf carts, etc.;

[0245] (4) Entertainment functions, such as entertainment vehicles, amusement park self-driving devices, balance vehicles, etc.;

[0246] (5) Special rescue functions, such as fire trucks, ambulances, power repair trucks, engineering rescue trucks, etc.

[0247] This application does not strictly limit the types of mobile tools, and no exhaustive list is given here.

[0248] The mobile tool provided in this application does not require the upgrade of additional hardware equipment (such as V2X equipment) or the design of complex algorithmic logic. It can utilize existing hardware resources and, based on improvements in control logic, can solve the problem of map engine module errors caused by traffic light ID jumps in scenarios with at least two sets of traffic lights, as well as the problem of the perception module being unable to identify the optimal set of traffic lights. The mobile tool can pass through waiting areas with at least two sets of traffic lights in accordance with traffic regulations, which can improve the driving stability and safety of the mobile tool and thus improve the efficiency of intersection traffic.

[0249] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0250] Alternatively, the present application can also be implemented as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) on which executable code (or computer program or computer instruction code) is stored. When the executable code (or computer program or computer instruction code) is executed by a processor of an electronic device (or server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0251] The embodiments of the present application have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or improvements to the technology in the market, or to enable other persons skilled in the art to understand the embodiments disclosed herein.

Claims

1. A trajectory planning method, characterized in that: include: Taking the current position of the mobile tool as the planning starting point, multiple trajectory sampling points are determined according to the preset sampling distance; Obtaining a state quantity constraint value of each trajectory sampling point and a motion state quantity of the planning starting point; Based on the state quantity constraint value of each trajectory sampling point and the motion state quantity of the planning starting point, a state prediction model is established; wherein the state prediction model includes an optimization function with the motion state quantity of each trajectory sampling point as the optimization target and the constraint conditions of the optimization target; Based on the state prediction model, the motion state quantity of each trajectory sampling point is solved to obtain the planned trajectory; wherein the motion state quantity includes a lateral state quantity and a longitudinal state quantity.

2. The trajectory planning method according to claim 1, characterized in that: The motion state quantity includes any one or more of the following: a driving speed, a speed derivative value related to the driving speed, a sampling time, a lateral position, and a position derivative value related to the lateral position.

3. The trajectory planning method according to claim 2, characterized in that: The construction process of the optimization function includes: Establishing the corresponding relationship between the driving speed and speed derivative value of each trajectory sampling point and the longitudinal speed change state to obtain the first sub-function; Establish the corresponding relationship between the sampling time of each trajectory sampling point and the driving efficiency to obtain the second sub-function; Establish the corresponding relationship between the lateral position and position derivative value of each trajectory sampling point and the steering state to obtain the third sub-function; Establishing the corresponding relationship between the driving speed, speed derivative value, position derivative value and lateral offset state of each trajectory sampling point to obtain the fourth sub-function; The first sub-function, the second sub-function, the third sub-function and the fourth sub-function are summed to obtain an optimized function.

4. The trajectory planning method according to claim 1, characterized in that: The process of determining the constraint conditions includes: Establish the correlation relationship between the motion state quantities of adjacent trajectory points to obtain the first sub-condition; Based on the motion state quantity of the planning starting point, the motion state quantity of the optimization starting point is limited to obtain a second sub-condition; Based on the state quantity constraint value, a value range of the motion state quantity of the trajectory sampling point is limited to obtain a third sub-condition; The first sub-condition, the second sub-condition and the third sub-condition are used as constraint conditions.

5. The trajectory planning method according to claim 4, characterized in that: The establishing of the association relationship between the motion state quantities of adjacent trajectory points to obtain the first sub-condition includes: Establish the correlation relationship between the longitudinal state quantities of adjacent trajectory points and obtain the longitudinal correlation condition; Establish the correlation relationship between the lateral state quantities of adjacent trajectory points and obtain the lateral correlation condition; The vertical association condition and the horizontal association condition are used as the first sub-condition.

6. The trajectory planning method according to claim 4, characterized in that: The state quantity constraint values ​​include a driving speed constraint value, a derivative constraint value related to the driving speed, a lateral position constraint value, and a derivative constraint value related to the lateral position; The third sub-condition is obtained by limiting the value range of the motion state quantity of the trajectory sampling point based on the state quantity constraint value, including: Based on the driving speed constraint value and the derivative constraint value related to the driving speed, a value range of the longitudinal state quantity of the trajectory sampling point is limited to obtain a longitudinal value condition; Based on the lateral position constraint value and the derivative constraint value related to the lateral position, a value range of the lateral state quantity of the trajectory sampling point is limited to obtain a lateral value condition; The longitudinal value-taking condition and the transverse value-taking condition are used as the third sub-condition.

7. The trajectory planning method according to claim 1, characterized in that: The step of solving the motion state quantity of each trajectory sampling point based on the state prediction model to obtain the planned trajectory includes: The state prediction model is input into the solver for optimization and solution to obtain the motion state quantity of each trajectory sampling point; All trajectory sampling points with known motion state quantities are taken as planning trajectories.

8. A trajectory planning device, characterized in that: include: The sampling module is used to determine multiple trajectory sampling points according to a preset sampling distance using the current position of the mobile tool as the planning starting point; An acquisition module, used to acquire the state quantity constraint value of each trajectory sampling point and the motion state quantity of the planning starting point; A modeling module, used to establish a state prediction model based on the state quantity constraint value of each trajectory sampling point and the motion state quantity of the planning starting point; wherein the state prediction model includes an optimization function with the motion state quantity of each trajectory sampling point as the optimization target and the constraint conditions of the optimization target; The planning module is used to solve the motion state quantity of each trajectory sampling point based on the state prediction model to obtain the planned trajectory; wherein the motion state quantity includes a lateral state quantity and a longitudinal state quantity.

9. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 7.

10. A mobile tool, characterized in that: include: A plurality of data sources and the electronic device as claimed in claim 9, wherein the data sources are communicatively connected with the electronic device.

11. A computer-readable storage medium, characterized in that: An executable code is stored thereon, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as claimed in any one of claims 1 to 7.

Images