Trajectory planning method, device and equipment for full trailer train and medium

Abstract

Embodiments of the present disclosure disclose a trajectory planning method, device, equipment and medium for a full-hanging truck train, the method comprising: obtaining a tracking deviation model for determining a first deviation vector of a target tractor and a second deviation vector of a target full-hanging trailer, and then constructing a trajectory optimization problem according to a safety margin evaluation function related to an actual state vector, safety constraints and the tracking deviation model, iteratively solving an initial reference trajectory in a region to be planned through the trajectory optimization problem, evaluating the safety margin by simultaneously considering the deviations of the tractor and the full-hanging trailer in the iterative solving process, obtaining an optimal target control quantity sequence, and then obtaining a target reference trajectory with the maximum passing safety margin, so that the full-hanging truck train composed of the tractor and the full-hanging trailer can pass with a larger safety margin, improving the safety of the full-hanging truck train passing through a narrow area.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and in particular to a trajectory planning method, apparatus, device, and medium for a full trailer truck train. Background Technology

[0002] A full trailer truck, consisting of a tractor unit and a full trailer, is widely used in logistics scenarios such as ports, airports, and factories. To improve transportation efficiency, some scenarios use full trailers with longer wheelbases. These vehicles are characterized by their longer wheelbases, requiring more turning space when navigating curves.

[0003] With the rapid development of autonomous driving technology, driverless trailer trucks are being deployed in various scenarios. Regarding traffic environments, trailer trucks typically need to navigate narrow areas with significant road curvature, such as ports, mines, and logistics parks. In these confined spaces, the long wheelbase and wide body of the trailer truck makes safe passage difficult, becoming a key bottleneck restricting the expansion of autonomous vehicle application scenarios and performance improvements. Summary of the Invention

[0004] To solve the above-mentioned technical problems, or at least partially solve them, this disclosure provides a trajectory planning method, apparatus, equipment, and medium for full-trailer trucks, enabling trajectory planning for full-trailer trucks so that they can pass through narrow areas with a greater safety margin, thus solving the technical problem in the prior art that full-trailer trucks with long wheelbases and wide bodies cannot safely pass through narrow areas.

[0005] In a first aspect, embodiments of this disclosure provide a trajectory planning method for a full-trailer truck train, the method comprising:

[0006] Obtain the tracking deviation model corresponding to the target full trailer truck train, wherein the target full trailer truck train includes a target tractor and a target full trailer trailer, and the tracking deviation model is used to determine the actual state vector corresponding to each discrete point, wherein the actual state vector includes a first deviation vector of the target tractor and a second deviation vector of the target full trailer trailer.

[0007] Based on the safety margin evaluation function of the target full-trailer truck, the safety constraints, and the tracking deviation model, a trajectory optimization problem is constructed, wherein the safety margin evaluation function is used to determine the passage safety margin of the target full-trailer truck based on the actual state vector.

[0008] Determine the initial reference trajectory of the target full-trailer truck in the area to be planned, and iteratively solve the initial reference trajectory based on the trajectory optimization problem to obtain the target control quantity sequence, wherein the target control quantity sequence includes the actual steering curvature corresponding to each discrete point;

[0009] The target reference trajectory of the target trailer truck is determined within the area to be planned based on the target control quantity sequence.

[0010] Secondly, embodiments of this disclosure also provide a positioning device, the device comprising:

[0011] The deviation model acquisition module acquires the tracking deviation model corresponding to the target full trailer truck train, wherein the target full trailer truck train includes a target tractor and a target full trailer trailer. The tracking deviation model is used to determine the actual state vector corresponding to each discrete point. The actual state vector includes a first deviation vector of the target tractor and a second deviation vector of the target full trailer trailer.

[0012] An optimization problem construction model is used to construct a trajectory optimization problem based on the safety margin evaluation function, safety constraints, and tracking deviation model of the target full-trailer truck. The safety margin evaluation function is used to determine the passage safety margin of the target full-trailer truck based on the actual state vector.

[0013] The optimization problem-solving module is used to determine the initial reference trajectory of the target full-trailer truck in the area to be planned, and to iteratively solve the initial reference trajectory based on the trajectory optimization problem to obtain the target control quantity sequence, wherein the target control quantity sequence includes the actual steering curvature corresponding to each discrete point;

[0014] The target trajectory determination module is used to determine the target reference trajectory of the target trailer truck train within the area to be planned based on the target control quantity sequence.

[0015] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising: one or more processors; a storage device for storing one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors implement the trajectory planning method for a full-trailer truck as described above.

[0016] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the trajectory planning method for a full-trailer truck train as described above.

[0017] This disclosure provides a trajectory planning method for a full-trailer truck train. It obtains a tracking deviation model to determine the first deviation vector of the target tractor and the second deviation vector of the target full-trailer. Then, based on a safety margin evaluation function related to the actual state vector, safety constraints, and the tracking deviation model, a trajectory optimization problem is constructed. The initial reference trajectory within the planning area is iteratively solved using this trajectory optimization problem. During the iterative solution process, the deviations of both the tractor and the full-trailer are considered to evaluate the safety margin, resulting in an optimal target control quantity sequence. This leads to the target reference trajectory with the largest passage safety margin, enabling the full-trailer truck train (comprising the tractor and the full-trailer) to pass with a greater safety margin, thus improving the safety of the full-trailer truck train passing through narrow areas. Attached Figure Description

[0018] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0019] Figure 1 This is a flowchart of a trajectory planning method for a full-trailer truck train according to an embodiment of this disclosure;

[0020] Figure 2 This is a schematic diagram of the structure of a target full trailer truck train according to an embodiment of this disclosure;

[0021] Figure 3 This is a schematic diagram of the structure of a target full trailer truck train according to an embodiment of this disclosure;

[0022] Figure 4 This is a schematic diagram illustrating the tracking deviation of a target full-trailer truck train relative to an initial reference trajectory in an embodiment of this disclosure;

[0023] Figure 5 This is a schematic diagram of the turning radii in the embodiments of this disclosure;

[0024] Figure 6 This is a schematic diagram of a contour point in an embodiment of this disclosure;

[0025] Figure 7 This is a schematic diagram of the structure of a trajectory planning device for a full-trailer truck train according to an embodiment of this disclosure;

[0026] Figure 8 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. Detailed Implementation

[0027] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0028] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0029] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0030] Figure 1 This is a flowchart illustrating a trajectory planning method for a full-trailer truck train according to an embodiment of this disclosure. The method can be executed by a trajectory planning device for the full-trailer truck train, which can be implemented in software and / or hardware and can be configured in an electronic device. Figure 1 As shown, the method may specifically include the following steps:

[0031] S110. Obtain the tracking deviation model corresponding to the target full trailer truck train, wherein the target full trailer truck train includes the target tractor and the target full trailer. The tracking deviation model is used to determine the actual state vector corresponding to each discrete point. The actual state vector includes the first deviation vector of the target tractor and the second deviation vector of the target full trailer.

[0032] In this embodiment of the disclosure, the target full-trailer truck train may consist of a target tractor and a target full-trailer trailer connected to the target tractor. For example, Figure 2 and Figure 3 This is a schematic diagram of the structure of a target full trailer truck train according to an embodiment of the present disclosure, wherein, Figure 3 The target full trailer is simplified into two semi-trailers. The first semi-trailer is connected to the target tractor, and the second semi-trailer is connected to the first semi-trailer.

[0033] like Figures 2-3 As shown, the heading angle of the target tractor is θ0, the heading angle of the front axle of the target full trailer is θ1, and the heading angle of the target full trailer is θ2. The angle between the front axles of the target tractor and the target full trailer is... The angle between the front and rear axles of the target full trailer trailer l fr0 l is the wheelbase of the target tractor.fr1 Let L be the wheelbase of the target full trailer. Let H be the connection point between the target tractor and the target full trailer, then L... h L is the distance from the center of the rear axle of the target tractor to the connection point H. b δ is the distance from the center of the front axle of the target full trailer to the connection point H. f Let v0 be the front wheel deflection angle of the target tractor. Let v0 be the speed at the center of the rear axle of the target tractor. Let (x0, y0) be the coordinates of the center of the rear axle of the target tractor, (x1, y1) be the coordinates of the center of the front axle of the target full trailer, and (x2, y2) be the coordinates of the center of the rear axle of the target full trailer.

[0034] L0 f L0 is the distance from the center of the front axle of the target tractor to the front end of the target tractor. r L2 is the distance from the center of the rear axle of the target tractor to the rear end of the target tractor, and W0 is the width of the target tractor. f L2 is the distance from the center of the front axle of the target full trailer to the front end of the target full trailer. r W1 is the distance from the center of the rear axle of the full trailer to the rear end of the target full trailer, and W2 is the width of the target full trailer.

[0035] Typically, the target tractor and the target trailer have the same width (W0 = W2), but there are cases where they differ. When the target tractor and the target trailer have different widths, the larger of the two widths can be taken as the width of the entire vehicle; that is, the target tractor and the target trailer can be considered to have the same width.

[0036] In this embodiment of the disclosure, the tracking deviation model can be used to describe the tracking deviation of the target trailer train relative to the initial reference trajectory, specifically the actual state vector of the target trailer train at each discrete point.

[0037] The discrete points can be points sampled from the initial reference trajectory according to a preset sampling distance. For example, assuming the preset sampling distance is Δs and the number of samples is N, the length of the initial reference trajectory can be N*Δs, resulting in N+1 discrete points (including the starting point in the initial reference trajectory).

[0038] The actual state vector describes the deviation information of the target trailer truck train relative to the initial reference trajectory. Specifically, the actual state vector can include a first deviation vector and a second deviation vector. The first deviation vector can include a first lateral deviation of the target tractor relative to the initial reference trajectory, a first heading deviation relative to the initial reference trajectory, a first angle between the front axle of the target tractor and the front axle of the target trailer, and a second angle between the front and rear axles of the target trailer. The second deviation vector can include a second lateral deviation and a second heading deviation of the target trailer relative to the initial reference trajectory.

[0039] Specifically, the first lateral deviation corresponding to each discrete point can be the distance between the projection point of the target tractor on the initial reference trajectory and the target tractor itself, and the second lateral deviation can be the distance between the projection point of the target trailer on the initial reference trajectory and the target trailer itself. The projection point can be: at the position corresponding to the arc length (i.e., kΔs, where k represents the index of the discrete point), a straight line perpendicular to the initial reference trajectory is drawn along the center of the rear axle; the intersection of this straight line and the initial reference trajectory is the projection point.

[0040] In this embodiment of the disclosure, the tracking deviation model can use the actual steering curvature at the current discrete point as the control variable, and determine the actual state vector at the next discrete point based on the actual state vector and the actual steering curvature at the current discrete point.

[0041] In one specific implementation, obtaining the tracking deviation model corresponding to the target full-trailer truck train includes: determining the first state transition matrix and the second state transition matrix for each discrete point based on the reference state vector and reference steering curvature of each discrete point in the initial reference trajectory; constructing the state vector transition relationship between the actual state vector of the current discrete point, the actual steering curvature of the current discrete point, and the actual state vector of the next discrete point based on the first state transition matrix, the second state transition matrix, and the constant term corresponding to the reference steering curvature; and using the state vector transition relationship as the tracking deviation model.

[0042] The first state transition matrix and the second state transition matrix can be composed of a reference state vector and a reference turning curvature. The reference state vector can be the state vector at the position corresponding to the arc length of the actual state vector in the initial reference trajectory, and the reference turning curvature can be the turning curvature at the arc length of the actual state vector (i.e., the arc length at the current projection point corresponding to the actual state vector) in the initial reference trajectory.

[0043] For example, starting from the first projection point of the rear axle center of the target tractor on the initial reference trajectory at the current moment, the initial reference trajectory is sampled at a fixed arc length (preset sampling distance) Δ. s Sampling is performed, and the reference turning curvature at each discrete point is denoted as... Where k is the index of the discrete point, and N+1 is the number of discrete points (including the starting point). The arc length of each discrete point relative to the first projection point can be denoted as...

[0044] After obtaining the first and second state transition matrices, a state vector transition relationship can be constructed by combining constant terms. This relationship allows the calculation of the actual state vector of the next discrete point from the actual state vector of the current discrete point and the actual turning curvature of the current discrete point. A tracking deviation model can then be constructed based on this state vector transition relationship. The derivation process of the first and second state transition matrices and the state vector transition relationship is illustrated below:

[0045] First, the equations describing the motion of the target trailer train can be:

[0046]

[0047]

[0048]

[0049]

[0050]

[0051] In the formula, κ represents the actual steering curvature of the target tractor, which can be considered as the control variable of the target tractor. It is related to the front wheel deflection angle δ of the target tractor. f The relationship is

[0052] Figure 4 This is a schematic diagram illustrating the tracking deviation of a target full-trailer truck train relative to an initial reference trajectory according to an embodiment of this disclosure. The initial reference trajectory is denoted as γ, the projection point of the target tractor on the initial reference trajectory is denoted as P0, and the arc length from projection point P0 to the starting point of the initial reference trajectory is denoted as s. The projection point of the rear axle center of the target full-trailer trailer on the initial reference trajectory is denoted as P2, and the arc length from projection point P2 to the starting point of the initial reference trajectory is denoted as s. tra .

[0053] like Figure 4 As shown, given an initial reference trajectory, the reference state vector at the corresponding arc length s can be obtained, which may include the reference heading θ of the target tractor. 0,γ Reference value of the angle between the front axle of the target tractor and the target full trailer. Reference value for the angle between the front axle and the rear axle of the target full trailer trailer. And the reference value δ of the front wheel deflection angle of the target tractor vehicle.f,γ .

[0054] Based on this, the heading deviation e of the target tractor relative to the initial reference trajectory can be defined. θ The actual heading θ0 of the target tractor and its reference heading θ 0,γ The angle between them, e θ =θ0-θ 0,γ The lateral deviation e of the target tractor relative to the initial reference trajectory. d Let P0 be the distance between the rear axle center of the target tractor and the projection point P0. The tracking deviation of the target tractor relative to the initial reference trajectory can be expressed as:

[0055]

[0056]

[0057]

[0058] In the formula, δ represents the reference turning curvature at point P0 on the initial reference trajectory. f,γ This represents the reference value for the front wheel deflection angle of the target tractor at point P0. Representing the derivative of the variable with respect to time, transforming the above formula to the Frenet coordinate system, we get:

[0059] e′ d =(1-e d κ γ (s))tan(e θ );

[0060]

[0061] In the formula, (·)′=d(·) / ds, representing the differential of the variable with respect to the arc length s. The above formula can be considered as the rate of change of lateral deviation and heading deviation with respect to the arc length s. Similarly, and Transforming to the Frenet coordinate system, we get:

[0062]

[0063]

[0064] Furthermore, it can make Let be the first deviation vector of the target tractor. Then, the compact form of the above formula can be:

[0065] χ′=f(χ,κ);

[0066] Define the reference state vector at each discrete point as follows: in, Expanding the above formula with respect to the reference state vector using a Taylor series and ignoring higher-order terms, we can obtain the state vector transition relationship of the target full-trailer truck train:

[0067] χ k+1 =A k χ k +B k κ k +G k ;

[0068] In the formula, This represents the first deviation vector of the target tractor at the discrete point. A k B k These are the first state transition matrix and the second state transition matrix, respectively. G k The constant term is a term that contains... The expression.

[0069] It should be noted that Taylor series expansion is one method of linearization. The embodiments disclosed herein are not limited to this method and can support other linearization methods, such as matrix exponential expansion and the Koopman operator.

[0070] After obtaining the above state vector transition relationship, the first actual state vector can be determined based on the current pose of the target tractor. Using steering curvature as the control variable, a reference control variable sequence is obtained after acquiring the initial reference trajectory. Given a current control quantity sequence Then, by tracking the state vector transition relationship in the deviation model, a series of deviation information of the target tractor relative to the initial reference trajectory can be obtained, denoted as... and

[0071] That is, based on the current control quantity sequence A series of actual state vectors can be obtained through the state vector transition relationship, where i represents the number of trajectory iterations. This method allows for the accurate construction of the tracking deviation model, facilitating the preparation of the actual state vectors describing the vehicle's tracking deviation at each discrete point.

[0072] In addition to constructing the state vector transition relationship, the tracking deviation model can also be used to calculate the second deviation vector of the target full trailer. It should be noted that the purpose of determining the second deviation vector of the target full trailer is to plan a route that allows long-wheelbase, large-sized full trailer trains to pass through narrow areas with a large safety margin. This requires ensuring that not only the deviation of the tractor unit does not exceed a safe range, but also the deviation of the full trailer does. Therefore, trajectory optimization can be performed by combining the deviations of the tractor unit and the full trailer, ensuring that the full trailer train can safely pass through narrow areas.

[0073] Optionally, obtaining the tracking deviation model corresponding to the target full-trailer truck train further includes: constructing a differential transformation relationship between the first deviation vector of the target tractor and the second deviation vector of the target full-trailer, so as to determine the second deviation vector through the differential transformation relationship and the first deviation vector; and using the differential transformation relationship as the tracking deviation model.

[0074] The first deviation vector includes the first lateral deviation of the target tractor relative to the initial reference trajectory, the first heading deviation, the first included angle between the front axle of the target tractor and the target trailer, and the second included angle between the front and rear axles of the target trailer. The second deviation vector includes the second lateral deviation and the second heading deviation of the target trailer relative to the initial reference trajectory. The differential transformation relationship satisfies the following formula:

[0075]

[0076]

[0077] In the formula, e d Indicates the first lateral deviation, e θ Indicates the first heading deviation. Indicates the first included angle. Indicates the second included angle. This indicates the second lateral deviation. Indicates the second heading deviation. These are the reference values ​​for the first lateral deviation, the first heading deviation, the first included angle, the second included angle, the second lateral deviation, and the second heading deviation, respectively, in the reference state vector.

[0078] Specifically, the second deviation vector of the rear axle center of the target full trailer trailer is denoted as χ. tra =[e d,tra e θ,tra ] T In this embodiment of the disclosure, χ can be obtained using the finite difference method. tra approximation This is used as the final second deviation vector.

[0079] The following describes the reference value of the second deviation vector in the reference state vector. The acquisition process will be explained as follows:

[0080] First, the reference value of the first deviation vector of the target tractor in the reference state vector is... After coordinate system transformation, the target tractor is represented in Cartesian coordinates (x0 y0 θ0); further, based on the angle between the target tractor and the target trailer... and vehicle dimensions (L) h ,L b This allows us to obtain the representation of the front axle center of the target full trailer in Cartesian coordinates (x1 y1 θ1); then, based on the angle between the front and rear axles of the target full trailer... and the wheelbase dimensions of the target full trailer (l) fr1 This allows us to obtain the representation of the rear axle center of the target full trailer in Cartesian coordinates (x² y² θ²); finally, (x² y² θ²) is projected onto the initial reference trajectory to calculate...

[0081] Furthermore, according to and The above difference transformation relationship can be obtained. In the calculation formula of the above difference transformation relationship, It cannot be obtained analytically, but it can be obtained using the finite difference method.

[0082] In this embodiment, the differential transformation relationship can also be used as the tracking deviation model, thereby making the tracking deviation model include the state vector transition relationship and the differential transformation relationship. The tracking deviation model can also be used to determine the second deviation vector based on the first deviation vector, thus realizing an accurate description of the deviation of the trailer in the full-trailer truck train. Compared with the tracking deviation model that only describes the deviation of the tractor in the full-trailer truck train, the tracking deviation model provided by this embodiment can better describe the tracking deviation of the full-trailer truck train, thereby ensuring the driving safety of the target reference trajectory solved iteratively.

[0083] S120. Based on the safety margin evaluation function, safety constraints, and tracking deviation model of the target full-trailer truck, construct a trajectory optimization problem. The safety margin evaluation function is used to determine the passage safety margin of the target full-trailer truck based on the actual state vector.

[0084] In this embodiment of the disclosure, the safety margin evaluation function is used to calculate the safety cost based on the actual state vector corresponding to each discrete point. The safety cost can be used to reflect the passage safety margin. The larger the passage safety margin, the greater the passage safety margin of the target full trailer truck train, that is, the higher the safety.

[0085] In one specific implementation, before constructing the trajectory optimization problem based on the safety margin evaluation function, safety constraints, and tracking deviation model of the target full-trailer truck, the method further includes: determining the weighted sum of the first lateral deviation and the second lateral deviation based on the first lateral deviation, the second lateral deviation, and the reference weight corresponding to the second lateral deviation, so as to describe the distribution difference between the projections of the target full-trailer truck on both sides of the initial reference trajectory through the weighted sum; and constructing the safety margin evaluation function of the target full-trailer truck based on the weighted sum corresponding to each discrete point.

[0086] For each discrete point, the weighted sum of the first lateral deviation and the second lateral deviation can take the following form: Among them, e d This is the first lateral deviation. denoted as the second lateral deviation, and W as the reference weight.

[0087] It should be noted that the purpose of using a weighted sum to construct the safety margin evaluation function is as follows: Since the target trailer truck consists of a target tractor and a target trailer, and the direction of the first lateral deviation is opposite to that of the second lateral deviation, the first and second lateral deviations can be used to represent the areas of the target trailer truck's projection onto the plane of the initial reference track, respectively. Then, through a weighted sum, the difference in the distribution of the projection on both sides of the track can be described, i.e., the difference in the areas of the projection on both sides of the track. To ensure that the projection of the target trailer truck onto the initial reference track plane is distributed as evenly as possible on both sides of the initial reference track, the relationship between the first and second lateral deviations should satisfy:

[0088]

[0089] Specifically, the smaller the weighted sum, the smaller the distribution difference between the projections on both sides of the initial reference trajectory. This means that the difference between the distance of one side of the target trailer truck relative to the initial reference trajectory and the distance of the other side relative to the initial reference trajectory is smaller. In other words, the two ends of the target trailer truck that are farthest from the initial reference trajectory are closer to the initial reference trajectory, and the distance between the two sides of the target trailer truck and the road boundary or obstacle of the area to be planned is greater.

[0090] In the above implementation, by constructing a safety margin evaluation function through weighted summation, the target reference trajectory with the largest traffic safety margin can be iteratively solved, thereby improving the safety margin of the planned trajectory.

[0091] The reference weights in the weighted sum can be determined as follows:

[0092] Optionally, before determining the weighted sum of the first lateral deviation and the second lateral deviation, the method further includes: determining the reference weight based on the reference radius of the target tractor's rear axle center point at the initial reference trajectory projection point, the actual turning radius of the target tractor's rear axle center point, the distance from the target tractor's rear axle center point to the connection point, the distance from the target full trailer's front axle center point to the connection point, and the target full trailer's wheelbase.

[0093] For example, the reference weights can be determined using the following formula:

[0094]

[0095] Among them, R ref Let R0 be the reference radius of the rear axle center of the target tractor at the initial reference trajectory projection point, and L be the actual turning radius of the rear axle center point of the target tractor. h L is the distance from the center point of the rear axle of the target tractor to the connection point. b l is the distance from the center point of the front axle of the target full trailer to the connection point. fr1 The wheelbase of the target full trailer.

[0096] Taking a trajectory with constant curvature as the initial reference trajectory as an example, the derivation process of the above-mentioned formula for calculating the reference weight is illustrated by way of example. Figure 5 As shown, Figure 5 This is a schematic diagram of the turning radii in the embodiments of this disclosure.

[0097] Among them, R ref R represents the reference radius of the target tractor's rear axle center at the projection point of the initial reference trajectory, R0 represents the actual turning radius of the target tractor's rear axle center, and R2 represents the actual turning radius of the target full trailer's rear axle center. tt,r R represents the actual turning radius at the outermost contour point of the target tractor vehicle. tt,l This indicates the actual turning radius at the innermost contour point (inner rear wheel) of the target full trailer. fr0 The wheelbase of the target tractor.

[0098] according to Figure 5 The geometric relationships shown can be used to obtain:

[0099]

[0100]

[0101]

[0102] To ensure that the projections of the target trailer trucks onto the initial reference track plane are distributed as evenly as possible on both sides of the initial reference track, the turning radius of the initial reference track must satisfy the following:

[0103]

[0104] Combining the above formula, we can obtain the expression for R0. After obtaining the expression for R0, the lateral deviation between the target tractor and the target full trailer can be simplified as:

[0105] e d =R ref -R0;

[0106]

[0107] Furthermore, the expression for calculating the reference weight W can be obtained.

[0108] In this embodiment of the disclosure, the square of the weighted sum can be determined for each discrete point, and then the sum of the squares of the weighted sums of all discrete points can be used as the safety margin evaluation function, such as:

[0109]

[0110] In the formula, This can be directly used as a safety cost, which reflects the safety margin of passage. In the above implementation, it is not necessary to calculate the area of ​​the target full-trailer truck distributed on both sides of the track separately; a weighted sum can be calculated instead, which improves the efficiency of track planning while ensuring track safety.

[0111] In this embodiment of the disclosure, a safety margin evaluation function can be constructed by further combining the traffic smoothness at discrete points with the square of the weighted sum.

[0112] Optionally, a safety margin evaluation function is constructed based on the weighted sum corresponding to each discrete point, including: determining the smoothness of traffic corresponding to the current discrete point by the sum of the squares of the differences in actual steering curvature between the current discrete point and the previous discrete point; determining the traffic balance corresponding to the discrete point by the weighted sum of the first lateral deviation and the second lateral deviation; and constructing a safety margin evaluation function for the target full-trailer truck train based on the smoothness and traffic balance corresponding to each discrete point. For example, the safety margin evaluation function could be:

[0113]

[0114] In the formula, ω k The weights corresponding to traffic smoothness. For traffic balance, J k For smooth traffic flow, κ k Let represent the actual steering curvature at the k-th discrete point. Cost is the safety cost, which reflects the traffic safety margin and is inversely proportional to it. It should be noted that the smaller the safety cost, the larger the traffic safety margin, and thus the higher the safety of the vehicle traveling along the planned trajectory.

[0115] In the above implementation, by constructing a safety margin evaluation function based on traffic smoothness and traffic balance, a trajectory with uniform projection distribution and high smoothness can be further planned, thereby improving the safety of the planned trajectory.

[0116] In this embodiment of the disclosure, the safety constraint can be a constraint used to restrict the target trailer truck train from traveling within a safe boundary range of the area to be planned. The area to be planned can be a narrow area. Specifically, safety constraints can be constructed using a first lateral deviation and a second lateral deviation to limit the lateral deviations from exceeding the safe boundary range.

[0117] In one specific implementation, before constructing the trajectory optimization problem based on the safety margin evaluation function, safety constraints, and tracking deviation model of the target full-trailer truck, the method further includes: constructing safety constraints based on the first lateral deviation, the second lateral deviation, the third lateral deviation of the contour point on the target full-trailer truck relative to the initial reference trajectory, and the safety boundary range corresponding to the area to be planned; wherein, the contour point is a position point on the inner or outer side of the target full-trailer truck, and the safety constraints are used to constrain the first lateral deviation, the second lateral deviation, and the third lateral deviation to be within the safety boundary range.

[0118] The third lateral deviation can be the distance between the contour point and its projection onto the initial reference trajectory. The safety boundary range can be the safe driving range determined by the road boundaries and obstacles of the area to be planned. For example, the safety boundary range can include an upper road safety boundary and a lower road safety boundary; exemplarily, the safety boundary range can be represented as: Specifically, this means that at the k-th discrete point, the upper boundary of the lateral deviation is η. ub,k The lower boundary of the lateral deviation is η. lb,k .

[0119] Specifically, the first lateral deviation, the second lateral deviation, and the third lateral deviation are all within the safe and convenient range, and can be expressed by the following formula:

[0120]

[0121] Where χ represents the first lateral deviation. This indicates the second lateral deviation. Indicates the third lateral deviation. It can represent the maximum value among the three deviations, that is, the safety constraint indicates that the maximum value is less than the safety boundary range.

[0122] In the expression for the above security constraints, Alternatively, it can be the sum of the maximum value of the three deviations and the reserved safety distance. That is, the safety constraint means that the maximum value of the lateral deviation plus the reserved safety distance must be less than the safety boundary range. The trajectory solved using this safety constraint can ensure that the vehicle always travels within the safety boundary range, and can also ensure that the vehicle maintains at least the reserved safety distance from the upper or lower boundary, further improving the safety of the planned trajectory.

[0123] In this embodiment of the disclosure, the third lateral deviation can be calculated based on the reference value of the first deviation vector in the actual state vector and the first deviation vector in the reference state vector. For example, see the following formula:

[0124]

[0125] In the formula, e d Indicates the first lateral deviation, e θ Indicates the first heading deviation. Indicates the first included angle. Indicates the second included angle. This is the third lateral deviation. These are the reference values ​​for the third lateral deviation, the first lateral deviation, the first heading deviation, the first included angle, and the second included angle, respectively, in the reference state vector.

[0126] In the formula, It can also be obtained through the finite difference method. For example, multiple points can be selected at equal intervals on the target trailer, such as... Figure 6 As shown, Figure 6 This is a schematic diagram of contour points in one embodiment of the present disclosure, wherein 2M contour points can be selected on the target full trailer trailer, and each contour point is denoted as...

[0127] By using the aforementioned finite difference method, the lateral deviation of the contour points on the target trailer can be determined, which facilitates the construction of safety constraints that take into account the third lateral deviation, ensuring the accuracy of the safety constraints and thus ensuring the accuracy of the planned trajectory.

[0128] After constructing the safety margin evaluation function, safety constraints, and tracking deviation model, a trajectory optimization problem can be constructed. For example, the trajectory optimization problem can be expressed by the following formula:

[0129]

[0130] ξ k+1 =Aξ k +Bκ k ,k∈(0,1,...,N-1);

[0131] ξ0=ξ satrt ,k0=k satrt ;

[0132] g(ξ k )≤B,k∈(0,1,...,N);

[0133] In the formula, The comprehensive state vector includes the first deviation vector, the second deviation vector, and the third lateral deviation.

[0134] Optionally, considering that excessively large or varying actual steering curvature would affect the smoothness and safety of the target trailer train passing through the planned area, the trajectory optimization problem may further include a first steering curvature constraint and a second steering curvature constraint. The first steering curvature constraint is used to ensure that the actual steering curvature at each discrete point does not exceed a preset threshold, and the second steering curvature constraint is used to ensure that the difference between the actual steering curvatures at adjacent discrete points does not exceed a preset variation.

[0135] For example, the first steering curvature constraint can be: |k k |≤k max ,k∈(0,1,...,N-1). The second turning curvature constraint can be: |k k -κ k-1 |≤Δκ max ,k∈(0,1,...,N-1),N is the number of sampling points.

[0136] In the above implementation, by using the first steering curvature constraint and the second steering curvature constraint together as constraints, a trajectory optimization problem can be constructed, which further improves the safety and smoothness of the planned trajectory.

[0137] S130. Determine the initial reference trajectory of the target full-trailer truck in the area to be planned. Iteratively solve the initial reference trajectory based on the trajectory optimization problem to obtain the target control quantity sequence, wherein the target control quantity sequence includes the actual steering curvature corresponding to each discrete point.

[0138] After obtaining the trajectory optimization problem, an initial reference trajectory can be determined. This initial reference trajectory is then substituted into the trajectory optimization problem for iterative solution to obtain the target control variable sequence. The iterative solution to the trajectory optimization problem can be a sequential quadratic programming approach, such as SQP (Sequential Quadratic Programming), IPOPT (Interior Point Optimizer), or CiLQR (Constrained Iterative Linear Quadratic Regulator).

[0139] The initial reference trajectory can be the lane centerline within the area to be planned; or, it can be an initial control quantity sequence, and then the initial reference trajectory can be determined based on the initial control quantity sequence and the tracking deviation model. The initial control quantity sequence can be randomly given, obtained through a discrete search algorithm, or obtained by polynomial fitting of an existing trajectory. Of course, the closer the initial control quantity sequence is to the optimal result, the faster the convergence speed of the iterative solution.

[0140] In one specific implementation, the initial reference trajectory is iteratively solved based on the trajectory optimization problem to obtain the target control quantity sequence. This includes: substituting the initial reference trajectory into the trajectory optimization problem, using maximizing the traffic safety margin as the objective function, and using safety constraints and the tracking deviation model as constraints, to determine the current optimal control quantity sequence; determining whether the iteration stopping condition is met; if not, updating the initial reference trajectory based on the current optimal control quantity sequence, and returning to the operation of substituting the initial reference trajectory into the trajectory optimization problem until the iteration stopping condition is met to obtain the target control quantity sequence.

[0141] The iteration stopping condition can be that the number of iterations reaches a preset number, or that the difference between the passage safety margins obtained after each iteration gradually converges.

[0142] That is, the lane centerline or the initial reference trajectory obtained from the initial control quantity sequence can be substituted into the trajectory optimization problem to solve for the current optimal control quantity sequence that satisfies the objective function and constraints. Then, it is determined whether the iteration stopping condition is met. If not, the initial reference trajectory is re-determined based on the current optimal control quantity sequence and the tracking deviation model. The new initial reference trajectory is then substituted back into the trajectory optimization problem. The above process is repeated until the iteration stopping condition is met. The last determined current optimal control quantity sequence is then used as the target control quantity sequence.

[0143] It should be noted that in each of the above iterations, the initial reference trajectory needs to be updated. Correspondingly, the tracking deviation model, the safety margin evaluation function, and the parameters related to the initial reference trajectory in the safety boundary are also updated, such as the reference state vector and the reference steering curvature. Furthermore, when the initial reference trajectory is updated, the discrete points in the initial reference trajectory can also be updated, i.e., the discrete points are redefined.

[0144] By iteratively solving the problem with the objective function of maximizing the safety margin, the trajectory with the largest safety margin can be obtained, thus ensuring the safety of the full trailer truck train in narrow areas.

[0145] S140. Determine the target reference trajectory of the target trailer truck train within the area to be planned based on the target control quantity sequence.

[0146] After obtaining the target control quantity sequence, further, based on the target control quantity sequence and the tracking deviation model, each actual state vector can be solved, and then a series of poses of the target trailer truck can be determined based on all actual state vectors. Through a series of poses and each actual steering curvature, the target reference trajectory can be obtained.

[0147] Furthermore, the target reference trajectory can be sent to the automatic driving control system of the target trailer truck, enabling the automatic driving control system to control the target trailer truck to travel along the target reference trajectory. It should be noted that, simultaneously with sending the target reference trajectory, each tracking point within the target reference trajectory can also be determined and sent to the automatic driving control system. The tracking points can be determined by the actual steering curvature in the target control sequence. The tracking points can be understood as the vehicle's position points within the vehicle traveling along the target reference trajectory. By controlling the tracking points to travel along the target reference trajectory, driving control of the vehicle can be achieved.

[0148] The trajectory planning method for full-trailer trucks provided in this embodiment can obtain a tracking deviation model for determining the first deviation vector of the target tractor and the second deviation vector of the target full-trailer. Then, based on the safety margin evaluation function, safety constraints, and tracking deviation model related to the actual state vector, a trajectory optimization problem is constructed. The initial reference trajectory in the planning area is iteratively solved by the trajectory optimization problem. In the iterative solution process, the deviations of the tractor and the full-trailer are considered simultaneously to evaluate the safety margin, thereby obtaining the optimal target control quantity sequence and the target reference trajectory with the largest passage safety margin. This allows the full-trailer truck as a whole, consisting of the tractor and the full-trailer, to pass with a large safety margin, improving the safety of the full-trailer truck passing through narrow areas.

[0149] Figure 7This is a schematic diagram of the trajectory planning device for a full-trailer truck train according to an embodiment of this disclosure. Figure 7 As shown: The device includes: a deviation model acquisition module 710, an optimization problem construction model 720, an optimization problem solving module 730, and a target trajectory determination module 740.

[0150] The deviation model acquisition module 710 acquires the tracking deviation model corresponding to the target full trailer truck train, wherein the target full trailer truck train includes a target tractor and a target full trailer trailer, and the tracking deviation model is used to determine the actual state vector corresponding to each discrete point, wherein the actual state vector includes a first deviation vector of the target tractor and a second deviation vector of the target full trailer trailer.

[0151] The optimization problem construction model 720 is used to construct a trajectory optimization problem based on the safety margin evaluation function, safety constraints, and tracking deviation model of the target full-trailer truck, wherein the safety margin evaluation function is used to determine the passage safety margin of the target full-trailer truck based on the actual state vector.

[0152] The optimization problem-solving module 730 is used to determine the initial reference trajectory of the target full-trailer truck in the area to be planned, and to iteratively solve the initial reference trajectory based on the trajectory optimization problem to obtain the target control quantity sequence, wherein the target control quantity sequence includes the actual steering curvature corresponding to each discrete point;

[0153] The target trajectory determination module 740 is used to determine the target reference trajectory of the target trailer truck train in the area to be planned based on the target control quantity sequence.

[0154] The trajectory planning device for full trailer trucks provided in this embodiment can execute the steps in the trajectory planning method for full trailer trucks provided in this embodiment, and has the execution steps and beneficial effects, which will not be repeated here.

[0155] Figure 8 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. See below for details. Figure 8 It shows a schematic diagram of a structure suitable for implementing the electronic device 500 in the embodiments of this disclosure. Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0156] like Figure 8As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 501, which can perform various appropriate actions and processes to implement the methods of the embodiments described herein, based on a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device 500. The processing device 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0157] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts, thereby implementing the trajectory planning method for a full-trailer truck as described above. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0158] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0159] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0160] Obtain the tracking deviation model corresponding to the target full trailer truck train, wherein the target full trailer truck train includes a target tractor and a target full trailer trailer, and the tracking deviation model is used to determine the actual state vector corresponding to each discrete point, wherein the actual state vector includes a first deviation vector of the target tractor and a second deviation vector of the target full trailer trailer.

[0161] Based on the safety margin evaluation function of the target full-trailer truck, the safety constraints, and the tracking deviation model, a trajectory optimization problem is constructed, wherein the safety margin evaluation function is used to determine the passage safety margin of the target full-trailer truck based on the actual state vector.

[0162] Determine the initial reference trajectory of the target full-trailer truck in the area to be planned, and iteratively solve the initial reference trajectory based on the trajectory optimization problem to obtain the target control quantity sequence, wherein the target control quantity sequence includes the actual steering curvature corresponding to each discrete point;

[0163] The target reference trajectory of the target trailer truck is determined within the area to be planned based on the target control quantity sequence.

[0164] Optionally, when one or more of the above-described procedures are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0165] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0166] Option 1: A trajectory planning method for a full-trailer truck train, the method comprising:

[0167] Obtain the tracking deviation model corresponding to the target full trailer truck train, wherein the target full trailer truck train includes a target tractor and a target full trailer trailer, and the tracking deviation model is used to determine the actual state vector corresponding to each discrete point, wherein the actual state vector includes a first deviation vector of the target tractor and a second deviation vector of the target full trailer trailer.

[0168] Based on the safety margin evaluation function of the target full-trailer truck, the safety constraints, and the tracking deviation model, a trajectory optimization problem is constructed, wherein the safety margin evaluation function is used to determine the passage safety margin of the target full-trailer truck based on the actual state vector.

[0169] Determine the initial reference trajectory of the target full-trailer truck in the area to be planned, and iteratively solve the initial reference trajectory based on the trajectory optimization problem to obtain the target control quantity sequence, wherein the target control quantity sequence includes the actual steering curvature corresponding to each discrete point;

[0170] The target reference trajectory of the target trailer truck is determined within the area to be planned based on the target control quantity sequence.

[0171] Option 2, according to the method described in Option 1, the step of obtaining the tracking deviation model corresponding to the target full-trailer truck train includes:

[0172] Based on the reference state vector and reference turning curvature of each discrete point in the initial reference trajectory, determine the first state transition matrix and the second state transition matrix of each discrete point.

[0173] Based on the first state transition matrix, the second state transition matrix, and the constant term corresponding to the reference turning curvature, a state vector transition relationship is constructed between the actual state vector of the current discrete point, the actual turning curvature of the current discrete point, and the actual state vector of the next discrete point.

[0174] The state vector transition relationship is used as the tracking deviation model.

[0175] Option 3, according to the method described in Option 2, further includes obtaining the tracking deviation model corresponding to the target full-trailer truck train:

[0176] A differential transformation relationship is constructed between the first deviation vector of the target tractor and the second deviation vector of the target full trailer, so as to determine the second deviation vector through the differential transformation relationship and the first deviation vector;

[0177] The difference transformation relationship is used as the tracking deviation model;

[0178] Wherein, the first deviation vector includes the first lateral deviation of the target tractor relative to the initial reference trajectory, the first heading deviation, the first included angle between the front axle of the target tractor and the front axle of the target trailer, and the second included angle between the front axle and the rear axle of the target trailer; and the second deviation vector includes the second lateral deviation and the second heading deviation of the target trailer relative to the initial reference trajectory.

[0179] The difference transformation relationship satisfies the following formula:

[0180]

[0181]

[0182] In the formula, e d e represents the first lateral deviation. θ This indicates the first heading deviation. Indicates the first included angle. This indicates the second included angle. This indicates the second lateral deviation. This indicates the second heading deviation. These are the reference values ​​for the first lateral deviation, the first heading deviation, the first included angle, the second included angle, the second lateral deviation, and the second heading deviation, respectively, in the reference state vector.

[0183] Option 4, according to the method described in Option 3, before constructing the trajectory optimization problem based on the safety margin evaluation function, safety constraints, and the tracking deviation model of the target full-trailer truck, further includes:

[0184] Based on the first lateral deviation, the second lateral deviation, and the reference weight corresponding to the second lateral deviation, a weighted sum of the first lateral deviation and the second lateral deviation is determined to describe the distribution difference between the projections of the target full-trailer truck on both sides of the initial reference trajectory through the weighted sum.

[0185] Based on the weighted sum corresponding to each discrete point, a safety margin evaluation function for the target full trailer truck train is constructed.

[0186] Option 5, according to the method of Option 4, before determining the weighted sum of the first lateral deviation and the second lateral deviation, further comprising:

[0187] The reference weight is determined based on the reference radius of the rear axle center point of the target tractor at the initial reference trajectory projection point, the actual turning radius of the rear axle center point of the target tractor, the distance from the rear axle center point of the target tractor to the connection point, the distance from the front axle center point of the target full trailer to the connection point, and the wheelbase of the target full trailer.

[0188] Option 6, according to the method described in Option 4, before constructing the trajectory optimization problem based on the safety margin evaluation function, safety constraints, and the tracking deviation model of the target full-trailer truck, further includes:

[0189] Safety constraints are constructed based on the first lateral deviation, the second lateral deviation, the third lateral deviation of the contour points on the target trailer relative to the initial reference trajectory, and the safety boundary range corresponding to the area to be planned.

[0190] Wherein, the contour point is a position point on the inside or outside of the target full trailer, and the safety constraint is used to constrain the first lateral deviation, the second lateral deviation, and the third lateral deviation to be within the safety boundary range.

[0191] Option 7: According to the method described in Option 4, the step of iteratively solving the initial reference trajectory based on the trajectory optimization problem to obtain the target control quantity sequence includes:

[0192] Substitute the initial reference trajectory into the trajectory optimization problem, take maximizing the traffic safety margin as the objective function, and take the safety constraints and the tracking deviation model as the constraint conditions to determine the current optimal control quantity sequence;

[0193] Determine whether the iteration stopping condition is met. If not, update the initial reference trajectory based on the current optimal control quantity sequence, and return to perform the operation of substituting the initial reference trajectory into the trajectory optimization problem until the iteration stopping condition is met, and obtain the target control quantity sequence.

[0194] Option 8: A trajectory planning device for a full-trailer truck train, comprising:

[0195] The deviation model acquisition module acquires the tracking deviation model corresponding to the target full trailer truck train, wherein the target full trailer truck train includes a target tractor and a target full trailer trailer. The tracking deviation model is used to determine the actual state vector corresponding to each discrete point. The actual state vector includes a first deviation vector of the target tractor and a second deviation vector of the target full trailer trailer.

[0196] An optimization problem construction model is used to construct a trajectory optimization problem based on the safety margin evaluation function, safety constraints, and tracking deviation model of the target full-trailer truck. The safety margin evaluation function is used to determine the passage safety margin of the target full-trailer truck based on the actual state vector.

[0197] The optimization problem-solving module is used to determine the initial reference trajectory of the target full-trailer truck in the area to be planned, and to iteratively solve the initial reference trajectory based on the trajectory optimization problem to obtain the target control quantity sequence, wherein the target control quantity sequence includes the actual steering curvature corresponding to each discrete point;

[0198] The target trajectory determination module is used to determine the target reference trajectory of the target trailer truck train within the area to be planned based on the target control quantity sequence.

[0199] Option 9: An electronic device, the electronic device comprising:

[0200] One or more processors;

[0201] Storage device for storing one or more programs;

[0202] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of schemes 1-7.

[0203] Option 10: A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of Options 1-7.

[0204] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

Claims

1. A trajectory planning method for a full trailer train, characterized by, The method includes: Obtain the tracking deviation model corresponding to the target full trailer truck train, wherein the target full trailer truck train includes a target tractor and a target full trailer trailer, and the tracking deviation model is used to determine the actual state vector corresponding to each discrete point, wherein the actual state vector includes a first deviation vector of the target tractor and a second deviation vector of the target full trailer trailer. Based on the safety margin evaluation function of the target full-trailer truck, the safety constraints, and the tracking deviation model, a trajectory optimization problem is constructed, wherein the safety margin evaluation function is used to determine the passage safety margin of the target full-trailer truck based on the actual state vector. Determine the initial reference trajectory of the target full-trailer truck in the area to be planned, and iteratively solve the initial reference trajectory based on the trajectory optimization problem to obtain the target control quantity sequence, wherein the target control quantity sequence includes the actual steering curvature corresponding to each discrete point; Based on the target control quantity sequence, determine the target reference trajectory of the target full-trailer truck train within the area to be planned; The method further includes: Based on the first lateral deviation of the target tractor relative to the initial reference trajectory, the second lateral deviation of the target trailer relative to the initial reference trajectory, and the reference weight corresponding to the second lateral deviation, a weighted sum of the first lateral deviation and the second lateral deviation is determined so as to describe the distribution difference between the projections of the target trailer train on both sides of the initial reference trajectory through the weighted sum. Based on the weighted sum corresponding to each discrete point, a safety margin evaluation function for the target full trailer truck train is constructed.

2. The method according to claim 1, characterized in that, The method for obtaining the tracking deviation model corresponding to the target full-trailer truck train includes: Based on the reference state vector and reference turning curvature of each discrete point in the initial reference trajectory, determine the first state transition matrix and the second state transition matrix of each discrete point. Based on the first state transition matrix, the second state transition matrix, and the constant term corresponding to the reference turning curvature, a state vector transition relationship is constructed between the actual state vector of the current discrete point, the actual turning curvature of the current discrete point, and the actual state vector of the next discrete point. The state vector transition relationship is used as the tracking deviation model.

3. The method according to claim 2, characterized in that, The method for obtaining the tracking deviation model corresponding to the target full-trailer truck train also includes: A differential transformation relationship is constructed between the first deviation vector of the target tractor and the second deviation vector of the target full trailer, so as to determine the second deviation vector through the differential transformation relationship and the first deviation vector; The difference transformation relationship is used as the tracking deviation model; Wherein, the first deviation vector includes the first lateral deviation of the target tractor relative to the initial reference trajectory, the first heading deviation, the first included angle between the front axle of the target tractor and the front axle of the target trailer, and the second included angle between the front axle and the rear axle of the target trailer; and the second deviation vector includes the second lateral deviation and the second heading deviation of the target trailer relative to the initial reference trajectory. The difference transformation relationship satisfies the following formula: ； ； In the formula, This represents the first lateral deviation. This indicates the first heading deviation. Indicates the first included angle. This indicates the second included angle. This indicates the second lateral deviation. This indicates the second heading deviation. , , , , , These are the reference values ​​for the first lateral deviation, the first heading deviation, the first included angle, the second included angle, the second lateral deviation, and the second heading deviation, respectively, in the reference state vector.

4. The method according to claim 1, characterized in that, Before determining the weighted sum of the first lateral deviation and the second lateral deviation, the method further includes: The reference weight is determined based on the reference radius of the rear axle center point of the target tractor at the initial reference trajectory projection point, the actual turning radius of the rear axle center point of the target tractor, the distance from the rear axle center point of the target tractor to the connection point, the distance from the front axle center point of the target full trailer to the connection point, and the wheelbase of the target full trailer.

5. The method according to claim 1, characterized in that, Before constructing the trajectory optimization problem based on the safety margin evaluation function, safety constraints, and tracking deviation model of the target full-trailer truck, the following steps are also included: Safety constraints are constructed based on the first lateral deviation, the second lateral deviation, the third lateral deviation of the contour points on the target trailer relative to the initial reference trajectory, and the safety boundary range corresponding to the area to be planned. Wherein, the contour point is a position point on the inside or outside of the target full trailer, and the safety constraint is used to constrain the first lateral deviation, the second lateral deviation, and the third lateral deviation to be within the safety boundary range.

6. The method according to claim 1, characterized in that, The iterative solution of the initial reference trajectory based on the trajectory optimization problem to obtain the target control variable sequence includes: Substitute the initial reference trajectory into the trajectory optimization problem, take maximizing the passage safety margin as the objective function, and take the safety constraints and the tracking deviation model as the constraint conditions to determine the current optimal control quantity sequence; Determine whether the iteration stopping condition is met. If not, update the initial reference trajectory based on the current optimal control quantity sequence, and return to perform the operation of substituting the initial reference trajectory into the trajectory optimization problem until the iteration stopping condition is met, and obtain the target control quantity sequence.

7. A trajectory planning device for a full-trailer truck train, characterized in that, include: The deviation model acquisition module acquires the tracking deviation model corresponding to the target full trailer truck train, wherein the target full trailer truck train includes a target tractor and a target full trailer. The tracking deviation model is used to determine the actual state vector corresponding to each discrete point. The actual state vector includes a first deviation vector of the target tractor and a second deviation vector of the target full trailer. An optimization problem construction model is used to construct a trajectory optimization problem based on the safety margin evaluation function, safety constraints, and the tracking deviation model of the target full-trailer truck. The safety margin evaluation function is used to determine the passage safety margin of the target full-trailer truck based on the actual state vector. The optimization problem-solving module is used to determine the initial reference trajectory of the target full-trailer truck in the area to be planned, and to iteratively solve the initial reference trajectory based on the trajectory optimization problem to obtain the target control quantity sequence, wherein the target control quantity sequence includes the actual steering curvature corresponding to each discrete point; The target trajectory determination module is used to determine the target reference trajectory of the target trailer truck train in the area to be planned based on the target control quantity sequence. The construction of the safety margin evaluation function includes: Based on the first lateral deviation of the target tractor relative to the initial reference trajectory, the second lateral deviation of the target trailer relative to the initial reference trajectory, and the reference weight corresponding to the second lateral deviation, a weighted sum of the first lateral deviation and the second lateral deviation is determined so as to describe the distribution difference between the projections of the target trailer train on both sides of the initial reference trajectory through the weighted sum. Based on the weighted sum corresponding to each discrete point, a safety margin evaluation function for the target full trailer truck train is constructed.

8. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

Images