Trajectory planning method, device and equipment of articulated vehicle and medium

Abstract

Embodiments of the present disclosure disclose a trajectory planning method, device, equipment and medium for articulated vehicles, the method comprising: obtaining a tracking deviation model and a safety margin evaluation function corresponding to a target articulated vehicle, constructing a safety constraint according to a profile point lateral deviation of the target semi-trailer, a safety boundary range corresponding to a region to be planned, a tractor lateral deviation and a semi-trailer lateral deviation, and then iteratively solving an initial reference trajectory to obtain a target control quantity sequence, so as to determine a target reference trajectory in the region to be planned, thereby realizing a safety constraint considering the deviation of the profile point of the semi-trailer, limiting the lateral deviation of the profile point of the semi-trailer from exceeding the safety boundary range, ensuring that the articulated vehicle with a long wheelbase and a wide body can safely pass through a narrow region, and improving the safety of the articulated vehicle passing through the narrow region.

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 articulated vehicles. Background Technology

[0002] As the focus of the autonomous driving market gradually shifts from passenger cars to commercial vehicles, the development of autonomous commercial vehicles is accelerating. Numerous technology companies have launched autonomous driving solutions for commercial vehicles and implemented them in multiple scenarios, marking the entry of autonomous commercial vehicle development into the product phase. Among them, articulated vehicles, due to their advantages such as long size, large cargo capacity, and low transportation costs, have received widespread attention in many commercial application scenarios such as ports, mines, and logistics parks, becoming a key research focus in the field of autonomous driving.

[0003] Compared to a single vehicle, an articulated vehicle adds a semi-trailer constrained by a towing pin, and can be simplified as a tractor-semi-trailer model. These vehicles are characterized by a wider body and a longer wheelbase for the semi-trailer, requiring greater turning space when navigating curves. Considering the typical application scenarios for this type of vehicle, such as ports, mines, and logistics parks, which often involve environments with narrow spaces and significant road curvature, long-wheelbase, wide-body articulated vehicles struggle to pass safely in these confined areas. Summary of the Invention

[0004] To address or at least partially address the aforementioned technical problems, this disclosure provides a trajectory planning method, apparatus, device, and medium for articulated vehicles, thereby enabling trajectory planning for articulated vehicles and resolving the technical problem in the prior art that articulated vehicles 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 an articulated vehicle, the method comprising:

[0006] Obtain the tracking deviation model and safety margin evaluation function corresponding to the target articulated vehicle, wherein the target articulated vehicle includes the target tractor and the target semi-trailer, the tracking deviation model is used to determine the actual state vector at each discrete point, and the safety margin evaluation function is used to determine the vehicle passage safety margin based on the actual state vector.

[0007] Safety constraints are constructed based on the lateral deviation of the outline points of the target semi-trailer, the lateral deviation of the tractor in the actual state vector, the lateral deviation of the semi-trailer, and the safety boundary range corresponding to the area to be planned.

[0008] An initial reference trajectory is determined within the area to be planned. The objective function is to maximize the vehicle traffic safety margin, and the tracking deviation model and the safety constraints are used as constraints. The solution is iteratively obtained to obtain a target control quantity sequence. Based on the target control quantity sequence, the target reference trajectory within the area to be planned is determined.

[0009] Secondly, embodiments of this disclosure also provide a trajectory planning device for an articulated vehicle, the device comprising:

[0010] The acquisition module is used to acquire the tracking deviation model and safety margin evaluation function corresponding to the target articulated vehicle. The target articulated vehicle includes a target tractor and a target semi-trailer. The tracking deviation model is used to determine the actual state vector at each discrete point. The safety margin evaluation function is used to determine the vehicle passage safety margin based on the actual state vector.

[0011] The constraint construction module is used to construct safety constraints based on the lateral deviation of the contour points of the target semi-trailer, the lateral deviation of the tractor in the actual state vector, the lateral deviation of the semi-trailer, and the safety boundary range corresponding to the area to be planned.

[0012] The iterative module is used to determine the initial reference trajectory within the area to be planned. It iteratively solves the problem using the maximization of vehicle traffic safety margin as the objective function, the tracking deviation model, and the safety constraints as constraints, to obtain a target control quantity sequence. Based on this target control quantity sequence, the target reference trajectory within the area to be planned is determined.

[0013] 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, causing the one or more processors to implement the trajectory planning method for an articulated vehicle as described above.

[0014] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the trajectory planning method for an articulated vehicle as described above.

[0015] This disclosure provides a trajectory planning method for articulated vehicles. By acquiring the tracking deviation model and safety margin evaluation function corresponding to the target articulated vehicle, and based on the lateral deviation of the target semi-trailer's contour points, the safety boundary range of the area to be planned, and the lateral deviations of the tractor and semi-trailer in the actual state vector of the target articulated vehicle, safety constraints are constructed. Then, using maximizing the vehicle's passage safety margin as the objective function and the tracking deviation model and safety constraints as the constraint conditions, the initial reference trajectory is iteratively solved to obtain the target control quantity sequence, thereby determining the target reference trajectory within the area to be planned. This method achieves safety constraints considering the deviation of the semi-trailer's contour points. By simultaneously limiting the lateral deviation of the semi-trailer's contour points to not exceed the safety boundary range, it ensures that articulated vehicles with long wheelbases and wide bodies can safely pass through narrow areas. Furthermore, by solving with maximizing the safety margin as the objective function, the final constructed trajectory has a large safety margin, further improving the safety of articulated vehicles passing through narrow areas. Attached Figure Description

[0016] 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.

[0017] Figure 1 This is a flowchart of a trajectory planning method for an articulated vehicle according to an embodiment of this disclosure;

[0018] Figure 2 This is a schematic diagram of an articulated vehicle according to an embodiment of the present disclosure;

[0019] Figure 3 This is a schematic diagram of another articulated vehicle according to an embodiment of the present disclosure;

[0020] Figure 4 This is a schematic diagram of another articulated vehicle according to an embodiment of the present disclosure;

[0021] Figure 5 This is a schematic diagram of a tracking deviation in an embodiment of this disclosure;

[0022] Figure 6 This is a schematic diagram of the tracking deviation of a target tractor in one embodiment of the present disclosure;

[0023] Figure 7 This is a schematic diagram of the turning radii in the embodiments of this disclosure;

[0024] Figure 8 This is a schematic diagram of a contour point in an embodiment of this disclosure;

[0025] Figure 9 This is a schematic diagram of the structure of a trajectory planning device for an articulated vehicle according to an embodiment of the present disclosure;

[0026] Figure 10 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 an articulated vehicle according to an embodiment of this disclosure. The method can be executed by a trajectory planning device for the articulated vehicle, 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 and safety margin evaluation function corresponding to the target articulated vehicle. The target articulated vehicle includes the target tractor and the target semi-trailer. The tracking deviation model is used to determine the actual state vector at each discrete point. The safety margin evaluation function is used to determine the vehicle passage safety margin based on the actual state vector.

[0032] The target articulated vehicle can be understood as consisting of a tractor and a semi-trailer bound by a towing pin. The target articulated vehicle is characterized by its wide body and long wheelbase of the semi-trailer, thus requiring greater turning space when navigating curves.

[0033] For example, Figure 2 This is a schematic diagram of an articulated vehicle according to an embodiment of this disclosure. Wherein, L1 is the wheelbase of the unmanned target tractor. fL1 is the distance from the center of the front axle of the target tractor to the front end of the target tractor. r L1 is the distance from the center of the rear axle of the target tractor to the rear end of the target tractor, and W is the width of the target tractor. M1 is the distance from the center of the rear axle of the target tractor to the drawbar (point H). L2 is the distance from the center of the rear axle of the target semi-trailer to the drawbar (point H). r The distance from the center of the rear axle of the target semi-trailer to the rear end of the target semi-trailer.

[0034] exist Figure 2 In this embodiment, the target tractor and the target semi-trailer have the same width. However, their widths can also be different. When the widths of the target tractor and the target semi-trailer are different, the larger of the two widths can be taken as the width of the entire vehicle. That is, in this embodiment, the target tractor and the target semi-trailer in the target articulated vehicle can be set to have the same width, W.

[0035] like Figure 2 As shown, the towing pin (point H) is located in front of the center of the rear axle of the target tractor. In addition, Figures 3-4 This is a schematic diagram of another articulated vehicle in an embodiment of this disclosure. The towing pin (point H) can also be located in an articulated structure at the center of the rear axle of the target tractor, such as... Figure 3 As shown; or, the towing pin (point H) can also be a hinged structure located behind the center of the rear axle of the target tractor, such as... Figure 4 As shown.

[0036] In this embodiment of the disclosure, the tracking deviation model can be a model used to describe the deviation of the target articulated vehicle relative to an initial reference trajectory. Specifically, the tracking deviation model can be used to determine the actual state vector of the target articulated vehicle at each discrete point in the initial reference trajectory. The actual state vector may include deviation information of the target tractor and the target semi-trailer.

[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] Specifically, a tracking deviation model can be constructed to determine the actual state vector at the current discrete point based on the actual state vector at the previous discrete point.

[0039] In one specific implementation, obtaining the tracking deviation model corresponding to the target articulated vehicle 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.

[0040] The reference state vector at a discrete point can be a reference vector in the initial reference trajectory corresponding to the actual state vector at the discrete point. The reference turning curvature at a discrete point can be the turning curvature of the initial reference trajectory at the discrete point. The determination process of the first and second state transition matrices is explained below:

[0041] Let the heading angle of the target tractor be... The heading angle of the target semi-trailer is The articulation angle between the target tractor and the target semi-trailer Let (x1, y1) represent the coordinates of the center of the rear axle of the target tractor, and (x2, y2) represent the coordinates of the center of the rear axle of the target semi-trailer. Then, the equation describing the motion of the target tractor can be written as:

[0042]

[0043] In the formula, v represents the speed at the center of the rear axle of the target tractor, and δ f Indicates the front wheel deflection angle of the target tractor. Representing x1, y1, respectively The rate of change of the angle between the target tractor and the target semi-trailer can be:

[0044]

[0045] In the formula, κ is the actual steering curvature of the target tractor, and its angle with the front wheel deflection δ of the target tractor is... f The relationship is: κ = tan(δ) f ) / L1.

[0046] Furthermore, the tracking deviation of the target articulated vehicle relative to the initial reference trajectory can be found in [reference needed]. Figure 5 , Figure 5 This is a schematic diagram illustrating a tracking deviation in an embodiment of this disclosure. For example... Figure 5As shown, the initial reference trajectory can be denoted as γ, the projection point of the target tractor on the initial reference trajectory can be denoted as P1, the projection point of the target semi-trailer on the initial reference trajectory can be denoted as P2, the arc length between the projection point P1 of the rear axle center of the target tractor on the initial reference trajectory and the starting point of the initial reference trajectory can be denoted as s, and the arc length between the projection point P2 of the rear axle center of the target semi-trailer on the initial reference trajectory and the starting point of the initial reference trajectory can be denoted as s. tra The projection point can be a straight line perpendicular to the initial reference trajectory drawn along the center of the rear axis, and the intersection of this straight line and the initial reference trajectory is the projection point.

[0047] See Figure 5 The heading deviation of the target tractor relative to the initial reference trajectory Let e ​​be the angle between the heading of the target tractor and the tangent direction of the initial reference trajectory at projection point P1, and let e be the lateral deviation of the target tractor relative to the initial reference trajectory. y P1 represents the distance between the rear axle center of the target tractor and the projection point P1. The heading deviation of the target semi-trailer relative to the initial reference trajectory is also represented. Let e ​​be the angle between the heading of the target semi-trailer and the tangent direction of the initial reference trajectory at projection point P2, and let e be the lateral deviation of the target semi-trailer relative to the initial reference trajectory. y,tra Let P2 be the distance between the rear axle center of the target semi-trailer and the projection point P2. The angle between the heading of the rear axle center of the target tractor and the heading of the rear axle center of the target semi-trailer is the articulation angle β1.

[0048] Furthermore, the tracking deviation of the target tractor relative to the reference trajectory and the rate of change of β1 can be expressed as:

[0049]

[0050]

[0051]

[0052]

[0053] In the formula, κ represents the derivative of a variable with respect to time. r (s) represents the reference steering curvature of the rear axle center of the target tractor at the initial reference trajectory projection point P1, which can be abbreviated as κ. r Let R ref Indicating the reference turning radius, we have Furthermore, it can be equivalently converted to an expression in the Frenet coordinate system:

[0054]

[0055]

[0056]

[0057] In the formula, (·)′=d(·) / ds, represents the differential of the variable with respect to the arc length s. Let Let z' represent the deviation vector of the target tractor. Then the above formula can be simplified to a compact form: z′=f(z,κ,κ) γ It should be noted that, for Figure 2 The center traction pin is located in front of the center of the rear axle of the target tractor vehicle. M1 can take a negative value. Figure 3 The center traction pin is located at the center of the rear axle of the target tractor vehicle, and M1 can be zero. Figure 4 The central traction pin is located behind the center of the rear axle of the target tractor vehicle, and M1 can be a positive value.

[0058] Furthermore, starting from point P1, the projection of the rear axle center of the target tractor onto the initial reference trajectory, the initial reference trajectory γ is extended with a fixed arc length Δ s Sampling is performed, and the reference turning curvature at each discrete point obtained from the sampling 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 P1 can be denoted as...

[0059] Define the reference state vector as Expanding the above formula using Taylor series (or matrix exponential expansion, Koopman operator, etc.) at each discrete point, and ignoring higher-order terms, yields a discrete linearized expression, which represents the state vector transition relationship between the actual state vectors at adjacent discrete points:

[0060] z k+1 =A k z k +B k κ+G;

[0061] In the formula, G is a constant term, z r,0 =z0. Where, A k This is the first state transition matrix, B k This is the second state transition matrix. k Let κ be the actual state vector at the k-th discrete point, and let κ be the actual turning curvature at the k-th discrete point. γ,k Let be the reference state vector at the kth discrete point.

[0062] Therefore, the formula for the state vector transition relationship described above can be used as a tracking deviation model. That is, the tracking deviation model can determine the actual state vector of the next discrete point based on the actual state vector of the current discrete point, the actual steering curvature, the reference state vector, the reference steering curvature, and the constant term.

[0063] In this embodiment of the disclosure, the actual steering curvature of the target tractor is used as the control quantity, if a sequence of control quantities is given... The current deviation vector can then be determined based on the pose of the target tractor. Then, based on the tracking deviation model, a series of deviation vectors of the target tractor relative to the initial reference trajectory are obtained, denoted as... For example, such as Figure 6 As shown, Figure 6 This is a schematic diagram of the tracking deviation of a target tractor in one embodiment of the present disclosure.

[0064] In the above implementation, by determining the first state transition matrix and the second state transition matrix, and then constructing the state vector transition relationship, the determination of the state vector based on the state vector transition relationship and the actual steering curvature is realized. This can more accurately describe the deviation of the target articulated vehicle at each discrete point, thereby ensuring the safety of the solved target reference trajectory.

[0065] In addition to describing the deviation vector of the target tractor relative to the initial reference trajectory, the deviation vector of the target semi-trailer relative to the initial reference trajectory can also be determined. It should be noted that the purpose of determining the deviation vector of the target semi-trailer is to plan a path that allows the long-wheelbase, large-sized articulated vehicle to pass through narrow areas with a large safety margin. This requires ensuring that not only the deviation of the tractor but also the deviation of the semi-trailer does not exceed a safe range. Therefore, trajectory optimization can be performed by combining the deviations of the tractor and semi-trailer to ensure that the articulated vehicle can safely pass through narrow areas.

[0066] In this embodiment of the disclosure, in addition to constructing a tracking deviation model that includes state vector transition relationships, the tracking deviation model can be used to determine the deviation vector of the target semi-trailer for each discrete point based on the deviation vector of the target tractor at the discrete point.

[0067] Optionally, obtaining the tracking deviation model corresponding to the target articulated vehicle further includes: constructing a differential transformation relationship between the tractor deviation vector and the semi-trailer deviation vector, so as to determine the semi-trailer deviation vector through the differential transformation relationship and the tractor deviation vector; and using the differential transformation relationship as the tracking deviation model.

[0068] The semi-trailer deviation vector includes the semi-trailer lateral deviation and the semi-trailer heading deviation; the difference transformation relationship satisfies the following formula:

[0069]

[0070]

[0071] In the formula, e y Indicates the lateral deviation of the tractor unit. β1 represents the tractor's heading deviation, and β1 represents the articulation angle. This indicates the lateral deviation of the semi-trailer. This indicates the semi-trailer's heading deviation. These are the reference values ​​for the lateral deviation of the tractor, the heading deviation of the tractor, the lateral deviation of the semi-trailer, the heading deviation of the semi-trailer, and the articulation angle, respectively, in the reference state vector.

[0072] Specifically, the actual state vector includes the tractor deviation vector. and semi-trailer deviation vector The tractor deviation vector includes the tractor lateral deviation e. y tractor heading deviation And the articulation angle β1, the semi-trailer deviation vector includes the semi-trailer lateral deviation e y,tra and semi-trailer heading deviation

[0073] In this embodiment of the disclosure, z can be obtained by the finite difference method. tra approximation This serves as the final deviation vector for the semi-trailer.

[0074] Specifically, firstly, the reference value of the semi-trailer deviation vector can be determined based on the reference value of the tractor deviation vector in the reference state vector. For example, the reference value of the tractor deviation vector can be... After coordinate system transformation, the pose in Cartesian coordinate system is obtained. Based on the angle β1 between the target tractor and the target semi-trailer, and the dimensions of the target articulated vehicle, the representation of the target semi-trailer in Cartesian coordinates (x) can be obtained. tra y tra θ tra ), will (x tra y tra θ tra Project onto the initial reference trajectory and calculate.

[0075] Then, the finite difference method is used to obtain The value of finite difference includes forms such as forward difference, backward difference, and central difference. Here, we take forward difference as an example, and the calculation formula is as follows:

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082] Furthermore, z can be obtained. tra approximation about and The linearized expression for this is the formula for the difference transformation relationship mentioned above. Where, It cannot be obtained analytically, but it can be obtained using the finite difference method.

[0083] In this embodiment of the disclosure, 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 semi-trailer deviation vector based on the tractor deviation vector, thus realizing an accurate description of the deviation of the semi-trailer in the articulated vehicle. Compared with the tracking deviation model that only describes the deviation of the tractor in the articulated vehicle, the tracking deviation model provided by this embodiment of the disclosure can better describe the tracking deviation of the articulated vehicle, thereby ensuring the driving safety of the target reference trajectory solved iteratively.

[0084] In addition to obtaining the tracking deviation model, a safety margin evaluation function can also be obtained. This function determines the safety margin for the target articulated vehicle as it travels along the initial reference trajectory within the planned area. The planned area can be a narrow region. A larger safety margin indicates a greater safety allowance for the target articulated vehicle, meaning higher safety.

[0085] In one specific implementation, obtaining the safety margin evaluation function corresponding to the target articulated vehicle includes: determining the weighted sum of the lateral deviations of the tractor and the semi-trailer based on the lateral deviation of the tractor, the lateral deviation of the semi-trailer, and the reference weights corresponding to the lateral deviation of the semi-trailer, so as to describe the distribution difference between the projections of the target articulated vehicle on both sides of the initial reference trajectory through the weighted sum; and constructing the safety margin evaluation function of the target articulated vehicle based on the weighted sums corresponding to each discrete point.

[0086] For each discrete point, the weighted sum of the lateral deviation of the tractor and the lateral deviation of the semi-trailer can be in the following form: Among them, e y For the lateral deviation of the tractor, W represents the lateral deviation of the semi-trailer, and W is 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 articulated vehicle consists of a target tractor and a target semi-trailer, and the lateral deviation direction of the tractor is opposite to that of the semi-trailer, the lateral deviation of the tractor and the semi-trailer can be used to represent the area of ​​the target articulated vehicle's projection onto the plane of the initial reference trajectory, respectively. Then, through a weighted sum, the difference in the distribution of the projection on both sides of the trajectory—that is, the difference in the area of ​​the projection on both sides of the trajectory—can be described. To ensure that the projection of the target articulated vehicle onto the initial reference trajectory plane is distributed as evenly as possible on both sides of the initial reference trajectory, the relationship between the lateral deviation of the tractor and the lateral deviation of the semi-trailer 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 articulated vehicle 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 articulated vehicle that are furthest from the initial reference trajectory are closer to the initial reference trajectory, and the distance between the two sides of the target articulated vehicle and the road boundary or obstacle of the area to be planned is greater.

[0090] The reference weights can be determined based on the reference turning radius (i.e., the turning radius at the projection point of the target tractor's rear axle center on the initial reference trajectory), the actual turning radius of the target tractor's rear axle center, and the actual turning radius of the target semi-trailer's rear axle center. For example, the reference weights can be calculated using the following formula:

[0091]

[0092] In the formula, W is the reference weight, and R... ref For reference turning radius, R1 represents the turning radius of the rear axle center of the target tractor, R2 represents the turning radius of the rear axle center of the target semi-trailer, and M1 is the distance from the rear axle center of the target tractor to the towing pin.

[0093] Taking a trajectory with constant curvature as the initial reference trajectory as an example, the derivation process of the formula for calculating the reference weight is illustrated by way of example. Figure 7 As shown, Figure 7This is a schematic diagram of the turning radii in the embodiments of this disclosure. Wherein, R1 represents the turning radius at the center of the rear axle of the tractor, R... road R represents the turning radius of the road centerline (the initial reference trajectory can be the road centerline). tt,r R represents the turning radius at the outermost contour point of the target tractor. tt,l This indicates the turning radius at the innermost point of the target semi-trailer's outline (inner rear wheel). Based on... Figure 7 The geometric relationship between the outermost contour point of the target tractor and the outer rear wheel can be obtained as follows:

[0094]

[0095]

[0096] To ensure that the projection of the target articulated vehicle onto the plane of the initial reference trajectory is distributed as evenly as possible on both sides of the trajectory, the turning radius of the initial reference trajectory must satisfy the following:

[0097]

[0098] Combining the above formula, we can obtain the expression for R1. Furthermore, the lateral deviation between the target tractor and the target semi-trailer can be simplified as follows:

[0099] e y =R ref -R1;

[0100]

[0101] Furthermore, the expression for calculating the reference weight W can be obtained.

[0102] 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:

[0103]

[0104] In the formula, This can be directly used as the passage cost, which reflects the safety margin of vehicle passage. In the above implementation, it is not necessary to calculate the area of ​​the target articulated vehicle distributed on both sides of the track separately; a weighted sum can be calculated, which improves the efficiency of track planning while ensuring track safety.

[0105] Of course, a safety margin evaluation function can be constructed by further combining the traffic smoothness at discrete points with the square of the weighted sum.

[0106] Optionally, a safety margin evaluation function for the target articulated vehicle is constructed based on the weighted sum corresponding to each discrete point, including: determining the smoothness of passage corresponding to the current discrete point by the sum of the squares of the differences in the actual steering curvature between the current discrete point and the previous discrete point; determining the balance of passage corresponding to the discrete point by the weighted sum of the lateral deviation of the tractor and the lateral deviation of the semi-trailer; and constructing a safety margin evaluation function for the target articulated vehicle based on the smoothness of passage and the balance of passage corresponding to each discrete point.

[0107] Among them, ride comfort describes the smoothness of vehicle operation, and ride balance describes the difference in the distribution of the vehicle's projection on both sides of the track. Specifically, the weighted sum of the lateral deviations of the tractor and the semi-trailer can be used as the ride balance, and the sum of the squares of the differences in the actual steering curvature between two adjacent discrete points can be used as the ride comfort. Furthermore, the safety margin evaluation function constructed based on ride balance and ride comfort can be:

[0108]

[0109] Where, ω k The weights corresponding to traffic smoothness. For traffic balance, J k For smooth traffic flow, κ k Let $C$ represent the actual turning curvature at the k-th discrete point, and $Cost$ be the toll cost, which reflects the vehicle's safety margin and is inversely proportional to it. It should be noted that a smaller toll cost indicates a larger safety margin, and consequently, a higher level of safety for the vehicle traveling along the planned trajectory.

[0110] 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.

[0111] S120. Based on the lateral deviation of the target semi-trailer's outline points, the lateral deviation of the tractor in the actual state vector, the lateral deviation of the semi-trailer, and the safety boundary range corresponding to the area to be planned, construct safety constraints.

[0112] Here, the contour points can be edge points located on both sides of the target semi-trailer. The lateral deviation of the contour points can be the distance between the contour points and their projection points on the initial reference trajectory. The safety boundary range can be the range within which the vehicle can safely travel, determined based on the road boundaries and obstacles of the area to be planned. Safety constraints can be constraints that prevent the target vehicle from colliding with the road boundaries or obstacles of the area to be planned.

[0113] In one specific implementation, safety constraints are constructed based on the lateral deviation of the target semi-trailer's outline point, the lateral deviation of the tractor in the actual state vector, the lateral deviation of the semi-trailer, and the safety boundary range corresponding to the area to be planned. This includes: determining the upper and lower safety boundaries of the road based on the road boundary of the area to be planned and obstacle information within the area; constructing the safety boundary range corresponding to the area to be planned based on the upper and lower safety boundaries of the road, with the goal of the lateral deviation of the outline point, the lateral deviation of the tractor, and the lateral deviation of the semi-trailer being within the safety boundary range, and constructing safety constraints accordingly.

[0114] That is, the safety boundary range can include the upper safety boundary and the lower safety boundary of the road. The upper and lower safety boundaries can be understood as the boundaries on either side of the road. For example, 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 .

[0115] Specifically, safety constraints can be constructed with the goal of ensuring that the lateral deviations of the contour point, the tractor, and the semi-trailer are all within the safety boundary range. That is, the lateral deviations of the contour point, the tractor, and the semi-trailer must all be less than the safety boundary range. For example:

[0116]

[0117] Where z represents the lateral deviation of the tractor. This indicates the lateral deviation of the semi-trailer. Indicates the lateral deviation of the contour points. It can represent the maximum value among the three deviations, that is, the safety constraint means that the maximum value is less than the safety boundary range.

[0118] 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.

[0119] In this embodiment of the disclosure, the lateral deviation of the contour point can be calculated based on the reference value of the tractor deviation vector in the actual state vector and the tractor deviation vector in the reference state vector.

[0120] Optionally, the actual state vector includes the tractor deviation vector and the semi-trailer deviation vector. The tractor deviation vector includes the tractor lateral deviation, the tractor heading deviation, and the articulation angle between the target tractor and the target semi-trailer. The lateral deviation of the contour point is obtained based on the following formula:

[0121]

[0122] Among them, e y Indicates the lateral deviation of the tractor unit. β1 represents the tractor's heading deviation, and β1 represents the articulation angle. Indicates the lateral deviation of the contour points. These represent the reference values ​​for the lateral deviation of the tractor, the lateral deviation of the profile point, the heading deviation of the tractor, and the articulation angle in the reference state vector, respectively.

[0123] In the above formula, It can also be obtained using the finite difference method. For example, multiple points can be selected at equal intervals on the target semi-trailer, such as... Figure 8 As shown, Figure 8 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 semi-trailer, and each contour point is denoted as... This represents the arc length corresponding to the kth discrete point.

[0124] By using the aforementioned finite difference method, the lateral deviation of the contour points on the target semi-trailer can be determined, which facilitates the construction of safety constraints that take into account the lateral deviation of the contour points, ensuring the accuracy of the safety constraints and thus ensuring the accuracy of the planned trajectory.

[0125] S130. Determine the initial reference trajectory within the area to be planned. Using the maximization of vehicle traffic safety margin as the objective function and the tracking deviation model and safety constraints as the constraints, perform iterative solution to obtain the target control quantity sequence. Based on the target control quantity sequence, determine the target reference trajectory within the area to be planned.

[0126] In this embodiment of the disclosure, the lane centerline within the area to be planned can be determined, and then the lane centerline can be used as the initial reference trajectory. Alternatively, an initial control quantity sequence can be obtained, 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.

[0127] Specifically, maximizing the vehicle traffic safety margin can be used as the objective function, with the tracking deviation model and safety constraints as the constraints, to construct a nonlinear programming problem. The initial reference trajectory is then substituted into this nonlinear programming problem for iterative solution to obtain the target control quantity sequence. This target control quantity sequence includes the actual steering curvature at each discrete point. The actual steering curvature at each discrete point can be the actual steering curvature issued before the target articulated vehicle reaches the next discrete point. For example, the nonlinear programming problem can be expressed by the following formula:

[0128]

[0129] χ k+1 =Aχ k +Bκ k ,k∈(0,1,...,N-1);

[0130] χ0=χ satrt ,κ0=κ satrt ;

[0131] g(χ k )≤B,k∈(0,1,...,N);

[0132] In the formula, The comprehensive state vector includes the tractor deviation vector, the semi-trailer deviation vector, and the profile point deviation vector, where the profile point deviation vector includes the profile point lateral deviation.

[0133] In this embodiment of the disclosure, the iterative solution to the nonlinear programming problem can be a sequential quadratic programming problem, such as SQP (Sequential Quadratic Programming), IPOPT (Interior Point Optimizer), or CiLQR (Constrained Iterative Linear Quadratic Regulator).

[0134] For example, an initial reference trajectory is determined within the area to be planned. The objective function is to maximize the vehicle traffic safety margin, and the tracking deviation model and safety constraints are used as constraints. An iterative solution is then performed to obtain the target control quantity sequence, including the following steps:

[0135] Step 1: Determine the initial reference trajectory within the area to be planned;

[0136] Step 2: Using the maximization of vehicle traffic safety margin as the objective function, and the tracking deviation model and safety constraints as the constraints, construct a nonlinear programming problem;

[0137] Step 3: Substitute the initial reference trajectory into the nonlinear programming problem to obtain the current control quantity sequence, and determine whether the iteration stopping condition is met. If not, update the initial reference trajectory based on the current control quantity sequence, and return to execute the step of substituting the initial reference trajectory into the nonlinear programming problem until the iteration stopping condition is met, and use the current control quantity sequence as the target control quantity sequence.

[0138] The iteration stopping condition can be that the number of iterations reaches a preset number, or that the difference between the vehicle traffic safety margins obtained after each iteration gradually converges.

[0139] That is, the initial reference trajectory can be obtained first based on the lane centerline or the initial control quantity sequence, and then the current control quantity sequence can be obtained by substituting it into the solution. A new initial reference trajectory can be determined based on the current control quantity sequence, and the new initial reference trajectory can be substituted into the solution again. The above process is repeated until the iteration stopping condition is met, and the last determined current control quantity sequence is taken as the target control quantity sequence.

[0140] 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.

[0141] 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 articulated vehicle 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.

[0142] Furthermore, the target reference trajectory can be sent to the autonomous driving control system of the target articulated vehicle, enabling the system to control the vehicle to travel along that trajectory. It's important to note that simultaneously with sending the target reference trajectory, tracking points within it can also be determined and sent to the autonomous driving control system. These tracking points can be determined by the actual steering curvature in the target control sequence. They can be understood as points within the vehicle that are traveling along the target reference trajectory. By controlling these tracking points to travel along the trajectory, driving control of the vehicle can be achieved.

[0143] Considering that excessively large or varying actual steering curvature would affect the smoothness and safety of the target articulated vehicle passing through the planned area, the method provided in this embodiment may optionally include: using the maximization of vehicle traffic safety margin as the objective function, a tracking deviation model, safety constraints, a first steering curvature constraint, and a second steering curvature constraint as constraints, performing a band-based solution to obtain a target control quantity sequence; wherein, the first steering curvature constraint is used to constrain the actual steering curvature at each discrete point from not exceeding a preset threshold, and the second steering curvature constraint is used to constrain the difference between the actual steering curvatures at adjacent discrete points from not exceeding a preset variation.

[0144] Wherein, the first turning curvature constraint can be: |κ k |≤k max ,k∈(0,1,...,N-1). The second turning curvature constraint can be: |k k -k k-1 |≤Δk max ,k∈(0,1,...,N-1),N is the number of sampling points.

[0145] In the above implementation, by using the first steering curvature constraint and the second steering curvature constraint as constraints, the optimal control quantity sequence that simultaneously satisfies the first steering curvature constraint and the second steering curvature constraint can be solved, further improving the safety and smoothness of the planned trajectory.

[0146] The trajectory planning method for articulated vehicles provided in this embodiment obtains the tracking deviation model and safety margin evaluation function corresponding to the target articulated vehicle. Based on the lateral deviation of the contour points of the target semi-trailer in the target articulated vehicle, the safety boundary range corresponding to the area to be planned, and the lateral deviations of the tractor and semi-trailer in the actual state vector of the target articulated vehicle, safety constraints are constructed. Then, with maximizing the vehicle passage safety margin as the objective function and the tracking deviation model and safety constraints as the constraint conditions, the initial reference trajectory is iteratively solved to obtain the target control quantity sequence, thereby determining the target reference trajectory in the area to be planned. This method realizes the safety constraint considering the deviation of the semi-trailer contour points. By limiting the lateral deviation of the semi-trailer contour points to not exceed the safety boundary range, it ensures that articulated vehicles with long wheelbases and wide bodies can safely pass through narrow areas. Furthermore, by solving with maximizing the safety margin as the objective function, the final constructed trajectory has a large safety margin, further improving the safety of articulated vehicles passing through narrow areas and solving the steering safety problem of articulated vehicles in narrow areas.

[0147] Figure 9 This is a schematic diagram of the trajectory planning device for an articulated vehicle according to an embodiment of this disclosure. Figure 9As shown: The device includes: an acquisition module 910, a constraint construction module 920, and an iteration module 930.

[0148] The acquisition module 910 is used to acquire the tracking deviation model and safety margin evaluation function corresponding to the target articulated vehicle. The target articulated vehicle includes a target tractor and a target semi-trailer. The tracking deviation model is used to determine the actual state vector at each discrete point. The safety margin evaluation function is used to determine the vehicle passage safety margin based on the actual state vector.

[0149] The constraint construction module 920 is used to construct safety constraints based on the lateral deviation of the contour points of the target semi-trailer, the lateral deviation of the tractor in the actual state vector, the lateral deviation of the semi-trailer, and the safety boundary range corresponding to the area to be planned.

[0150] The iterative module 930 is used to determine the initial reference trajectory within the area to be planned, and to perform iterative solution with the maximization of vehicle traffic safety margin as the objective function, the tracking deviation model and the safety constraints as the constraints, to obtain the target control quantity sequence, and to determine the target reference trajectory within the area to be planned based on the target control quantity sequence.

[0151] The trajectory planning device for articulated vehicles provided in this embodiment can execute the steps in the trajectory planning method for articulated vehicles provided in this embodiment, and has the execution steps and beneficial effects, which will not be repeated here.

[0152] Figure 10 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. See below for details. Figure 10 It shows a schematic diagram of a structure suitable for implementing the electronic device 500 in the embodiments of this disclosure. Figure 10 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0153] like Figure 10 As 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.

[0154] 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 an articulated vehicle 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.

[0155] 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.

[0156] 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:

[0157] Obtain the tracking deviation model and safety margin evaluation function corresponding to the target articulated vehicle, wherein the target articulated vehicle includes the target tractor and the target semi-trailer, the tracking deviation model is used to determine the actual state vector at each discrete point, and the safety margin evaluation function is used to determine the vehicle passage safety margin based on the actual state vector.

[0158] Safety constraints are constructed based on the lateral deviation of the outline points of the target semi-trailer, the lateral deviation of the tractor in the actual state vector, the lateral deviation of the semi-trailer, and the safety boundary range corresponding to the area to be planned.

[0159] An initial reference trajectory is determined within the area to be planned. The objective function is to maximize the vehicle traffic safety margin, and the tracking deviation model and the safety constraints are used as constraints. The solution is iteratively obtained to obtain a target control quantity sequence. Based on the target control quantity sequence, the target reference trajectory within the area to be planned is determined.

[0160] Optionally, when one or more of the above-described procedures are executed by the electronic device, the electronic device may also perform other steps described in the above embodiments.

[0161] 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.

[0162] Option 1: A trajectory planning method for an articulated vehicle, the method comprising:

[0163] Obtain the tracking deviation model and safety margin evaluation function corresponding to the target articulated vehicle, wherein the target articulated vehicle includes the target tractor and the target semi-trailer, the tracking deviation model is used to determine the actual state vector at each discrete point, and the safety margin evaluation function is used to determine the vehicle passage safety margin based on the actual state vector.

[0164] Safety constraints are constructed based on the lateral deviation of the outline points of the target semi-trailer, the lateral deviation of the tractor in the actual state vector, the lateral deviation of the semi-trailer, and the safety boundary range corresponding to the area to be planned.

[0165] An initial reference trajectory is determined within the area to be planned. The objective function is to maximize the vehicle traffic safety margin, and the tracking deviation model and the safety constraints are used as constraints. The solution is iteratively obtained to obtain a target control quantity sequence. Based on the target control quantity sequence, the target reference trajectory within the area to be planned is determined.

[0166] Option 2: Based on the method described in Option 1, safety constraints are constructed according to the lateral deviation of the target semi-trailer's contour points, the lateral deviation of the tractor in the actual state vector, the lateral deviation of the semi-trailer, and the safety boundary range corresponding to the area to be planned. These constraints include:

[0167] Based on the road boundary of the area to be planned and the obstacle information within the area to be planned, the upper boundary and lower boundary of road safety are determined.

[0168] Based on the upper and lower boundaries of road safety, a safety boundary range corresponding to the area to be planned is constructed. With the lateral deviation of the contour point, the lateral deviation of the tractor, and the lateral deviation of the semi-trailer located within the safety boundary range as the target, safety constraints are constructed.

[0169] Option 3: According to the method described in Option 1, the actual state vector includes a tractor deviation vector and a semi-trailer deviation vector. The tractor deviation vector includes the tractor lateral deviation, the tractor heading deviation, and the articulation angle between the target tractor and the target semi-trailer. The lateral deviation of the contour point is obtained based on the following formula:

[0170]

[0171] Among them, e y This indicates the lateral deviation of the tractor unit. β1 represents the heading deviation of the tractor, and β2 represents the articulation angle. This indicates the lateral deviation of the contour points. These represent the reference values ​​for the lateral deviation of the tractor, the lateral deviation of the profile point, the heading deviation of the tractor, and the articulation angle in the reference state vector, respectively.

[0172] Option 4: Based on the method described in Option 3, obtain the tracking deviation model corresponding to the target articulated vehicle, including:

[0173] 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.

[0174] 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.

[0175] The state vector transition relationship is used as the tracking deviation model.

[0176] Option 5: According to the method described in Option 4, obtaining the tracking deviation model corresponding to the target articulated vehicle further includes:

[0177] A differential transformation relationship is constructed between the tractor deviation vector and the semi-trailer deviation vector, so as to determine the semi-trailer deviation vector through the differential transformation relationship and the tractor deviation vector;

[0178] The difference transformation relationship is used as the tracking deviation model;

[0179] The semi-trailer deviation vector includes the semi-trailer lateral deviation and the semi-trailer heading deviation;

[0180] The difference transformation relationship satisfies the following formula:

[0181]

[0182]

[0183] In the formula, e y This indicates the lateral deviation of the tractor unit. β1 represents the heading deviation of the tractor, and β2 represents the articulation angle. This indicates the lateral deviation of the semi-trailer. This indicates the heading deviation of the semi-trailer. These are the reference values ​​for the lateral deviation of the tractor, the heading deviation of the tractor, the lateral deviation of the semi-trailer, the heading deviation of the semi-trailer, and the articulation angle, respectively, in the reference state vector.

[0184] Option 6: According to the method described in Option 1, obtain the safety margin evaluation function corresponding to the target articulated vehicle, including:

[0185] Based on the lateral deviation of the tractor, the lateral deviation of the semi-trailer, and the reference weight corresponding to the lateral deviation of the semi-trailer, a weighted sum of the lateral deviation of the tractor and the lateral deviation of the semi-trailer is determined, so as to describe the distribution difference between the projections of the target articulated vehicle on both sides of the initial reference trajectory through the weighted sum.

[0186] Based on the weighted sum corresponding to each discrete point, a safety margin evaluation function for the target articulated vehicle is constructed.

[0187] Option 7: According to the method described in Option 6, the step of constructing the safety margin evaluation function of the target articulated vehicle based on the weighted sum corresponding to each discrete point includes:

[0188] The sum of the squares of the differences in the actual turning curvature between the current discrete point and the previous discrete point is determined as the smoothness of passage corresponding to the current discrete point.

[0189] The traffic balance degree corresponding to the discrete point is determined by the weighted sum of the lateral deviation of the tractor and the lateral deviation of the semi-trailer corresponding to the discrete point.

[0190] Based on the smoothness and balance of traffic corresponding to each discrete point, a safety margin evaluation function for the target articulated vehicle is constructed.

[0191] Option 8: A trajectory planning device for an articulated vehicle, comprising:

[0192] The acquisition module is used to acquire the tracking deviation model and safety margin evaluation function corresponding to the target articulated vehicle. The target articulated vehicle includes a target tractor and a target semi-trailer. The tracking deviation model is used to determine the actual state vector at each discrete point. The safety margin evaluation function is used to determine the vehicle passage safety margin based on the actual state vector.

[0193] The constraint construction module is used to construct safety constraints based on the lateral deviation of the contour points of the target semi-trailer, the lateral deviation of the tractor in the actual state vector, the lateral deviation of the semi-trailer, and the safety boundary range corresponding to the area to be planned.

[0194] An iterative module is used to determine the initial reference trajectory within the area to be planned, and to perform iterative solution with the maximization of vehicle traffic safety margin as the objective function, the tracking deviation model and the safety constraints as the constraints, to obtain the target control quantity sequence, and to determine the target reference trajectory within the area to be planned based on the target control quantity sequence.

[0195] Option 9: An electronic device, the electronic device comprising:

[0196] One or more processors;

[0197] Storage device for storing one or more programs;

[0198] 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.

[0199] 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.

[0200] 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 articulated vehicle, characterized in that, The method includes: Obtain the tracking deviation model and safety margin evaluation function corresponding to the target articulated vehicle, wherein the target articulated vehicle includes the target tractor and the target semi-trailer, the tracking deviation model is used to determine the actual state vector at each discrete point, and the safety margin evaluation function is used to determine the vehicle passage safety margin based on the actual state vector. Based on the lateral deviation of the outline points of the target semi-trailer, the lateral deviation of the target tractor in the actual state vector, the lateral deviation of the target semi-trailer, and the safety boundary range corresponding to the area to be planned, safety constraints are constructed. An initial reference trajectory is determined within the area to be planned. The objective function is to maximize the vehicle traffic safety margin, and the tracking deviation model and the safety constraints are used as constraints. The solution is iteratively obtained to obtain a target control quantity sequence. Based on the target control quantity sequence, the target reference trajectory within the area to be planned is determined. The actual state vector includes the target tractor deviation vector and the target semi-trailer deviation vector; the tracking deviation model determines the actual state vector of the next discrete point based on the actual state vector of the current discrete point, the actual steering curvature, the reference state vector, the reference steering curvature, and a constant term; the tracking deviation model is also used to determine the target semi-trailer deviation vector for each discrete point based on the target tractor deviation vector at the discrete point.

2. The method of claim 1, wherein, Based on the lateral deviation of the target semi-trailer's contour points, the lateral deviation of the target tractor in the actual state vector, the lateral deviation of the target semi-trailer, and the safety boundary range corresponding to the area to be planned, safety constraints are constructed, including: Based on the road boundary of the area to be planned and the obstacle information within the area to be planned, the upper boundary and lower boundary of road safety are determined. Based on the upper and lower boundaries of road safety, a safety boundary range corresponding to the area to be planned is constructed. With the lateral deviation of the contour point, the lateral deviation of the target tractor, and the lateral deviation of the target semi-trailer located within the safety boundary range as targets, safety constraints are constructed.

3. The method of claim 1, wherein, The actual state vector includes the target tractor deviation vector and the target semi-trailer deviation vector. The target tractor deviation vector includes the target tractor lateral deviation, the target tractor heading deviation, and the articulation angle between the target tractor and the target semi-trailer. The lateral deviation of the contour point is obtained based on the following formula: in, This indicates the lateral deviation of the target tractor. This indicates the heading deviation of the target tractor. Indicates the hinge angle, This indicates the lateral deviation of the contour points. , , , These represent the reference values ​​for the lateral deviation of the target tractor, the lateral deviation of the contour point, the heading deviation of the target tractor, and the articulation angle, respectively, in the reference state vector.

4. The method of claim 3, wherein, Obtain the tracking deviation model corresponding to the target articulated vehicle, including: 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.

5. The method of claim 4, wherein, The method for obtaining the tracking deviation model corresponding to the target articulated vehicle further includes: A differential transformation relationship is constructed between the target tractor deviation vector and the target semi-trailer deviation vector, so as to determine the target semi-trailer deviation vector through the differential transformation relationship and the target tractor deviation vector; The difference transformation relationship is used as the tracking deviation model; The target semi-trailer deviation vector includes the target semi-trailer lateral deviation and the target semi-trailer heading deviation; The difference transformation relationship satisfies the following formula: ； ； In the formula, This indicates the lateral deviation of the target tractor. This indicates the heading deviation of the target tractor. Indicates the hinge angle, This indicates the lateral deviation of the target semi-trailer. This indicates the heading deviation of the target semi-trailer. , , , , These are the reference values ​​for the lateral deviation of the target tractor, the heading deviation of the target tractor, the lateral deviation of the target semi-trailer, the heading deviation of the target semi-trailer, and the articulation angle, respectively, in the reference state vector.

6. The method of claim 1, wherein, Obtain the safety margin evaluation function corresponding to the target articulated vehicle, including: Based on the lateral deviation of the target tractor, the lateral deviation of the target semi-trailer, and the reference weight corresponding to the lateral deviation of the target semi-trailer, a weighted sum of the lateral deviation of the target tractor and the lateral deviation of the target semi-trailer is determined, so as to describe the distribution difference between the projections of the target articulated vehicle 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 articulated vehicle is constructed.

7. The method of claim 6, wherein, The construction of the safety margin evaluation function for the target articulated vehicle based on the weighted sum corresponding to each discrete point includes: The sum of the squares of the differences in the actual turning curvature between the current discrete point and the previous discrete point is determined as the smoothness of passage corresponding to the current discrete point. The traffic balance degree corresponding to the discrete point is determined by the weighted sum of the lateral deviation of the target tractor and the lateral deviation of the target semi-trailer corresponding to the discrete point. Based on the smoothness and balance of traffic corresponding to each discrete point, a safety margin evaluation function for the target articulated vehicle is constructed.

8. A trajectory planning device for a vehicle with articulated wheels, characterized in that include: The acquisition module is used to acquire the tracking deviation model and safety margin evaluation function corresponding to the target articulated vehicle. The target articulated vehicle includes a target tractor and a target semi-trailer. The tracking deviation model is used to determine the actual state vector at each discrete point. The safety margin evaluation function is used to determine the vehicle passage safety margin based on the actual state vector. The constraint construction module is used to construct safety constraints based on the lateral deviation of the contour points of the target semi-trailer, the lateral deviation of the target tractor in the actual state vector, the lateral deviation of the target semi-trailer, and the safety boundary range corresponding to the area to be planned. An iterative module is used to determine the initial reference trajectory within the area to be planned, and to perform iterative solution with the maximization of vehicle traffic safety margin as the objective function, the tracking deviation model and the safety constraints as the constraints, to obtain the target control quantity sequence, and to determine the target reference trajectory within the area to be planned based on the target control quantity sequence. The actual state vector includes the target tractor deviation vector and the target semi-trailer deviation vector; the tracking deviation model determines the actual state vector of the next discrete point based on the actual state vector of the current discrete point, the actual steering curvature, the reference state vector, the reference steering curvature, and a constant term; the tracking deviation model is also used to determine the target semi-trailer deviation vector for each discrete point based on the target tractor deviation vector at the discrete point.

9. An electronic device, comprising: 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 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images