Clamped B-Spline curve local trajectory planning method and system based on BWO

Abstract

The invention relates to the technical field of automobiles, in particular to a Clapped B-Spline curve local trajectory planning method and system based on BWO, and the method comprises the steps: S1, obtaining the original coordinate data of a UTM coordinate system; wherein the original coordinate data comprises a free vehicle coordinate, a pilot vehicle coordinate and course angle data; and S2, when the free vehicle meets the formation joining condition, generating an optimal driving track of the free vehicle through a track generation algorithm based on a pre-configured driving rule and the original coordinate data. Compared with the prior art, the method has the advantages that the defects of insufficient smoothness and adjustability of a traditional Bezier curve can be overcome, and the problem of possible insufficient flexibility in a complex scene can be solved.

Description

Technical Field

[0001] This application relates to the field of automotive technology, and in particular to a method and system for local trajectory planning of Clamped B-Spline curves based on BWO. Background Technology

[0002] Heavy-duty commercial vehicle platooning is a crucial technology in intelligent transportation. Through vehicle-to-vehicle (V2V) communication technology, it enables multiple heavy-duty commercial vehicles to travel collaboratively with smaller distances, reducing air resistance, fuel consumption, and emissions, thereby improving transportation efficiency. Platooning also alleviates traffic congestion and increases road utilization. Its technological foundation includes advanced vehicle sensing systems (radar, cameras, lidar) and communication technologies (such as C-V2X) to achieve real-time information sharing and collaborative control between vehicles. Furthermore, platooning reduces driver fatigue and improves safety. With technological advancements and improved regulations, heavy-duty commercial vehicle platooning is expected to become an important mode of future logistics transportation, driving sustainable development in the industry. Vehicle platooning refers to two or more vehicles traveling in a convoy with a certain distance between them. In platooning, each following vehicle senses the speed and braking status of the lead vehicle and maintains the same driving behavior as the vehicle in front, thereby improving safety. Path planning generates a collision-free trajectory that satisfies the vehicle's own constraints based on the vehicle's starting and destination points.

[0003] However, when a new vehicle joins the platoon from a non-platoon state, it needs to first plan an initial trajectory from its current position to a designated following position within the platoon—this is local trajectory planning. This allows for the seamless transition from independent driving to platooning, accurately matching the platoon's speed, spacing, and trajectory. In this specific scenario, commonly used local trajectory planning algorithms exhibit significant limitations; these include Bézier curves, Dijkstra's algorithm, graph search, and fifth-order polynomial methods.

[0004] While traditional Bézier curves offer smoothness and adjustability, they may lack flexibility when faced with complex access conditions such as real-time changes in vehicle speed and dynamically adjusted queue spacing. Dijkstra's algorithm is suitable for shortest path planning in non-dynamic environments, but it is computationally intensive and has a long response time, making it unsuitable for real-time planning. Graph search methods are suitable for global planning, but they have slow convergence, complex environment modeling, and low computational efficiency. The fifth-order polynomial method can generate smooth lane-change curves, but the coefficient calculation is complex, it is sensitive to initial conditions, and it is difficult to accurately describe the dynamic behavior of vehicles.

[0005] In summary, existing methods, when planning trajectories for joining a convoy, need to respond quickly to convoy dynamics to avoid missing the opportunity to join, while also ensuring smooth and accurate trajectories for safe integration. This often leads to problems such as stuttering and poor connection of the trajectory, or the pursuit of high-quality trajectories increases the complexity of the algorithm and reduces real-time performance. Therefore, these methods still need improvement.

[0006] Based on the above, this application provides a local trajectory planning method and system for Clamped B-Spline curves based on BWO, in order to solve the technical defects existing in the prior art. Summary of the Invention

[0007] The purpose of this invention is to provide a local trajectory planning method and system for Clamped B-Spline curves based on BWO, which can improve upon the shortcomings of traditional Bézier curves, such as insufficient smoothness and adjustability, and the potential lack of flexibility in complex scenarios. The specific solution is as follows:

[0008] A local trajectory planning method for Clamped B-Spline curves based on BWO, the method comprising the following steps:

[0009] S1: Obtain the raw coordinate data of the UTM coordinate system; wherein, the raw coordinate data includes: free vehicle coordinates, navigator vehicle coordinates and heading angle data;

[0010] S2: When a free vehicle meets the conditions for joining a platoon, the optimal driving trajectory of the free vehicle is generated based on the pre-configured driving rules and original coordinate data through a trajectory generation algorithm.

[0011] Optionally, step S1: Obtain the raw coordinate data of the UTM coordinate system, specifically including:

[0012] S11: Translate the origin of the UTM coordinate system to the center coordinate of the rear axle of the free-wheeling vehicle to obtain a translation coordinate system with the center of the rear axle of the free-wheeling vehicle as the origin;

[0013] S12: Based on the raw coordinate data of UTM, obtain the coordinates of the rear axle center of the navigator in the translation coordinate system;

[0014] S13: Using the origin of the translation coordinate system as the rotation center, rotate the translation coordinate system clockwise according to the heading angle of the free vehicle to obtain a local coordinate system with the direction of travel of the free vehicle as the positive direction of the Y-axis, and obtain the target coordinates of the rear axle center of the navigator in the local coordinate system; where the navigation angle is the angle when rotating clockwise from due north to the direction of travel of the free vehicle under UTM.

[0015] Optionally, step S2: When the free vehicle meets the conditions for joining the formation, based on the pre-configured driving rules and original coordinate data, the optimal driving trajectory of the free vehicle is generated through a trajectory generation algorithm, specifically including:

[0016] In the local coordinate system, when the free vehicle is behind the lead vehicle, the free vehicle meets the conditions for joining the formation.

[0017] The driving rules include start-point constraints and end-point constraints.

[0018] The starting point constraint is that the tangent direction at the starting point of the driving trajectory is equal to the heading angle of the vehicle; the ending point constraint is that the tangent direction at the ending point of the driving trajectory is equal to the tangent direction angle of the road at the ending point.

[0019] The starting point of the driving trajectory is the current rear axle center of the free vehicle; the ending point of the driving trajectory is the rear axle center corresponding to the target position of the formation behind the navigator vehicle.

[0020] When the qualification for joining the platoon is approved, the optimal driving trajectory of the free vehicle is generated by inputting the starting coordinates of the free vehicle and the ending coordinates of the target position of the platoon based on the driving rules.

[0021] Optionally, when the platoon qualification judgment result is passed, based on the driving rules and the starting coordinates of the free vehicle and the ending coordinates of the platoon target position, the data is input into the trajectory generation algorithm to generate the optimal driving trajectory of the free vehicle, specifically including:

[0022] Based on the starting coordinates of the free vehicle, the ending coordinates of the formation target position, vehicle dynamics constraint data, and Clamped B-Spline curve parameters, the number and coordinates of control points are adjusted through a preset trajectory generation algorithm to generate several initial Clamped B-Spline candidate curves.

[0023] Obtain the solution vector corresponding to the candidate solution of each initial candidate curve; each solution vector includes the coordinates of a corresponding number of control points and the number of control points.

[0024] Based on the solution vector of each candidate solution and vehicle dynamics constraint data, a pre-defined weighted method is used to calculate the fitness function value F corresponding to the candidate solution of each initial candidate curve.

[0025] All candidate solutions and their corresponding fitness function values ​​are input into the BWO algorithm. Through iterative search, the solution vector with the minimum fitness function value is obtained and taken as the optimal solution vector. The optimal solution vector includes the coordinates of the optimal control point and the number of optimal control points.

[0026] Based on the optimal number of control points, the node vector of the Clamped B-Spline curve is generated using a parameterization method for the Clamped B-Spline curve.

[0027] Based on the node vectors and the coordinates of the optimal control points, the optimal Clamped B-Spline curve is generated to obtain the optimal driving trajectory.

[0028] Optionally, the parameterization method for the Clamped B-Spline curve selects a cubic Clamped B-Spline curve with a curve order P of 3, and achieves endpoint interpolation characteristics by repeating the first and last nodes.

[0029] Optionally, based on the optimal number of control points, the node vector of the Clamped B-Spline curve is generated using a parameterization method for the Clamped B-Spline curve, specifically including:

[0030] Based on the optimal number of control points N output by the BWO algorithm, and with the endpoint constraints and smoothness requirements of the formation trajectory as the objectives, the node vector is generated by a parameterization method of the Clamped B-Spline curve.

[0031] The node vector is designed with endpoint constraints at the center of the rear axle of the free vehicle at the starting point of the trajectory and the target position behind the lead vehicle at the ending point. It is configured using a quasi-uniform distribution of cubic Clamped B-Spline curves. The first and last nodes are repeated according to the curve order + 1 times, and the middle nodes are uniformly interpolated according to the curve domain. The length L of the node vector matches the mapping relationship between the number of optimal control points N and the curve order p, so that the segmented control accuracy of the control points on the trajectory meets the vehicle dynamics constraints. The length L of the node vector is equal to the number of optimal control points N plus the curve order + 1.

[0032] A local trajectory planning system for Clamped B-Spline curves based on BWO, the system comprising:

[0033] The acquisition module is configured to acquire raw coordinate data in the UTM coordinate system; wherein, the raw coordinate data includes: free vehicle coordinates, navigator vehicle coordinates, and heading angle data;

[0034] The generation module is configured to generate the optimal driving trajectory of a free vehicle based on pre-configured driving rules and original coordinate data, using a trajectory generation algorithm, when the free vehicle meets the conditions for joining the formation.

[0035] An electronic device includes: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method.

[0036] A computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the method described herein.

[0037] A simulation platform, comprising:

[0038] An electronic device for implementing the steps of the method;

[0039] A processor that runs a program, and when the program runs, it executes the steps of the method from data output by the electronic device.

[0040] A storage medium for storing a program that, when run, executes the steps of the method on data output from an electronic device.

[0041] The above solution achieves the following beneficial technical effects:

[0042] This application provides a local trajectory planning method and system based on BWO (Binary Flow Object) Clamped B-Spline curves. Using the UTM coordinate system as the coordinate reference eliminates the accumulated errors of traditional local coordinate systems, ensuring the accuracy of coordinate data for both the free vehicle and the lead vehicle. Based on this, when a free vehicle meets the conditions for joining the platoon, the optimal driving trajectory of the free vehicle is generated through a trajectory generation algorithm based on pre-configured driving rules and original coordinate data, avoiding deviations in the trajectory start and end points. Simultaneously, the smoothness of the curve meets the dynamic requirements of commercial vehicles for driving smoothness, ultimately achieving the goal of generating precise entry, smooth transition, and dynamically feasible platooning trajectory. Compared to existing technologies, this significantly improves upon the shortcomings of traditional Bézier curves in terms of smoothness, adjustability, and potential inflexibility in complex scenarios. Attached Figure Description

[0043] Figure 1 This is a flowchart illustrating a local trajectory planning method for Clamped B-Spline curves based on BWO.

[0044] Figure 2 This is a flowchart illustrating one embodiment of the BWO-based Clamped B-Spline curve local trajectory planning method;

[0045] Figure 3This is a block diagram of a BWO-based Clamped B-Spline curve local trajectory planning system. Detailed Implementation

[0046] To make the purpose, technical solution, and advantages of this application clearer, the following will be described in conjunction with the appendix. Figures 1-3 This application will be described in further detail. It is obvious that the described embodiments are merely some, not all, of the embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments described herein without inventive effort are within the scope of protection of this application.

[0047] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0048] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0049] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0050] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0051] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0052] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0053] like Figure 1 The method shown is a local trajectory planning method for Clamped B-Spline curves based on BWO, which includes the following steps:

[0054] S1: Obtain the raw coordinate data of the UTM coordinate system; wherein, the raw coordinate data includes: free vehicle coordinates, navigator vehicle coordinates and heading angle data;

[0055] S2: When a free vehicle meets the conditions for joining a platoon, the optimal driving trajectory of the free vehicle is generated based on the pre-configured driving rules and original coordinate data through a trajectory generation algorithm.

[0056] Among them, BWO is the Beluga Whale Optimization Algorithm; UTM stands for Universal Transverse Mercator.

[0057] Specifically, this embodiment uses the UTM coordinate system as the coordinate reference, which can eliminate the accumulated error of the traditional local coordinate system and ensure the accuracy of the coordinate data of the free vehicle and the lead vehicle. On this basis, when the free vehicle meets the conditions for joining the formation, the optimal driving trajectory of the free vehicle is generated by the trajectory generation algorithm based on the pre-configured driving rules and the original coordinate data, avoiding deviation of the trajectory start and end points. At the same time, the smoothness of the curve meets the dynamic requirements of commercial vehicles for driving smoothness, and finally achieves the goal of precise entry, smooth transition and dynamic feasible formation trajectory generation.

[0058] See Figure 2 As shown, step S1: Obtain the raw coordinate data of the UTM coordinate system, specifically including:

[0059] S11: Translate the origin of the UTM coordinate system to the center coordinate of the rear axle of the free-wheeling vehicle to obtain a translation coordinate system with the center of the rear axle of the free-wheeling vehicle as the origin;

[0060] S12: Based on the raw coordinate data of UTM, obtain the coordinates of the rear axle center of the navigator in the translation coordinate system;

[0061] S13: Using the origin of the translation coordinate system as the rotation center, rotate the translation coordinate system clockwise according to the heading angle of the free vehicle to obtain a local coordinate system with the direction of travel of the free vehicle as the positive direction of the Y-axis, and obtain the target coordinates of the rear axle center of the navigator in the local coordinate system; where the navigation angle is the angle when rotating clockwise from due north to the direction of travel of the free vehicle under UTM.

[0062] Specifically, this embodiment uses a high-precision UTM coordinate system as the original data. By translating the origin to the center of the rear axle of the free vehicle, the starting point of the trajectory planning is directly fixed as the origin (0,0) of the coordinate system, eliminating the need for additional calculation of the starting point offset. This adapts to the construction constraint that the endpoint interpolation of the Clamped B-Spline curve requires anchoring the starting point. Then, by rotating the free vehicle's heading angle clockwise to obtain a local coordinate system with the driving direction in the positive Y-axis direction, the global coordinates are transformed into relative coordinates centered on the free vehicle. At this point, the target coordinates of the lead vehicle are (lateral offset, longitudinal distance). This design allows for a more intuitive understanding of the lateral lane adjustment and longitudinal parking distance required for joining the platoon, greatly simplifying the parameterization definition of the subsequent trajectory endpoint. At the same time, this transformation is entirely based on the free vehicle's own state, avoiding interference from irrelevant positional information in the global coordinates. Thus, the trajectory planning relies entirely on the relative positional relationship between the free vehicle and the lead vehicle, ensuring the accuracy inheritance of coordinate data and reducing the impact of Clamped B-Spline through target alignment of the local coordinate system. The complexity of curve control point coordinate calculation and BWO algorithm optimization of target parameter mapping is reduced to ensure accurate endpoints, direction adaptation, and efficient computation in subsequent trajectory generation.

[0063] To facilitate the calculation of the relative positions of the two vehicles, this embodiment employs a coordinate system transformation method involving translation followed by rotation. Specifically, the origin of the coordinate system is first translated to the position of the free vehicle (the lead vehicle), then a two-dimensional coordinate system is established with the heading angle as the positive y-axis, and finally, a coordinate rotation is performed. In the Universal Transverse Mercator (UTM) coordinate system, the heading angle refers to the angle rotated clockwise from true north. After the coordinate translation and rotation, the relative positions of the free vehicle and the lead vehicle can be determined in the new coordinate system. The free vehicle can only join the formation when it is behind the lead vehicle. Otherwise, it is prohibited from joining the formation.

[0064] In one specific embodiment, step S2: When the free vehicle meets the conditions for joining the formation, based on the pre-configured driving rules and original coordinate data, the optimal driving trajectory of the free vehicle is generated through a trajectory generation algorithm, specifically including:

[0065] In the local coordinate system, when a free car is behind the lead car, the free car meets the conditions for joining the formation; for example, when the Y-value of the rear axle center of the lead car is greater than 0, the free car meets the conditions for joining the formation.

[0066] The driving rules include start-point constraints and end-point constraints.

[0067] The starting point constraint is that the tangent direction at the starting point of the driving trajectory is equal to the heading angle of the vehicle; the ending point constraint is that the tangent direction at the ending point of the driving trajectory is equal to the tangent direction angle of the road at the ending point.

[0068] The starting point of the driving trajectory is the center of the rear axle of the free vehicle; the ending point of the driving trajectory is the center of the rear axle corresponding to the target position of the formation behind the lead vehicle, that is, the preset target endpoint coordinates in the local coordinate system. It can be understood that when driving in formation, the free vehicle needs to connect to the fixed parking space behind the lead vehicle. The reference point of this parking space is the virtual rear axle center of the corresponding position behind the lead vehicle. Using this as the endpoint can ensure the spacing and alignment accuracy of vehicles in the formation.

[0069] When the qualification for joining the platoon is approved, the optimal driving trajectory of the free vehicle is generated by inputting the starting coordinates of the free vehicle and the ending coordinates of the target position of the platoon based on the driving rules.

[0070] Specifically, this embodiment predefines driving rules, namely, the starting point constraint is that the tangent direction of the starting point is equal to the heading angle of the free vehicle, thus associating the direction of the trajectory starting point with the current driving direction of the vehicle, avoiding sudden changes in direction when the trajectory starts (such as the vehicle moving forward but the trajectory suddenly deviating to the left), thereby satisfying the dynamic characteristics of the vehicle's large steering inertia and the inability to make sharp turns; the ending point constraint is that the tangent direction of the ending point is equal to the tangent direction angle of the road, by aligning the direction of the trajectory ending point with the road trend and the platoon driving direction, ensuring that the free vehicle can directly match the platoon driving state after entering the platoon, without the need for secondary direction adjustment; at the same time, by specifying that the trajectory starting and ending points are the rear axle center of the vehicle, the problem of the trajectory appearing reasonable but the actual vehicle being unable to drive due to reference point deviation can be avoided; by directly inputting these rules and the coordinates of the starting and ending points into the trajectory generation algorithm, and by utilizing the characteristics of tools such as Clamped B-Spline curves, the endpoint position constraints and endpoint tangent constraints are also satisfied at the same time, without the need to design an additional complex constraint processing module, greatly reducing the computational requirements and indirectly simplifying the algorithm.

[0071] It's understandable that, since vehicles cannot slide in place during movement, the generated curves need to satisfy the starting direction constraint. Furthermore, when performing lane changes and turns, the trajectory at the endpoint must adhere to the constraints of the road's structural features; the tangent direction of the trajectory must be the same as the road's trend. Therefore, the endpoint of the generated trajectory needs to satisfy the endpoint direction constraint. The starting and ending points are locked at the rear axle centers of the following and lead vehicles, respectively, to avoid problems caused by reference point deviations that prevent the actual vehicles from moving.

[0072] In one specific embodiment, when the platoon qualification judgment result is passed, based on the driving rules and the starting coordinates of the free vehicle and the ending coordinates of the platoon target position, the data is input into the trajectory generation algorithm to generate the optimal driving trajectory of the free vehicle, specifically including:

[0073] Based on the starting coordinates of the free vehicle and the ending coordinates of the formation target position, vehicle dynamics constraint data, and Clamped B-Spline curve parameters, a number of initial Clamped B-Spline candidate curves are generated by adjusting the number and coordinates of control points through a preset trajectory generation algorithm. The vehicle dynamics constraints include at least the following dynamic parameters: maximum turning radius, maximum acceleration, deceleration, Jerk threshold, etc.

[0074] Clamped B-Spline curve parameters include curve type and range of control point quantity;

[0075] Obtain the solution vector corresponding to the candidate solution of each initial candidate curve; each solution vector includes the coordinates of a corresponding number of control points and the number of control points; for example, each solution vector is equal to the coordinates of control point 1, the coordinates of control point 2, ..., the coordinates of control point N, and the number of control points N;

[0076] Based on the solution vector of each candidate solution and vehicle dynamics constraint data, a pre-defined weighted method is used to calculate the fitness function value F corresponding to the candidate solution of each initial candidate curve.

[0077] All candidate solutions and their corresponding fitness function values ​​are input into the BWO algorithm. Through iterative search, the solution vector with the minimum fitness function value is obtained and taken as the optimal solution vector. The optimal solution vector includes the coordinates of the optimal control point and the number of optimal control points.

[0078] Based on the optimal number of control points, the node vector of the Clamped B-Spline curve is generated using a parameterization method for the Clamped B-Spline curve.

[0079] Based on the node vectors and the coordinates of the optimal control points, the optimal Clamped B-Spline curve is generated to obtain the optimal driving trajectory.

[0080] It should be noted that the candidate solution includes: the set of control point coordinates and the number of control points, which is mathematically represented as a solution vector of (coordinates of control point 1, coordinates of control point 2, ..., coordinates of control point N, number of control points N).

[0081] Furthermore, a pre-defined weighted method is employed to calculate the fitness function value corresponding to the candidate solution of each initial candidate curve, specifically including:

[0082] The fitness function value is obtained by a preset weighting method based on the trajectory smoothness index, Jerk comfort index, trajectory feasibility index, and control point efficiency index. The trajectory smoothness index is represented by the mean square value of the curve curvature, the Jerk comfort index is represented by the sum of squares of acceleration, and the trajectory feasibility index checks whether the trajectory meets the vehicle dynamics constraints. The weight of each index can be set according to the requirements, such as giving a higher weight to smoothness.

[0083] As can be understood, the step of optimizing the number of control points in the Beluga optimization algorithm involves several steps. First, a Clamped B-Spline curve is generated, with the number of control points arbitrarily selected between 4 and 15. Next, the fitness function is calculated, which is a weighted average of the trajectory smoothness index, Jerk comfort index, trajectory feasibility index, and the number of control points. The trajectory smoothness index is represented by the mean square value of the curve curvature, the Jerk comfort index by the sum of squared accelerations, and the trajectory feasibility index checks whether the trajectory meets vehicle dynamics constraints. Then, the Beluga optimization algorithm uses [control point coordinate vector, number of control points] as each solution (for individual Beluga vehicles) and runs the algorithm. A smaller fitness function value indicates a better solution. Finally, based on the optimal control points, a node vector is obtained, and another Clamped B-Spline curve is generated. This curve ensures that the trajectory not only meets the smoothness requirements but also conforms to the actual needs of vehicle driving.

[0084] Furthermore, based on real-time requirements, this application presets the number of iterations; in particular, under the condition of queuing in a stable driving state, the number of iterations is the first threshold (50 times); the advantage is that the algorithm fully searches and obtains the extreme optimal solution, but the disadvantage is that the calculation time is slightly longer and cannot meet the millisecond-level response.

[0085] If a queue is added in an emergency, the iteration count is based on the second threshold (30 times). While ensuring a fast response, real-time performance is achieved by sacrificing accuracy, and the dynamic constraints and minimum smoothness requirements are met.

[0086] Furthermore, the parameterization method for the Clamped B-Spline curve selects a cubic Clamped B-Spline curve with a curve order P of 3, and achieves endpoint interpolation characteristics by repeating the first and last nodes.

[0087] In one specific embodiment, based on the optimal number of control points, the node vector of the Clamped B-Spline curve is generated using a parameterization method for the Clamped B-Spline curve, specifically including:

[0088] Based on the optimal number of control points N output by the BWO algorithm, and with the endpoint constraints and smoothness requirements of the formation trajectory as the goal, the node vector is generated by a parameterization method of the Clamped B-Spline curve.

[0089] The node vector is designed with endpoint constraints at the center of the rear axle of the free vehicle at the starting point of the trajectory and the target position behind the lead vehicle at the ending point. It is configured using a quasi-uniform distribution of cubic Clamped B-Spline curves. The first and last nodes are repeated according to the curve order + 1 times, and the middle nodes are uniformly interpolated according to the curve domain. The length L of the node vector matches the mapping relationship between the number of optimal control points N and the curve order p, so that the segmented control accuracy of the control points on the trajectory meets the vehicle dynamics constraints. The length L of the node vector is equal to the number of optimal control points N plus the curve order + 1.

[0090] Specifically, this solution optimizes Clamped B-Spline curves based on the White Whale optimization algorithm to achieve local trajectory planning for commercial vehicles. This method uses the position of the following vehicle as the starting point and the position of the lead vehicle as the ending point, and performs interpolation calculations using the Clamped B-Spline curve to obtain a smooth and continuous trajectory. Compared to Bézier curves, this trajectory has local controllability; adjusting a single control point only affects a local curve segment, while adjusting a single control point on a Bézier curve globally affects the curve shape. It also possesses high-order continuity: the Clamped B-Spline curve naturally satisfies C² continuity (acceleration continuity), making it suitable for vehicle dynamics constraints. Furthermore, it offers flexibility: through flexible configuration of node vectors and control points, complex paths (such as multi-segment spliced ​​trajectories) can be generated to adapt to complex road surfaces. Specifically, this method uses a cubic Clamped B-Spline curve (p=3), achieving endpoint interpolation characteristics by repeating the first and last nodes. The number of control points is determined based on the Beluga Whale Optimization (BWO) algorithm. The node vectors are quasi-uniformly distributed, and the length of each node vector equals the number of control points plus the curve order plus 1. Furthermore, the node vectors are in the range [0,0,0,0,t4,...,t]. n-3 [,1,1,1,1], where n represents the length of the node vector. Internal node t4 to t n-3Typically, the curves are evenly distributed or adjusted according to their shape to achieve a uniformly clamped distribution. The forced curve passes through the start and end control points so that it can pass through the starting and ending points. Furthermore, because the curve has the advantage that the line connecting the end point and the adjacent node is tangent to the curve, it can satisfy the constraints of the road structure characteristics, that is, the tangent direction of the driving trajectory is the same as the road trend.

[0091] On the other hand, this application provides a local trajectory planning system for Clamped B-Spline curves based on BWO, such as Figure 3 As shown, the system includes:

[0092] The acquisition module is configured to acquire raw coordinate data in the UTM coordinate system; wherein, the raw coordinate data includes: free vehicle coordinates, navigator vehicle coordinates, and heading angle data;

[0093] The generation module is configured to generate the optimal driving trajectory of a free vehicle based on pre-configured driving rules and original coordinate data, using a trajectory generation algorithm, when the free vehicle meets the conditions for joining the formation.

[0094] It is worth noting that although this system only discloses the acquisition module and the generation module, it does not mean that this system is limited to the above-mentioned basic functional modules. On the contrary, what this invention intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can add one or more functional modules in combination with the prior art to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. It cannot be assumed that the scope of protection of the claims of this invention is limited to the above-disclosed basic functional modules just because this embodiment only discloses a few basic functional modules.

[0095] On the other hand, this application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0096] The memory stores a computer program that, when executed by a processor, causes the processor to perform the steps of the method.

[0097] On the other hand, this application provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the method.

[0098] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0099] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetically switched memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms. The databases involved in the embodiments provided in this application can include at least one of relational and non-relational databases. Non-relational databases can include blockchain-based distributed databases, etc., and are not limited thereto. The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited thereto.

[0100] A simulation platform, comprising:

[0101] An electronic device for implementing the steps of the method;

[0102] A processor that runs a program, which, when running, executes the steps of the method claimed in the electronic device from data output by the program.

[0103] A storage medium for storing a program that, when run, executes the steps of the method on data output from an electronic device.

[0104] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0105] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A BWO-based clamped B-spline curve local trajectory planning method, characterized in that, The method comprises the following steps: S1: obtaining original coordinate data of a UTM coordinate system; wherein the original coordinate data comprises free car coordinates, lead car coordinates and heading angle data; S2: when the free car meets the joining formation condition, generating an optimal driving trajectory of the free car based on pre-configured driving rules and the original coordinate data through a trajectory generation algorithm.

2. The method of claim 1, wherein, Step S1: obtaining original coordinate data of a UTM coordinate system, specifically comprising: S11: translating the origin of the UTM coordinate system to the center coordinate of the rear axle of the free car to obtain a translated coordinate system with the center of the rear axle of the free car as the origin; S12: obtaining the coordinate of the center of the rear axle of the lead car in the translated coordinate system based on the original coordinate data of the UTM; S13: taking the origin of the translated coordinate system as the center of rotation, rotating the translated coordinate system clockwise according to the heading angle of the free car to obtain a local coordinate system with the driving direction of the free car as the positive direction of the Y axis and to obtain the target coordinate of the center of the rear axle of the lead car in the local coordinate system; wherein the navigation angle is the angle from the north direction clockwise to the driving direction of the free car in the UTM.

3. The method of claim 2, wherein, Step S2: when the free car meets the joining formation condition, generating an optimal driving trajectory of the free car based on pre-configured driving rules and the original coordinate data through a trajectory generation algorithm, specifically comprising: In the local coordinate system, when the free car is behind the lead car, the free car meets the joining formation condition; The driving rules include start point constraints and end point constraints; The start point constraint is that the tangent direction of the start point of the driving trajectory is equal to the heading angle of the free car; the end point constraint is that the tangent direction of the end point of the driving trajectory is equal to the tangent direction angle of the road at the end point position; Wherein, the start point of the driving trajectory is the current center of the rear axle of the free car; the end point of the driving trajectory is the center of the rear axle corresponding to the target position of the formation behind the lead car; When the joining eligibility judgment result is passed, the start point coordinate of the free car and the end point coordinate of the formation target position are input into the trajectory generation algorithm based on the driving rules to generate the optimal driving trajectory of the free car.

4. The method of claim 3, wherein, When the joining eligibility judgment result is passed, the start point coordinate of the free car and the end point coordinate of the formation target position are input into the trajectory generation algorithm based on the driving rules to generate the optimal driving trajectory of the free car, specifically comprising: Based on the start point coordinate of the free car and the end point coordinate data of the formation target position, vehicle dynamics constraint data and Clamped B-Spline curve parameters, the number and coordinates of control points are adjusted through a preset trajectory generation algorithm to generate a plurality of initial Clamped B-Spline candidate curves; Obtain the solution vector corresponding to each candidate solution of each initial candidate curve; each solution vector comprises a corresponding number of control point coordinates and control point numbers; Based on the solution vector of each candidate solution and the vehicle dynamics constraint data, a preset weighting method is used to calculate the fitness function value F corresponding to each candidate solution of each initial candidate curve; All candidate solutions and their corresponding fitness function values are input into the BWO algorithm, and the solution vector with the minimum fitness function value is obtained through algorithm iterative search and taken as the optimal solution vector; wherein the optimal solution vector comprises optimal control point coordinates and optimal control point numbers; The parameterization method of the Clamped B-Spline curve selects a cubic Clamped B-Spline curve with a curve order P of 3, and realizes an end point interpolation characteristic by repeating the first and last nodes. The parameterization method of the Clamped B-Spline curve selects a cubic Clamped B-Spline curve with a curve order P of 3, and realizes an end point interpolation characteristic by repeating the first and last nodes.

5. The method of claim 4, wherein, The parameterization method of the Clamped B-Spline curve selects a cubic Clamped B-Spline curve with a curve order P of 3, and realizes an end point interpolation characteristic by repeating the first and last nodes.

6. The method of claim 5, wherein, The parameterization method of the Clamped B-Spline curve selects a cubic Clamped B-Spline curve with a curve order P of 3, and realizes an end point interpolation characteristic by repeating the first and last nodes. The parameterization method of the Clamped B-Spline curve selects a cubic Clamped B-Spline curve with a curve order P of 3, and realizes an end point interpolation characteristic by repeating the first and last nodes. The parameterization method of the Clamped B-Spline curve selects a cubic Clamped B-Spline curve with a curve order P of 3, and realizes an end point interpolation characteristic by repeating the first and last nodes.

7. A BWO-based clamped B-spline curve local trajectory planning system, characterized in that, The system comprises: The acquisition module is configured to acquire original coordinate data in the UTM coordinate system; wherein the original coordinate data comprises: free vehicle coordinates, leader vehicle coordinates and heading angle data; The generation module is configured to, when the free vehicle meets the joining condition of the formation, generate an optimal driving trajectory of the free vehicle based on a pre-configured driving rule and the original coordinate data through a trajectory generation algorithm.

8. An electronic device comprising: The processor, the communication interface, the memory and the communication bus are in communication with each other; and the memory stores a computer program, which, when executed by the processor, causes the processor to execute the steps of the method in any one of claims 1-6. 9.A computer readable storage medium storing a computer program executable by an electronic device, the computer program comprising instructions for causing the electronic device to perform the method of any one of claims 1 to 8. When the computer program is running on the electronic device, the electronic device executes the steps of the method in any one of claims 1-6.

10. An emulation platform, characterized by The electronic device is configured to execute the steps of the method in any one of claims 1-6. The processor is configured to execute the steps of the method in any one of claims 1-6 when a program is running. The storage medium is configured to store a program, which, when running, executes the steps of the method in any one of claims 1-6 for data output from the electronic device. ​

Images