Vehicle driving track determination method and device, processor and electronic equipment

Abstract

The invention discloses a vehicle driving track determination method and device, a processor and electronic equipment. The method comprises the steps that state information of a first vehicle and attribute information of a second vehicle are obtained, the second vehicle is pulled by the first vehicle, the state information is used for representing the position where the first vehicle is located and / or obstacles on a road where the first vehicle is located, and the attribute information is used for representing the outline of the second vehicle and the position where the second vehicle is located; based on the state information and the attribute information, determining an initial trajectory for enabling the first vehicle and the second vehicle to execute a docking task; in response to the fact that the feasibility information of the initial track meets a feasibility information threshold value, performing segmentation processing on the initial track to obtain a segmentation result, and processing the segmentation result to obtain a target track; and according to the target trajectory, controlling the first vehicle and the second vehicle to run so as to execute a docking task. The technical problem that the docking driving track of the vehicle docking task cannot be effectively determined is solved.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and more specifically, to a method, apparatus, processor, and electronic device for determining the driving trajectory of a vehicle. Background Technology

[0002] Currently, vehicles (such as unmanned tractors) are increasingly widely used in logistics, warehousing, airports, ports and other scenarios. In particular, the automatic docking of unmanned tractors and trailers has become the key to improving operational efficiency in the cargo transfer process.

[0003] However, in related technologies, when an unmanned tractor unit (ARTU) docks with a trailer, it relies on a single sensor for environmental perception. During docking, the ARTU needs to consider its own motion control, the trailer's attitude, and the relative motion between the two. Existing planning algorithms are inefficient in handling this complex motion coupling and struggle to find a trajectory that satisfies both safe distance requirements and ensures precise docking. When encountering an unsolvable trajectory, existing ARTUs lack effective retry mechanisms and strategy adjustments. Once trajectory solving fails, the vehicle remains stationary for an extended period, potentially even causing the entire logistics system to shut down.

[0004] Furthermore, in related technologies, the docking point is usually fixed and cannot be adaptively adjusted according to the actual position, attitude, and changes in the external environment of the trailer. This increases the error and failure rate during the docking process between the unmanned tractor and the trailer. Therefore, the technical problem of not being able to effectively determine the docking trajectory for vehicle docking tasks still exists.

[0005] There is currently no effective solution to the aforementioned technical problems. Summary of the Invention

[0006] This invention provides a method, apparatus, processor, and electronic device for determining the driving trajectory of a vehicle, in order to at least solve the technical problem of the inability to effectively determine the driving trajectory of a vehicle docking task.

[0007] According to one aspect of the present invention, a method for determining the driving trajectory of a vehicle is provided. The method may include: acquiring state information of a first vehicle and attribute information of a second vehicle, wherein the second vehicle is pulled by the first vehicle, the state information is used to indicate the position of the first vehicle and / or obstacles on the road where the first vehicle is located, and the attribute information is used to indicate the outline of the second vehicle and the position of the second vehicle; determining an initial trajectory for the first vehicle and the second vehicle to perform a docking task based on the state information and the attribute information; segmenting the initial trajectory in response to the feasibility information of the initial trajectory satisfying a feasibility information threshold to obtain a segmentation result; and processing the segmentation result to obtain a target trajectory, wherein the feasibility information is used to indicate the degree of feasibility of solving the initial trajectory; and controlling the first vehicle and the second vehicle to drive according to the target trajectory to perform the docking task.

[0008] Optionally, the segmentation result includes a first segmentation result and a second segmentation result. In response to the feasibility information of the initial trajectory satisfying a feasibility information threshold, the initial trajectory is segmented to obtain the segmentation result, including: in response to the feasibility information satisfying a feasibility information threshold, the initial trajectory is segmented to obtain the current position of the first vehicle and the extended position of the docking heading direction between the first and second vehicles; the trajectory between the current position and the extended position in the initial trajectory is determined as the first segmentation result; and in response to the feasibility information satisfying a feasibility information threshold, the initial trajectory is segmented to obtain the docking position of the second vehicle; the trajectory between the docking position and the extended position is determined as the second segmentation result, wherein the docking heading direction is used to represent the heading angle corresponding to the line connecting the docking position and the current position.

[0009] Optionally, the segmented results are processed to obtain the target trajectory, including: for the first segmented result, smoothing and velocity planning are performed starting from the initial trajectory to obtain the first target trajectory; for the second segmented result, uniform deceleration is performed to obtain the second target trajectory; and the first and second target trajectories are spliced ​​together to obtain the target trajectory.

[0010] Optionally, the first target trajectory and the second target trajectory are spliced ​​together to obtain a target trajectory, including: splicing the first target trajectory and the second target trajectory to obtain a third target trajectory; detecting the third target trajectory to obtain a detection result; and determining the third target trajectory as the target trajectory in response to the detection result that the first vehicle did not collide with the obstacle during the execution of the third target trajectory.

[0011] Optionally, the method further includes: in response to the detection result that the first vehicle has collided with the obstacle, re-determining the target trajectory, or terminating the docking mission.

[0012] Optionally, the method further includes: in response to the feasibility information not meeting the feasibility information threshold, controlling the first vehicle to travel to the target area; within the target area, analyzing the initial trajectory according to a target number of times to obtain the analysis result, wherein the target number of times is used to represent the upper limit of the number of times the initial trajectory is analyzed; and in response to the analysis result indicating that the feasibility information does not meet the feasibility information threshold, terminating the docking task.

[0013] According to another aspect of the present invention, a vehicle trajectory determination device is also provided. The device may include: an acquisition unit, configured to acquire state information of a first vehicle and attribute information of a second vehicle, wherein the second vehicle is pulled by the first vehicle, the state information is used to indicate the position of the first vehicle and / or obstacles on the road where the first vehicle is located, and the attribute information is used to indicate the outline of the second vehicle and the position of the second vehicle; a determination unit, configured to determine an initial trajectory for enabling the first vehicle and the second vehicle to perform a docking task based on the state information and attribute information; a segmentation unit, configured to segment the initial trajectory in response to the feasibility information of the initial trajectory satisfying a feasibility information threshold, to obtain a segmentation result, and to process the segmentation result to obtain a target trajectory, wherein the feasibility information is used to indicate the feasibility of solving the initial trajectory; and an execution unit, configured to control the first vehicle and the second vehicle to drive according to the target trajectory to perform the docking task.

[0014] According to another aspect of the present invention, a processor is also provided. The processor is used to run a program, wherein the program, when run by the processor, performs the methods described in the embodiments of the present invention.

[0015] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention during runtime.

[0016] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0017] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0018] According to another aspect of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0019] According to another aspect of the present invention, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of the present invention.

[0020] According to another aspect of the present invention, a vehicle is also provided. The vehicle includes a memory and a processor. The memory stores an executable program; the processor runs the program, which, when executed, implements the methods described in the embodiments of the present invention.

[0021] In this embodiment of the invention, if it is necessary to control vehicles to perform a docking task, the state information of the first vehicle and the attribute information of the second vehicle can be obtained. The second vehicle is pulled by the first vehicle. The state information indicates the position of the first vehicle and / or obstacles on the road where the first vehicle is located. The attribute information indicates the outline of the second vehicle and its position. Based on the state information and attribute information, an initial trajectory for the first and second vehicles to perform the docking task can be determined. In response to the feasibility information of the initial trajectory satisfying a feasibility information threshold, the initial trajectory can be segmented to obtain a segmentation result. The segmentation result can then be processed to obtain a target trajectory. The feasibility information indicates the degree of feasibility of solving the initial trajectory. The first and second vehicles can be controlled to travel according to the target trajectory to perform the docking task. In other words, by integrating the state information of the first vehicle and the attribute information of the second vehicle, the embodiments of the present invention can more comprehensively assess environmental conditions and determine the initial trajectory. By dividing the initial trajectory in the docking process into different stages and processing them, it can ensure both the continuity and safety of the overall driving path and the precise control of the docking stage. Thus, the target trajectory (i.e., the docking driving trajectory) can be effectively determined when performing the docking task, solving the technical problem of not being able to effectively determine the docking driving trajectory of the vehicle docking task and achieving the technical effect of effectively determining the docking driving trajectory of the vehicle docking task. Attached Figure Description

[0022] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0023] Figure 1 This is a flowchart of a method for determining the driving trajectory of a vehicle according to an embodiment of the present invention;

[0024] Figure 2 This is a flowchart of a method for solving the driving trajectory of a tractor and trailer docking according to an embodiment of the present invention;

[0025] Figure 3This is a schematic diagram of the docking trajectory and relative position relationship between the tractor and trailer according to an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of a vehicle trajectory determination device according to an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, functional component, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, functional components, or devices.

[0029] According to an embodiment of the present invention, an embodiment of a method for determining the driving trajectory of a vehicle is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] Figure 1 This is a flowchart of a method for determining the driving trajectory of a vehicle according to an embodiment of the present invention, as shown below. Figure 1 As shown, the method may include the following steps.

[0031] Step S102: Obtain the status information of the first vehicle and the attribute information of the second vehicle.

[0032] In the technical solution provided in step S102 of the present invention, the second vehicle is pulled by the first vehicle. The first vehicle can be an unmanned tractor, and the second vehicle can be a trailer. The status information can be used to indicate the position of the first vehicle and / or obstacles on the road where the first vehicle is located, and the attribute information can be used to indicate the outline of the second vehicle and the position of the second vehicle.

[0033] In this embodiment, before the first vehicle (e.g., an unmanned tractor) and the second vehicle (e.g., a trailer) perform the docking task, it is necessary to acquire and process information about the vehicles' own status and the surrounding environment, that is, the status information of the first vehicle and the attribute information of the second vehicle. This attribute information is the basis for subsequent trajectory planning and safe docking.

[0034] Optionally, an unmanned tractor, also known as a driverless tractor or an automated guided tow tractor (AGTT), is a vehicle capable of operating autonomously without human intervention, used for material handling, cargo transportation, and other similar scenarios. AGTTs utilize various sensors to perceive their surroundings and, using navigation and control systems, travel along predetermined routes or dynamically planned paths to complete the transfer of goods from one location to another.

[0035] Alternatively, a trailer is a transport vehicle that is not powered on its own and needs to be towed by a tractor (such as an unmanned tractor, truck, van, or locomotive). Trailers can be designed in different forms to meet specific transport needs, such as flatbed trailers, box trailers, tank trailers, and refrigerated trailers, which can be used in road, rail, and sea transport, significantly increasing freight volume and improving transport efficiency.

[0036] Optionally, the status information can be the positioning information of the first vehicle itself and the obstacles in the surrounding environment. Status information can be acquired through onboard sensors, such as LiDAR, cameras, Global Positioning System (GPS), and Inertial Measurement Unit (IMU). The perception module can detect surrounding obstacles in real time, including static obstacles (such as shelves and walls) and dynamic obstacles (such as other vehicles and people), and output the position, outline, and motion information (including speed, acceleration, angular velocity, etc.) of the obstacles.

[0037] Optionally, the attribute information may include, but is not limited to, the outline dimensions, position, and heading information of the second vehicle. Attribute information can be detected using visual and laser recognition technology. For example, a marker (special reflector) can be placed on the trailer, and images and point cloud information can be acquired by the unmanned tractor's rear-facing camera and LiDAR sensor. After processing and recognition by the perception module, the geometric center position coordinates and heading angle information of the trailer can be calculated.

[0038] In this embodiment of the invention, based on state and attribute information, a suitable path can be calculated from the current position of the unmanned tractor to the docking position of the trailer, while avoiding collisions with obstacles. The outline and position information of the trailer help the unmanned tractor precisely control its docking posture and speed, ensuring the safety and smoothness of the docking operation. The analysis of comprehensive information can help the unmanned tractor system make real-time decisions, such as whether it is necessary to adjust the driving route or docking strategy to adapt to constantly changing environmental conditions.

[0039] Step S104: Based on the status information and attribute information, determine the initial trajectory for the first vehicle and the second vehicle to perform the docking task.

[0040] In the technical solution provided by step S104 of the present invention, after obtaining the state information of the first vehicle and the attribute information of the second vehicle, the initial trajectory for the first vehicle and the second vehicle to perform the docking task can be determined based on the state information (e.g., the real-time position, speed, acceleration of the unmanned tractor and obstacles in the surrounding environment) and attribute information (e.g., the specific size, outline, position and heading angle information of the trailer).

[0041] In this embodiment, the prediction module can predict the trajectory of obstacles over a future period based on current and historical time-series obstacles, using methods such as Kalman filtering or prediction models, to obtain an initial trajectory. This initial trajectory can be used for collision detection in subsequent trajectory planning, improving the safety of the trailer docking trajectory. Furthermore, based on the geometric center coordinates and heading angle information of the trailer, the trailer docking point data can be calculated, thereby determining the docking position between the unmanned tractor and the trailer.

[0042] For example, using hybrid A The algorithm determines the initial trajectory, which is A The algorithm can combine static map information and dynamic obstacle prediction to plan a path, i.e., an initial trajectory, for the unmanned tractor unit from its current location to the trailer docking point. The algorithm can treat obstacles as insurmountable nodes and find the path with the lowest cost by calculating a cost function. The cost function can include considerations of multiple dimensions such as path length, time required, and travel cost.

[0043] In this embodiment of the invention, based on state information and attribute information, an initial trajectory for enabling the first vehicle and the second vehicle to perform a docking task can be determined. The initial trajectory is a rough path from the current position of the unmanned tractor to the docking position of the trailer, taking into account the basic spatial layout and obstacle conditions.

[0044] Step S106: In response to the feasibility information of the initial trajectory satisfying the feasibility information threshold, the initial trajectory is segmented to obtain the segmentation result, and the segmentation result is processed to obtain the target trajectory.

[0045] In the technical solution provided in step S106 of the present invention, the feasibility information can be used to indicate the degree of feasibility of solving the initial trajectory. The target trajectory can be the docking driving trajectory.

[0046] In this embodiment, after determining the initial trajectory for the first vehicle and the second vehicle to perform the docking task based on the state information and attribute information, the initial trajectory can be segmented to obtain the segmentation result if the feasibility information of the initial trajectory meets the feasibility information threshold, and the segmentation result can be processed to obtain the target trajectory.

[0047] Optionally, feasibility information can be used to represent an evaluation metric for whether the initial trajectory can safely and without collision execute the docking mission based on current environmental conditions and the states of the first and second vehicles. This evaluation metric can integrate multiple factors such as obstacle prediction, vehicle kinematic constraints, and environmental constraints.

[0048] Optionally, if the feasibility information of the initial trajectory meets the feasibility information threshold, for example, in the case of a hybrid A... The algorithm can consider dynamic and static obstacles during the process of solving the coarse trajectory, and obtain a collision-free initial solution for the trajectory optimization algorithm to process. This initial trajectory can then be segmented to obtain the first segment and the last segment. Subsequently, the segmented results can be processed separately to generate a safer and more efficient driving path, that is, to obtain the target trajectory.

[0049] In this embodiment of the invention, the above steps can generate a highly safe, efficient and accurate docking trajectory, providing support for the automated docking of unmanned tractor vehicles and trailers, thereby helping to improve the level of automated operations in the entire logistics, warehousing and other scenarios.

[0050] Step S108: Control the first and second vehicles to drive according to the target trajectory in order to perform the docking task.

[0051] In the technical solution provided by step S108 of the present invention, after the feasibility information of the initial trajectory meets the feasibility information threshold, the initial trajectory is segmented to obtain the segmentation result, and the segmentation result is processed to obtain the target trajectory. Then, the first vehicle and the second vehicle can be controlled to drive according to the target trajectory to perform the docking task.

[0052] In this embodiment, the autonomous driving system of the unmanned tractor can adjust the output of the drive motor, steering mechanism, and braking system in real time based on each point in the target trajectory and its corresponding driving parameters (such as speed, acceleration, steering angle, etc.) to ensure that the first vehicle can travel along the planned path. Especially in the final stage of the trajectory, the deceleration rate and heading angle of the first vehicle can be strictly controlled to achieve precise and smooth docking.

[0053] Optionally, throughout the entire journey, the unmanned tractor can continuously monitor its own status and environmental changes, including its relative position to obstacles, changes in the trailer's position, and unexpected situations along the path. This real-time monitoring helps to adjust control strategies promptly to address potential emergencies and ensure the smooth execution of the docking mission. While the trailer itself does not move actively, the unmanned tractor needs to consider the trailer's inertia and position during docking to avoid unnecessary friction or collisions. In some cases, the unmanned tractor can also guide the trailer into the correct position and orientation through fine-tuning, ensuring consistency and reliability of the docking.

[0054] Optionally, if unexpected obstacles or environmental changes are encountered during the journey, the autonomous driving system of the unmanned tractor can react quickly and adjust the initial trajectory in real time to bypass obstacles or adapt to new environmental conditions. During the execution of the docking task, if unexpected situations arise, such as timeouts in target trajectory calculation or the inability to eliminate potential collision risks with obstacles, timely responses can be made, such as terminating the current docking task or reporting the fault status to the cloud control platform, to avoid greater losses.

[0055] In this embodiment of the invention, precise vehicle control, real-time monitoring, real-time adjustment and feedback mechanisms can ensure the efficient and safe execution of docking tasks.

[0056] In steps S102 to S108 of the present invention, if it is necessary to control the vehicles to perform a docking task, the state information of the first vehicle and the attribute information of the second vehicle can be obtained. The second vehicle is pulled by the first vehicle. The state information indicates the position of the first vehicle and / or obstacles on the road where the first vehicle is located. The attribute information indicates the outline of the second vehicle and the position of the second vehicle. Based on the state information and attribute information, an initial trajectory for the first and second vehicles to perform the docking task can be determined. In response to the feasibility information of the initial trajectory satisfying a feasibility information threshold, the initial trajectory can be segmented to obtain a segmentation result. The segmentation result can then be processed to obtain a target trajectory. The feasibility information indicates the degree of feasibility of solving the initial trajectory. The first and second vehicles can be controlled to drive according to the target trajectory to perform the docking task. In other words, by integrating the state information of the first vehicle and the attribute information of the second vehicle, the embodiments of the present invention can more comprehensively assess environmental conditions and determine the initial trajectory. By dividing the initial trajectory in the docking process into different stages and processing them, it can ensure both the continuity and safety of the overall driving path and the precise control of the docking stage. Thus, the target trajectory (i.e., the docking driving trajectory) can be effectively determined when performing the docking task, solving the technical problem of not being able to effectively determine the docking driving trajectory of the vehicle docking task and achieving the technical effect of effectively determining the docking driving trajectory of the vehicle docking task.

[0057] The method described in this embodiment will be further described below.

[0058] As an optional embodiment, the segmentation result includes a first segmentation result and a second segmentation result. Step S106 involves segmenting the initial trajectory in response to the feasibility information satisfying the feasibility information threshold, to obtain the segmentation result, including: segmenting the initial trajectory in response to the feasibility information satisfying the feasibility information threshold to obtain the current position of the first vehicle and the extended position of the docking heading direction between the first vehicle and the second vehicle; determining the trajectory between the current position and the extended position in the initial trajectory as the first segmentation result; and segmenting the initial trajectory in response to the feasibility information satisfying the feasibility information threshold to obtain the docking position of the second vehicle; determining the trajectory between the docking position and the extended position as the second segmentation result, wherein the docking heading direction is used to represent the heading angle corresponding to the line connecting the docking position and the current position.

[0059] In this embodiment, the segmentation result may include a first segmentation result and a second segmentation result. The first segmentation result may be the first segment of the trajectory. The second segmentation result may be the last segment of the trajectory.

[0060] Optionally, in response to the feasibility information satisfying the feasibility information threshold, the initial trajectory can be segmented to obtain the current position of the first vehicle (e.g., Figure 3 Point A in the diagram), and the extension of the docking direction between the first and second vehicles (e.g., point A in the diagram), and the position of the docking direction between the first and second vehicles (e.g., point A in the diagram). Figure 3 Point C in the initial trajectory); can be the current position in the initial trajectory (e.g., Figure 3 From point A in the diagram to the extended position (e.g., Figure 3 The trajectory between point C in the diagram is determined as the first segmentation result. Furthermore, in response to the feasibility information satisfying the feasibility information threshold, the initial trajectory is segmented to obtain the docking position of the second vehicle, i.e., the trailer docking position (e.g., ...). Figure 3 Point B in the diagram); the docking location (e.g., Figure 3 From point B in the middle to the extended position (e.g., point B in the middle) to the extended position (e.g. Figure 3 The trajectory between point C in the initial trajectory is determined as the second segment result. That is, the endpoint of the initial trajectory solution is the extension point from the trailer docking position towards the unmanned tractor-trailer docking direction; this point is set as... Figure 3 Point C in the equation. The initial trajectory solution starts from the vehicle's current position coordinates, i.e. Figure 3 Point A in the equation. The solution terminates at the trailer docking point, i.e. Figure 3 Point B in the diagram.

[0061] Optionally, the first segment result (the initial trajectory) involves the long-distance travel of the unmanned tractor, requiring consideration of obstacle avoidance, driving efficiency, and changes in the dynamic environment within a complex setting. The final trajectory is... Figure 3 From point C to the trailer docking point B ( Figure 3 A path between (in the middle), which is usually short. Figure 3 Point C in the trajectory planning is the midpoint and the last point of free movement that the unmanned tractor must reach during the docking mission. From... Figure 3 Starting from point C, the unmanned tractor will enter the final docking preparation stage under height control. Figure 3 Point B in the diagram is the docking point for the trailer, marking the end of the entire docking process. The unmanned tractor unit must ultimately park precisely at this point to complete the connection with the trailer.

[0062] It should be noted that points A, B, and C described in this invention are all... Figure 3 Points A, B, and C in the diagram will not be elaborated upon further.

[0063] Optionally, the docking heading direction is the heading angle corresponding to the line connecting the trailer docking position and the current position of the unmanned tractor. Since the docking heading direction directly affects the attitude control of the unmanned tractor during the docking process, ensuring accurate trailer connection without deviation or collision, determining the docking heading direction is crucial for optimizing the initial trajectory solution.

[0064] In this embodiment of the application, the segmented processing described above not only improves the accuracy and safety of docking between the unmanned tractor and the trailer, but also demonstrates the flexibility and robustness of automated docking operations in complex environments. This has a significant promoting effect on improving the efficiency of unmanned operations in logistics, warehousing and other scenarios.

[0065] As an optional embodiment, step S106, processing the segmented results to obtain the target trajectory, includes: performing smoothing and velocity planning processing on the first segmented result, starting from the initial trajectory, to obtain the first target trajectory; performing uniform deceleration operation processing on the second segmented result to obtain the second target trajectory; and splicing the first target trajectory and the second target trajectory to obtain the target trajectory.

[0066] In this embodiment, by refining the first and second segmentation results of the segmentation, the final target trajectory is generated, which can guide the safe docking of the first and second vehicles.

[0067] Optionally, the first segment result (i.e., the initial trajectory from point A to point C) can be smoothed, starting from the initial trajectory, to remove discontinuities or sharp turns, making the unmanned tractor's path smoother, reducing vehicle bumps, and improving passenger comfort and cargo safety during operation. Based on the smoothing process, a suitable speed curve can be planned for the initial trajectory. This means maintaining a low speed near the starting point A to ensure accurate environmental perception, gradually accelerating as approaching the midpoint C to improve overall driving efficiency, and appropriately decelerating before point C to prepare for precise control of the final trajectory segment.

[0068] Optionally, uniform deceleration control can be applied to the second segment result (i.e., the final trajectory from point C to point B) to ensure that the unmanned tractor can smoothly decelerate until it stops when docking with the trailer. Uniform deceleration not only prevents cargo displacement or structural stress caused by sudden deceleration, but also ensures that the vehicles make contact with minimal momentum, reducing impact and improving the smoothness and safety of docking.

[0069] Optionally, the first target trajectory, which has undergone smoothing and speed planning, and the second target trajectory, which has undergone uniform deceleration, are spliced ​​together to form a complete target trajectory. This splicing process must ensure the continuity and smooth transition of the two trajectories at point C, avoiding abrupt changes at the splicing point that could affect the continuity and safety of the first vehicle's movement.

[0070] Optionally, if the feasibility information of the initial trajectory meets the feasibility information threshold, that is, if the trajectory feasibility analysis passes, then the initial trajectory solution is performed. To ensure the control of the final docking attitude of the unmanned tractor, the final segment of the trajectory solution uses a straight line segment with a length ranging from 0.5m to 1m to improve the accuracy of the control between the unmanned tractor and the trailer. Therefore, the endpoint of the trajectory solution is the extension point from the trailer docking position to the docking direction of the unmanned tractor and trailer. This point can be set as point C, and the extension length can be 0.5 to 1m, which can be adjusted according to the actual working conditions. The trajectory from point C to point B can be set as the final segment, using a uniform deceleration (acceleration set to a fixed value) speed solution method to ensure the smoothness of the docking process between the unmanned tractor and the trailer.

[0071] Optionally, the trajectory from point A to point C can be defined as the initial path, which can be achieved using a search-based path planning method (e.g., a hybrid path planning approach). The initial trajectory is generated using algorithms such as quadratic programming. Starting from the initial trajectory, optimization algorithms (e.g., quadratic programming) can be used to smooth and speed-plan the initial trajectory, generating a precise docking trajectory. After the trajectories at both ends are solved, they can be spliced ​​together to form a complete trailer docking trajectory, i.e., the target trajectory.

[0072] In this embodiment of the application, by processing the segmented results, not only are the initial and final trajectories of the unmanned tractor and trailer docking optimized, but also the safety, efficiency and smoothness of the docking operation are greatly improved through smoothing, speed planning and uniform deceleration control.

[0073] As an optional embodiment, the first target trajectory and the second target trajectory are spliced ​​together to obtain a target trajectory, including: splicing the first target trajectory and the second target trajectory to obtain a third target trajectory; detecting the third target trajectory to obtain a detection result; and determining the third target trajectory as the target trajectory in response to the detection result that the first vehicle did not collide with the obstacle during the execution of the third target trajectory.

[0074] In this embodiment, the optimized first target trajectory (the initial trajectory, from point A to point C) is spliced ​​with the second target trajectory (the final trajectory, from point C to point B) to form a continuous third target trajectory. This third target trajectory guides the unmanned tractor vehicle throughout its journey from its current position to the final docking point. Collision detection can be performed on the optimized trajectory; that is, the third target trajectory is detected to determine whether it collides with any obstacles during its execution.

[0075] Alternatively, a continuous-time collision detection method can be employed. Specifically, multiple collision detections are performed on the unmanned tractor-trailer against all obstacles in a time series, ensuring that the unmanned tractor-trailer maintains a safe distance from obstacles at every moment during the execution of the third target trajectory. This detection method can effectively capture potential collision risks in high-speed dynamic environments and is more accurate and comprehensive than static time-point detection.

[0076] Optionally, if the collision detection results show that the unmanned tractor will not collide with obstacles while traveling along the third target trajectory, this indicates that the third target trajectory is feasible in terms of safety. In this case, the third target trajectory can be confirmed as the final target trajectory, and the unmanned tractor can travel according to this target trajectory to safely, efficiently, and accurately complete the docking task with the trailer.

[0077] In this embodiment of the application, the above steps ensure that the trajectory followed by the unmanned tractor and trailer during docking is not only theoretically coherent and optimized, but also avoids collisions with obstacles in actual execution, thereby improving the safety and reliability of automated docking operations.

[0078] As an optional embodiment, the method further includes: in response to the detection result that the first vehicle has collided with an obstacle, re-determining the target trajectory, or terminating the docking task.

[0079] In this embodiment, if performing the docking task based on the current target trajectory (third target trajectory) may lead to a collision between the first vehicle and an obstacle, a trajectory replanning mechanism can be immediately activated to adjust the first target trajectory (previous trajectory) and / or the second target trajectory (final trajectory) to avoid the obstacle. Different path planning algorithms can be used, such as changing the position of the starting point A or the intermediate point C, or finding a new passageway outside the predicted path of the obstacle. Once the new trajectory planning is completed, collision detection can be performed again to verify whether the replanned trajectory still poses a collision risk. Only when the new trajectory passes this detection can it be considered the final target trajectory and used to guide the docking task of the unmanned tractor.

[0080] Optionally, if, after multiple attempts, a collision-free trajectory cannot be planned, or the replanning process exceeds the preset time limit (e.g., 30 seconds), it means the current environmental conditions are too complex to safely execute the docking task. In this case, a conservative approach can be taken: terminate the current docking task and report the reason for the failure and the current environmental status to the cloud control platform or other higher-level management systems. This can help the system conduct more in-depth fault analysis, or dispatch other unmanned tractors or allow manual intervention to address the trailer docking requirements in the current scenario.

[0081] Optionally, when faced with a collision risk, the system can automatically determine which of the above strategies to adopt based on the actual situation and preset rules. For example, if the obstacle is temporary or can be avoided by adjusting vehicle driving parameters, the target trajectory can be redefined. Conversely, if the obstacle is permanent or the dynamic environmental changes exceed the system's processing capacity, the docking mission can be terminated directly to avoid potential equipment damage or operational interruption.

[0082] In the embodiments of this application, the present invention ensures both safety and efficiency in docking tasks through the above-described embodiments. By employing flexible trajectory replanning and a timely docking task termination mechanism, it effectively addresses docking challenges in complex environments, providing a solid technical foundation for the widespread application of unmanned tractor vehicles in logistics, warehousing, and other automation scenarios.

[0083] As an optional embodiment, the method further includes: in response to the feasibility information not meeting the feasibility information threshold, controlling the first vehicle to travel to the target area; within the target area, analyzing the initial trajectory according to a target number of times to obtain analysis results, wherein the target number of times is used to represent the upper limit of the number of times the initial trajectory is analyzed; and in response to the analysis result indicating that the feasibility information does not meet the feasibility information threshold, terminating the docking task.

[0084] In this embodiment, if the preliminary analysis finds that the current position or environmental conditions of the first vehicle cause the unmanned tractor to fail to solve the docking trajectory between the unmanned tractor and the trailer, that is, the feasibility information does not meet the feasibility information threshold and the collision-free rough trajectory cannot be solved, it indicates that the unmanned tractor cannot safely dock with the trailer under the current environmental conditions, and it is necessary to control the unmanned tractor to drive towards the preset suggested area (target area).

[0085] Optionally, the suggested area can be a range of 5m to the left and right of the trailer's centerline and 20m forward. This range can be adjusted according to the size of the unmanned tractor and trailer. When the unmanned tractor is within this suggested area, it can improve the hybrid A The success rate of the algorithm in solving the rough trajectory.

[0086] Optionally, the target number of attempts can be N. After the unmanned tractor reaches the new location, that is, after driving to the target area, it can repeatedly attempt to solve the rough trajectory, up to N times (N can be set according to the actual scenario). If a feasible trajectory cannot be planned after multiple attempts, the docking task is terminated and an anomaly is reported.

[0087] Optionally, collision detection in this stage can employ a bounding box-based continuous collision detection method. At each time step, a simple geometric bounding box is generated for the unmanned tractor and the obstacle, and the overlap between the two is detected. If a collision-free coarse trajectory is obtained, it can be handed over to the trajectory optimization module for trajectory smoothing, and the unmanned vehicle-trailer docking task can be performed.

[0088] Optionally, each of the above attempts can be based on the latest environmental perception data to reassess factors such as obstacle prediction and trailer position changes, and attempt to plan a new initial trajectory. If, in a certain attempt, the analysis results show that the feasibility information of the trajectory meets the feasibility information threshold, then the docking task can continue to be executed according to this trajectory. If, after reaching the maximum number of attempts, all attempts fail to produce a feasible trajectory that meets the feasibility information threshold, it can be determined that the docking task cannot be executed safely and efficiently under the current environment or location, and the docking process will be terminated.

[0089] Optionally, if the docking mission is terminated, the unmanned tractor will cease further actions and return to a safe or starting position to avoid unnecessary risks in infeasible environments. Simultaneously, the unmanned tractor can report its current status, including the reason for termination and the number of attempts, to the cloud control platform or a remote operator via a communication system, facilitating fault diagnosis, scenario analysis, or subsequent scheduling.

[0090] In this embodiment of the invention, if it is necessary to control vehicles to perform a docking task, the state information of the first vehicle and the attribute information of the second vehicle can be obtained. The second vehicle is pulled by the first vehicle. The state information indicates the position of the first vehicle and / or obstacles on the road where the first vehicle is located. The attribute information indicates the outline of the second vehicle and its position. Based on the state information and attribute information, an initial trajectory for the first and second vehicles to perform the docking task can be determined. In response to the feasibility information of the initial trajectory satisfying a feasibility information threshold, the initial trajectory can be segmented to obtain a segmentation result. The segmentation result can then be processed to obtain a target trajectory. The feasibility information indicates the degree of feasibility of solving the initial trajectory. The first and second vehicles can be controlled to travel according to the target trajectory to perform the docking task. In other words, by integrating the state information of the first vehicle and the attribute information of the second vehicle, the embodiments of the present invention can more comprehensively assess environmental conditions and determine the initial trajectory. By dividing the initial trajectory in the docking process into different stages and processing them, it can ensure both the continuity and safety of the overall driving path and the precise control of the docking stage. Thus, the target trajectory (i.e., the docking driving trajectory) can be effectively determined when performing the docking task, solving the technical problem of not being able to effectively determine the docking driving trajectory of the vehicle docking task and achieving the technical effect of effectively determining the docking driving trajectory of the vehicle docking task.

[0091] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0092] Currently, with the increasing automation levels in the logistics industry and in scenarios such as ports and airports, unmanned tractor units can be applied to cargo transfer. Unmanned tractor units need to precisely dock with trailers to achieve efficient and safe cargo transportation. However, in actual operating environments, due to factors such as dynamic changes in obstacles, uncertain trailer positions, and complex motion coupling between the tractor and trailer, the docking process often faces problems such as difficult trajectory planning, high collision risk, and low docking success rate.

[0093] In related technologies, trajectory planning methods are often based on static environment assumptions or only consider the motion control of the tractor itself, without fully taking into account the influence of trailer attitude and dynamic obstacles in the surrounding environment. In addition, these technologies lack effective retry mechanisms and strategy adjustments when trajectory solving fails, resulting in poor system fault tolerance and difficulty in operating stably in real-world complex scenarios.

[0094] To address the aforementioned problems, this invention proposes a method for planning the docking trajectory between an unmanned tractor and a trailer, solving issues such as complex trajectory planning, poor environmental adaptability, and weak fault tolerance in related technologies. Specifically, firstly, the unmanned tractor receives a trailer docking task and autonomously proceeds to the trailer operation waiting area. After parking, the tractor obtains its real-time location information via a positioning module. Simultaneously, a perception module detects obstacle information around the vehicle, including its position, outline, and motion state. An obstacle trajectory prediction algorithm, based on the obstacle information obtained by the perception module, predicts the obstacle's trajectory over a future period. Finally, a rear camera and a lidar sensor from the unmanned tractor jointly identify and detect the trailer's outline and position information. Based on the trailer's outline information, the docking position data between the unmanned tractor and the trailer is calculated, including the trailer docking position coordinates and heading angle information (trailer heading).

[0095] In addition, by combining the obstacle prediction trajectory and the docking position information of the unmanned tractor and trailer, a feasibility analysis of trajectory solving can be performed. The trailer position heading information used in the trajectory solving feasibility analysis can be the heading angle obtained by connecting the center position of the unmanned tractor's rear axle to the trailer position. Using this method can improve the success rate of trajectory solving and reduce the difficulty of solving the unmanned tractor's end docking trajectory. If it is not feasible, the unmanned tractor is controlled to drive to the preset suggested area and the solution is re-solved (the suggested area mainly refers to the area within 5m to the left and right of the trailer's center line and 20m forward, which can be adjusted according to the size of the unmanned tractor and trailer), and the attempt is repeated up to N times (N is the system setting value); if it is still not feasible after more than N attempts, the docking task is terminated and the fault status is reported to the cloud control platform.

[0096] If the trajectory is feasible, it is segmented (decomposed into a first segment and a last segment), and the initial trajectory is solved sequentially. After the initial trajectory is solved, it is optimized to generate a precise docking trajectory for both ends, and then the trajectory is stitched together. Next, obstacle collision detection is performed on the complete trailer docking trajectory. If there is no collision risk, the final trajectory is output and docking is executed; otherwise, the trajectory planning is restarted. If the trajectory planning and optimization takes more than 30 seconds, a fault status is reported to the cloud control platform.

[0097] The above method solves the technical problem of being unable to effectively determine the docking trajectory of a vehicle docking task, and achieves the technical effect of effectively determining the docking trajectory of a vehicle docking task.

[0098] Figure 2 This is a flowchart of a method for solving the driving trajectory of a tractor and trailer docking according to an embodiment of the present invention, as shown below. Figure 2 As shown, the method may include the following steps.

[0099] Step S201: Obtain the location of the unmanned tractor.

[0100] In this embodiment, the unmanned towing vehicle obtains its own positioning information and information about obstacles in the surrounding environment through onboard sensors (such as LiDAR, cameras, GPS / IMU, etc.). That is, it obtains the positioning information of the unmanned towing vehicle.

[0101] Step S202: Detect obstacles using the perception module.

[0102] In this embodiment, the perception module can detect surrounding obstacles in real time, including static obstacles (such as shelves and walls) and dynamic obstacles (such as other vehicles and people), and output the position, outline, and motion information (such as speed, acceleration, angular velocity, etc.) of the obstacles. That is, obstacle information is obtained.

[0103] Step S203: Detect trailer position.

[0104] In this embodiment, for the trailer target, the perception module detects the trailer's outline dimensions, position, and heading information using visual and laser recognition technology. That is, it obtains the trailer's outline and position information.

[0105] Step S204: Use the prediction module to predict the obstacle trajectory.

[0106] In this embodiment, the prediction module, based on current and historical obstacle information, uses methods such as Kalman filtering or artificial intelligence prediction models to predict the obstacle's trajectory over a future period. This trajectory information will be used for collision detection in subsequent trajectory planning, improving the safety of the trailer docking trajectory. In other words, the obstacle trajectory is obtained.

[0107] Step S205: Solve for trailer docking position information.

[0108] In this embodiment, markers (special reflectors) can be placed on the trailer. Images and point cloud information are acquired by the unmanned tractor's rear-facing camera and LiDAR sensor. After processing and recognition by the perception module, the geometric center coordinates and heading angle of the trailer are calculated. Based on the geometric center coordinates and heading angle of the trailer, the docking point data is solved to calculate the optimal docking position between the unmanned tractor and the trailer. That is, the trailer docking position information is obtained.

[0109] Step S206: Preprocess the location information of the unmanned tractor and trailer.

[0110] In this embodiment, after obtaining the unmanned tractor positioning information, obstacle trajectory and trailer docking position information, the unmanned tractor and trailer position information can be preprocessed.

[0111] Optionally, the unmanned tractor acquires its own positioning information and information about obstacles in the surrounding environment through onboard sensors (including LiDAR, cameras, GPS / IMU, etc.). The perception module detects surrounding obstacles in real time, including static obstacles (such as shelves and walls) and dynamic obstacles (such as other vehicles and people), and outputs the position, outline, and motion information (including speed, acceleration, angular velocity, etc.) of the obstacles. Based on current and historical obstacle information, the prediction module uses methods such as Kalman filtering or artificial intelligence prediction models to predict the trajectory of obstacles over a future period. This trajectory information will be used for collision detection in subsequent trajectory planning, improving the safety of the trailer docking trajectory.

[0112] Optionally, for the trailer target, the perception module detects the trailer's outline dimensions, position, and heading information using visual and laser recognition technology. Specifically, a marker (special reflector) is placed on the trailer, and images and point cloud information are acquired by the unmanned tractor's rear-facing camera and LiDAR sensor. After processing and recognition by the perception module, the geometric center position coordinates and heading angle information of the trailer are calculated. Based on the trailer's outline geometric center position coordinates and heading angle information, the trailer docking point data is solved, and the optimal docking position between the unmanned tractor and the trailer is calculated.

[0113] Step S207: Whether the feasibility analysis of trajectory solution is passed.

[0114] In this embodiment, after preprocessing the location information of the unmanned tractor and trailer, a feasibility analysis of trajectory solving can be performed by combining the obstacle prediction trajectory and the current positions of the tractor and trailer. If the feasibility analysis passes, step S208 can be executed; otherwise, if the feasibility analysis fails, step S211 can be executed.

[0115] Step S208: Solve for the initial trajectory.

[0116] In this embodiment, if the trajectory feasibility analysis passes, the initial trajectory solution is then performed.

[0117] Step S209: Optimize the trailer docking and driving trajectory.

[0118] In this embodiment, to ensure control of the final docking posture of the unmanned tractor, the final segment of the trajectory solution can be a straight line segment with a length ranging from 0.5m to 1m to improve the accuracy of vehicle control. Therefore, the endpoint of the trajectory solution is the extension point from the trailer docking position to the docking direction of the unmanned tractor and trailer, designated as point C, with an extension length of 0.5 to 1m, which can be adjusted according to actual working conditions. The trajectory from point C to point B is set as the final segment, using a uniform deceleration (with acceleration set to a fixed value) speed solution method to ensure the smoothness of the docking process between the unmanned tractor and trailer.

[0119] Optionally, the trajectory from point A to point C can be defined as the first segment of the path, and a search-based path planning method (such as hybrid A) can be used. The process involves several algorithms (such as quadratic programming) to generate the final trailer docking trajectory. Starting from the initial trajectory, optimization algorithms (such as quadratic programming) are used to smooth the trajectory and plan its speed, generating a precise docking trajectory. After the trajectories at both ends are solved, they are spliced ​​together to form a complete trailer docking trajectory.

[0120] Step S210: Perform obstacle collision detection.

[0121] In this embodiment, collision detection can be performed on the optimized trajectory to determine whether a collision occurs with an obstacle during trajectory execution. If the detection passes, the trajectory is sent as the final trajectory to the unmanned tractor for docking.

[0122] Step S211: Do not perform the docking of the unmanned tractor and trailer.

[0123] In this embodiment, if the detection fails, the trajectory can be replanned or the task can be terminated.

[0124] Step S212: Drive the unmanned towing vehicle to the suggested area.

[0125] In this embodiment, without performing the docking of the unmanned tractor with the trailer, the unmanned tractor can be driven to the suggested area.

[0126] Optionally, if by mixing A If the algorithm cannot solve the collision-free coarse trajectory, it indicates that the unmanned tractor cannot safely dock with the trailer under the current environmental conditions, and it is necessary to guide the unmanned tractor towards a preset suggested area. The suggested area mainly refers to the region within 5m to the left and right of the trailer's centerline and 20m forward. This area can be adjusted according to the dimensions of the unmanned tractor and trailer. When the unmanned tractor is within this area, it can improve the hybrid A... The success rate of the algorithm in solving the rough trajectory.

[0127] Step S213: Check if the number of attempts is greater than N.

[0128] In this embodiment, after the unmanned tractor reaches a new location, it repeatedly attempts to solve the coarse trajectory, up to N times (N is set by the user according to the actual scenario). If the number of attempts is greater than N, the docking task ends; otherwise, if the number of attempts is less than or equal to N, step S207 can be executed.

[0129] If a feasible trajectory cannot be planned after multiple attempts, the system terminates the docking task and reports an anomaly. Collision detection in this phase employs a bounding box-based continuous collision detection method. At each time step, a simple geometric bounding box is generated for the unmanned tractor and the obstacle, and the system checks for overlap. If a collision-free coarse trajectory is obtained, it is then processed by the trajectory optimization module for trajectory smoothing before the unmanned vehicle docking with the trailer is executed.

[0130] In this embodiment of the invention, if it is necessary to control vehicles to perform a docking task, the state information of the first vehicle and the attribute information of the second vehicle can be obtained. The second vehicle is pulled by the first vehicle. The state information indicates the position of the first vehicle and / or obstacles on the road where the first vehicle is located. The attribute information indicates the outline of the second vehicle and its position. Based on the state information and attribute information, an initial trajectory for the first and second vehicles to perform the docking task can be determined. In response to the feasibility information of the initial trajectory satisfying a feasibility information threshold, the initial trajectory can be segmented to obtain a segmentation result. The segmentation result can then be processed to obtain a target trajectory. The feasibility information indicates the degree of feasibility of solving the initial trajectory. The first and second vehicles can be controlled to travel according to the target trajectory to perform the docking task. In other words, by integrating the state information of the first vehicle and the attribute information of the second vehicle, the embodiments of the present invention can more comprehensively assess environmental conditions and determine the initial trajectory. By dividing the initial trajectory in the docking process into different stages and processing them, it can ensure both the continuity and safety of the overall driving path and the precise control of the docking stage. Thus, the target trajectory (i.e., the docking driving trajectory) can be effectively determined when performing the docking task, solving the technical problem of not being able to effectively determine the docking driving trajectory of the vehicle docking task and achieving the technical effect of effectively determining the docking driving trajectory of the vehicle docking task.

[0131] Figure 3 This is a schematic diagram illustrating the docking trajectory and relative positional relationship between a lead vehicle and a trailer according to an embodiment of the present invention, as shown below. Figure 3 As shown, a hybrid A can be used. The algorithm performs a coarse trajectory calculation for the docking position of the unmanned tractor and trailer. The starting point for the calculation is the current position coordinates of the vehicles, i.e. Figure 3 Point A is the starting heading, which is the vehicle's current heading angle. The solution terminates at the trailer docking point, i.e. Figure 3 At point B, the heading at the termination point is determined by the heading angle corresponding to the line connecting the trailer docking position and the vehicle's current position. This heading angle is then set as the docking heading between the unmanned tractor and the trailer. Figure 3 As shown by the middle arrow 1. Figure 3 Point C is the docking trajectory of the unmanned tractor and trailer, mixed with A. The algorithm can take into account dynamic and static obstacle information during the process of solving the coarse trajectory and solve the initial solution without collision, which is then processed by the trajectory optimization algorithm.

[0132] In this embodiment of the invention, the following beneficial effects are achieved through the above steps.

[0133] Through trajectory feasibility analysis and retry mechanism: feasibility is judged before trajectory solution to avoid invalid calculation; multiple attempts and strategy adjustments are supported to improve system fault tolerance.

[0134] A phased trajectory solving strategy is adopted: for the reversing trajectory, it is divided into the final trajectory and the initial trajectory. Different trajectory solving strategies are used for different trajectory segments, making the trajectory solving process more flexible, ensuring that the heading of the final trajectory remains unchanged, and improving vehicle control and docking smoothness.

[0135] Adaptive solution for trailer docking position: Based on the actual state of the trailer, the docking position point and the docking direction between the unmanned tractor and the trailer are adaptively calculated to adapt to various trailer types and attitudes, thereby improving the success rate of trailer docking.

[0136] By employing a suggested area guidance mechanism, vehicles are guided to a safe area when a trajectory is not feasible, thus avoiding vehicle congestion and repeated failures and improving the success rate and safety of trailer docking.

[0137] According to embodiments of the present invention, a vehicle trajectory determination device is also provided. It should be noted that this vehicle trajectory determination device can be used to execute the vehicle trajectory determination method described in the embodiments.

[0138] Figure 4 This is a schematic diagram of a vehicle trajectory determination device according to an embodiment of the present invention. Figure 4 As shown, the vehicle trajectory determination device 400 may include: an acquisition unit 402, a determination unit 404, a segmentation unit 406, and an execution unit 408.

[0139] The acquisition unit 402 is used to acquire the status information of the first vehicle and the attribute information of the second vehicle, wherein the second vehicle is pulled by the first vehicle, the status information is used to indicate the position of the first vehicle and / or obstacles on the road where the first vehicle is located, and the attribute information is used to indicate the outline of the second vehicle and the position of the second vehicle.

[0140] The determining unit 404 is used to determine the initial trajectory for enabling the first vehicle and the second vehicle to perform docking tasks based on state information and attribute information.

[0141] Segmentation unit 406 is used to segment the initial trajectory in response to the feasibility information of the initial trajectory satisfying the feasibility information threshold, to obtain segmentation results, and to process the segmentation results to obtain the target trajectory, wherein the feasibility information is used to represent the feasibility of solving the initial trajectory.

[0142] The execution unit 408 is used to control the first vehicle and the second vehicle to drive according to the target trajectory in order to perform the docking task.

[0143] Optionally, the segmentation result includes a first segmentation result and a second segmentation result. The segmentation unit 406 includes: a first segmentation subunit, used to segment the initial trajectory in response to the feasibility information satisfying the feasibility information threshold, to obtain the current position of the first vehicle and the extended position of the docking heading of the first vehicle and the second vehicle; a second segmentation subunit, used to determine the trajectory between the current position and the extended position in the initial trajectory as the first segmentation result, and to segment the initial trajectory in response to the feasibility information satisfying the feasibility information threshold, to obtain the docking position of the second vehicle; and a first determination subunit, used to determine the trajectory between the docking position and the extended position as the second segmentation result, wherein the docking heading direction is used to represent the heading angle corresponding to the line connecting the docking position and the current position.

[0144] Optionally, the segmentation unit 406 includes: a first processing subunit, used to perform smoothing and velocity planning processing on the first segmentation result, starting from the initial trajectory, to obtain a first target trajectory; a second processing subunit, used to perform uniform deceleration operation processing on the second segmentation result to obtain a second target trajectory; and a third processing subunit, used to splice the first target trajectory and the second target trajectory to obtain a target trajectory.

[0145] Optionally, the third processing subunit includes: a splicing subunit, used to splice the first target trajectory and the second target trajectory to obtain a third target trajectory; to detect the third target trajectory to obtain a detection result; and a second determining subunit, used to determine the third target trajectory as the target trajectory in response to the detection result that the first vehicle did not collide with the obstacle during the execution of the third target trajectory.

[0146] Optionally, the vehicle trajectory determination device 400 further includes a third determination subunit, used to re-determine the target trajectory or terminate the docking task in response to the detection result that the first vehicle has collided with an obstacle.

[0147] Optionally, the vehicle trajectory determination device 400 further includes: a control subunit, configured to control the first vehicle to travel to the target area in response to the feasibility information not meeting the feasibility information threshold; an analysis subunit, configured to analyze the initial trajectory within the target area according to a target number of times to obtain the analysis result, wherein the target number of times is used to represent the upper limit of the number of times the initial trajectory is analyzed; and a termination subunit, configured to terminate the docking task in response to the analysis result indicating that the feasibility information does not meet the feasibility information threshold.

[0148] In this embodiment, the acquisition unit 402 acquires the state information of the first vehicle and the attribute information of the second vehicle, wherein the second vehicle is pulled by the first vehicle, the state information is used to indicate the position of the first vehicle and / or obstacles on the road where the first vehicle is located, and the attribute information is used to indicate the outline of the second vehicle and the position of the second vehicle; the determination unit 404 determines the initial trajectory for the first and second vehicles to perform the docking task based on the state information and attribute information; the segmentation unit 406 segments the initial trajectory in response to the feasibility information threshold of the initial trajectory to obtain the segmentation result, and processes the segmentation result to obtain the target trajectory, wherein the feasibility information is used to indicate the feasibility of solving the initial trajectory; the execution unit 408 controls the first and second vehicles to drive according to the target trajectory to perform the docking task, thereby solving the technical problem of not being able to effectively determine the docking driving trajectory of the vehicle docking task and achieving the technical effect of effectively determining the docking driving trajectory of the vehicle docking task.

[0149] Embodiments of this application also provide an electronic device, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention during runtime.

[0150] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of the present invention.

[0151] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of the present invention.

[0152] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of the present invention.

[0153] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of the present invention.

[0154] According to another aspect of the present invention, a vehicle is also provided. The vehicle includes a memory and a processor. The memory stores an executable program; the processor runs the program, which, when executed, implements the methods described in the embodiments of the present invention.

[0155] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0156] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0157] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0158] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0159] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0160] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining the driving trajectory of a vehicle, characterized in that, include: Obtain the status information of the first vehicle and the attribute information of the second vehicle, wherein the second vehicle is pulled by the first vehicle, the status information is used to indicate the position of the first vehicle and / or obstacles on the road where the first vehicle is located, and the attribute information is used to indicate the outline of the second vehicle and the position of the second vehicle. Based on the state information and the attribute information, an initial trajectory is determined for the first vehicle and the second vehicle to perform the docking task; In response to the feasibility information of the initial trajectory satisfying a feasibility information threshold, the initial trajectory is segmented to obtain a segmentation result, and the segmentation result is processed to obtain a target trajectory, wherein the feasibility information is used to represent the degree of feasibility of solving the initial trajectory; The first vehicle and the second vehicle are controlled to travel according to the target trajectory in order to perform the docking task.

2. The method according to claim 1, characterized in that, The segmentation results include a first segmentation result and a second segmentation result. In response to the feasibility information of the initial trajectory satisfying a feasibility information threshold, the initial trajectory is segmented to obtain segmentation results, including: In response to the feasibility information satisfying the feasibility information threshold, the initial trajectory is segmented to obtain the current position of the first vehicle and the extended position of the docking heading of the first vehicle and the second vehicle. The trajectory between the current position and the extended position in the initial trajectory is determined as the first segmentation result, and, In response to the feasibility information satisfying the feasibility information threshold, the initial trajectory is segmented to obtain the docking position of the second vehicle; The trajectory between the docking position and the extended position is determined as the second segmentation result, wherein the docking heading direction is used to represent the heading angle corresponding to the line connecting the docking position and the current position.

3. The method according to claim 2, characterized in that, The segmentation results are processed to obtain the target trajectory, including: For the first segmentation result, starting from the initial trajectory, smoothing and velocity planning are performed to obtain the first target trajectory; The second segmented result is processed by uniform deceleration to obtain the second target trajectory; The first target trajectory and the second target trajectory are spliced ​​together to obtain the target trajectory.

4. The method according to claim 3, characterized in that, The target trajectory is obtained by concatenating the first target trajectory and the second target trajectory, including: The first target trajectory and the second target trajectory are spliced ​​together to obtain the third target trajectory; The trajectory of the third target is detected, and the detection result is obtained; In response to the detection result that the first vehicle did not collide with the obstacle during the execution of the third target trajectory, the third target trajectory is determined as the target trajectory.

5. The method according to claim 4, characterized in that, The method further includes: In response to the detection result indicating that the first vehicle has collided with the obstacle, the target trajectory is redefined, or the docking task is terminated.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: In response to the feasibility information not meeting the feasibility information threshold, the first vehicle is controlled to travel to the target area; Within the target area, the initial trajectory is analyzed according to a target number of times to obtain analysis results, wherein the target number of times represents the upper limit of the number of times the initial trajectory is analyzed; If the analysis result indicates that the feasibility information does not meet the feasibility information threshold, the docking task is terminated.

7. A device for determining the driving trajectory of a vehicle, characterized in that, include: An acquisition unit is used to acquire the status information of a first vehicle and the attribute information of a second vehicle, wherein the second vehicle is pulled by the first vehicle, the status information is used to indicate the position of the first vehicle and / or obstacles on the road where the first vehicle is located, and the attribute information is used to indicate the outline of the second vehicle and the position of the second vehicle. The determining unit is configured to determine, based on the state information and the attribute information, an initial trajectory for enabling the first vehicle and the second vehicle to perform a docking task; A segmentation unit is configured to segment the initial trajectory in response to the feasibility information of the initial trajectory satisfying a feasibility information threshold, to obtain a segmentation result, and to process the segmentation result to obtain a target trajectory, wherein the feasibility information is used to represent the degree of feasibility of solving the initial trajectory. An execution unit is used to control the first vehicle and the second vehicle to travel according to the target trajectory in order to perform the docking task.

8. A processor, characterized in that, The processor is used to run a program, wherein the program executes the method according to any one of claims 1 to 6 when it runs.

9. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 6.

10. A vehicle, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 6.

Images