Vehicle navigation method and device and electronic device

Abstract

The invention discloses a vehicle navigation method and device and an electronic device. The method comprises the steps that a previous frame guide line and a current frame guide line of a vehicle are obtained based on vehicle navigation information, the vehicle navigation information is used for providing a driving path of the vehicle, and the current frame guide line is used for guiding the driving path of the vehicle at the current moment; the previous frame of guide line is used for guiding a driving path of the vehicle at the previous moment of the current moment; smoothing the current frame guide line based on the previous frame guide line to obtain a smooth guide line; and navigating the vehicle based on the smooth guide line. According to the invention, the technical problem that the steering wheel of the vehicle shakes due to the instability of the guide line between continuous frames in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a vehicle navigation method, device, and electronic device. Background Art

[0002] In autonomous driving technology, vehicle path planning and tracking rely on stable guidance lines between consecutive frames to ensure safe and smooth driving. However, existing technologies can cause significant jitter in guidance lines between frames due to fluctuations in sensor data and transient environmental conditions. This can lead to frequent adjustments to the vehicle control system, particularly unnecessary steering wheel vibration, which not only reduces passenger comfort but also potentially compromises driving safety.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] Embodiments of the present invention provide a vehicle navigation method, apparatus, and electronic device to at least solve the technical problem in the related art of jittering of the vehicle steering wheel due to unstable guide lines between consecutive frames.

[0005] According to one aspect of an embodiment of the present invention, a vehicle navigation method is provided, comprising: obtaining a previous frame guide line and a current frame guide line of a vehicle based on vehicle navigation information, wherein the vehicle navigation information is used to provide a driving path of the vehicle, the current frame guide line is used to guide the driving path of the vehicle at the current moment, and the previous frame guide line is used to guide the driving path of the vehicle at the moment before the current moment; smoothing the current frame guide line based on the previous frame guide line to obtain a smoothed guide line; and navigating the vehicle based on the smoothed guide line.

[0006] Furthermore, the current frame guide line is smoothed based on the previous frame guide line to obtain a smooth guide line, including: obtaining a current frame point set of the current frame guide line; projecting the current frame point set onto the previous frame guide line to obtain a previous frame point set, wherein the current frame point set includes multiple guide points on the current frame guide line; determining a smooth point set based on the current frame point set and the previous frame point set; and generating a smooth guide line based on the smooth point set.

[0007] Furthermore, a smooth point set is determined based on the current frame point set and the previous frame point set, including: adding the first cost function, the second cost function, the third cost function and the fourth cost function to obtain a target cost function; determining a constraint distance based on the first point and the second point, wherein the first point is used to represent any point in the current frame point set, the second point is used to represent a point corresponding to the first point in the previous frame point set, and the constraint distance is used to represent a straight-line distance between the first point and the second point; and determining a smooth point set based on the target cost function and the constraint distance.

[0008] Furthermore, determining a smooth point set based on the target cost function and the constraint distance includes: determining multiple smooth points based on the target cost function and the constraint distance, wherein a straight-line distance between any one of the multiple smooth points and the first point does not exceed the constraint distance, and a straight-line distance between any one of the multiple smooth points and the second point does not exceed the constraint distance; and determining the smooth point set based on the multiple smooth points.

[0009] Furthermore, the vehicle navigation method also includes: obtaining a first coordinate difference based on the difference between the horizontal coordinate of any point in the previous frame point set and the horizontal coordinate of the corresponding smooth point; obtaining a second coordinate difference based on the difference between the vertical coordinate of any point in the previous frame point set and the vertical coordinate of the corresponding smooth point; determining a first deviation based on the sum of the squares of the first coordinate difference and the second coordinate difference; and determining a first cost function based on the product of the first deviation and the first weight.

[0010] Furthermore, the vehicle navigation method also includes: obtaining a third coordinate difference based on the difference between the horizontal coordinate of any point in the current frame point set and the horizontal coordinate of the corresponding smooth point; obtaining a fourth coordinate difference based on the difference between the vertical coordinate of any point in the current frame point set and the vertical coordinate of the corresponding smooth point; determining a second deviation based on the sum of the squares of the third coordinate difference and the fourth coordinate difference; and determining a second cost function based on the product of the second deviation and the second weight.

[0011] Furthermore, the vehicle navigation method further includes: obtaining a Euclidean distance length based on coordinates of any two adjacent smooth points in the smooth point set; and determining a third cost function based on a product of the Euclidean distance length and a third weight.

[0012] Furthermore, the vehicle navigation method also includes: determining a first vector based on a first smooth point and a second smooth point, wherein the first smooth point is any point among a plurality of smooth points and the first smooth point is adjacent to the second smooth point; determining a second vector based on the second smooth point and a third smooth point, wherein the second smooth point is adjacent to the third smooth point; determining the vector sum of the first vector and the second vector; and determining a fourth cost function based on the product of the vector sum and a fourth weight.

[0013] Furthermore, the vehicle navigation method further includes: adjusting the first weight according to a first filtering requirement so that the geometry of the smooth guide line approaches the geometry of the guide line of the previous frame, wherein the first filtering requirement is used to reduce the filtering intensity of the guide line of the current frame.

[0014] Furthermore, the vehicle navigation method further includes: adjusting the second weight according to a second filtering requirement so that the geometry of the smooth guide line approaches the geometry of the current frame guide line, wherein the second filtering requirement is used to increase the filtering strength of the current frame guide line.

[0015] According to another aspect of an embodiment of the present invention, a vehicle navigation device is also provided, including: an acquisition module, the acquisition module is used to acquire the vehicle's previous frame guide line and current frame guide line based on vehicle navigation information, wherein the vehicle navigation information is used to provide the vehicle's driving path, the current frame guide line is used to guide the vehicle's driving path at the current moment, and the previous frame guide line is used to guide the vehicle's driving path at the moment before the current moment; a processing module, the processing module is used to smooth the current frame guide line based on the previous frame guide line to obtain a smooth guide line; and a navigation module, the navigation module is used to navigate the vehicle based on the smooth guide line.

[0016] Optionally, the processing module is also used to obtain a current frame point set of the current frame guide line; project the current frame point set onto the previous frame guide line to obtain a previous frame point set, wherein the current frame point set includes multiple guide points on the current frame guide line; determine a smooth point set based on the current frame point set and the previous frame point set; and generate a smooth guide line based on the smooth point set.

[0017] Optionally, the processing module is also used to add the first cost function, the second cost function, the third cost function and the fourth cost function to obtain a target cost function; determine the constraint distance based on the first point and the second point, wherein the first point is used to represent any point in the current frame point set, the second point is used to represent the point corresponding to the first point in the previous frame point set, and the constraint distance is used to represent the straight-line distance between the first point and the second point; determine the smooth point set based on the target cost function and the constraint distance.

[0018] Optionally, the processing module is also used to determine multiple smooth points based on the target cost function and the constraint distance, wherein the straight-line distance between any one of the multiple smooth points and the first point does not exceed the constraint distance, and the straight-line distance between any one of the multiple smooth points and the second point does not exceed the constraint distance; and determine a smooth point set based on the multiple smooth points.

[0019] Optionally, the processing module is also used to obtain a first coordinate difference based on the difference between the horizontal coordinate of any point in the previous frame point set and the horizontal coordinate of the corresponding smooth point; obtain a second coordinate difference based on the difference between the vertical coordinate of any point in the previous frame point set and the vertical coordinate of the corresponding smooth point; determine a first deviation based on the sum of the squares of the first coordinate difference and the second coordinate difference; and determine a first cost function based on the product of the first deviation and the first weight.

[0020] Optionally, the processing module is also used to obtain a third coordinate difference based on the difference between the horizontal coordinate of any point in the current frame point set and the horizontal coordinate of the corresponding smooth point; to obtain a fourth coordinate difference based on the difference between the vertical coordinate of any point in the current frame point set and the vertical coordinate of the corresponding smooth point; to determine the second deviation based on the sum of the squares of the third coordinate difference and the fourth coordinate difference; and to determine the second cost function based on the product of the second deviation and the second weight.

[0021] Optionally, the processing module is further configured to obtain a Euclidean distance length based on coordinates of any two adjacent smooth points in the smooth point set; and determine a third cost function based on a product of the Euclidean distance length and a third weight.

[0022] Optionally, the processing module is also used to determine a first vector based on a first smooth point and a second smooth point, wherein the first smooth point is any point among a plurality of smooth points and the first smooth point is adjacent to the second smooth point; determine a second vector based on the second smooth point and a third smooth point, wherein the second smooth point is adjacent to the third smooth point; determine the vector sum of the first vector and the second vector; and determine a fourth cost function based on the product of the vector sum and a fourth weight.

[0023] Optionally, the processing module is further configured to adjust the first weight according to a first filtering requirement so that the geometry of the smoothed guide line approaches the geometry of the guide line of the previous frame, wherein the first filtering requirement is configured to reduce the filtering intensity of the guide line of the current frame.

[0024] Optionally, the processing module is further configured to adjust the second weight according to a second filtering requirement so that the geometry of the smoothed guide line approaches the geometry of the guide line of the current frame, wherein the second filtering requirement is configured to increase the filtering strength of the guide line of the current frame.

[0025] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the vehicle navigation method in various embodiments of the present invention when running on a computer or processor.

[0026] According to another aspect of an embodiment of the present invention, an electronic device is provided, including a memory and a processor. The memory stores a computer program, and the processor is configured to run the computer program to execute the vehicle navigation method in various embodiments of the present invention.

[0027] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the vehicle navigation method in each embodiment of the present invention is implemented.

[0028] In an embodiment of the present invention, an information fusion method is adopted. First, the vehicle's previous frame guide line and current frame guide line are obtained based on the vehicle navigation information, wherein the vehicle navigation information is used to provide the vehicle's driving path, the current frame guide line is used to guide the vehicle's driving path at the current moment, and the previous frame guide line is used to guide the vehicle's driving path at the previous moment. Then, the current frame guide line is smoothed based on the previous frame guide line to obtain a smoothed guide line. Finally, the vehicle is navigated based on the smoothed guide line, achieving the goals of high precision, high continuity and low curvature change in path planning, thereby achieving the technical effect of significantly enhancing the driving stability of autonomous driving, and further solving the technical problem in the related art that the steering wheel of the vehicle shakes due to the instability of the guide line between consecutive frames. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0030] Figure 1 is a flow chart of a vehicle navigation method according to an embodiment of the present invention;

[0031] Figure 2 is a schematic diagram of an optional method for determining a constraint range according to an embodiment of the present invention;

[0032] Figure 3 is a schematic diagram of an optional smoothed guide line according to an embodiment of the present invention;

[0033] Figure 4 is a schematic diagram of an optional vehicle navigation device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0035] In order to enable those skilled in the art to better understand the present technical solution, some relevant terms are explained as follows:

[0036] Guide lines: In the field of autonomous driving and path planning, during vehicle driving, guide lines are reference lines used to generate the vehicle's optimal driving path. They are usually calculated based on the current vehicle position, destination, and road characteristics (such as lane lines, obstacles, etc.).

[0037] Quadratic Programming Optimizer: A QP optimizer is a mathematical tool used to solve optimization problems with quadratic objective functions and linear constraints. In this technical solution, the QP optimizer is used to smooth the path, ensuring that the generated path not only conforms to the characteristics of the current guide line but also maintains good continuity and stability with the guide line of the previous frame.

[0038] Curvature, a geometric quantity that describes the curvature of a curve, directly impacts the smoothness and safety of a vehicle's ride in path planning. Abnormally high or low curvature can cause the vehicle to swerve or become unstable. Therefore, maintaining consistent and reasonable curvature is a key goal in path optimization.

[0039] Frame stability refers to the smoothness of the path generated by the path planning and control algorithms over consecutive time frames. Within consecutive frames of a video stream or sensor input, the path should not experience dramatic fluctuations or jumps to ensure vehicle continuity and passenger safety and comfort.

[0040] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0041] According to an embodiment of the present invention, an embodiment of a vehicle navigation method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] Figure 1 A vehicle navigation method according to an embodiment of the present invention is as follows: Figure 1As shown, the method includes the following steps:

[0043] Step S1, obtaining a previous frame guide line and a current frame guide line of the vehicle based on vehicle navigation information, wherein the vehicle navigation information is used to provide a driving path of the vehicle, the current frame guide line is used to guide the driving path of the vehicle at the current moment, and the previous frame guide line is used to guide the driving path of the vehicle at the moment before the current moment;

[0044] In the embodiment of the present invention, the vehicle navigation information may be understood as navigation information generated by a vehicle navigation device according to a user's departure and destination, and is used to provide a driving route for the vehicle.

[0045] The previous frame guide line can be understood as the guide line planned by the system at the previous moment based on information such as the vehicle position, speed, road conditions, obstacle detection results, etc. at the previous moment. The previous frame guide line is used to guide the vehicle's driving path at the previous moment.

[0046] The current frame's guiding lines are defined by the system based on the current vehicle position, speed, road conditions, and obstacle detection results. These lines guide the vehicle's path at that moment. Because the current road environment may change, the guiding lines from the previous frame and the current frame may differ due to these changes, ensuring the vehicle's immediate response to current driving needs.

[0047] In an embodiment of the present invention, by obtaining the vehicle's previous frame guide line and current frame guide line based on vehicle navigation information, the continuity of historical paths and the ability to respond instantly to current road conditions are effectively combined, ensuring the stability, safety, and comfort of path planning. At the same time, the efficiency and accuracy of the algorithm are optimized, providing a more reliable and comfortable driving experience for autonomous vehicles.

[0048] Step S2, smoothing the guide line of the current frame based on the guide line of the previous frame to obtain a smooth guide line;

[0049] In the embodiment of the present invention, the smoothing process can be understood as optimizing and repairing the discontinuity and jitter of the guide line of the current frame based on the guide line of the previous frame.

[0050] The smooth guide line can be understood as a smoother and more stable driving path generated by smoothing the guide line of the current frame based on the guide line of the previous frame.

[0051] Smoothing the guide line of the current frame based on the guide line of the previous frame to obtain a smooth guide line can be understood as optimizing and repairing the discontinuity and jitter existing in the guide line of the current frame on the basis of the guide line of the previous frame, thereby obtaining a smoother and continuous driving path.

[0052] For example, when smoothing the current frame guide line based on the previous frame guide line to obtain a smoothed guide line, the current frame point set on the current frame guide line can be first obtained and projected onto the previous frame guide line to obtain the previous frame point set, wherein the current frame point set includes multiple guide points on the current frame guide line. A target cost function and a constraint distance are then constructed based on the current frame point set and the previous frame point set. When constructing the target cost function, a first cost function, a second cost function, a third cost function, and a fourth cost function can be first determined, and these four sub-cost functions are added together to obtain the target cost function. The constraint distance is determined based on the straight-line distance between any first point in the current frame point set and a second point corresponding to the first point in the previous frame point set. By minimizing the target cost function, a smoothed point set is obtained, wherein the value range of any point in the smoothed point set does not exceed the constraint distance. Finally, a smoothed guide line is generated based on the smoothed point set. The smoothed guide line obtained through the above steps has good continuity, smoothness, and stability.

[0053] In an embodiment of the present invention, the guide line of the current frame is smoothed based on the guide line of the previous frame to obtain a smooth guide line. This can eliminate path mutations caused by data acquisition noise, algorithm fluctuations or environmental changes, ensure the continuity of the vehicle's driving path between frames and minimize the amplitude of changes, thereby improving the stability of vehicle driving and the comfort experience of passengers.

[0054] Step S3: Navigate the vehicle based on the smooth guide line.

[0055] In an embodiment of the present invention, navigating a vehicle based on a smooth guide line can be understood as, in autonomous driving and advanced driver assistance systems, using a smooth guide line as an optimized path to guide the vehicle's driving direction and ensure safety, stability, and comfort during driving. The smooth guide line is obtained by optimizing and processing the current frame guide line, aiming to eliminate or reduce abrupt turns, discontinuous points, and high curvature areas in the current frame guide line, and to generate a straighter, curvature-continuous driving path that conforms to road characteristics. Based on this smooth guide line, the vehicle's navigation system can more accurately control the vehicle's position and speed, allowing it to move smoothly along a preset path without unnecessary sharp turns or acceleration or deceleration, thereby improving the vehicle's adaptability in complex environments and the passengers' riding experience.

[0056] Through the above steps, an information fusion method is adopted. First, the vehicle's previous frame guide line and current frame guide line are obtained based on the vehicle navigation information, wherein the vehicle navigation information is used to provide the vehicle's driving path, the current frame guide line is used to guide the vehicle's driving path at the current moment, and the previous frame guide line is used to guide the vehicle's driving path at the previous moment. Then, the current frame guide line is smoothed based on the previous frame guide line to obtain a smooth guide line. Finally, the vehicle is navigated based on the smooth guide line, achieving the purpose of high precision, high continuity and low curvature change in path planning, thereby achieving the technical effect of significantly enhancing the driving stability of autonomous driving, and further solving the technical problem in the related technology that the steering wheel of the vehicle shakes due to the instability of the guide line between consecutive frames.

[0057] Optionally, in step S2, the guide line of the current frame is smoothed based on the guide line of the previous frame to obtain a smooth guide line, which includes the following execution steps:

[0058] Step S21, obtaining the current frame point set of the current frame guide line;

[0059] Step S22, projecting the current frame point set onto the previous frame guide line to obtain the previous frame point set, wherein the current frame point set includes multiple guide points on the current frame guide line;

[0060] Step S23, determining a smooth point set based on the current frame point set and the previous frame point set;

[0061] Step S24: generating a smooth guide line based on the smooth point set.

[0062] In an embodiment of the present invention, the current frame point set can be understood as a point set consisting of multiple guide points that constitute the current frame guide line. The multiple guide points are usually represented by (x, y) coordinates, reflecting the ideal driving path of the vehicle under current conditions.

[0063] The previous frame point set can be understood as the point set obtained by projecting the points in the current frame point set onto the guide line of the previous frame. Similarly, the points in the previous frame point set are also composed of a series of (x, y) coordinate points, which represent the planned path of the vehicle at the previous moment.

[0064] The smoothed point set can be understood as the point set obtained by optimizing the current frame point set based on the previous frame point set. The smoothed point set is used to generate an optimized guidance path that meets the current driving requirements while maintaining the continuity and stability of the historical path.

[0065] Obtaining the current frame point set of the current frame guide line can be understood as representing the vehicle driving path planned by the system at the current moment as a series of points defined in a spatial coordinate system, thereby obtaining the current frame point set.

[0066] Projecting the current frame point set onto the previous frame guide line to obtain the previous frame point set can be understood as follows: in order to establish a connection between the current frame and the previous frame guide path, the system projects each point in the current frame point set onto the previous frame guide line, thereby finding a corresponding position for each path point of the current frame in the previous frame guide path to form the previous frame point set.

[0067] Determining the smooth point set based on the current frame point set and the previous frame point set can be understood as the system using optimization tools (such as quadratic programming optimizer, Kalman filter, etc.) to calculate and adjust the coordinate positions of the points in the current frame point set based on the coordinate information of the current frame point set and the previous frame point set to generate a smooth point set. The generation of the smooth point set aims to minimize the swing amplitude of the path between frames, while ensuring that the curvature change is within a safe and reasonable range, to achieve a smooth transition in path planning. By optimizing the points in the current frame point set, the system can generate a guidance path that meets the current driving needs and maintains continuity.

[0068] Generating a smooth guideline based on a smooth point set can be understood as generating a new driving path based on the smooth point set. This smooth guideline is not only the result of optimizing the current frame's point set, but also comprehensively considers the influence of the previous frame's point set, ensuring the continuity and stability of the guidance path.

[0069] In an embodiment of the present invention, a smooth point set is determined based on the current frame point set and the previous frame point set, and a smooth guide line is determined based on the smooth point set, which provides a smoother, continuous and reasonable driving guidance for the autonomous driving vehicle, and helps to improve the vehicle's driving stability and ride comfort.

[0070] Optionally, in step S23, determining a smooth point set according to the current frame point set and the previous frame point set includes the following execution steps:

[0071] Step S231, adding the first cost function, the second cost function, the third cost function and the fourth cost function to obtain a target cost function;

[0072] Step S232, determining a constrained distance based on the first point and the second point, wherein the first point is used to represent any point in the current frame point set, the second point is used to represent the point corresponding to the first point in the previous frame point set, and the constrained distance is used to represent the straight-line distance between the first point and the second point;

[0073] Step S233: Determine a smooth point set based on the target cost function and the constraint distance.

[0074] In this embodiment of the present invention, the first cost function is used to measure the deviation between the points in the smooth point set and the points in the previous frame point set to maintain the continuity and consistency of the path in the time series, prevent sudden fluctuations in path planning due to detection errors or environmental factors, and thus maintain the smoothness of vehicle driving and the comfort of passengers.

[0075] The second cost function is used to measure the deviation between the points in the smooth point set and the points in the current frame point set, reflecting the environmental information and road conditions at the current moment, so as to quickly adapt to possible dynamic changes, help the vehicle respond to obstacles on the road in a timely manner, and improve driving safety.

[0076] The third cost function is used to solve the Euclidean distance between any two adjacent points in the smooth point set to maintain continuity and uniformity within the smooth point set. By minimizing the difference in Euclidean distance between adjacent points, it ensures that the path planning does not contain excessive or insufficient local curvature, thus avoiding unnecessary sharp turns or freezes.

[0077] The fourth cost function is used to solve the vector sum of the vectors composed of adjacent points in the smooth point set. By calculating the local vector sum composed of three adjacent smooth points, the continuity and rationality of the path curvature are ensured, and the occurrence of sudden changes in curvature is prevented, thereby improving the safety and comfort of autonomous driving vehicles.

[0078] The target cost function is used to represent the sum of the first cost function, the second cost function, the third cost function, and the fourth cost function. By minimizing the target cost function, a smooth point set for constructing a smooth guide line can be obtained. Based on the smooth point set, an optimized driving path can be created for the autonomous driving vehicle, thereby improving the overall driving experience.

[0079] The constraint distance determines the upper limit of the deviation distance allowed between the first and second points. Figure 2 is a schematic diagram of an optional method for determining a constraint range according to an embodiment of the present invention, such as Figure 2 As shown in FIG, by calculating the straight-line distance between any first point and the corresponding second point, the constraint range of the solution, that is, the constraint distance, is obtained.

[0080] The target cost function is obtained by adding the first, second, third, and fourth cost functions. This can be understood as combining the contributions of the first, second, third, and fourth cost functions to form a unified cost evaluation standard, namely the target cost function. The target cost function reflects a comprehensive consideration of path continuity, immediacy, uniformity, and vector continuity, quantifying various path quality indicators through a weighted summation.

[0081] Determining the constraint distance based on the first and second points can be understood as setting boundary conditions for the optimization process, ensuring that the optimized path points do not shift significantly relative to the first or second points. The first and second points correspond to the same positions on the guide line in the current and previous frames, respectively. By measuring the straight-line distance between these two points, a constraint condition, the constraint distance, can be set. The constraint distance limits the range of possible values during the solution, ensuring the continuity and stability of the path and avoiding sudden changes in the path caused by excessive adjustments during the optimization process.

[0082] Determining the smooth point set based on the target cost function and the constraint distance can be understood as solving the target cost function based on the constraint distance to obtain the smooth point set, thereby providing optimized path point data for the subsequent generation of smooth guide lines.

[0083] In the embodiment of the present invention, by solving the target cost function, a smooth point set is obtained, which effectively addresses the problems of path continuity and inter-frame stability, thereby significantly improving vehicle driving safety and riding comfort.

[0084] Optionally, in step S233, determining a smooth point set based on the target cost function and the constraint distance includes the following execution steps:

[0085] Step S2331, determining a plurality of smooth points based on the target cost function and the constraint distance, wherein a straight-line distance between any one of the plurality of smooth points and the first point does not exceed the constraint distance, and a straight-line distance between any one of the plurality of smooth points and the second point does not exceed the constraint distance;

[0086] Step S2332: Determine a smooth point set based on multiple smooth points.

[0087] In the embodiment of the present invention, determining multiple smooth points based on the target cost function and the constraint distance can be understood as follows: in the process of path optimization, based on the constraint distance, the algorithm determines a series of smooth points by minimizing the target cost function. The target cost function comprehensively considers multiple important characteristics of the path, such as deviation from the guidance path of the previous frame, continuity, smoothness, etc., to ensure that the generated path meets the predetermined driving requirements and can cope with complex road environments. The introduction of the constraint distance is to limit the maximum straight-line distance between any smooth point and the adjacent points before and after in the optimization result, to prevent curvature anomalies in the path planning, and to ensure the spatial continuity of the path and the safety of driving. Therefore, each smooth point must be selected within the constraint distance range, so that the entire path is both continuous and smooth, avoiding excessive curvature or sudden turns, and enhancing the driving stability of the autonomous driving vehicle and the riding comfort of the passengers.

[0088] Determining a smooth point set based on multiple smooth points can be understood as integrating these smooth points into an ordered set, known as a smooth point set. A smooth point set is not simply a list of points, but rather a series of points ordered according to the path's direction of travel. The connections between the multiple smooth points form the optimized path trajectory. This ensures the path's logic and continuity, facilitating the subsequent conversion of the smooth point set into actual driving instructions, guiding the autonomous vehicle safely and smoothly along the planned path. Furthermore, the generation of the smooth point set provides a foundation for subsequent path evaluation and adjustments, ensuring the overall efficiency and accuracy of path planning.

[0089] In an embodiment of the present invention, multiple smoothing points are first determined based on the target cost function and the constraint distance, and then a smoothing point set is determined based on the multiple smoothing points. On the basis of considering various path attributes and constraints, a continuous and smooth path is generated, which effectively improves the safety, stability and riding comfort of the autonomous driving vehicle.

[0090] Optionally, in the vehicle navigation method, determining the first cost function includes the following steps:

[0091] A first coordinate difference is obtained by subtracting the horizontal coordinate of any point in the point set of the previous frame from the horizontal coordinate of the corresponding smooth point;

[0092] The second coordinate difference is obtained by subtracting the ordinate of any point in the previous frame point set from the ordinate of the corresponding smooth point;

[0093] Determine a first deviation based on the sum of squares of the first coordinate difference and the second coordinate difference;

[0094] A first cost function is determined based on a product of the first bias and the first weight.

[0095] In the embodiment of the present invention, any point in the last frame point set (denoted as point (P_{last})) is marked with its horizontal coordinate as x i_last , the horizontal coordinate of the point in the smooth point set corresponding to point (P_{last}) (denoted as point (P_{smooth})) is x i , the first coordinate difference is used to represent x i and x i_last The difference reflects the horizontal displacement change of the optimized smoothing point relative to the previous frame point.

[0096] Similar to the first coordinate difference, the second coordinate difference is processed for the vertical coordinate. Any point in the previous frame point set (recorded as point (P_{last})) is marked with its vertical coordinate as y i_last , the vertical coordinate of the point in the smooth point set corresponding to point (P_{last}) (denoted as point (P_{smooth})) is yi , the second coordinate difference is used to represent y i and y i_last The difference reflects the vertical displacement change of the optimized smoothing point relative to the previous frame point.

[0097] The first deviation is obtained by calculating the sum of the squares of the first coordinate difference and the second coordinate difference, which measures the position difference between the smoothed point and the corresponding point in the previous frame.

[0098] The first weight can be understood as a coefficient assigned to the first deviation. The first weight is used to adjust the influence of the guide line of the previous frame in the optimization process. The first weight can be denoted as W, which is not limited here.

[0099] Based on the difference between the horizontal coordinate of any point in the previous frame point set and the horizontal coordinate of the corresponding smooth point, the first coordinate difference is obtained. It can be understood as: for any point in the previous frame point set (P_{last}), find the corresponding smooth point (P_{smooth}), and then calculate the difference between the horizontal coordinates of the two points. The result is the first coordinate difference, which is x i -x i_last .

[0100] Based on the difference between the ordinate of any point in the previous frame point set and the ordinate of the corresponding smooth point, the second coordinate difference is obtained. It can be understood as: for any point in the previous frame point set (P_{last}), find the corresponding smooth point (P_{smooth}), and then calculate the difference between the ordinates of the two points. The result is the second coordinate difference, which is y i -y i_last .

[0101] Based on the product of the first deviation and the first weight, determining the first cost function can be understood as multiplying the first deviation and the first weight to obtain the first cost function. For example, the first cost function can be recorded as Cost1, Cost1 = ∑(x i -x i_last ) 2 +(y i -y i_last ) 2 *W, no restrictions here.

[0102] In this embodiment of the present invention, by calculating the first and second coordinate differences—the deviations between the smoothed point and the previous frame point in both horizontal and vertical coordinates—the system accurately assesses the consistency of the newly planned path with the historical driving trajectory. The squared sum of these differences is used as the first deviation, which is multiplied by the first weight W to generate the first cost function. This controls path smoothness, ensuring that the planned path maintains appropriate followability even when the vehicle encounters sudden environmental changes. This avoids drastic fluctuations in the driving route caused by overcorrection, reducing unnecessary energy consumption and stress on vehicle hardware.

[0103] Optionally, in the vehicle navigation method, determining the second cost function includes the following steps:

[0104] The third coordinate difference is obtained by subtracting the horizontal coordinate of any point in the current frame point set from the horizontal coordinate of the corresponding smooth point;

[0105] A fourth coordinate difference is obtained by subtracting the vertical coordinate of any point in the current frame point set from the vertical coordinate of the corresponding smooth point;

[0106] determining a second deviation based on the sum of squares of the third coordinate difference and the fourth coordinate difference;

[0107] A second cost function is determined based on a product of the second bias and the second weight.

[0108] In the embodiment of the present invention, any point in the current frame point set (denoted as point (P_{now})) is marked with its horizontal coordinate as x i_now , the horizontal coordinate of the point in the smooth point set corresponding to point (P_{now}) (denoted as point (P_{smooth})) is x i , the third coordinate difference is used to represent x i and x i_now The difference reflects the horizontal displacement change of the optimized smoothing point relative to the current frame point.

[0109] Similar to the third coordinate difference, the fourth coordinate difference is processed for the vertical coordinate. Any point in the current frame point set (recorded as point (P_{now})) is marked with its vertical coordinate as y i_now , the vertical coordinate of the point in the smooth point set corresponding to point (P_{now}) (denoted as point (P_{smooth})) is y i , the fourth coordinate difference is used to represent y i and y i_now The difference reflects the vertical displacement change of the optimized smoothing point relative to the current frame point.

[0110] The second deviation is obtained by calculating the sum of the squares of the third coordinate difference and the fourth coordinate difference, which measures the position difference between the smoothed point and the corresponding point in the current frame.

[0111] The second weight can be understood as a coefficient assigned to the second deviation. The second weight is used to adjust the influence of the current frame guide line in the optimization process. The second weight can be recorded as Z and is not limited here.

[0112] Based on the difference between the horizontal coordinate of any point in the current frame point set and the horizontal coordinate of the corresponding smooth point, the third coordinate difference can be obtained. It can be understood as: for any point in the current frame point set (P_{now}), find the corresponding smooth point (P_{smooth}), and then calculate the difference between the horizontal coordinates of the two points. The result is the third coordinate difference, which is x i -x i_now .

[0113] Based on the difference between the ordinate of any point in the current frame point set and the ordinate of the corresponding smooth point, the fourth coordinate difference is obtained. It can be understood as: for any point in the current frame point set (P_{now}), find the corresponding smooth point (P_{smooth}), and then calculate the difference between the ordinates of the two points. The result is the fourth coordinate difference, which is y i -y i_now .

[0114] Based on the product of the second deviation and the second weight, determining the second cost function can be understood as multiplying the second deviation and the second weight to obtain the second cost function. For example, the first cost function can be recorded as Cost2, Cost2 = ∑(x i -x i_now ) 2 +(y i -y i_now ) 2 *Z, no restriction here.

[0115] In this embodiment of the present invention, by calculating the differences between the third and fourth coordinates—the deviations between the horizontal and vertical coordinates of the smoothed point and the current frame point—the system quantifies how well the new path aligns with the immediate driving environment. The sum of the squares of these differences is used as the second deviation, which is then multiplied by the second weight Z to form the second cost function. This ensures that the vehicle's planned path can quickly adapt to dynamic changes in the surrounding environment, such as road obstacles and changing traffic conditions. Furthermore, by adjusting the value of the second weight Z, the continuity and stability of the path are maintained, avoiding sudden changes in path planning caused by over-responsiveness to real-time information, which could impact driving safety and passenger comfort.

[0116] Optionally, in the vehicle navigation method, determining the third cost function includes the following execution steps:

[0117] Based on the coordinates of any two adjacent smooth points in the smooth point set, the Euclidean distance length is obtained;

[0118] A third cost function is determined based on the product of the Euclidean distance length and the third weight.

[0119] In this embodiment of the present invention, the Euclidean distance refers to the straight-line distance between any two adjacent smooth points in a smooth point set. In path planning, the Euclidean distance reflects the positional differences between path points and is used to measure the path's coherence and density, ensuring that the path is neither too sparse nor too dense, and that appropriate point spacing is maintained.

[0120] The third weight can be understood as a parameter in the optimization algorithm, used to balance the relative importance of the Euclidean distance between path points in the objective cost function. The size of the third weight determines the algorithm's trade-off between pursuing a smooth path and maintaining a reasonable distribution of path points. For example, the third weight can be denoted by Y, which is not limited here. A higher third weight Y means that the algorithm tends to generate more evenly spaced path points, avoiding unnecessary path twists and turns, thereby reducing frequent vehicle turns during path execution and improving driving smoothness and safety.

[0121] Based on the coordinates of any two adjacent smooth points in the smooth point set, the Euclidean distance length can be obtained. It can be understood that by calculating the Euclidean distance between any two adjacent smooth points in the smooth point set, a series of data representing the lengths of various parts of the path can be obtained, which helps to evaluate the overall smoothness and coherence of the path and ensure the smoothness of the curvature of the path. For example, the coordinates of any two adjacent smooth points in the smooth point set are marked as (x i ,y i ) and (x i+1 ,y i+1 ), then the Euclidean distance between these two smooth points is D = (x i -x i+1 ) 2 +(y i -y i+1 ) 2 , there is no restriction here.

[0122] Based on the product of the Euclidean distance length and the third weight, determining the third cost function can be understood as multiplying the Euclidean distance length and the third weight to obtain the third cost function. For example, the third cost function can be recorded as Cost3, Cost3 = ∑(x i -x i+1 ) 2 +(y i -y i+1 ) 2*Y, the larger the value of the third cost function, the less smooth the path and the worse the continuity; conversely, if the function value is smaller, it means that the path is smoother and more continuous, which is more suitable for vehicle driving.

[0123] In this embodiment of the present invention, by adjusting the third weight, Y, we can control path smoothness and the continuity of the smooth guide line, ensuring that path planning responds to immediate driving environment changes while maintaining a positive driving experience and avoiding unnecessary sharp turns or sudden acceleration and deceleration, thereby improving vehicle safety and passenger comfort. The introduction of the third cost function ensures that path planning not only pursues efficiency and speed, but also fully considers driving smoothness and safety.

[0124] Optionally, in the vehicle navigation method, determining the fourth cost function includes the following steps:

[0125] Determine a first vector based on a first smooth point and a second smooth point, wherein the first smooth point is any point among a plurality of smooth points, and the first smooth point is adjacent to the second smooth point;

[0126] determining a second vector based on a second smooth point and a third smooth point, wherein the second smooth point is adjacent to the third smooth point;

[0127] determining a vector sum of the first vector and the second vector;

[0128] A fourth cost function is determined based on the product of the vector sum and the fourth weight.

[0129] In the embodiment of the present invention, the first vector may be understood as a vector pointing from the first smooth point to the second smooth point, including direction change and displacement information from the first smooth point to the second smooth point.

[0130] The second vector can be understood as a vector pointing from the second smooth point to the third smooth point, including direction change and displacement information from the second smooth point to the third smooth point.

[0131] The fourth weight can be understood as a pre-set parameter that adjusts the influence of vector continuity and path curvature. For example, the fourth weight can be denoted by X. Increasing the fourth weight X will cause the optimization result to be more inclined to maintain vector continuity and path smoothness, reducing sharp turns, while decreasing the fourth weight X allows for greater curvature changes, resulting in a more tortuous path.

[0132] Determining the vector sum of the first vector and the second vector can be understood as adding the first vector and the second vector to obtain the vector sum, thereby evaluating the directional continuity of the path between any two points, ensuring that the path does not have sharp angle changes, and improving driving smoothness and safety.

[0133] Determining the fourth cost function based on the product of the vector sum and the fourth weight can be understood as multiplying the vector sum and the fourth weight to obtain the fourth cost function. For example, the fourth cost function can be recorded as Cost4, Cost4 = ∑(x i-1 +x i+1 -2x i ) 2 +(y i-1 +y i+1 -2y i ) 2 *X. The fourth cost function ensures the curvature continuity of the path within a local area by quantifying the relationship between the vector sum and the path smoothness. The calculation of the fourth cost function is based on the magnitude and direction of the vector sum and a preset fourth weight X, which is used to adjust the relative importance of curvature changes in path optimization.

[0134] In an embodiment of the present invention, the first vector and the second vector between adjacent smooth points are calculated to obtain the vector sum of the first vector and the second vector, and the vector sum is multiplied by the fourth weight to obtain a fourth cost function. The fourth cost function ensures that the algorithm not only focuses on immediate path adjustments to cope with environmental changes, but also strictly controls the abnormal growth of path curvature, avoiding unnecessary sharp turns, thereby significantly improving vehicle driving stability and passenger comfort.

[0135] Optionally, the vehicle navigation method further includes the following execution steps:

[0136] The first weight is adjusted according to a first filtering requirement to make the geometric shape of the smoothed guide line approach the geometric shape of the guide line of the previous frame, wherein the first filtering requirement is used to reduce the filtering intensity of the guide line of the current frame.

[0137] In an embodiment of the present invention, the first filtering requirement can be understood as the degree and method of filtering the guide line of the current frame. The first filtering requirement is used to instruct the optimization algorithm how to adjust the first weight W in order to control the extent to which the smooth guide line should be close to the geometric shape of the guide line of the previous frame.

[0138] Adjusting the first weight W based on the first filtering requirement ensures that the smoothed guide line's geometry approaches that of the previous frame's guide line. The magnitude of the first weight W measures the influence of the previous frame's guide line in the optimization process. The magnitude of the first weight W directly influences the weight of the first cost function in the objective function, thereby affecting the degree of similarity between the smoothed guide line and the previous frame's guide line.

[0139] In an embodiment of the present invention, the first filtering requirement is a strategy adjustment. By modifying the first weight W, the system can flexibly adjust the degree of dependence of the optimized smooth guide line on the guide line of the previous frame according to actual needs to achieve the desired filtering effect and path continuity level.

[0140] Optionally, the vehicle navigation method further includes the following execution steps:

[0141] The second weight is adjusted according to a second filtering requirement to make the geometry of the smoothed guide line approach the geometry of the guide line of the current frame, wherein the second filtering requirement is used to increase the filtering strength of the guide line of the current frame.

[0142] In an embodiment of the present invention, the second filtering requirement can be understood as a strategic requirement proposed in the path planning optimization algorithm in order to make the geometry of the smooth guide line closer to the geometry of the current frame guide line. The second filtering requirement is used to adjust the algorithm's sensitivity and dependence on the current frame information.

[0143] The second weight is adjusted based on the second filtering requirement to bring the smoothed guideline's geometry closer to that of the current frame's guideline. Increasing the second weight, Z, directly affects the smoothed guideline's geometric proximity to the current frame's guideline, making the planned path more adaptable to the ever-changing driving environment. When the second weight, Z, is increased, the smoothed guideline calculation prioritizes minimizing deviations from the current frame's guideline, enabling the algorithm to more sensitively detect and respond to subtle changes in the driving environment, ensuring the vehicle can quickly adjust to a route appropriate to current conditions.

[0144] In the embodiment of the present invention, the size of the second weight Z is adjusted according to the second filtering requirement in order to better integrate and utilize the real-time data of the current frame in path planning, so as to improve the immediate responsiveness and accuracy of path planning and ensure that the vehicle can make safe, efficient and stable driving decisions on complex and changeable roads.

[0145] Figure 3 is a schematic diagram of an optional smoothed guide line according to an embodiment of the present invention, such as Figure 3As shown, first, the points on the guide line of the current frame are preprocessed and projected onto the path formed by the guide line of the previous frame. Through this matching, a correspondence between the point set of the current frame and the point set of the previous frame can be established, which helps the algorithm understand the spatial changes and continuity requirements between the two frames. Next, the optimization problem is established using the point set of the current frame and the point set of the previous frame. Based on the constraints, a smooth point set is obtained by minimizing the objective cost function. Based on the smooth point set, a smooth guide line is constructed. Finally, the smooth guide line is applied to the path planning and navigation of the autonomous vehicle to ensure that the optimized smooth guide line can bring better stability and ride comfort in actual driving.

[0146] 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, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0147] According to an embodiment of the present invention, an embodiment of a vehicle navigation device is provided. It should be noted that the device can be used to execute the above-mentioned vehicle navigation method.

[0148] Figure 4 is a schematic diagram of an optional vehicle navigation device according to an embodiment of the present invention, such as Figure 4 As shown, the vehicle navigation device 400 includes: an acquisition module 401, which is used to acquire the previous frame guide line and the current frame guide line of the vehicle based on the vehicle navigation information, wherein the vehicle navigation information is used to provide the vehicle's driving path, the current frame guide line is used to guide the vehicle's driving path at the current moment, and the previous frame guide line is used to guide the vehicle's driving path at the previous moment before the current moment; a processing module 402, which is used to smooth the current frame guide line based on the previous frame guide line to obtain a smooth guide line; and a navigation module 403, which is used to navigate the vehicle based on the smooth guide line.

[0149] Optionally, the processing module 402 is also used to obtain a current frame point set of the current frame guide line; project the current frame point set onto the previous frame guide line to obtain the previous frame point set, wherein the current frame point set includes multiple guide points on the current frame guide line; determine a smooth point set based on the current frame point set and the previous frame point set; and generate a smooth guide line based on the smooth point set.

[0150] Optionally, the processing module 402 is also used to add the first cost function, the second cost function, the third cost function and the fourth cost function to obtain a target cost function; determine the constraint distance based on the first point and the second point, wherein the first point is used to represent any point in the current frame point set, the second point is used to represent the point corresponding to the first point in the previous frame point set, and the constraint distance is used to represent the straight-line distance between the first point and the second point; determine the smooth point set based on the target cost function and the constraint distance.

[0151] Optionally, the processing module 402 is further used to determine multiple smooth points based on the target cost function and the constraint distance, wherein the straight-line distance between any one of the multiple smooth points and the first point does not exceed the constraint distance, and the straight-line distance between any one of the multiple smooth points and the second point does not exceed the constraint distance; and determine a smooth point set based on the multiple smooth points.

[0152] Optionally, the processing module 402 is also used to obtain a first coordinate difference based on the difference between the horizontal coordinate of any point in the previous frame point set and the horizontal coordinate of the corresponding smooth point; obtain a second coordinate difference based on the difference between the vertical coordinate of any point in the previous frame point set and the vertical coordinate of the corresponding smooth point; determine a first deviation based on the sum of the squares of the first coordinate difference and the second coordinate difference; and determine a first cost function based on the product of the first deviation and the first weight.

[0153] Optionally, the processing module 402 is further used to obtain a third coordinate difference based on the difference between the horizontal coordinate of any point in the current frame point set and the horizontal coordinate of the corresponding smooth point; to obtain a fourth coordinate difference based on the difference between the vertical coordinate of any point in the current frame point set and the vertical coordinate of the corresponding smooth point; to determine the second deviation based on the sum of the squares of the third coordinate difference and the fourth coordinate difference; and to determine the second cost function based on the product of the second deviation and the second weight.

[0154] Optionally, the processing module 402 is further configured to obtain a Euclidean distance based on coordinates of any two adjacent smooth points in the smooth point set; and determine a third cost function based on a product of the Euclidean distance and a third weight.

[0155] Optionally, the processing module 402 is further used to determine a first vector based on a first smooth point and a second smooth point, wherein the first smooth point is any point among a plurality of smooth points and the first smooth point is adjacent to the second smooth point; determine a second vector based on the second smooth point and a third smooth point, wherein the second smooth point is adjacent to the third smooth point; determine the vector sum of the first vector and the second vector; and determine a fourth cost function based on the product of the vector sum and a fourth weight.

[0156] Optionally, the processing module 402 is further configured to adjust the first weight according to a first filtering requirement so that the geometry of the smoothed guide line approaches the geometry of the guide line of the previous frame, wherein the first filtering requirement is configured to reduce the filtering intensity of the guide line of the current frame.

[0157] Optionally, the processing module 402 is further configured to adjust the second weight according to a second filtering requirement so that the geometry of the smoothed guide line approaches the geometry of the guide line of the current frame, wherein the second filtering requirement is configured to increase filtering strength for the guide line of the current frame.

[0158] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the vehicle navigation method in various embodiments of the present invention when running on a computer or processor.

[0159] According to another aspect of an embodiment of the present invention, an electronic device is provided, including a memory and a processor. The memory stores a computer program, and the processor is configured to run the computer program to execute the vehicle navigation method in various embodiments of the present invention.

[0160] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the vehicle navigation method in each embodiment of the present invention is implemented.

[0161] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0162] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0163] Units described as separate components may or may not be physically separate, and 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 may be selected to achieve the purpose of the present embodiment according to actual needs.

[0164] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0165] If the integrated unit is implemented in the form of 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, 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. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0166] The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A vehicle navigation method, characterized in that: include: Acquiring a previous frame guide line and a current frame guide line of the vehicle based on vehicle navigation information, wherein the vehicle navigation information is used to provide a driving path of the vehicle, the current frame guide line is used to guide the driving path of the vehicle at the current moment, and the previous frame guide line is used to guide the driving path of the vehicle at the moment before the current moment; Smoothing the guide line of the current frame based on the guide line of the previous frame to obtain a smooth guide line; The vehicle is navigated based on the smooth guide line.

2. The method according to claim 1, characterized in that The smoothing of the guide line of the current frame based on the guide line of the previous frame to obtain a smooth guide line includes: Obtaining a current frame point set of the current frame guide line; Projecting the current frame point set onto the previous frame guide line to obtain a previous frame point set, wherein the current frame point set includes a plurality of guide points on the current frame guide line; Determine a smoothing point set according to the current frame point set and the previous frame point set; The smooth guide line is generated based on the smooth point set.

3. The method according to claim 2, characterized in that The determining of a smoothing point set according to the current frame point set and the previous frame point set includes: Add the first cost function, the second cost function, the third cost function and the fourth cost function to obtain a target cost function; Determining a constrained distance based on a first point and a second point, wherein the first point is used to represent any point in the current frame point set, the second point is used to represent a point in the previous frame point set corresponding to the first point, and the constrained distance is used to represent a straight-line distance between the first point and the second point; The smooth point set is determined based on the target cost function and the constraint distance.

4. The method according to claim 3, characterized in that The determining of the smooth point set based on the target cost function and the constraint distance includes: determining a plurality of smooth points based on the target cost function and the constraint distance, wherein a straight-line distance between any one of the plurality of smooth points and the first point does not exceed the constraint distance, and a straight-line distance between any one of the plurality of smooth points and the second point does not exceed the constraint distance; The smooth point set is determined based on the plurality of smooth points.

5. The method according to claim 3, characterized in that The method further comprises: Obtaining a first coordinate difference value based on the difference between the horizontal coordinate of any point in the previous frame point set and the horizontal coordinate of the corresponding smooth point; Obtaining a second coordinate difference value based on the difference between the ordinate of any point in the previous frame point set and the ordinate of the corresponding smooth point; determining a first deviation according to a sum of squares of the first coordinate difference and the second coordinate difference; The first cost function is determined based on a product of the first deviation and a first weight.

6. The method according to claim 3, characterized in that The method further comprises: Obtaining a third coordinate difference value based on the difference between the abscissa of any point in the current frame point set and the abscissa of the corresponding smooth point; Obtaining a fourth coordinate difference value based on the difference between the ordinate of any point in the current frame point set and the ordinate of the corresponding smooth point; determining a second deviation according to the sum of squares of the third coordinate difference and the fourth coordinate difference; The second cost function is determined based on a product of the second deviation and a second weight.

7. The method according to claim 3, characterized in that The method further comprises: Obtaining a Euclidean distance based on coordinates of any two adjacent smooth points in the smooth point set; The third cost function is determined based on the product of the Euclidean distance length and the third weight.

8. The method according to any one of claims 3 to 7, characterized in that The method further comprises: Determine a first vector based on a first smooth point and a second smooth point, wherein the first smooth point is any point among the plurality of smooth points, and the first smooth point is adjacent to the second smooth point; determining a second vector based on the second smooth point and a third smooth point, wherein the second smooth point is adjacent to the third smooth point; determining a vector sum of the first vector and the second vector; The fourth cost function is determined based on a product of the vector sum and a fourth weight.

9. The method according to claim 5, characterized in that The method further comprises: The first weight is adjusted according to a first filtering requirement to make the geometry of the smoothed guide line approach the geometry of the guide line of the previous frame, wherein the first filtering requirement is used to reduce the filtering intensity of the guide line of the current frame.

10. The method according to claim 6, characterized in that The method further comprises: The second weight is adjusted according to a second filtering requirement to make the geometry of the smooth guide line approach the geometry of the current frame guide line, wherein the second filtering requirement is used to increase the filtering strength of the current frame guide line.

11. A vehicle navigation device, characterized in that: The device comprises: an acquisition module, the acquisition module being configured to acquire a previous frame guide line and a current frame guide line of the vehicle based on vehicle navigation information, wherein the vehicle navigation information is configured to provide a driving path of the vehicle, the current frame guide line is configured to guide the driving path of the vehicle at the current moment, and the previous frame guide line is configured to guide the driving path of the vehicle at the moment before the current moment; a processing module, configured to smooth the guide line of the current frame based on the guide line of the previous frame to obtain a smooth guide line; A navigation module is configured to navigate the vehicle based on the smooth guide line.

12. A computer-readable storage medium, characterized in that The storage medium stores a computer program, wherein the computer program is configured to execute the vehicle navigation method according to any one of claims 1 to 10 when running on a computer or a processor.

13. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the vehicle navigation method according to any one of claims 1 to 10.

14. A computer program product, characterized in that The invention comprises a computer program, which implements the vehicle navigation method according to any one of claims 1 to 10 when being executed by a processor.

Images