A method and apparatus for smoothing path curvature based on geometric topology

Abstract

The present disclosure relates to a geometric topology-based path curvature smoothing method and device, electronic equipment and storage medium. The method comprises: obtaining a path point set of a preset recording path, and performing low-smoothness fitting based on a polynomial to generate a path point set of a fitted path containing uniformly spaced path points; generating a connected region based on a preset radius from the path point set of the fitted path, and performing rasterization processing on the connected region in a preset map based on a preset interval to generate a rasterized connected region; performing path solving on the rasterized connected region to generate a path to be smoothed, and performing smoothing processing on the path to be smoothed based on a preset smoothing algorithm according to a preset minimum turning radius of a vehicle to generate a driving path. The present disclosure can smooth a path with large curvature fluctuations without being affected by problems such as point overlap, unevenness, omission and noise in the original path point set, and has higher universality.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of unmanned driving, and in particular, to a path curvature smoothing method and device based on geometric topology, an electronic device, and a computer readable storage medium. BACKGROUND

[0002] An unmanned mine truck is an important development direction of intelligent mine. The vehicle control module of the unmanned system of the mine truck needs to control the automatic steering to make the mine truck travel along a fixed path. The input global path of the unmanned system is generally calculated by a planning algorithm or recorded by the actual driving path of human driving. Compared with the flexibility of the algorithm to calculate the global path, the method of recording the path in advance can improve the safety of vehicle operation. In the mine scene, the range of the unmanned vehicle team is fixed, so the method of recording the path is more suitable in actual application. The main problem faced by path recording is that the path curvature fluctuates greatly. During the recording process, the path collection vehicle will stop, reverse, and turn around, and the recording tool will deviate from the GPS and the data will drop frames. The above phenomena will cause the collected path point set to be uneven, overlapping, or missing, resulting in a large path curvature fluctuation.

[0003] In the scenario of recording a path with large curvature, the existing path smoothing method cannot obtain a good processing result. The main reasons for the large curvature are path point overlap, unevenness, missing, and noise. The existing methods mainly include fitting, interpolation, and energy function-based methods. When using the interpolation method, it is necessary to pass through the existing path points, so it cannot handle paths with missing points and noise. When using the energy function-based method, all point sets need to satisfy the minimum function value, so it cannot handle uneven and noisy paths. When using the fitting method, it cannot handle paths with many noise points because it cannot use appropriate smoothness for different parts of the path.

[0004] The robot path smoothing method and system based on a fifth-order Bezier curve in the prior art obtains grid map information and a polyline path connecting a starting point and a target point, establishes a convex optimization model based on a fifth-order Bezier curve, and designs a quadratic programming algorithm to quickly optimize to obtain a smooth path. However, this construction method of the Bezier curve breaks the coupling influence of the horizontal coordinate and the vertical coordinate on the curvature smoothing and cannot explain the optimality of the smoothness of the generated path. The mobile robot path smoothing method connects adjacent nodes of the initial path and compares the slope of the adjacent line to identify irrelevant points and inflection points. Then, the inflection points are connected and the irrelevant points are sequentially selected and inserted into the inflection point path. Finally, the inflection point smoothing algorithm is used to smooth the inserted path. However, this method is based on the premise that the straight line region connected by all path points is feasible. If the path is broken, the straight line region connected by the path points at both ends of the break may not be drivable, or the curvature at the inflection point may not meet the minimum turning radius of the vehicle.

[0005] Therefore, one or more methods are needed to address the above problems.

[0006] It should be noted that the information disclosed in the above BACKGROUND section is only for the purpose of strengthening the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] The purpose of the present disclosure is to provide a geometric topology-based path curvature smoothing method, device, electronic equipment and computer readable storage medium, thereby at least to some extent overcoming one or more problems caused by the limitations and defects of the related art.

[0008] According to one aspect of the present disclosure, a geometric topology-based path curvature smoothing method is provided, comprising:

[0009] Obtaining a path point set of a preset recorded path, and fitting the path point set of the preset recorded path based on a polynomial to generate a path point set of a fitted path containing uniformly spaced path points;

[0010] Generating a connected region based on a preset radius from the path point set of the fitted path, and rasterizing the connected region based on a preset interval in a preset map to generate a rasterized connected region;

[0011] Solving a path for the rasterized connected region to generate a path to be smoothed, and smoothing the path to be smoothed based on a preset smoothing algorithm according to a preset minimum turning radius of a vehicle to generate a driving path.

[0012] In an exemplary embodiment of the present disclosure, the method further comprises:

[0013] Obtaining a path point set of a preset recorded path, and segmenting the path point set of the preset recorded path according to a preset rule;

[0014] Fitting the segmented path point set of the preset recorded path based on a polynomial:

[0015] x(t) = f i (t) = a i0 +a i1 t+a i2 t 2 +a i3 t 3 +a i4 t 4 +a i5 t 5

[0016] y(t) = gi (t) = b i0 +b i1 t+b i2 t 2 +b i3 t 3 +b i4 t 4 +b i5 t 5

[0017] The fitting process is performed to take the square sum of the third derivative of x(t) and y(t) as the optimization objective function:

[0018] The path point set of the fitting path is generated;

[0019] Wherein, a is a coefficient, t is time, f(t) and g(t) are the functional relationship between t and x and y, and n is the polynomial power.

[0020] In an exemplary embodiment of the present disclosure, the constraint condition for fitting the path point set of the preset recording path based on the polynomial in the method is:

[0021] The first derivative, the second derivative, and the third derivative of the connection are continuous;

[0022] The difference between the path point coordinates in the path point set of the preset recording path and the path point coordinates in the path point set of the fitting path processed based on the fitting polynomial is less than a preset interval.

[0023] In an exemplary embodiment of the present disclosure, the method further comprises:

[0024] The path point set of the fitting path is based on a preset radius, and the path points in the path point set of the fitting path are taken as the center to perform the Voronoi processing to generate a connected region;

[0025] And the connected region is rasterized based on a preset interval in a preset map to generate a rasterized connected region.

[0026] In an exemplary embodiment of the present disclosure, the method further comprises:

[0027] The preset map is rasterized based on a preset interval M, and in the preset map of the rasterization, the path point set P k of all k path points in the path point set of the fitting path is:

[0028] {P1, P2, P3,..., P k}

[0029] P kgenerating a circular region Q with a preset radius r k is:

[0030] {Q1, Q2, Q3,... Q k};

[0031] marking a grid where the circular region Q k is located as a connected grid, and counting all connected grids to generate a rasterized connected region.

[0032] In an exemplary embodiment of the present disclosure, the method further comprises:

[0033] solving a path for the rasterized connected region based on an A* algorithm to generate a path to be smoothed;

[0034] performing smoothing processing on the path to be smoothed based on a gradient descent algorithm according to a preset minimum turning radius of a vehicle to generate a driving path.

[0035] In an exemplary embodiment of the present disclosure, the method further comprises:

[0036] After performing smoothing processing on the path to be smoothed based on a gradient descent algorithm according to a preset minimum turning radius of a vehicle, performing smoothing processing on curvature values between adjacent points in a path point set to be smoothed based on an energy function to generate a driving path.

[0037] In an aspect of the present disclosure, a path curvature smoothing device based on geometric topology is provided, comprising:

[0038] a path fitting module configured to obtain a path point set of a preset recorded path, and perform low-smoothness fitting on the path point set of the preset recorded path based on a polynomial to generate a path point set of a fitted path containing uniformly spaced path points;

[0039] a connected region generation module configured to generate a connected region based on a preset radius from the path point set of the fitted path, and perform rasterization processing on the connected region in a preset map based on a preset interval to generate a rasterized connected region;

[0040] a smoothing processing module configured to solve a path for the rasterized connected region to generate a path to be smoothed, and perform smoothing processing on the path to be smoothed based on a preset smoothing algorithm according to a preset minimum turning radius of a vehicle to generate a driving path.

[0041] In an aspect of the present disclosure, an electronic device is provided, comprising:

[0042] a processor; and

[0043] A memory having computer readable instructions stored thereon, the computer readable instructions, when executed by the processor, implement the method according to any one of the preceding method embodiments.

[0044] In one aspect of the present disclosure, a computer readable storage medium is provided, having a computer program stored thereon, the computer program, when executed by a processor, implements the method according to any one of the preceding method embodiments.

[0045] One of the exemplary embodiments of the present disclosure is a geometric topology-based path curvature smoothing method, wherein the method comprises: obtaining a path point set of a preset recording path, and performing low-smoothness fitting based on a polynomial to generate a path point set of a fitted path containing uniformly spaced path points; generating a connected region based on a preset radius from the path point set of the fitted path, and performing rasterization processing on the connected region based on a preset interval in a preset map to generate a rasterized connected region; performing path solving on the rasterized connected region to generate a path to be smoothed, and performing smoothing processing on the path to be smoothed based on a preset smoothing algorithm according to a preset minimum turning radius of a vehicle to generate a driving path. The present disclosure has higher universality by performing smoothing processing on a path with large curvature fluctuation and is not affected by problems such as point overlap, non-uniformity, omission, and noise in the original path point set.

[0046] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0047] The above and other features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0048] Figure 1 A flowchart of a geometric topology-based path curvature smoothing method according to an exemplary embodiment of the present disclosure is shown;

[0049] Figures 2A-2B An application scenario schematic diagram of a geometric topology-based path curvature smoothing method according to an exemplary embodiment of the present disclosure is shown;

[0050] Figure 3 An application scenario schematic diagram of a geometric topology-based path curvature smoothing method according to an exemplary embodiment of the present disclosure is shown;

[0051] Figure 4 A schematic block diagram of a geometric topology-based path curvature smoothing device according to an exemplary embodiment of the present disclosure is shown;

[0052] Figure 5 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown schematically; and

[0053] Figure 6 A schematic diagram of a computer-readable storage medium according to an example embodiment of the present disclosure is shown schematically. DETAILED DESCRIPTION

[0054] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments, however, can be implemented in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example embodiments to those skilled in the art. Like reference numerals refer to like elements throughout the several views.

[0055] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the

[0056] The block diagrams in the drawings show only the functionality of the architecture and do not imply any particular physical structure or organization of the components. For example, the functional entities can be implemented in software, hardware, or a combination thereof. The functional entities can be implemented in one or more software modules or hardware units, or a combination thereof, in different networks and / or processor devices and / or microcontroller devices.

[0057] In the present example embodiment, firstly, a path curvature smoothing method based on geometric topology is provided; referring to FIG. 1, the path curvature smoothing method based on geometric topology can include the following steps: Figure 1

[0058] In step S110, a path point set of a preset recording path is acquired, and the path point set of the preset recording path is fitted based on a polynomial with low smoothness to generate a path point set of a fitted path containing uniformly spaced path points;

[0059] In step S120, a connected region is generated based on a preset radius from the path point set of the fitted path, and the connected region is rasterized based on a preset interval in a preset map to generate a rasterized connected region;

[0060] ​In step S130, path solving is performed on the rasterized connected region to generate a to-be-smoothed path, and the to-be-smoothed path is smoothed based on a preset smoothing algorithm according to a preset minimum turning radius of a vehicle to generate a driving path.

[0061] In one of the example embodiments of the present disclosure, a path curvature smoothing method based on geometric topology is provided, which includes: obtaining a path point set of a preset recorded path, and performing low-smoothness fitting on the path point set based on a polynomial to generate a path point set of a fitted path containing uniformly spaced path points; generating a connected region based on a preset radius from the path point set of the fitted path, and performing rasterization on the connected region in a preset map based on a preset interval to generate a rasterized connected region; performing path solving on the rasterized connected region to generate a to-be-smoothed path, and smoothing the to-be-smoothed path based on a preset smoothing algorithm according to a preset minimum turning radius of a vehicle to generate a driving path. The present disclosure can smooth a path with large curvature fluctuations without being affected by problems such as point overlap, non-uniformity, omission, and noise in the original path point set, and has higher universality.

[0062] In the following, a path curvature smoothing method based on geometric topology in the example embodiment will be further described.

[0063] In step S110, a path point set of a preset recorded path can be obtained, and the path point set of the preset recorded path is fitted based on a polynomial to generate a path point set of a fitted path containing uniformly spaced path points.

[0064] In the example embodiment, the method further includes:

[0065] A path point set of a preset recorded path is obtained, and the path point set of the preset recorded path is segmented according to a preset rule;

[0066] The segmented path point set of the preset recorded path is fitted based on a polynomial:

[0067] x(t)=f i (t)=a i0 +a i1 t+a i2 t 2 +a i3 t 3 +a i4 t 4 +a i5 t 5

[0068] y(t)=g i (t)=b i0 +b i1 t+bi2 t 2 +b i3 t 3 +b i4 t 4 +b i5 t 5

[0069] The fitting process is performed to take the square sum of the third derivative of x(t) and y(t) as the optimization objective function:

[0070] The path point set of the fitted path is generated;

[0071] Wherein, a is a coefficient, t is time, f(t) and g(t) are the functional relationship between t and x and y, and n is the polynomial power.

[0072] In the embodiment of the present example, the constraint condition for fitting the path point set of the preset recording path based on the polynomial is:

[0073] The first derivative, the second derivative, and the third derivative of the connection are continuous;

[0074] The difference between the path point coordinates in the path point set of the preset recording path and the path point coordinates in the path point set of the fitted path based on the fitted polynomial is less than the preset interval.

[0075] In the above constraint condition, the smaller the threshold value is, the more similar the original trajectory is, so the threshold value should be less than or equal to the expected path point interval M to ensure the similarity of the fitted path.

[0076] In the embodiment of the present example, the input path point set is fitted by a conventional path fitting method with a low smoothness to solve the point overlap and obtain a uniform path point set. The value of the smoothness should be less than or equal to the interval of the final path point.

[0077] The path point of the recording path is missing and has more noise, resulting in large curvature fluctuation. The fitting method uses the existing polynomial fitting, which can obtain a path with high similarity to the original path and uniform point set distribution after processing the input path. However, it can be seen that the fitted path still has large curvature fluctuation.

[0078] In step S120, the path point set of the fitted path can be used to generate a connected region based on a preset radius, and the connected region can be rasterized based on a preset interval in a preset map to generate a rasterized connected region.

[0079] In the embodiment of the present example, the method further comprises:

[0080] The set of path points of the fitted path is topologically processed based on a preset radius, with the path points in the set of path points of the fitted path as the center to generate a connected region.

[0081] The connected regions are then rasterized in a preset map at preset intervals to generate rasterized connected regions.

[0082] In this example embodiment, the method further includes:

[0083] The preset map is rasterized based on a preset interval M. In the rasterized preset map, the path point set P of all k path points in the path point set of the fitted path is... k for:

[0084] (P1, P2, P3...P) k}

[0085] For P k Generate a circular region Q with a preset radius r. k for:

[0086] {Q1, Q2, Q3......Q k};

[0087] The circular region Q k The grid cell in question is marked as a connected grid cell. All connected grid cells are counted to generate a rasterized connected region.

[0088] In this example embodiment, the map is first rasterized into a grid with expected pathpoint intervals M, the input pathpoints are topologically converted into connected regions, and then the regions are rasterized into drivable areas, which become the input map for subsequent path planning algorithms.

[0089] In path topology, circles are generated with each path point as its center and the road width L as its diameter. All intersecting circles then form the final connected region. Specifically, assuming path points A and B, and half the road width r, the reachable region is as follows: Figure 2A As shown, the grid width is the expected path point interval M.

[0090] In the above diagram, the region Q1 centered at point A(x1, y1) and the region Q2 centered at point B(x2, y2) have no intersection, therefore they are not connected. Thus, in step S110, the path is fitted such that the interval between path points is less than or equal to M. Since M is much smaller than the road width L, the circular regions formed by the resulting point sets must intersect, as shown below. Figure 2B As shown. In summary, since the circles at each adjacent path point must intersect, the complete region formed by all the circles is connected.

[0091] Suppose there is a path with k points, and the distance between the path points after fitting is l, then the path point set can be expressed as follows, where P k is a two-tuple (x k , y k ), x k , y k represent the horizontal and vertical coordinates of P k .

[0092] {P1, P2, P3,..., P k}

[0093] After topological processing of the continuous path generated by fitting, let Q k be <P k , r>, where r represents the drivable area radius with P k as the center, the value of r is determined by the user according to the application scenario (generally half of the road width), and r needs to satisfy The connected road generated after topological processing can be expressed as follows.

[0094] {Q1, Q2, Q3,..., Q k}

[0095] The local curvature of the road map after rasterization and topological processing of the complete path is shown in Figure 3 , where the lines are path points, and the squares are connected regions formed by the intersection of the grid of the topological circle of the path points.

[0096] In step S130, the rasterized connected region can be solved by path, and the to-be-smoothed path is generated. The to-be-smoothed path is smoothed based on a preset smoothing algorithm according to a preset minimum turning radius of the vehicle to generate a driving path.

[0097] In the embodiment of the present example, the method further comprises:

[0098] solving the rasterized connected region based on the A* algorithm to generate a to-be-smoothed path;

[0099] The to-be-smoothed path is smoothed based on the gradient descent algorithm according to the preset minimum turning radius of the vehicle to generate a driving path.

[0100] In the embodiment of the present example, the method further comprises:

[0101] After smoothing the to-be-smoothed path based on the gradient descent algorithm according to the preset minimum turning radius of the vehicle, the to-be-smoothed path is smoothed based on the energy function to smooth the curvature value between adjacent points in the to-be-smoothed path point set to generate a driving path.

[0102] In the embodiment of the present example, the path solving uses a currently mature path solving algorithm such as A* algorithm, and the path curvature smoothing part is as shown in the following figure, including the following steps: grid connected region path solving, gradient descent method smoothing path, and energy function based path smoothing.

[0103] The gradient descent method smoothing path mainly realizes that the overall path solved by the currently mature gradient descent algorithm is located in the middle of the road as much as possible to ensure the similarity with the original path, and the gradient descent method can ensure that the maximum curvature of the path point meets the constraint of the minimum turning radius of the vehicle.

[0104] The above gradient descent method processes the solved path, which can only ensure that the maximum curvature of the path is less than the minimum turning radius constraint of the vehicle, and therefore further smoothing is required. The energy function based path smoothing mainly processes the above path by using the currently existing energy function based path curvature smoothing method, which ensures that the maximum curvature value of the path point set meets the minimum turning radius constraint, and makes the curvature value between adjacent points smooth.

[0105] In the embodiment of the present example, low smoothing degree fitting is used to make the path point interval uniform and meet the high similarity with the original path. The grid connected region and the topological path point set are used to obtain a grid map to re-solve the path. The gradient descent method and the energy function based method are used to smooth the path, which can ensure that the maximum curvature meets the minimum turning radius of the vehicle and the curvature value between points is smooth.

[0106] It should be noted that although the steps of the method in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. In addition or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be divided into multiple steps, etc.

[0107] In addition, in the embodiment of the present example, a path curvature smoothing device based on geometric topology is also provided. Referring to Figure 4 As shown in the figure, the path curvature smoothing device based on geometric topology 400 can include a path fitting module 410, a connected region generation module 420, and a smoothing processing module 430. Wherein:

[0108] The path fitting module 410 is configured to obtain a path point set of a preset recorded path, and perform low smoothing degree fitting on the path point set of the preset recorded path based on a polynomial to generate a path point set of a fitted path containing uniformly spaced path points.

[0109] The connected region generation module 420 is used to generate a connected region from the set of path points of the fitted path based on a preset radius, and to perform rasterization processing on the connected region in a preset map based on a preset interval to generate a rasterized connected region.

[0110] The smoothing processing module 430 is used to solve the path of the gridded connected region, generate the path to be smoothed, and smooth the path to be smoothed according to the preset minimum turning radius of the vehicle based on the preset smoothing algorithm to generate the driving path.

[0111] The specific details of each of the above-mentioned path curvature smoothing device modules based on geometric topology have been described in detail in the corresponding path curvature smoothing method based on geometric topology, so they will not be repeated here.

[0112] It should be noted that although several modules or units of a path curvature smoothing device 400 based on geometric topology have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0113] Furthermore, in an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0114] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented as entirely hardware embodiments, entirely software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, collectively referred to herein as “circuit,” “module,” or “system.”

[0115] The following reference Figure 5 To describe an electronic device 500 according to such an embodiment of the present invention. Figure 5 The electronic device 500 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0116] like Figure 5 As shown, the electronic device 500 is manifested in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: at least one processing unit 510, at least one storage unit 520, a bus 530 connecting different system components (including storage unit 520 and processing unit 510), and a display unit 540.

[0117] The storage unit stores program codes which can be executed by the processing unit 510, so that the processing unit 510 performs the steps described in the above "Exemplary Method" section according to various exemplary embodiments of the present application. For example, the processing unit 510 can perform the steps S110 to S130 as shown in the above FIG. 1. Figure 1

[0118] The storage unit 520 can include a readable medium in the form of volatile storage unit, such as a random access memory (RAM) 5201 and / or a cache memory 5202, and further include a read-only memory (ROM) 5203.

[0119] The storage unit 520 can further include a program / utility 5204 having a set of program modules 5205 such as an operating system, one or more application programs, other program modules, and program data, each of which can give the electronic device 500 the ability to operate in a networked environment, as each of these examples is known to those skilled in the art, or a combination of some of these examples.

[0120] The bus 550 can represent one or more of several types of bus structures, including a storage unit bus or bus controller, a peripheral bus, a graphics acceleration port, a processing unit bus, or a local bus using any of a variety of bus architectures.

[0121] The electronic device 500 can also communicate with one or more external devices 570 such as a keyboard or pointing device, a Bluetooth device, etc.; other devices that enable a user to interact with the electronic device 500; and / or one or more devices that enable the electronic device 500 to communicate with one or more other computing devices. Such communication can be facilitated by an Input / Output (I / O) interface 550. Still yet, the electronic device 500 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the Internet, through a network adapter 560. As depicted, the network adapter 560 can communicate with the other components of the electronic device 500 through the bus 550. It should be appreciated that although the network adapter 560 is depicted as a single component, the network adapter 560 can comprise two or more components that work together to facilitate communications between the electronic device 500 and one or more other computing devices. It should be appreciated that the electronic device 500 can be a part of a larger system, and that communication can occur via the network adapter 560 in conjunction with one or more other components of that system. Further, it should be appreciated that the bus 550 can be one or more busses, and that the bus 550 can be implemented using any suitable type of architecture, including a bus architecture having any combination of asynchronous, synchronous, wired-or, wireless, or other communication technologies.

[0122] ​Those skilled in the art can easily understand from the above description of the embodiments that the example embodiments described herein can be implemented by software or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a plurality of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0123] In the example embodiments of the present disclosure, a computer readable storage medium is also provided, on which a program product capable of implementing the above-mentioned method of the present disclosure is stored. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes program codes for causing a terminal device to perform the steps described in the above-mentioned “example method” section according to various example embodiments of the present disclosure when the program product is run on the terminal device.

[0124] Reference Figure 6 As shown, a program product 600 for implementing the above-mentioned method according to the embodiments of the present disclosure is described, which can adopt a portable compact disc read-only memory (CD-ROM) and include program codes, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited to this, and in this document, the readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, device or apparatus.

[0125] The program product can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium may, for example, be but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0126] A computer readable signal medium can include a propagated data signal with computer executable code embodied therein. For example, a propagated signal can be an electromagnetic signal, an optical signal, and / or any other suitable type of signal. Such a propagated signal can be in the form of electrical magnetic waves, optical waves, and / or any other suitable type of waves upon which computer executable code is embodied. A suitable medium for storing and / or transmitting computer readable code includes one or more types of random access memory (RAM), magnetic storage, optical storage, and / or any other suitable type of storage.

[0127] Program code embodied on a computer readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0128] Computer readable program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider. The application program code can be downloaded to the user's computing device from an external computing device or server through any type of network, including a local area network, a wide area network, or the Internet using a browser or other applet.

[0129] Furthermore, the above-described figures are only schematic and are non-limiting. It is readily understood that the processes depicted in the figures are not necessarily performed in the order depicted. Further, it is readily understood that the processes can be performed synchronously or asynchronously, and that the processes can be performed in a different order than depicted in the figures.

[0130] Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and practice of the present disclosure. The present application is intended to cover any and all adaptations or variations of the present disclosure having equivalent or similar purpose and effect. It is intended to include what is described in the specification and claims and equivalents thereto. The specification and examples given are intended as illustrative only and are not intended to limit the true scope of the present disclosure.

[0131] It is to be understood that the application is not limited to the precise construction described and as shown in the accompanying drawings, which will be readily apparent to those skilled in the art. The scope of the application is defined only by the claims appended hereto.

Claims

1. A method for smoothing path curvature based on geometric topology, characterized in that, The method comprises: acquiring a path point set of a preset recording path, and performing low-smoothness fitting on the path point set of the preset recording path based on a polynomial to generate a path point set of a fitted path containing uniformly spaced path points; generating a connected region based on a preset radius from the path point set of the fitted path, and performing rasterization processing on the connected region in a preset map based on a preset interval to generate a rasterized connected region; The method further comprises: generating a connected region based on a preset radius from the path point set of the fitted path by taking the path points in the path point set of the fitted path as the center; and performing rasterization processing on the connected region in a preset map based on a preset interval to generate a rasterized connected region; The preset map is rasterized based on a preset interval M. In the rasterized preset map, the path point set P of all k path points in the path point set of the fitted path is... k for: {P1, P2, P3... P k} For P k generating a circular region Q with a preset radius r k is: {Q1,Q2,Q3......Q k}; The circular region Q k The grid where the circular region Q is located is marked as a connected grid, and all connected grids are counted to generate a rasterized connected region. solving a path for the rasterized connected region to generate a path to be smoothed, and performing smoothing processing on the path to be smoothed based on a preset smoothing algorithm according to a preset minimum turning radius of a vehicle to generate a driving path; The method further comprises: acquiring a path point set of a preset recording path, and performing segmentation processing on the path point set of the preset recording path according to a preset rule; performing fitting processing on the segmented path point set of the preset recording path based on a polynomial: x(t) = f i (t) = a i0 + a i1 t + a i2 t 2 + a i3 t 3 + a i4 t 4 + a i5 t 5 y(t) = g i (t) = b i0 + b i1 t + b i2 t 2 + b i3 t 3 + b i4 t 4 + b i5 t 5 taking the square sum of the third-order derivatives of x(t) and y(t) as an optimization objective function: generating a set of path points of a fitted path; where a is a coefficient, t is time, f(t) and g(t) are functional relationships between t and x and y, and n is a polynomial power.

2. The method of claim 1, wherein, The constraint condition for fitting the path point set of the preset recording path based on a polynomial in the method is: the first-order derivative, the second-order derivative, and the third-order derivative at the connection are continuous; the difference between the path point coordinates in the path point set of the preset recording path and the path point coordinates in the path point set of the fitted path obtained by fitting processing based on the fitted polynomial is less than a preset interval.

3. The method of claim 1, wherein, The method further comprises: solving a path for the rasterized connected region based on an A* algorithm to generate a path to be smoothed; performing smoothing processing on the path to be smoothed based on a gradient descent algorithm according to a preset minimum turning radius of a vehicle to generate a driving path.

4. The method of claim 3, wherein, The method further comprises: after performing smoothing processing on the path to be smoothed based on a gradient descent algorithm according to a preset minimum turning radius of a vehicle, performing smoothing processing on the path to be smoothed based on an energy function on the curvature values between adjacent points in the path to be smoothed to generate a driving path.

5. A geometry topology based path curvature smoothing apparatus, characterized by, Based on the method of claim 1, the device comprises: a path fitting module configured to acquire a path point set of a preset recording path, and perform low-smoothness fitting on the path point set of the preset recording path based on a polynomial to generate a path point set of a fitted path containing uniformly spaced path points; a connected region generation module configured to generate a connected region based on a preset radius from the path point set of the fitted path, and perform rasterization processing on the connected region in a preset map based on a preset interval to generate a rasterized connected region; a smoothing processing module configured to solve a path for the rasterized connected region to generate a path to be smoothed, and perform smoothing processing on the path to be smoothed based on a preset smoothing algorithm according to a preset minimum turning radius of a vehicle to generate a driving path.

6. An electronic device, comprising: ​ a processor; and a memory having computer readable instructions stored thereon, the computer readable instructions, when executed by the processor, implement the method according to any one of claims 1 to 4.

7. A computer readable storage medium having stored thereon a computer program, the computer program, when executed by a processor, implementing the method according to any one of claims 1 to 4.

Images