Path generation method and device, computer device, storage medium and program product

Abstract

The application relates to a path generation method and device, computer equipment, a storage medium and a program product. The method comprises the following steps: generating an initial path according to an initial motion state, a target motion state and a preset angle of a target object, updating the initial path and the preset angle based on the initial path in combination with a preset clothoid curve to generate an updated path and an updated angle; in the case that the curvature of the updated path is less than a preset maximum curvature, constructing a target path of the target object according to the updated path and the updated angle; wherein the initial path is composed of two circular arcs with the same radius and opposite directions, and the preset angle is an included angle between a continuous curvature turning curve and a continuous curvature circle; the method increases the constraint condition of the maximum curvature, can obtain a path with the minimum maximum curvature, and improves the rationality of path planning.

Description

Technical Field

[0001] The present application relates to the field of path planning technology, and in particular to a path generation method, apparatus, computer equipment, storage medium, and program product. Background Art

[0002] With the rapid development of artificial intelligence (AI), the demand for autonomous navigation in intelligent devices such as robots, drones, and vehicles is increasing in real-world applications. Path planning, as a core technology for autonomous navigation, has become a research focus. Path planning encompasses both local and global path planning. Local path planning enables real-time obstacle avoidance and deviation correction.

[0003] When planning a local path, existing path planning methods create a maximum curvature that is too large, exceeding the steering limit of the smart device while in motion. This results in the smart device being unable to steer while in motion. Therefore, existing path planning methods produce unreasonable paths for smart devices. Summary of the Invention

[0004] Based on this, it is necessary to provide a path generation method, device, computer equipment, storage medium and program product that can improve the rationality of path planning in response to the above technical problems.

[0005] In a first aspect, the present application provides a path generation method, the method comprising:

[0006] An initial path is generated based on the initial motion state of the target object, the target motion state, and a preset angle; the initial path consists of two circular arcs with the same radius and opposite directions; the preset angle is the angle between the continuous curvature turning curve and the continuous curvature circle; the continuous curvature turning curve consists of a first clothoid curve, a circular arc, and a second clothoid curve; the continuous curvature circle consists of the starting point and end point of the continuous curvature turning curve and the center of the circular arc;

[0007] The initial path and the preset angle are updated based on the initial path in combination with a preset clothoid curve to generate an updated path and an updated angle; the preset clothoid curve is generated based on the initial path;

[0008] When the curvature of the updated path is less than the preset maximum curvature, a target path of the target object is constructed according to the updated path and the updated angle.

[0009] In one embodiment, the initial motion state includes a first coordinate and a first heading angle of the target object at the initial position, and the target motion state includes a second coordinate and a second heading angle of the target object at the target position; generating an initial path according to the initial motion state, the target motion state, and the preset angle of the target object includes:

[0010] Determine the distance between the initial position and the target position based on the first coordinate and the second coordinate;

[0011] An initial path is generated according to the first heading angle, the second heading angle, the distance, and the preset angle.

[0012] In one embodiment, updating the initial path and the preset angle based on the initial path combined with the preset clothoid curve to generate an updated path and an updated angle includes:

[0013] Obtaining a curvature velocity of an initial path, and generating a preset clothoid curve based on the curvature velocity of the initial path, a preset angle, and a preset maximum curvature velocity;

[0014] The preset angle is updated according to the radius of the preset clothoid curve and the radius of the initial path, and the initial path is updated based on the updated angle to generate an updated path.

[0015] In one embodiment, updating a preset angle according to a radius of a preset clothoid curve and a radius of an initial path, and updating the initial path based on the updated angle to generate an updated path includes:

[0016] updating the preset angle according to the relationship between the radius of the preset clothoid curve and the radius of the initial path to generate an updated angle;

[0017] The initial path is updated based on the updated angle to generate an updated path;

[0018] updating the preset clothoid curve according to the updated angle and the updated path to generate an updated clothoid curve;

[0019] Use the updated path as the new initial path, the updated angle as the new preset angle, and the updated spiral curve as the new preset spiral curve, and repeat the steps of generating the updated angle, generating the updated path, and generating the updated spiral curve until the value range corresponding to the updated angle meets the preset range condition.

[0020] In one embodiment, updating the preset angle based on the relationship between the radius of the preset clothoid curve and the radius of the initial path to generate the updated angle includes:

[0021] The preset angle range is updated according to the size relationship between the radius of the preset clothoid curve and the radius of the initial path, the preset angle range, and the preset angle, to generate an updated angle range; the preset angle range is a value range of the preset angle;

[0022] Calculate the updated angle based on the updated angle range.

[0023] In one embodiment, updating the preset clothoid curve according to the updated angle and the updated path to generate an updated clothoid curve includes:

[0024] Determine whether the updated angle range meets the preset range conditions;

[0025] When the updated angle range does not satisfy the preset range condition, the preset clothoid curve is updated according to the updated angle and the updated path to generate an updated clothoid curve.

[0026] In one embodiment, the steps of generating an updated angle, generating an updated path, and generating an updated clothoid curve are executed in a loop until a value range corresponding to the updated angle satisfies a preset range condition, including:

[0027] The steps of generating an updated angle, generating an updated path, and generating an updated clothoid curve are executed cyclically until the updated angle range satisfies a preset range condition.

[0028] In one embodiment, when the curvature of the updated path is less than a preset maximum curvature, constructing a target path of the target object according to the updated path and the updated angle includes:

[0029] When the curvature of the updated path is less than the preset maximum curvature and the curvature speed of the updated path is less than or equal to the preset maximum curvature speed, a target path of the target object is constructed according to the updated path and the updated angle.

[0030] In one embodiment, the method further comprises:

[0031] When the curvature of the updated path is less than the preset maximum curvature and the curvature speed of the updated path is greater than the preset maximum curvature speed, a target path of the target object is constructed according to the updated path and the updated angle range.

[0032] In one embodiment, the method further comprises:

[0033] Construct the global target path of the target object based on the target path of the target object.

[0034] In a second aspect, the present application also provides a path generation device. The device includes:

[0035] A generation module is configured to generate an initial path based on the initial motion state of the target object, the target motion state, and a preset angle; the initial path is composed of two circular arcs having the same radius and in opposite directions; the preset angle is the angle between the continuous curvature turning curve and the continuous curvature circle; the continuous curvature turning curve is composed of a first clothoid curve, a circular arc, and a second clothoid curve; and the continuous curvature circle is composed of the starting point and end point of the continuous curvature turning curve and the center of the circular arc;

[0036] An updating module, configured to update the initial path and the preset angle based on the initial path in combination with a preset clothoid curve, to generate an updated path and an updated angle; the preset clothoid curve is generated based on the initial path;

[0037] The construction module is configured to construct a target path of the target object according to the updated path and the updated angle if the curvature of the updated path is less than a preset maximum curvature.

[0038] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the path generation method in the first aspect when executing the computer program.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the path generation method in the first aspect.

[0040] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the path generation method in the first aspect.

[0041] The above-mentioned path generation method, apparatus, computer device, storage medium and program product generate an initial path based on the initial motion state, target motion state and preset angle of the target object, and update the initial path and preset angle based on the initial path in combination with a preset clothoid curve to generate an updated path and updated angle; then, when the curvature of the updated path is less than the preset maximum curvature, construct a target path of the target object based on the updated path and the updated angle; wherein the initial path is composed of two circular arcs with the same radius and opposite directions to each other, the preset angle is the angle between the continuous curvature turning curve and the continuous curvature circle, and the continuous curvature turning curve is composed of the first clothoid curve. The path generation method provided in the embodiment of the present application adds a constraint condition of maximum curvature when performing path planning, which can avoid the problem that the curvature of the generated path is too large, resulting in the inability of the intelligent device to turn in a moving state, thereby improving the rationality of path planning; in addition, the method can also obtain a path with the minimum maximum curvature, so that the intelligent device can achieve high-speed turning. At the same time, the method can also meet the real-time requirements of path planning, quickly calculate the local path, and improve the movement efficiency of the intelligent device. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A diagram of an application environment of a path generation method in one embodiment;

[0043] Figure 2 Schematic diagram of a flow chart of a path generation method in one embodiment;

[0044] Figure 3 Schematic diagram of the curve structure of the initial path in one embodiment;

[0045] Figure 4 Schematic diagram of the curve structure of a continuous curvature turning curve and a continuous curvature circle in one embodiment;

[0046] Figure 5 Schematic diagram of the curve structure of a dual-continuous curvature turning curve in one embodiment;

[0047] Figure 6 is a flow chart of a path generation method according to another embodiment;

[0048] Figure 7 is a flow chart of a path generation method according to another embodiment;

[0049] Figure 8 is a flow chart of a path generation method according to another embodiment;

[0050] Figure 9 is a flow chart of a path generation method according to another embodiment;

[0051] Figure 10 FIG1 is a schematic diagram showing how the angle μ changes with the curvature speed at a fixed curvature in one embodiment;

[0052] Figure 11 A schematic diagram of a path structure of a global path generated by global path planning in one embodiment;

[0053] Figure 12 is a structural block diagram of a path generating device in one embodiment;

[0054] Figure 13 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0056] First, before specifically introducing the technical solutions of the embodiments of the present disclosure, we will first introduce the technical background or technological evolution context on which the embodiments of the present disclosure are based. Path planning is a key technology for autonomous navigation of intelligent devices such as robots, drones, and vehicles. Taking robots as an example, mobile robots are widely used in various environments, such as indoors, on roads, in grasslands, and in mountains. Movement in these different environments requires path planning to further determine how to control the robot to move along the planned path.

[0057] Path planning methods are usually divided into global path planning and local path planning. The global path planning range is usually more than hundreds of meters and requires obtaining road and obstacle information in the map. Road navigation several kilometers away or parking in a parking lot can be regarded as global path planning; local path planning is usually planning within the range that the robot perception system can perceive. There may be dynamic obstacles or obstacle information that cannot be obtained in advance within the perception range, and there may be path tracking errors caused by the perception system and control system. Therefore, local path planning is required for real-time obstacle avoidance or correction.

[0058] For wheeled mobile robots, the curvature of their paths must be continuous, unless they stop and turn in place. A path composed of clothoids, arcs, and straight lines is a path with continuous curvature. Furthermore, to enable mobile robots to move at higher speeds, a smaller curvature of the planned path is more conducive to high-speed maneuvering. Common local path planning methods, such as polynomial curves, Bezier curves, and clothoid curves, can cause the maximum curvature of the path to be too large, preventing the robot from turning. This problem persists even after replanning.

[0059] For example, in local path planning methods based on polynomials, the path is composed of fifth-order polynomials or higher-order polynomials. This type of method is more complex to calculate the curvature, which is not conducive to optimizing the parts with excessive curvature. In addition, it is difficult to ensure the continuity of the curvature at low orders. Therefore, it is necessary to use a polynomial representation of fifth order or higher. The final path obtained is not the one with the smallest maximum curvature.

[0060] The local path planning method based on the Dubins path or RS (Reeds-Shepp) path uses a path composed of arcs and straight lines to connect the starting point to the target point according to certain conditional rules. The path composed of arcs and straight lines cannot meet the requirements of continuous curvature. In practical applications, it is difficult to track the mobile robot when it has speed, and it cannot meet the requirements of high-speed maneuverability.

[0061] Local path planning based on the clothoid curve, the curvature of the clothoid curve is continuous, but this method cannot provide a path with the minimum maximum curvature, or does not consider the curvature problem, or considers it but only approximates it with a smaller curvature, and does not provide a method to obtain a path with the minimum maximum curvature. In addition, there are many parameters, resulting in excessive calculation and difficulty in real-time calculation.

[0062] Therefore, the present application proposes a path generation method that can provide a path with the minimum maximum curvature to meet the needs of high-speed maneuvering. By using the method of the present application, it is possible to realize the path connection from the starting point to the target point in the local path planning of the plane. The curvature of the path is continuous and the maximum curvature is the minimum under normal circumstances (such as turning and lane changing operations). In addition, this method is a method for quickly calculating the local path, which can meet the real-time requirements of path planning.

[0063] The following describes the technical solutions involved in the embodiments of the present disclosure in conjunction with the scenarios to which the embodiments of the present disclosure are applied.

[0064] Figure 1 FIG. 1 is a schematic diagram of an application environment of a path generation method in an embodiment. Figure 1As shown, the application environment includes a computer device 120. The computer device 120 generates an initial path based on the initial motion state, target motion state, and preset angle of the target object; updates the initial path and preset angle based on the initial path in combination with a preset clothoid curve to generate an updated path and an updated angle; if the curvature of the updated path is less than a preset maximum curvature, constructs a target path for the target object based on the updated path and the updated angle; wherein the initial path is composed of two circular arcs with the same radius and opposite directions; the preset angle is the angle between the continuous curvature steering curve and the continuous curvature circle; the continuous curvature steering curve is composed of a first clothoid curve, an arc, and a second clothoid curve; the continuous curvature circle is composed of the starting point, end point, and center of the arc of the continuous curvature steering curve; the preset clothoid curve is generated based on the initial path.

[0065] Among them, the computer device 120 can be but is not limited to robots, drones, vehicles and other intelligent devices involved in path planning. The computer device 120 can also be a server that is connected to the intelligent device for communication. Specifically, it can be implemented with an independent server or a server cluster composed of multiple servers. It can also be a control device that is connected to the intelligent device for communication, etc. The control device includes but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices.

[0066] In one embodiment, Figure 2 As shown, a path generation method is provided, which is described by taking the method applied to the above-mentioned computer device as an example, and includes the following steps:

[0067] Step 201 : generating an initial path according to the initial motion state of the target object, the target motion state, and a preset angle.

[0068] Among them, the target object is the computer device, the initial motion state of the target object can be the motion state of the target object at the current position, and the target motion state of the target object can be the motion state of the target position; optionally, the initial motion state of the target object can also be the motion state of the target object at the starting position of a certain path, and the target motion state of the target object can be the motion state at the end position of the certain path.

[0069] In addition, the initial path in this embodiment can be a path composed of two arcs with the same radius and in opposite directions, which can be called a two-arc (Arc-Arc, abbreviated as AA) path, such as Figure 3 As shown, the center O1 of the first arc, the center O2 of the second arc, and the intersection C of the first arc and the second arc in the initial path may not be on the same straight line.

[0070] Furthermore, the preset angle is the angle μ between the continuous curvature turning curve and the continuous curvature circle, such as Figure 4 As shown, the continuous curvature turn (CC Turn) curve consists of a first clothoid curve, a circular arc, and a second clothoid curve. Figure 3 The initial curvature of the thick curve is 0, the curvature increases linearly to a fixed curvature and then remains constant, and finally the curvature decreases linearly until it reaches 0; the continuous curvature circle (CCCircle) is composed of the starting point, end point and center of the arc segment of the continuous curvature turning curve, that is, the continuous curvature circle is an arc segment generated with the center of the arc in the continuous curvature turning curve as the center and the distance between the starting point or end point of the continuous curvature turning curve and the center of the arc as the radius R (that is, the radius of the CC Circle), as shown in Figure 3 The thin curve in the .

[0071] Optionally, when performing path planning, an initial path can be generated based on the initial motion state of the target object at the starting point of the path, the target motion state of the target object at the end point of the path, and the above-mentioned preset angle. For example, the initial motion state of the target object, the target motion state of the target object, and the above-mentioned preset angle can be input into a preset AA path generation algorithm to output the initial path.

[0072] Step 202 : updating the initial path and the preset angle based on the initial path in combination with the preset clothoid curve to generate an updated path and an updated angle.

[0073] The preset clothoid curve is generated based on the initial path, that is, after the initial path is generated, the preset clothoid curve is generated according to relevant parameters of the initial path. It should be noted that different initial paths will correspond to different preset clothoid curves.

[0074] Specifically, after obtaining the initial path and the preset circuit curve, the initial path and the preset angle can be updated based on the initial path combined with the preset circuit curve to generate an updated path and an updated angle; optionally, the preset angle can be updated based on the first parameter of the initial path and the second parameter of the preset circuit curve to obtain an updated angle, and then, based on the updated angle, the initial motion state and the target motion state of the above-mentioned target object, an updated path is generated; wherein, the first parameter of the initial path may include the radius of the initial path, and the second parameter of the preset circuit curve may include the radius of the preset circuit curve.

[0075] For example, the first parameter of the initial path, the second parameter of the preset clothoid curve, and the preset angle can be input into a preset update algorithm to obtain an updated angle. Optionally, when updating the preset angle, a constraint corresponding to the preset angle can also be set, such as a value range of the preset angle. The computer device can then input the first parameter of the initial path, the second parameter of the preset clothoid curve, the value range of the preset angle, and the preset angle into the preset update algorithm to obtain an updated angle.

[0076] Furthermore, after obtaining the updated angle and the updated path, it can be determined whether to continue updating based on the preset judgment conditions. If the preset judgment conditions are not met, the update will continue until the preset judgment conditions are met. If the preset judgment conditions are met, the update will be stopped to obtain the final updated angle and the updated path; wherein, the preset judgment conditions can be related to at least one of the constraint conditions corresponding to the preset angle, the continuous curvature turning curve, and the continuous curvature circle.

[0077] Step 203 : When the curvature of the updated path is less than the preset maximum curvature, a target path of the target object is constructed according to the updated path and the updated angle.

[0078] The target path is a double continuous curvature turn (DCCT) curve consisting of two CC Turn curves with the same CC Circle radius and opposite directions. Figure 5 In addition, the preset maximum curvature is related to the speed of the computer device in motion. The higher the speed of the computer device, the smaller the corresponding maximum curvature.

[0079] Specifically, after obtaining the updated path, the curvature of the updated path is determined, and based on the relationship between the updated path curvature and the preset maximum curvature, a determination is made as to whether a target path can be generated. If the curvature of the updated path is less than or equal to the preset maximum curvature, the target path can be generated. In this case, the target path for the target object can be constructed based on the updated path and the updated angle. If the curvature of the updated path is greater than the preset maximum curvature, it indicates that no target path that meets the conditions does exist.

[0080] Optionally, the target path of the target object can be constructed based on the third parameter of the updated path, the updated angle, the initial motion state and the target motion state of the target object; illustratively, the third parameter of the updated path, the updated angle, the initial motion state and the target motion state of the target object can be input into a preset target path generation algorithm to obtain the target path of the target object; wherein the third parameter of the updated path may include the radius, curvature, curvature speed, position state of the intersection C, etc. of the updated path.

[0081] In the above-mentioned path generation method, the computer device generates an initial path according to the initial motion state, target motion state and preset angle of the target object, and updates the initial path and preset angle based on the initial path in combination with a preset clothoid curve to generate an updated path and an updated angle; then, when the curvature of the updated path is less than the preset maximum curvature, the target path of the target object is constructed according to the updated path and the updated angle; wherein the initial path is composed of two circular arcs with the same radius and opposite directions to each other, the preset angle is the angle between the continuous curvature turning curve and the continuous curvature circle, and the continuous curvature turning curve is composed of a first clothoid curve, a circular arc and a second The continuous curvature circle is composed of a starting point, an end point and a center point of the continuous curvature turning curve; the preset clothoid curve is generated based on the initial path; the path generation method provided in the embodiment of the present application adds a constraint condition of maximum curvature when performing path planning, which can avoid the problem that the curvature of the generated path is too large, resulting in the computer device being unable to turn in a moving state, thereby improving the rationality of path planning; in addition, the method can also obtain a path with the minimum maximum curvature, so that the computer device can achieve high-speed turning. At the same time, the method can also meet the real-time requirements of path planning, quickly calculate the local path, and improve the movement efficiency of the computer device.

[0082] In an optional embodiment of the present application, the initial motion state of the target object includes the first coordinates and the first heading angle of the target object at the initial position, and the target motion state of the target object includes the second coordinates and the second heading angle of the target object at the target position; according to the above description, the initial position of the target object can be the current position of the target object, or the starting position of the target object on a certain path, etc. Correspondingly, the target position of the target object can be the target position relative to the current position, or the end position on a certain path, etc.

[0083] Based on this, Figure 6 As shown, the above step 201 of "generating an initial path according to the initial motion state of the target object, the target motion state and the preset angle" may include:

[0084] Step 601: Determine the distance between the initial position and the target position according to the first coordinate and the second coordinate.

[0085] Specifically, after obtaining the first coordinate of the target object at the initial position and the second coordinate at the target position, the straight-line distance between the two points can be calculated by the coordinates of the two points according to a mathematical calculation formula, that is, the distance between the target object at the initial position and the target position can be obtained.

[0086] Step 602: Generate an initial path according to the first heading angle, the second heading angle, the distance, and the preset angle.

[0087] Optionally, the computer device can input the first heading angle of the target object at the initial position, the second heading angle of the target object at the target position, the distance between the initial position and the target position, and the preset angle into the above-mentioned preset AA path generation algorithm, and output the initial path.

[0088] This embodiment provides a method for generating an initial path. Based on the first heading angle of the initial position, the second heading angle of the target position, the distance between the initial position and the target position, and the preset angle, a unique initial path can be obtained through mathematical theory, which can improve the feasibility of initial path generation.

[0089] Figure 7 This is a flow chart of a path generation method in another embodiment. This embodiment relates to an optional implementation process in which a computer device updates an initial path and a preset angle based on an initial path combined with a preset clothoid curve to generate an updated path and an updated angle. Based on the above embodiment, Figure 7 As shown, the above step 202 includes:

[0090] Step 701 : Obtain the curvature velocity of the initial path, and generate a preset clothoid curve based on the curvature velocity of the initial path, a preset angle, and a preset maximum curvature velocity.

[0091] The curvature speed of the path is the rate of change of the path curvature, and a maximum curvature speed is preset.

[0092] Optionally, after generating the initial path, the computer device can determine the curvature speed of the initial path. Then, the computer device can input the curvature speed, preset angle and preset maximum curvature speed of the initial path into a preset clothoid curve generation algorithm to generate a preset clothoid curve.

[0093] Step 702 : updating the preset angle according to the radius of the preset clothoid curve and the radius of the initial path, and updating the initial path based on the updated angle to generate an updated path.

[0094] In one implementation, the computer device can update the preset angle based on the size relationship between the radius of the preset spiral curve and the radius of the initial path to obtain an updated angle, and update the initial path based on the updated angle, that is, generate an updated path based on the updated angle, the initial motion state of the target object, and the target motion state.

[0095] Alternatively, as Figure 8 As shown, the updating process of the preset angle and initial path may include:

[0096] Step 801 : updating a preset angle according to a size relationship between a radius of a preset clothoid curve and a radius of an initial path, and generating an updated angle.

[0097] Optionally, when the radius of the preset clothoid curve is greater than the radius of the initial path, it can be determined that the preset angle is too small. In this case, the preset angle should be increased to obtain the increased angle as the updated angle. When the radius of the preset clothoid curve is less than the radius of the initial path, it can be determined that the preset angle is too large. In this case, the preset angle should be decreased to obtain the decreased angle as the updated angle. Optionally, when increasing or decreasing the preset angle, the updated angle can be obtained according to a preset increase and a preset decrease, wherein the preset increase and the preset decrease can be the same or different. Exemplarily, the preset increase and the preset decrease are the same and are 1 degree. In this case, the updated angle can be obtained according to the preset angle, the preset increase, or the preset decrease.

[0098] Step 802: Update the initial path based on the updated angle to generate an updated path.

[0099] Specifically, an updated path is generated according to the updated angle, the initial motion state of the target object, and the target motion state.

[0100] Step 803 : updating the preset clothoid curve according to the updated angle and the updated path to generate an updated clothoid curve.

[0101] Specifically, the curvature speed of the updated path can be obtained, and based on the curvature speed of the updated path, the updated angle and the preset maximum curvature speed, an updated spiral curve corresponding to the updated path can be generated; the method of generating a spiral curve based on the curvature speed, angle and preset maximum curvature speed of the path can be described in the above-mentioned relevant content and will not be repeated here.

[0102] In step 804, the updated path is used as the new initial path, the updated angle is used as the new preset angle, and the updated spiral curve is used as the new preset spiral curve. The steps of generating the updated angle, generating the updated path, and generating the updated spiral curve are executed repeatedly until the value range corresponding to the updated angle meets the preset range condition.

[0103] Among them, for the angle that is continuously updated in a cycle, that is, the angle μ between the continuous curvature turning curve and the continuous curvature circle, a preset range condition related to the value range corresponding to the angle can be set in advance, and based on the preset range condition, the angle is cyclically updated until the value range corresponding to the updated angle meets the preset range condition, so that the angle that meets the condition and the path that meets the condition can be obtained, and the path that meets the condition is the AA path that meets the condition.

[0104] This embodiment provides a method for updating a preset angle and an initial path. The curvature speed of the initial path is obtained, and then a preset spiral curve is generated based on the curvature speed of the initial path, the preset angle, and the preset maximum curvature speed. Furthermore, the preset angle is updated according to the radius of the preset spiral curve and the radius of the initial path, and the initial path is updated based on the updated angle to generate an updated path, which can improve the feasibility of angle updating and path updating.

[0105] In an optional embodiment of the present application, for the preset angle, a preset angle range corresponding to the preset angle may be pre-set, that is, a value range of the preset angle, and the preset angle range includes a preset maximum angle and a preset minimum angle; optionally, when the above-mentioned computer device updates the preset angle, the preset angle may be updated in combination with the preset angle range, such as Figure 9 As shown, based on the above embodiment, the above step 801 includes:

[0106] Step 901 : updating the preset angle range according to the size relationship between the radius of the preset clothoid curve and the radius of the initial path, the preset angle range, and the preset angle, to generate an updated angle range.

[0107] Referring to the relevant description of the above-mentioned step 801, when the radius of the preset spiral curve is larger than the radius of the initial path, it can be determined that the preset angle is too small. At this time, the preset angle should be increased to obtain the increased angle as the updated angle; based on this, when updating the preset angle range, the preset minimum angle in the preset angle range can be modified and replaced with the preset angle to obtain an updated angle range with the preset angle as the minimum angle and the preset maximum angle as the maximum angle; for example: when the preset angle range is [8,45] and the preset angle is 15, if it is determined that the preset angle is to be increased, then the preset angle is used as the minimum angle to obtain an updated angle range of [15,45].

[0108] When the radius of the preset spiral curve is smaller than the radius of the initial path, it can be determined that the preset angle is too large. In this case, the preset angle should be reduced to obtain the reduced angle as the updated angle; based on this, when updating the preset angle range, the preset maximum angle in the preset angle range can be modified and replaced with the preset angle to obtain an updated angle range with the preset minimum angle as the minimum angle and the preset angle as the maximum angle; based on the above example, if it is determined that the preset angle needs to be reduced, then the preset angle is used as the maximum angle to obtain an updated angle range of [8,15].

[0109] Step 902: Calculate the updated angle according to the updated angle range.

[0110] Optionally, after obtaining the updated angle range, an angle can be randomly determined from the updated angle range as the updated angle; or the updated angle can be calculated according to a preset calculation method based on the updated angle range; illustratively, the preset calculation method can be a median calculation method, a mean calculation method, or other calculation methods, etc., and the embodiments of the present application do not make specific limitations on this; taking the median calculation method as an example, the updated angle is equal to half of the sum of the minimum angle and the maximum angle in the updated angle range. For example: assuming that the updated angle range is [15,45], then the updated angle is (15+45) / 2=30.

[0111] In this embodiment, a method for updating a preset angle is provided. The computer device first updates the preset angle range based on the size relationship between the radius of the preset spiral curve and the radius of the initial path, the preset angle range and the preset angle, and generates an updated angle range; then, based on the updated angle range, the updated angle is calculated; compared to updating the preset angle by preset increase and preset decrease, the speed and accuracy of the angle update can be improved.

[0112] Based on the above embodiment, when executing the above step 803, the computer device can first determine whether the updated angle range meets the preset range condition; if the updated angle range does not meet the preset range condition, the preset spiral curve is updated according to the updated angle and the updated path to generate an updated spiral curve; the preset range condition here can be set based on the updated angle range. For example, the preset range condition can be whether the difference between the maximum angle and the minimum angle in the updated angle range is less than a preset threshold.

[0113] That is to say, after each loop, it is first determined whether the next loop is to be performed based on the updated angle range obtained after the loop. If it is determined that the updated angle range does not meet the preset range condition, it means that the loop operation must continue. When performing the next loop, the preset spiral curve can be updated based on the updated angle and updated path obtained in the previous loop to generate an updated spiral curve. Then, based on the size relationship between the radius of the updated spiral curve and the radius of the updated path obtained in the previous loop, the updated angle obtained in the previous loop is updated to obtain the updated angle corresponding to this loop. Further, based on the updated angle corresponding to this loop, the initial motion state of the target object and the target motion state, the updated path corresponding to this loop is generated.

[0114] Based on the above embodiment, when executing the above step 804, the computer device may cyclically execute the steps of generating an updated angle, generating an updated path, and generating an updated clothoid curve until the updated angle range meets the preset range condition.

[0115] During each loop, an updated angle range can be obtained. Based on the updated angle range, it is determined whether the updated angle range meets the preset range condition, that is, whether the difference between the maximum angle and the minimum angle in the updated angle range is less than the preset threshold; when it is determined that the difference is less than the preset threshold, the loop can be terminated, and the updated angle and updated path obtained after the last loop are obtained.

[0116] In an optional embodiment of the present application, the above-mentioned step 203 "when the curvature of the updated path is less than the preset maximum curvature, constructing the target path of the target object according to the updated path and the updated angle" may include: when the curvature of the updated path is less than the preset maximum curvature, and the curvature speed of the updated path is less than or equal to the preset maximum curvature speed, the target path of the target object can be constructed according to the updated path and the updated angle.

[0117] Optionally, when the curvature of the updated path is less than the preset maximum curvature and the curvature speed of the updated path is greater than the preset maximum curvature speed, the target path of the target object can be constructed based on the updated path and the updated angle range obtained in the last cycle; optionally, the target path of the target object can be constructed based on the updated path and the minimum angle in the updated angle range. Of course, the target path of the target object can also be constructed based on the maximum angle in the updated angle range, or the target path of the target object can also be constructed based on any angle in the updated angle range.

[0118] In this embodiment, based on the two constraints of the curvature and curvature speed of the updated path, a target path of the target object is constructed to obtain an optimal path planning, which can improve the reliability and accuracy of the path planning.

[0119] In a specific embodiment of the present application, the process of generating a DCCT path may include:

[0120] Step 1: Get the initial motion state q0 of the target object at the initial position and the target motion state q d ; Wherein, the initial motion state includes the first coordinates and the first heading angle of the target object at the initial position, and the target motion state includes the second coordinates and the second heading angle of the target object at the target position;

[0121] Step 2: normalize the initial motion state and the target motion state to obtain a first heading angle of the target object at the initial position, a second heading angle of the target object at the target position, and a distance between the initial position and the target position;

[0122] Step 3: Execute a loop to obtain an AA path that meets the conditions. The loop includes:

[0123] ① Based on the preset angle, the first heading angle of the target object at the initial position, the second heading angle of the target object at the target position, and the distance between the initial position and the target position, an AA path is generated; the structure of the AA path is as follows Figure 4 As shown, the AA path consists of two arcs, which can form the CC Circle path corresponding to the DCCT path;

[0124] Exemplarily, the method for generating the AA path can be expressed by the following formula:

[0125]

[0126]

[0127]

[0128]

[0129] Wherein, μ is the preset angle, θ0 is the first heading angle of the target object at the initial position; The angle between the line AO1 connecting the center O1 of the first arc and the starting point A of the AA path, and the line AB connecting the starting point A and the end point B of the AA path; θ d is the second heading angle of the target object at the target position; is the angle between the line BO2 connecting the center O2 of the second arc and the starting point B of the AA path, and the extended line AB connecting the starting point A and the end point B of the AA path; R is the radius of the first and second arcs, which can also be called the radius of the AA path; C is the intersection of the first and second arcs, q c is the vector consisting of the position of the intersection point C and the heading angle.

[0130] ② Get the radius of the AA path, and based on the preset angle μ, the radius R of the AA path and the maximum curvature speed σ max , determine the curvature κ and curvature velocity σ corresponding to the AA path;

[0131] ③Judge κ 2 Is / 2σ+μ>π true? If not, it means there is a path with the minimum maximum curvature, and we proceed to the next step. If it is true, there is no path with the minimum maximum curvature;

[0132] ④ Generate a clothoid curve based on the curvature speed, preset angle, and preset maximum curvature rate corresponding to the AA path, and update the preset angle and the preset angle range according to the size relationship between the radius of the clothoid curve and the radius of the AA path to generate an updated angle range and an updated angle μ; for example, the preset angle range can be

[0133] ⑤ Determine whether the difference between the maximum angle and the minimum angle in the updated angle range is less than the preset threshold. If the difference is greater than or equal to the preset threshold, the updated angle is used as the preset angle, the updated angle range is used as the preset angle range, and steps ① to ⑤ are executed in a loop; if the difference is less than the preset threshold, the loop ends.

[0134] Step 4: For the AA path obtained by the loop, if the absolute value of the curvature of the AA path is greater than or equal to the preset maximum curvature, it means that there is no path with the minimum maximum curvature; if the absolute value of the curvature of the AA path is less than the preset maximum curvature, a DCCT path is generated based on the AA path. This includes the following two cases:

[0135] ① If the absolute value of the curvature of the AA path is less than the preset maximum curvature, and the absolute value of the curvature speed of the AA path is greater than the preset maximum curvature speed, then based on the initial motion state q0 of the target object at the initial position and the target motion state q d , the motion state q of the intersection point C of the AA path c , the radius R of the AA path, the curvature κ and curvature speed σ of the AA path, and the minimum angle in the updated angle range obtained by the loop, generate a DCCT path;

[0136] ② If the absolute value of the curvature of the AA path is less than the preset maximum curvature, and the absolute value of the curvature speed of the AA path is less than or equal to the preset maximum curvature speed, then based on the initial motion state q0 of the target object at the initial position and the target motion state q d , the motion state q of the intersection point C of the AA path c , the radius R of the AA path, the curvature κ and curvature speed σ of the AA path, and the updated angle μ obtained after the loop are used to generate the DCCT path.

[0137] It should be noted that when two CC Turn curves form a DCCT curve, the direction selection of CC Turn includes the following cases, where θ0 is the angle between the first heading angle at the initial position and the initial and final positions, θ d is the angle between the second heading angle at the target position and the initial and final positions.

[0138] (1) When θ0+θ d When <0, the DCCT path consists of a counterclockwise CC Turn curve and a clockwise CC Turn curve with the same radius as the CC Circle.

[0139] (2) When θ0+θ d When >0, the DCCT path consists of a clockwise CC Turn curve and a counterclockwise CC Turn curve with the same radius as the CC Circle.

[0140] (3) When θ0 = -θ d When ≠0, the path is a counterclockwise CC Turn curve (when θ0<0) or a clockwise CC Turn curve (when θ0>0).

[0141] (4) When θ0 = -θ d When =0, the path is a straight line.

[0142] Furthermore, based on the above steps, the judgment condition for the minimum maximum curvature can be obtained. When the following conditions are met, the DCCT path is the path with the minimum maximum curvature:

[0143] (1)μ<π-κ 2 / (2σ);

[0144] (2)max 0≤t≤T (θ(t))-min 0≤t≤T (θ(t))≤π / 2; where θ(t) is the difference between the angle between points A and C and the angle between points B and C in the AA path;

[0145] (3) The deflection angle δ of each CC Turn curve CC All satisfy δ CC >κ 2 / σ;

[0146] When conditions (1) and (3) are met, the generated curve satisfies the definition of the DCCT curve; when condition (2) is met, the corresponding AA path has the minimum curvature, that is, the CC Circle of the DCCT path has the minimum curvature. The image of the angle μ changing with the curvature speed σ under a fixed curvature is as follows: Figure 10 shown.

[0147] The DCCT path generation process in this embodiment enables path planning with minimal maximum curvature. A smaller maximum curvature ensures the safety of the mobile robot and allows for faster travel at higher speeds. Furthermore, the calculated path has the lowest maximum curvature, providing an important reference for path planning, as a smaller maximum curvature is not possible. This provides guidance for limiting the robot's speed and can also be used to determine whether a road is passable at a certain speed. Furthermore, the fast calculation method ensures real-time application and can also be calculated and stored offline for rapid recall during application.

[0148] In an optional embodiment of the present application, based on the above embodiments, after obtaining the target path of the target object, that is, a DCCT path, a global target path of the target object can be constructed based on the target path, that is, a complete global path can be formed by combining multiple local paths.

[0149] For example, Figure 11 As shown, after determining the starting point A and the end point B of the target object, the original path from the starting point A to the end point B can be generated based on the traditional path planning method (such as Figure 11The black curve in the figure is then used to divide the original path into multiple segmented paths. For each segmented path, the initial motion state corresponding to the starting point of the segmented path and the target motion state corresponding to the end point are determined. Then, the DCCT path corresponding to the segmented path is generated using the above-mentioned local path generation method. Finally, based on the DCCT path corresponding to each segmented path, a global path from starting point A to end point B is generated by combining them, as shown in the figure. Figure 11 The gray curve shown in is formed by connecting five DCCT paths.

[0150] It can be found that the path optimized by DCCT path is smoother, suitable for robot path tracking, avoiding sharp turns in the path, allowing the robot to pass at a faster speed and in a shorter time.

[0151] Furthermore, the DCCT path can also be used to determine whether a path between two points is passable. For example, given an initial and final motion state, the DCCT path can be calculated to obtain the minimum maximum curvature κ, which can be used to determine if there is no continuous curvature path with a smaller curvature. If the robot cannot turn at the curvature κ, then there is no continuous curvature path connecting the two points, and the path can be determined to be impassable.

[0152] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0153] Based on the same inventive concept, embodiments of the present application also provide a path generation device for implementing the aforementioned path generation method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more of the following path generation device embodiments can be found in the aforementioned limitations of the path generation method and are not further elaborated here.

[0154] In one embodiment, Figure 12 As shown, a path generation device is provided, including: a generation module 1201, an update module 1202 and a construction module 1203, wherein:

[0155] Generation module 1201 is used to generate an initial path based on the initial motion state of the target object, the target motion state and the preset angle; the initial path is composed of two arcs with the same radius and opposite directions; the preset angle is the angle between the continuous curvature steering curve and the continuous curvature circle, the continuous curvature steering curve is composed of a first clothoid curve, an arc and a second clothoid curve, and the continuous curvature circle is composed of the starting point, end point and center of the arc of the continuous curvature steering curve.

[0156] The updating module 1202 is configured to update the initial path and the preset angle based on the initial path in combination with a preset clothoid curve to generate an updated path and an updated angle; the preset clothoid curve is generated based on the initial path.

[0157] The construction module 1203 is configured to construct a target path of the target object according to the updated path and the updated angle when the curvature of the updated path is less than a preset maximum curvature.

[0158] In one embodiment, the initial motion state includes the first coordinates and the first heading angle of the target object at the initial position, and the target motion state includes the second coordinates and the second heading angle of the target object at the target position; the above-mentioned generation module 1201 is specifically used to determine the distance between the initial position and the target position based on the first coordinates and the second coordinates; and generate an initial path based on the first heading angle, the second heading angle, the distance and the preset angle.

[0159] In one embodiment, the update module 1202 includes an acquisition unit and an update unit; wherein the acquisition unit is used to acquire the curvature speed of the initial path, and generate a preset spiral curve based on the curvature speed of the initial path, a preset angle and a preset maximum curvature speed; the update unit is used to update the preset angle according to the radius of the preset spiral curve and the radius of the initial path, and update the initial path based on the updated angle to generate an updated path.

[0160] In one embodiment, the above-mentioned updating unit is specifically used to update the preset angle according to the size relationship between the radius of the preset spiral curve and the radius of the initial path to generate an updated angle; update the initial path based on the updated angle to generate an updated path; update the preset spiral curve according to the updated angle and the updated path to generate an updated spiral curve; use the updated path as the new initial path, the updated angle as the new preset angle, and the updated spiral curve as the new preset spiral curve, and repeatedly execute the steps of generating the updated angle, generating the updated path, and generating the updated spiral curve until the value range corresponding to the updated angle meets the preset range condition.

[0161] In one embodiment, the above-mentioned updating unit is specifically used to update the preset angle range based on the size relationship between the radius of the preset spiral curve and the radius of the initial path, the preset angle range and the preset angle, and generate an updated angle range; based on the updated angle range, calculate the updated angle; wherein the preset angle range is the value range of the preset angle.

[0162] In one embodiment, the above-mentioned update unit is specifically used to determine whether the updated angle range meets the preset range conditions; when the updated angle range does not meet the preset range conditions, the preset spiral curve is updated according to the updated angle and the updated path to generate an updated spiral curve.

[0163] In one embodiment, the updating unit is specifically configured to cyclically execute the steps of generating an updated angle, generating an updated path, and generating an updated clothoid curve until the updated angle range satisfies a preset range condition.

[0164] In one embodiment, the above-mentioned construction module 1203 includes a first construction unit, which is used to construct a target path of the target object according to the updated path and the updated angle when the curvature of the updated path is less than a preset maximum curvature and the curvature speed of the updated path is less than or equal to the preset maximum curvature speed.

[0165] In one embodiment, the above-mentioned construction module 1203 includes a second construction unit, which is used to construct a target path of the target object according to the updated path and the updated angle range when the curvature of the updated path is less than the preset maximum curvature and the curvature speed of the updated path is greater than the preset maximum curvature speed.

[0166] In one embodiment, the construction module 1203 is further configured to construct a global target path of the target object according to the target path of the target object.

[0167] Each module in the path generation device described above may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0168] In one embodiment, a computer device is provided. The computer device may be the above-mentioned smart device, or a server connected to the smart device for communication, or a control device connected to the smart device for communication, etc. The internal structure diagram thereof may be as follows: Figure 13As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data such as the motion status of the smart device. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a path generation method is implemented.

[0169] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the path generation method in any of the above embodiments when executing the computer program.

[0170] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the path generation method in any of the above embodiments are implemented.

[0171] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps of the path generation method in any of the above embodiments are implemented.

[0172] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0173] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0174] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A path generation method for autonomous navigation of smart devices, characterized in that: The method comprises: An initial path is generated based on the initial motion state of the target object, the target motion state, and a preset angle; the initial path is composed of two circular arcs with the same radius and opposite directions; the preset angle is the angle between a continuous curvature turning curve and a continuous curvature circle, the continuous curvature turning curve is composed of a first clothoid curve, a circular arc, and a second clothoid curve, and the continuous curvature circle is composed of the starting point and end point of the continuous curvature turning curve and the center of the circular arc; Based on the initial path and a preset clothoid curve, the initial path and the preset angle are updated to generate an updated path and an updated angle; the preset clothoid curve is generated based on the initial path; The updating of the initial path and the preset angle based on the initial path in combination with a preset clothoid curve to generate an updated path and an updated angle includes: Acquiring a curvature velocity of the initial path, and generating a preset clothoid curve based on the curvature velocity of the initial path, the preset angle, and a preset maximum curvature velocity; The preset angle is updated according to the radius of the preset clothoid curve and the radius of the initial path, and the initial path is updated based on the updated angle to generate an updated path. The updating of the preset angle according to the radius of the preset clothoid curve and the radius of the initial path, and the updating of the initial path based on the updated angle to generate an updated path, comprises: updating the preset angle according to a size relationship between the radius of the preset clothoid curve and the radius of the initial path to generate an updated angle; updating the initial path based on the updated angle to generate an updated path; updating the preset clothoid curve according to the updated angle and the updated path to generate an updated clothoid curve; The updated path is used as the new initial path, the updated angle is used as the new preset angle, and the updated clothoid curve is used as the new preset clothoid curve. The steps of generating the updated angle, generating the updated path, and generating the updated clothoid curve are repeatedly performed until the value range corresponding to the updated angle meets the preset range condition. If the curvature of the updated path is less than a preset maximum curvature, a target path of the target object is constructed according to the updated path and the updated angle.

2. The method according to claim 1, characterized in that The initial motion state includes a first coordinate and a first heading angle of the target object at the initial position, and the target motion state includes a second coordinate and a second heading angle of the target object at the target position; The generating of the initial path according to the initial motion state of the target object, the target motion state and the preset angle includes: determining a distance between the initial position and the target position according to the first coordinate and the second coordinate; An initial path is generated according to the first heading angle, the second heading angle, the distance, and a preset angle.

3. The method according to claim 1, characterized in that The updating of the preset angle according to the relationship between the radius of the preset clothoid curve and the radius of the initial path to generate an updated angle includes: updating the preset angle range according to the relationship between the radius of the preset clothoid curve and the radius of the initial path, the preset angle range, and the preset angle, to generate an updated angle range; the preset angle range is a value range of the preset angle; An updated angle is calculated according to the updated angle range.

4. The method according to claim 3, characterized in that The updating of the preset clothoid curve according to the updated angle and the updated path to generate an updated clothoid curve includes: Determining whether the updated angle range meets the preset range condition; If not, the preset clothoid curve is updated according to the updated angle and the updated path to generate an updated clothoid curve.

5. The method according to claim 3, characterized in that The steps of generating an updated angle, generating an updated path, and generating an updated clothoid curve are executed cyclically until a value range corresponding to the updated angle satisfies a preset range condition, including: The steps of generating an updated angle, generating an updated path, and generating an updated clothoid curve are executed cyclically until the updated angle range satisfies the preset range condition.

6. The method according to claim 3, characterized in that If the curvature of the updated path is less than a preset maximum curvature, constructing a target path of the target object according to the updated path and the updated angle includes: If the curvature of the updated path is less than the preset maximum curvature, and the curvature speed of the updated path is less than or equal to the preset maximum curvature speed, a target path of the target object is constructed according to the updated path and the updated angle.

7. The method according to claim 6, characterized in that The method further comprises: If the curvature of the updated path is less than the preset maximum curvature, and the curvature speed of the updated path is greater than the preset maximum curvature speed, a target path of the target object is constructed according to the updated path and the updated angle range.

8. The method according to claim 1, characterized in that The method further comprises: A global target path of the target object is constructed according to the target path of the target object.

9. A path generation device for autonomous navigation of smart devices, characterized in that: The device comprises: a generation module for generating an initial path based on the initial motion state of the target object, the target motion state, and a preset angle; the initial path is composed of two circular arcs having the same radius and in opposite directions; the preset angle is the angle between a continuous curvature turning curve and a continuous curvature circle; the continuous curvature turning curve is composed of a first clothoid curve, a circular arc, and a second clothoid curve; the continuous curvature circle is composed of the starting point and end point of the continuous curvature turning curve and the center of the circular arc; an updating module, configured to update the initial path and the preset angle based on the initial path in combination with a preset clothoid curve, to generate an updated path and an updated angle; the preset clothoid curve is generated based on the initial path; The update module includes: an acquiring unit, configured to acquire a curvature velocity of an initial path, and generate a preset clothoid curve based on the curvature velocity of the initial path, a preset angle, and a preset maximum curvature velocity; an updating unit, configured to update a preset angle according to a radius of the preset clothoid curve and a radius of the initial path, and to update the initial path based on the updated angle to generate an updated path; The updating unit is specifically configured to: updating the preset angle according to the relationship between the radius of the preset clothoid curve and the radius of the initial path to generate an updated angle; The initial path is updated based on the updated angle to generate an updated path; updating the preset clothoid curve according to the updated angle and the updated path to generate an updated clothoid curve; The updated path is used as the new initial path, the updated angle is used as the new preset angle, and the updated clothoid curve is used as the new preset clothoid curve. The steps of generating the updated angle, generating the updated path, and generating the updated clothoid curve are executed repeatedly until the value range corresponding to the updated angle meets the preset range condition. A construction module is configured to construct a target path of the target object according to the updated path and the updated angle if the curvature of the updated path is less than a preset maximum curvature.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images