Path planning method and system and electronic equipment

Abstract

The invention provides a path planning method, a path planning system and electronic equipment, and relates to the field of vehicle path planning. And the curvature change variance and the curvature variance of the Bezier curve are fully utilized to find a path which satisfies the optimal path smoothness and has the minimum path radius greater than the minimum turning radius of the vehicle, so that accurate path planning can be realized only through the low-order Bezier curve.

Description

Technical Field

[0001] The present invention relates to the field of vehicle path planning, and in particular, to a path planning method, system and electronic device. Background Art

[0002] For an AGV (Automated Guided Vehicle) vehicle, reasonable path planning can enable the AGV to operate efficiently. Generally speaking, a straight line is the most efficient route between two points. However, for a broken-line route, such as an L-shaped route, at the inflection point, it is necessary to first control the AGV vehicle to stop at this point and then rotate in place to change the driving direction. Therefore, the path connected by two straight lines is not efficient for the AGV vehicle. In the industry, Bezier curves are usually used for path planning to obtain a smooth path curve.

[0003] Bezier curves need to consider the smoothness of the route and the minimum turning radius of the vehicle. Generally speaking, the smaller the curvature change rate, the smoother the route; the smaller the curvature, the larger the radius, and it can be greater than the minimum turning radius of the vehicle. For Bezier routes, in the prior art, mainly third-order Bezier and fifth-order Bezier are used. However, the low-order Bezier has limited accuracy, and the high-order Bezier is complex to draw; moreover, the drawing process of the Bezier curve belongs to graphic design, while the AGV vehicle belongs to vehicle operation. It is difficult to associate the minimum turning radius of the vehicle when drawing the Bezier curve, resulting in poor results when using Bezier for path planning. Summary of the Invention

[0004] In view of this, an object of the present invention is to provide a path planning method, system and electronic device. The method generates multiple Bezier curves according to the route heading of the AGV vehicle, and fully utilizes the curvature change variance and curvature variance of the Bezier curve to find a path that satisfies the optimal route smoothness and the minimum route radius greater than the minimum turning radius of the vehicle, so as to achieve accurate path planning only through low-order Bezier curves.

[0005] In a first aspect, an embodiment of the present invention provides a path planning method, which is applied to the path planning of an AGV vehicle. The method includes:

[0006] Determine the first information of the starting straight line and the second information of the ending straight line of the AGV vehicle;

[0007] Determine the first control point set corresponding to the starting straight line and the second control point set corresponding to the ending straight line according to the first information and the second information, and generate multiple Bezier curves by using the first control points in the first control point set and the second control points in the second control point set;

[0008] Calculate the variance of the curvature change rate and the curvature variance corresponding to each Bezier curve;

[0009] According to the variance of the curvature change rate and the curvature variance corresponding to each Bezier curve, determine the weighted value corresponding to each Bezier curve, and determine the path between the starting straight line and the ending straight line as the Bezier curve corresponding to the maximum weighted value.

[0010] Optionally, determine the first control point set corresponding to the starting straight line and the second control point set corresponding to the ending straight line according to the first information and the second information, and generate multiple Bezier curves by using the first control points in the first control point set and the second control points in the second control point set, including:

[0011] Obtain the first starting point coordinates, the first ending point coordinates and the first direction information of the starting straight line included in the first information; and obtain the second starting point coordinates, the second ending point coordinates and the second direction information of the ending straight line included in the second information;

[0012] Determine the ray direction corresponding to the starting straight line according to the first direction information, and construct the first control point set along the ray direction based on the first starting point coordinates and the first ending point coordinates according to a preset first quantity;

[0013] Determine the reflected ray direction corresponding to the ending straight line according to the second direction information, and construct the second control point set along the reflected ray direction based on the second starting point coordinates and the second ending point coordinates according to a preset second quantity;

[0014] Traverse the first control points in the first control point set and the second control points in the second control point set, and combine the first control points and the second control points in pairs in sequence to generate multiple cubic Bezier curves.

[0015] Optionally, calculate the variance of the curvature change rate and the curvature variance corresponding to each Bezier curve, including:

[0016] For each Bezier curve, divide the Bezier curve into multiple curve segments according to a preset quantity, and calculate the curvature of each curve segment;

[0017] According to the curvature of each curve segment, calculate the curvature change rate between adjacent curve segments, and calculate the variance of the curvature change rate corresponding to the Bezier curve according to the curvature change rate;

[0018] According to the curvature of each curve segment, calculate the curvature variance corresponding to the Bezier curve.

[0019] Optionally, determine the weighted value corresponding to each Bezier curve according to the variance of the curvature change rate and the curvature variance corresponding to each Bezier curve, including:

[0020] Obtain the variance of the curvature change rate corresponding to each Bezier curve, determine the first sorting result of the variance of the curvature change rate, and determine the first weight value of each Bezier curve according to the first sorting result;

[0021] Obtain the curvature variance corresponding to each Bezier curve, determine the second sorting result of the curvature variance, and determine the second weight value of each Bezier curve according to the second sorting result;

[0022] Determine the weighted value corresponding to each Bezier curve based on the first weight value and the second weight value.

[0023] Optionally, obtaining the variance of the curvature change rate corresponding to each Bezier curve, determining the first sorting result of the variance of the curvature change rate, and determining the first weight value of each Bezier curve according to the first sorting result includes:

[0024] Obtain the variance of the curvature change rate corresponding to all Bezier curves, obtain the first sorting result after sorting according to the value of the variance of the curvature change rate, and use the first sorting result to determine the first index value corresponding to each Bezier curve;

[0025] Obtain the preset first weight multiplier, and use the first index value and the first weight multiplier to determine the first weight value.

[0026] Optionally, obtaining the curvature variance corresponding to each Bezier curve, determining the second sorting result of the curvature variance, and determining the second weight value of each Bezier curve according to the second sorting result includes:

[0027] Obtain the curvature variance corresponding to all Bezier curves, obtain the second sorting result after sorting according to the value of the curvature variance, and use the second sorting result to determine the second index value corresponding to each Bezier curve;

[0028] Obtain the preset second weight multiplier, and use the second index value and the second weight multiplier to determine the second weight value.

[0029] Optionally, the first weight multiplier and the second weight multiplier satisfy the following formula:

[0030]

[0031] where, w1 is the first weight multiplier; w2 is the second weight multiplier; w max is the maximum angular velocity of the AGV vehicle; a lat_max is the maximum lateral acceleration of the AGV vehicle.

[0032] Optionally, determining the weighted value corresponding to each Bezier curve based on the first weight value and the second weight value includes:

[0033] Traverse the first weight value and the second weight value corresponding to each Bezier curve;

[0034] Calculate the sum result of the first weight value and the second weight value corresponding to each Bezier curve, and use the sum result to determine the weighted value corresponding to each Bezier curve.

[0035] In a second aspect, the present invention provides a path planning system, which is applied to the path planning of an AGV vehicle. The system includes:

[0036] An initialization module, configured to determine the first information of the starting straight line and the second information of the ending straight line of the AGV vehicle;

[0037] A Bezier curve generation module, configured to determine a first control point set corresponding to the starting straight line and a second control point set corresponding to the ending straight line according to the first information and the second information, and generate a plurality of Bezier curves by using the first control points in the first control point set and the second control points in the second control point set;

[0038] A calculation module, configured to calculate the variance of the curvature change rate and the variance of the curvature corresponding to each Bezier curve;

[0039] A path planning execution module, configured to determine the weighted value corresponding to each Bezier curve according to the variance of the curvature change rate and the variance of the curvature corresponding to each Bezier curve, and determine the Bezier curve corresponding to the maximum weighted value as the path between the starting straight line and the ending straight line.

[0040] In a third aspect, an embodiment of the present invention further provides an electronic device, including a processor and a memory. The memory stores computer-executable instructions that can be executed by the processor. The processor executes the computer-executable instructions to implement the steps of the path planning method provided in the first aspect.

[0041] In a fourth aspect, an embodiment of the present invention further provides a storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to implement the steps of the path planning method provided in the first aspect.

[0042] A path planning method, system and electronic device provided by an embodiment of the present invention. In the process of path planning for an AGV vehicle, first, the first information of the starting straight line and the second information of the ending straight line of the AGV vehicle are determined; then, according to the first information and the second information, a first control point set corresponding to the starting straight line and a second control point set corresponding to the ending straight line are determined, and a plurality of Bezier curves are generated by using the first control points in the first control point set and the second control points in the second control point set; subsequently, the variance of the curvature change rate and the variance of the curvature corresponding to each Bezier curve are calculated; finally, according to the variance of the curvature change rate and the variance of the curvature corresponding to each Bezier curve, the weighted value corresponding to each Bezier curve is determined, and the Bezier curve corresponding to the maximum weighted value is determined as the path between the starting straight line and the ending straight line. This method generates a plurality of Bezier curves according to the route heading of the AGV vehicle, and fully utilizes the variance of the curvature change and the variance of the curvature of the Bezier curve to find a path that satisfies the optimal route smoothness and the minimum route radius is greater than the minimum turning radius of the vehicle, so as to achieve accurate path planning only through low-order Bezier curves.

[0043] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification, claims and drawings.

[0044] To make the above objectives, features and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. Description of the Drawings

[0045] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0046] Figure 1 It is a flowchart of a path planning method provided by an embodiment of the present invention;

[0047] Figure 2 It is a flowchart of step S102 in a path planning method provided by an embodiment of the present invention;

[0048] Figure 3 It is a flowchart of step S103 in a path planning method provided by an embodiment of the present invention;

[0049] Figure 4In step S104 of a path planning method provided by an embodiment of the present invention, a flowchart for determining the weighted value corresponding to each Bezier curve according to the variance of the curvature change rate and the curvature variance corresponding to each Bezier curve;

[0050] Figure 5 A flowchart of step S401 in a path planning method provided by an embodiment of the present invention;

[0051] Figure 6 A flowchart of step S402 in a path planning method provided by an embodiment of the present invention;

[0052] Figure 7 A flowchart of step S403 of a path planning method provided by an embodiment of the present invention;

[0053] Figure 8 A schematic diagram of the starting straight line and the ending straight line of an AGV vehicle in a path planning method provided by an embodiment of the present invention;

[0054] Figure 9 A schematic structural diagram of a path planning system provided by an embodiment of the present invention;

[0055] Figure 10 A schematic structural diagram of an electronic device provided by an embodiment of the present invention.

[0056] Icon:

[0057] 910 - Initialization module; 920 - Bezier curve generation module; 930 - Calculation module; 940 - Path planning execution module;

[0058] 101 - Processor; 102 - Memory; 103 - Bus; 104 - Communication interface. Specific embodiments

[0059] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0060] For an AGV vehicle, reasonable path planning can enable the AGV to operate efficiently. Generally speaking, a straight line is the most efficient route between two points. However, for a zigzag route, such as an L-shaped route, at the inflection point, it is necessary to first control the AGV vehicle to stop at this point and then rotate in place to change the driving direction. Therefore, a path connected by two straight lines is not efficient for an AGV vehicle. In the industry, Bezier curves are usually used for path planning to obtain a smooth path curve.

[0061] Bezier curves need to consider the smoothness of the route and the minimum turning radius of the vehicle. Generally speaking, the smaller the curvature change rate, the smoother the route; the smaller the curvature, the larger the radius, and it can be greater than the minimum turning radius of the vehicle. For Bezier routes, in the prior art, mainly two methods of third-order Bezier and fifth-order Bezier are adopted. However, the low-order Bezier has limited accuracy, and the high-order Bezier is complex to draw; moreover, the drawing process of Bezier curves belongs to graphic design, while the AGV vehicle belongs to vehicle operation. It is difficult to associate the minimum turning radius of the vehicle when drawing Bezier curves, resulting in poor effects when using Bezier for path planning. Based on this, the embodiments of the present invention provide a path planning method, system and electronic device. This method generates multiple Bezier curves according to the route heading of the AGV vehicle, and fully utilizes the curvature change variance and curvature variance of the Bezier curves to find a path that satisfies the optimal route smoothness and the minimum route radius greater than the minimum turning radius of the vehicle, so as to achieve accurate path planning only through low-order Bezier curves.

[0062] For the convenience of understanding this embodiment, first, a path planning method disclosed in the embodiments of the present invention will be introduced in detail. This method is applied to the path planning of AGV vehicles, as Figure 1 shown, this method includes:

[0063] Step S101, determine the first information of the starting straight line and the second information of the ending straight line of the AGV vehicle.

[0064] In an actual application scenario, the operation of an AGV vehicle is usually within a preset working area. The starting straight line represents the initial trajectory of the AGV vehicle when it starts to drive, and the ending straight line is the straight line where the end point of its target driving trajectory is located. After determining the starting straight line and the ending straight line, the positional relationship between the starting straight line and the ending straight line is determined by obtaining the first information of the starting straight line and the second information of the ending straight line, and thus the driving direction of the vehicle is clarified.

[0065] Obtaining the end coordinates of the starting straight line and the starting coordinates of the ending straight line is a crucial step. The coordinate information of these two points will be used to calculate the approximate direction of the AGV vehicle from the starting position to the ending position, that is, the route heading. The determination of the route heading provides an important direction guidance for subsequent path planning. It can help the AGV vehicle drive orderly towards the target position and avoid blind movement. For example, in a goods handling scenario in a warehouse, the AGV vehicle needs to move from a certain position in the storage area (corresponding to the starting straight line) to a designated position in the shipping area (corresponding to the ending straight line). By determining the end of the starting straight line and the start of the ending straight line, the driving direction of the vehicle can be clarified.

[0066] Step S102: Determine the first control point set corresponding to the starting straight line and the second control point set corresponding to the ending straight line according to the first information and the second information, and generate multiple Bézier curves by using the first control points in the first control point set and the second control points in the second control point set.

[0067] A Bézier curve is a mathematical curve widely used in computer graphics and path planning. It can flexibly describe the shape of the curve through control points. Select a series of points on the starting straight line according to the route heading determined in the previous step to form the first control point set, and these points will be used as the control points related to the start of generating the Bézier curve. Similarly, select a series of points on the ending straight line to form the second control point set as the control points related to the end. By reasonably combining the first control points in the first control point set and the second control points in the second control point set, multiple Bézier curves with different shapes can be generated. These Bézier curves represent the possible driving paths of the AGV vehicle from the starting straight line to the ending straight line. For example, Bézier curves with different bending degrees and directions are generated according to different combinations of point sets to adapt to different working environments and driving requirements. By generating multiple Bézier curves, more possibilities can be provided for subsequent path selection to find the optimal driving path.

[0068] Step S103: Calculate the variance of the curvature change rate and the variance of the curvature corresponding to each Bézier curve.

[0069] Curvature is an important parameter describing the bending degree of a curve, and the curvature change rate reflects how fast the bending degree of the curve changes. For each generated Bézier curve, calculating its variance of the curvature change rate and the variance of the curvature is of great significance. The variance of the curvature change rate can measure the stability of the change in the bending degree of the curve at different positions. The smaller the variance, the smoother the change in the bending degree of the curve, and the easier it is for the AGV vehicle to be controlled and operated during driving.

[0070] The curvature variance reflects the fluctuation of the overall bending degree of the curve. Specifically, the first sorting result can be obtained by sorting the variances of the curvature change rates of each Bezier curve, and the first weight value is determined according to this sorting result. The Bezier curves with a higher ranking (i.e., smaller variances of the curvature change rates) will obtain larger first weight values. Similarly, the second sorting result is obtained by sorting the curvature variances, and then the second weight value is determined. These weight values will be used to comprehensively evaluate the quality of each Bezier curve in order to select the optimal path in the subsequent steps.

[0071] Step S104: Determine the weighted value corresponding to each Bezier curve according to the variance of the curvature change rate and the curvature variance corresponding to each Bezier curve, and determine the Bezier curve corresponding to the maximum weighted value as the path between the starting straight line and the ending straight line.

[0072] After obtaining the variance of the curvature change rate and the curvature variance, the weighted value corresponding to each Bezier curve can be obtained by determining the weighted values corresponding to the two and performing weighted calculations on them. This weighted value comprehensively considers two important factors, namely the variance of the curvature change rate and the curvature variance of the curve, and can more comprehensively reflect the quality of the curve. By comparing the weighted values of all Bezier curves, the maximum value is found, and the Bezier curve corresponding to the maximum value is determined as the optimal driving path of the AGV vehicle from the starting straight line to the ending straight line. In this way, the AGV vehicle can drive along this optimal path, improving the driving efficiency and safety while ensuring the driving stability.

[0073] Optionally, step S102 of determining the first control point set corresponding to the starting straight line and the second control point set corresponding to the ending straight line according to the first information and the second information, and generating multiple Bezier curves by using the first control points in the first control point set and the second control points in the second control point set, as Figure 2 shown, includes:

[0074] Step S201: Obtain the first information including the first starting point coordinates, the first ending point coordinates and the first direction information of the starting straight line; and obtain the second information including the second starting point coordinates, the second ending point coordinates and the second direction information of the ending straight line.

[0075] The preset coordinate system is a reference framework established to accurately describe the position and movement trajectory of an AGV vehicle within the working area. Common preset coordinate systems include the Cartesian rectangular coordinate system, polar coordinate system, etc. In practical applications, the Cartesian rectangular coordinate system is widely adopted due to its simplicity, intuitiveness, and ease of calculation. In the Cartesian rectangular coordinate system, a straight line can be represented by various forms of expressions, such as the slope-intercept form y = kx + b (where k is the slope and b is the intercept), the point-slope form y - y0 = k(x - x0) (where (x0, y0) is a point on the straight line and k is the slope), etc. To determine the expressions of the starting straight line and the ending straight line, first, the coordinate information of at least two points on the straight line needs to be obtained. The coordinates of these points can be determined based on the design drawing of the working area and known fixed reference points. The process of obtaining the straight line expression is a simple process of obtaining a linear equation with one variable, which will not be elaborated here.

[0076] After obtaining the expressions of the starting straight line and the ending straight line, the first information including the first starting point coordinates, the first ending point coordinates, and the first direction information of the starting straight line, and the second information including the second starting point coordinates, the second ending point coordinates, and the second direction information of the ending straight line can be obtained based on this coordinate system, as specifically Figure 8 shown.

[0077] Step S202: Determine the ray direction corresponding to the starting straight line according to the first direction information, and construct a first control point set along the ray direction based on the first starting point coordinates and the first ending point coordinates according to a preset first quantity.

[0078] Step S203: Determine the reflected ray direction corresponding to the ending straight line according to the second direction information, and construct a second control point set along the reflected ray direction based on the second starting point coordinates and the second ending point coordinates according to a preset second quantity.

[0079] Step S204: Traverse the first control points in the first control point set and the second control points in the second control point set, and generate multiple cubic Bézier curves by combining the first control points and the second control points in pairs in sequence.

[0080] In an actual scenario, 144 cubic Bézier curves can be generated according to the route heading. Specifically, 12 points are generated along the ray direction of the starting straight line and the reflected ray direction of the ending straight line respectively (i.e., the first quantity is 12 and the second quantity is also 12). These 12 * 12 points are combined in pairs as control points to generate 144 cubic Bézier curves. The setting of the first control point and the second control point can be realized according to external inputs such as the minimum turning radius of the AGV vehicle, the relationship between speed and AGV trajectory tracking; or it can be simply evenly divided.

[0081] Optionally, step S103 of calculating the variance of the curvature change rate and the curvature variance corresponding to each Bézier curve, as Figure 3As shown in the figure, it includes:

[0082] Step S301: For each Bezier curve, divide the Bezier curve into multiple curve segments according to a preset quantity, and calculate the curvature of each curve segment.

[0083] Step S302: According to the curvature of each curve segment, calculate the curvature change rate between adjacent curve segments, and calculate the variance of the curvature change rate corresponding to the Bezier curve according to the curvature change rate.

[0084] Step S303: According to the curvature of each curve segment, calculate the variance of the curvature corresponding to the Bezier curve.

[0085] Continuing with the above scenario, for each Bezier curve among 144 Bezier curves, divide the Bezier curve into multiple curve segments, such as 100 segments, according to a preset quantity, and calculate the curvature of each curve segment. Among 144 cubic Bezier curves, each cubic Bezier curve is broken into several segments, such as 100 segments, and the curvature of these curve segments is calculated. It is necessary to consider that the connection at the head and tail of the 144 cubic Bezier curves may be a straight line or a curve. If the connection at the head and tail is a straight line, the curvature optimization target at the head and tail is set to 0; if the connection at the head and tail is a curve, the curvature at the head and tail needs to be input as the optimization target value.

[0086] Then, according to the curvature of each curve segment, calculate the curvature change rate between adjacent curve segments, calculate the variance of the curvature change rate corresponding to the Bezier curve according to the curvature change rate, and calculate the variance of the curvature corresponding to the Bezier curve according to the curvature of each curve segment. In this embodiment, taking the connections at the head and tail as straight lines as an example, for the curvatures of these 102 curves, the variance of the change rates (a total of 101 values are output) between adjacent two are calculated to obtain the variance of the curvature change rate; similarly, the variance of the curvatures of 100 curve segments (a total of 100 values) is calculated to obtain the variance of the curvature.

[0087] Optionally, according to the variance of the curvature change rate and the variance of the curvature corresponding to each Bezier curve, determine the weighted value corresponding to each Bezier curve, as Figure 4 shown in the figure, it includes:

[0088] Step S401: Obtain the variance of the curvature change rate corresponding to each Bezier curve, determine the first sorting result of the variance of the curvature change rate, and determine the first weight value of each Bezier curve according to the first sorting result.

[0089] Step S402: Obtain the variance of the curvature corresponding to each Bezier curve, determine the second sorting result of the variance of the curvature, and determine the second weight value of each Bezier curve according to the second sorting result.

[0090] Step S403: Determine the weighted value corresponding to each Bezier curve based on the first weight value and the second weight value.

[0091] For simplicity of description, the following describes five cubic Bézier curves. For example, these five curves are a, b, c, d, and e respectively. After sorting them according to the variance of the curvature change rate, the first sorting result is: c, a, b, d, e. At this time, the first weight values of c, a, b, d, and e are set in the order of the first sorting result.

[0092] Similarly, obtain the curvature variances corresponding to a, b, c, d, and e, determine the second sorting result of the curvature variances as: e, d, a, c, b, and then set the second weight values of e, d, a, c, and b in the order of the second sorting result. After the first weight value and the second weight value are determined, the weighted sum of the two can be obtained to get the weighted value corresponding to each Bézier curve.

[0093] Optionally, the steps of obtaining the variance of the curvature change rate corresponding to each Bézier curve, determining the first sorting result of the variance of the curvature change rate, and determining the first weight value of each Bézier curve according to the first sorting result, as Figure 5 shown, include:

[0094] Step S501, obtain the variances of the curvature change rates corresponding to all Bézier curves, sort them according to the values of the variances of the curvature change rates to obtain the first sorting result, and use the first sorting result to determine the first index value corresponding to each Bézier curve;

[0095] Step S502, obtain a preset first weight multiplier, and use the first index value and the first weight multiplier to determine the first weight value.

[0096] Specifically, in the process of determining the first weight value, after sorting according to the values of the variances of the curvature change rates, the first sorting result is c, a, b, d, e, and their corresponding first index values are set in ascending order as 1, 2, 3, 4, 5 respectively. The first index value represents the magnitude of the variance of the curvature change rate of each Bézier curve. The smaller the first index value, the smoother the route.

[0097] Then, the first weight value is calculated by obtaining a preset first weight multiple, and specifically, the first index value needs to be fully utilized to achieve this. When the first weight value represents that the larger the numerical value, the smoother the route, the corresponding sub-weight value needs to be updated through the first index value. Specifically, the first index values of c, a, b, d, and e are 1, 2, 3, 4, and 5 respectively. During the calculation using the first index value, they need to be re-sorted, and the obtained sub-weight values are 5, 4, 3, 2, and 1 respectively. Then, after multiplying the above values by the preset first weight multiple of 1.6, the first weight values corresponding to c, a, b, d, and e are: 5 * 1.6 = 8, 4 * 1.6 = 6.4, 3 * 1.6 = 4.8, 2 * 1.6 = 3.2, 1 * 1.6 = 1.6. At this time, the route corresponding to the first weight value has the optimal route smoothness.

[0098] Optionally, the steps S402 of obtaining the curvature variance corresponding to each Bezier curve, determining the second sorting result of the curvature variance, and determining the second weight value of each Bezier curve according to the second sorting result are as Figure 6 shown, and include:

[0099] Step S601, obtaining the curvature variances corresponding to all Bezier curves, sorting them according to the numerical values of the curvature variances to obtain the second sorting result, and using the second sorting result to determine the second index value corresponding to each Bezier curve;

[0100] Step S602, obtaining a preset second weight multiple, and using the second index value and the second weight multiple to determine the second weight value.

[0101] Similarly, during the process of determining the second weight value, after sorting according to the numerical values of the curvature variances, the second sorting result is: e, d, a, c, b, and their corresponding second index values are set in ascending order as 1, 2, 3, 4, and 5 respectively. The second index value represents the magnitude of the curvature variance of each Bezier curve. The smaller the second index value, the greater the radius at the minimum radius of the route is than the minimum turning radius of the vehicle.

[0102] Then, the second weight value is calculated by obtaining a preset second weight multiple, and specifically, the second index value needs to be fully utilized to achieve this. Similar to the calculation process of the first weight value, when calculating the second weight value, the corresponding sub-weight value is also updated through the second index value. Specifically, the second index values of e, d, a, c, and b are 1, 2, 3, 4, and 5 respectively. During the calculation using the second index value, they need to be re-sorted, and the obtained sub-weight values are 5, 4, 3, 2, and 1 respectively. Then, after multiplying the above values by the preset second weight multiple of 1.0, the second weight values corresponding to e, d, a, c, and b are 5, 4, 3, 2, and 1 respectively.

[0103] Optionally, the first weight multiple and the second weight multiple satisfy the following formula:

[0104]

[0105] where w1 is the first weight multiple; w2 is the second weight multiple; w max is the maximum angular velocity of the AGV vehicle; a lat_max is the maximum lateral acceleration of the AGV vehicle.

[0106] It should be noted that there is a specific relationship between the first weight multiple and the second weight multiple. The first weight multiple is associated with the curvature change rate, which reflects the severity of the path turning and directly affects the steering angular velocity of the vehicle. If it is too high, it may exceed the actuator's ability and cause unstable tracking; the second weight multiple is associated with the curvature variance, which reflects the overall smoothness of the path. A large variance means frequent direction adjustments, affecting the control accuracy.

[0107] The first weight multiple is related to the vehicle's steering sensitivity. If the vehicle is sensitive to the steering rate, the higher the first weight multiple; the second weight multiple is related to the vehicle's lateral acceleration. If the vehicle is sensitive to the lateral acceleration, the higher the second weight multiple.

[0108] Optionally, step S403 of determining the weighted value corresponding to each Bezier curve based on the first weight value and the second weight value is as Figure 7 shown and includes:

[0109] Step S701, traverse the first weight value and the second weight value corresponding to each Bezier curve;

[0110] Step S702, calculate the sum result of the first weight value and the second weight value corresponding to each Bezier curve, and use the sum result to determine the weighted value corresponding to each Bezier curve.

[0111] After the result of the weighted value is calculated according to the above first weight value and second weight value, the final result is:

[0112] a = 4 * 1.6 + 3 = 6.4 + 3 = 9.4;

[0113] b = 3 * 1.6 + 1 = 4.8 + 1 = 5.8;

[0114] c = 5 * 1.6 + 2 = 8 + 2 = 10;

[0115] d = 2 * 1.6 + 4 = 3.2 + 4 = 7.2;

[0116] e = 1 * 1.6 + 5 = 1.6 + 5 = 6.6;

[0117] At this time, select the Bezier curve corresponding to the largest value of c as the optimal path between the starting line and the ending line.

[0118] As can be seen from the path planning method mentioned in the above embodiments, this method generates multiple Bezier curves according to the route heading of the AGV vehicle, and fully utilizes the variance of the curvature change and the curvature variance of the Bezier curve to find a path that satisfies the optimal route smoothness and the minimum radius of the route is greater than the minimum turning radius of the vehicle, so as to achieve accurate path planning only through low-order Bezier curves.

[0119] Corresponding to the path planning method provided in the foregoing embodiments, an embodiment of the present invention provides a path planning system, which is applied to the path planning of an AGV vehicle, as Figure 9 shown, the system includes:

[0120] An initialization module 910, configured to determine first information of the starting line of the AGV vehicle and second information of the ending line;

[0121] A Bezier curve generation module 920, configured to determine a first control point set corresponding to the starting line and a second control point set corresponding to the ending line according to the first information and the second information, and generate multiple Bezier curves by using the first control points in the first control point set and the second control points in the second control point set;

[0122] A calculation module 930, configured to calculate the variance of the curvature change rate and the curvature variance corresponding to each Bezier curve;

[0123] A path planning execution module 940, configured to determine the weighted value corresponding to each Bezier curve according to the variance of the curvature change rate and the curvature variance corresponding to each Bezier curve, and determine the Bezier curve corresponding to the maximum weighted value as the path between the starting line and the ending line.

[0124] As can be seen from the path planning system mentioned in the above embodiments, this system generates multiple Bezier curves according to the route heading of the AGV vehicle, and fully utilizes the variance of the curvature change and the curvature variance of the Bezier curve to find a path that satisfies the optimal route smoothness and the minimum radius of the route is greater than the minimum turning radius of the vehicle, so as to achieve accurate path planning only through low-order Bezier curves.

[0125] For the path planning system provided by the embodiment of the present invention, its implementation principle and the technical effects produced are the same as those of the foregoing path planning method embodiment. For a brief description, for the parts not mentioned in the system embodiment, reference may be made to the corresponding content in the foregoing path planning method embodiment.

[0126] This embodiment also provides an electronic device, and the structural schematic diagram of the electronic device is as Figure 10As shown, the device includes a processor 101 and a memory 102; wherein, the memory 102 is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the steps of the above path planning method.

[0127] Figure 10 The electronic device shown also includes a bus 103 and a communication interface 104, and the processor 101, the communication interface 104 and the memory 102 are connected through the bus 103.

[0128] Among them, the memory 102 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. The bus 103 may be an ISA bus, a PCI bus or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 10 only a bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0129] The communication interface 104 is used to connect to at least one user terminal and other network units through a network interface, and send the encapsulated IPv4 packet or IPv4 packet to the user terminal through the network interface.

[0130] The processor 101 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 101 or the instructions in the form of software. The above-mentioned processor 101 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present disclosure can be directly embodied as being executed and completed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 102, and the processor 101 reads the information in the memory 102 and combines its hardware to complete the steps of the method in the foregoing embodiments.

[0131] An embodiment of the present invention further provides a storage medium, on which a computer program is stored, and when the computer program is run by a processor, it executes the steps of the path planning method in the foregoing embodiments.

[0132] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, equipment, and methods can be implemented in other ways. The system embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other may be through some communication interfaces, and the indirect coupling or communication connection of the devices or units may be in an electrical, mechanical, or other form.

[0133] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] In addition, each functional unit in various embodiments of the present invention may be integrated in a processing unit, may exist separately physically for each unit, or two or more units may be integrated in one unit.

[0135] If the said function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0136] Finally, it should be noted that: the above-described embodiments are only specific implementation manners of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the technical field can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements for some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A path planning method, characterized in that, The method is applied to path planning of an AGV vehicle, and the method includes: Determine first information of a starting straight line and second information of an ending straight line of the AGV vehicle; Determine a first control point set corresponding to the starting straight line and a second control point set corresponding to the ending straight line according to the first information and the second information, and generate a plurality of Bézier curves by using a first control point in the first control point set and a second control point in the second control point set; Calculate the variance of the curvature change rate and the curvature variance corresponding to each Bézier curve; Determine the weighted value corresponding to each Bézier curve according to the variance of the curvature change rate and the curvature variance corresponding to each Bézier curve, and determine the Bézier curve corresponding to the maximum weighted value as the path between the starting straight line and the ending straight line.

2. The path planning method according to claim 1, characterized in that The determining the first control point set corresponding to the starting straight line and the second control point set corresponding to the ending straight line according to the first information and the second information, and generating a plurality of Bézier curves by using the first control point in the first control point set and the second control point in the second control point set includes: Obtain that the first information includes a first starting point coordinate, a first ending point coordinate and first direction information of the starting straight line; and obtain that the second information includes a second starting point coordinate, a second ending point coordinate and second direction information of the ending straight line; Determine the ray direction corresponding to the starting straight line according to the first direction information, and construct the first control point set along the ray direction based on the first starting point coordinate and the first ending point coordinate according to a preset first quantity; Determine the reflected ray direction corresponding to the ending straight line according to the second direction information, and construct the second control point set along the reflected ray direction based on the second starting point coordinate and the second ending point coordinate according to a preset second quantity; Traverse the first control points in the first control point set and the second control points in the second control point set, and generate a plurality of cubic Bézier curves by combining the first control points and the second control points pairwise in sequence.

3. The path planning method according to claim 1, characterized in that The calculating the variance of the curvature change rate and the curvature variance corresponding to each Bézier curve includes: For each Bézier curve, divide the Bézier curve into a plurality of curve segments according to a preset quantity, and calculate the curvature of each curve segment; Calculate the curvature change rate between adjacent curve segments according to the curvature of each curve segment, and calculate the variance of the curvature change rate corresponding to the Bézier curve according to the curvature change rate; Calculate the curvature variance corresponding to the Bézier curve according to the curvature of each curve segment.

4. The path planning method according to claim 1, wherein The determining the weighted value corresponding to each Bézier curve according to the variance of the curvature change rate and the curvature variance corresponding to each Bézier curve includes: Obtain the variance of the curvature change rate corresponding to each Bézier curve, determine a first sorting result of the variance of the curvature change rate, and determine a first weight value of each Bézier curve according to the first sorting result; Obtain the curvature variance corresponding to each of the Bezier curves, determine the second sorting result of the curvature variance, and determine the second weight value of each of the Bezier curves according to the second sorting result; Determine the weighted value corresponding to each of the Bezier curves based on the first weight value and the second weight value.

5. The path planning method according to claim 4, wherein The obtaining the curvature change rate variance corresponding to each of the Bezier curves, determining the first sorting result of the curvature change rate variance, and determining the first weight value of each of the Bezier curves according to the first sorting result includes: Obtain the curvature change rate variances corresponding to all of the Bezier curves, obtain the first sorting result after sorting according to the values of the curvature change rate variances, and use the first sorting result to determine the first index value corresponding to each of the Bezier curves; Obtain a preset first weight multiplier, and use the first index value and the first weight multiplier to determine the first weight value.

6. The path planning method according to claim 5, wherein The obtaining the curvature variance corresponding to each of the Bezier curves, determining the second sorting result of the curvature variance, and determining the second weight value of each of the Bezier curves according to the second sorting result includes: Obtain the curvature variances corresponding to all of the Bezier curves, obtain the second sorting result after sorting according to the values of the curvature variances, and use the second sorting result to determine the second index value corresponding to each of the Bezier curves; Obtain a preset second weight multiplier, and use the second index value and the second weight multiplier to determine the second weight value.

7. The path planning method according to claim 6, characterized in that The first weight multiplier and the second weight multiplier satisfy the following formula: w2 = 1 - w1; Among them, w1 is the first weight magnification factor; w2 is the second weight magnification factor; w max is the maximum angular velocity of the AGV vehicle; a lat_max is the maximum lateral acceleration of the AGV vehicle.

8. The path planning method according to claim 4, wherein Determining the weighted value corresponding to each of the Bezier curves based on the first weight value and the second weight value includes: Traverse the first weight value and the second weight value corresponding to each of the Bezier curves; Calculate the summation result of the first weight value and the second weight value corresponding to each of the Bezier curves, and use the summation result to determine the weighted value corresponding to each of the Bezier curves.

9. A path planning system, characterized in that, The system is applied to the path planning of an AGV vehicle, and the system includes: An initialization module, configured to determine the first information of the starting straight line and the second information of the ending straight line of the AGV vehicle; A Bezier curve generation module, configured to determine a first control point set corresponding to the starting straight line and a second control point set corresponding to the ending straight line according to the first information and the second information, and generate a plurality of Bezier curves by using the first control points in the first control point set and the second control points in the second control point set; A calculation module, configured to calculate the curvature change rate variance and the curvature variance corresponding to each of the Bezier curves; A path planning execution module, configured to determine the weighted value corresponding to each of the Bezier curves according to the curvature change rate variance and the curvature variance corresponding to each of the Bezier curves, and determine the Bezier curve corresponding to the maximum weighted value as the path between the starting straight line and the ending straight line.

10. An electronic device, characterized in that, It includes a processor and a memory, and the memory stores computer-executable instructions that can be executed by the processor. The processor executes the computer-executable instructions to implement the steps of the path planning method according to any one of claims 1 to 8.

Images