Path Planning Method, Apparatus, Device and Computer Readable Storage Medium

Abstract

The present application discloses a path planning method, device, equipment and computer-readable storage medium, belonging to the field of wireless communication technology. When the driverless forklift reaches a preset position, this application detects whether there is a deviation in the placement position of the goods to be picked up, where the preset position is the pause position when the driverless forklift is ready to pick up the goods; if so, the picking point coordinates are re-determined according to the placement position; the genetic algorithm is used to plan the picking route of the driverless forklift from the preset position to the picking point coordinates; the driverless forklift is controlled to reach the picking point coordinates according to the picking route to complete the picking, wherein when the driverless forklift reaches the picking point coordinates according to the picking route, the body posture of the driverless forklift is consistent with the tray of the goods to be picked up. It realizes that the driverless forklift is applicable to the picking scenario where the position of the goods changes in real time.

Description

Technical Field

[0001] The present application relates to the field of intelligent industrial robots, and particularly to a path planning method, device, equipment, and computer-readable storage medium. Background Art

[0002] With the rapid popularization of AGV (Automated Guided Vehicle), there is a scenario where a manual forklift places goods at a connection position, and an autonomous forklift picks up the goods at the connection position. Since the manual forklift cannot guarantee the accuracy of picking up and placing goods, there is a risk that the goods are placed with too large a deviation, resulting in the autonomous forklift hitting the goods.

[0003] One way to solve this problem is to draw a compact limit frame on the ground, set the positions for picking up and placing goods in advance, and draw the driving route of the autonomous forklift. When performing the picking up and placing operations, first ensure that the manual forklift puts the goods into the limit frame, and then the autonomous forklift drives according to the preset route to pick up and place the goods. This method will greatly increase the difficulty of manual operations and significantly reduce the operation efficiency.

[0004] Therefore, there is currently a technical problem that autonomous forklifts are difficult to adapt to the real-time changes in the positions of goods.

[0005] The above content is only used to assist in understanding the technical solution of the present application, and does not represent an admission that the above content is prior art. Summary of the Invention

[0006] The main purpose of the present application is to provide a path planning method, device, equipment, and computer-readable storage medium, aiming to solve the technical problem that autonomous forklifts are difficult to adapt to the real-time changes in the positions of goods.

[0007] To achieve the above object, the present application provides a path planning method, and the path planning method includes the following steps:

[0008] When the autonomous forklift reaches a preset position, detect whether there is a deviation in the placement position of the goods to be picked up, where the preset position is the pause position when the autonomous forklift is ready to pick up the goods;

[0009] If so, re-determine the coordinates of the picking point according to the placement position;

[0010] Use a genetic algorithm to plan the picking route of the autonomous forklift from the preset position to the coordinates of the picking point;

[0011] Control the autonomous forklift to reach the coordinates of the picking point according to the picking route to complete the picking. When the autonomous forklift reaches the coordinates of the picking point according to the picking route, the body posture of the autonomous forklift is consistent with the pallet of the goods to be picked up.

[0012] Optionally, the step of planning the picking route of the driverless forklift from the preset position to the picking point coordinates by using a genetic algorithm includes:

[0013] Obtain an initial population based on a Bezier curve;

[0014] Continuously perform selection iteration on the initial population until the fitness of the optimal individual reaches a given threshold to obtain a final generation population;

[0015] Decode the individuals of the final generation population to obtain target control points, and the curve fitted by the target control points is the picking route.

[0016] Optionally, the step of obtaining an initial population based on a Bezier curve includes:

[0017] Obtain an initial individual based on the Bezier curve;

[0018] Set the initial population size to a first preset number,

[0019] Repeat the step of obtaining the initial individual the number of times of the preset number to obtain an initial population of the first preset number.

[0020] Optionally, the step of obtaining an initial individual based on the control points of the Bezier curve includes:

[0021] Select the preset position and the picking point coordinates as the first control point and the last control point of the Bezier curve;

[0022] Insert a second preset number of control points between the first control point and the last control point, and the coordinates of the second preset number of control points are randomly obtained;

[0023] Encode all the control points of the Bezier curve in sequence to obtain an initial individual.

[0024] Optionally, the step of inserting a second preset number of control points between the first control point and the last control point, and the coordinates of the second preset number of control points are randomly obtained further includes:

[0025] Set that the penultimate control point and the last control point are on the same straight line, and the direction of the straight line is perpendicular to the front surface of the tray, so that when the driverless forklift reaches the picking point coordinates, the body posture of the driverless forklift is consistent with the tray of the goods to be picked.

[0026] Optionally, the step of inserting a second preset number of control points between the first control point and the last control point, and the coordinates of the second preset number of control points are randomly obtained further includes:

[0027] It is set that all the control points of the second preset quantity are located within a circle with the line connecting the first control point and the last control point as the diameter, so as to reduce the number of iterations. Among them, the second control point is the in-point of the first control point and the third control point.

[0028] Optionally, after the step of controlling the driverless forklift to reach the picking point coordinates according to the picking route to complete picking, it includes:

[0029] When the driverless forklift reaches the picking point coordinates, control the driverless forklift to pick up the goods to be picked;

[0030] When the driverless forklift completes picking, control the driverless forklift to return to the preset position according to the picking route.

[0031] In addition, to achieve the above object, the present application further provides a path planning device, and the device includes:

[0032] A detection module, configured to detect whether there is a deviation in the placement position of the goods to be picked when the driverless forklift reaches the preset position, and the preset position is the pause position when the driverless forklift is ready to pick up the goods;

[0033] A determination module, configured to, if so, re-determine the picking point coordinates according to the placement position;

[0034] A planning module, configured to plan the picking route of the driverless forklift from the preset position to the picking point coordinates by using a genetic algorithm;

[0035] A control module, configured to control the driverless forklift to reach the picking point coordinates according to the picking route to complete picking. Among them, when the driverless forklift reaches the picking point coordinates according to the picking route, the body posture of the driverless forklift is consistent with the tray of the goods to be picked.

[0036] In addition, to achieve the above object, the present application further provides a path planning device, and the device includes: a memory, a processor, and a path planning program stored on the memory and executable on the processor, and the path planning program is configured to implement the steps of the path planning method according to any one of claims 1 to 7.

[0037] In addition, to achieve the above object, the present application further provides a readable storage medium, on which a path planning program is stored, and when the path planning program is executed by a processor, it implements the steps of the path planning method according to any one of claims 1 to 7.

[0038] In order to make the driverless forklift applicable to scenarios where the positions of goods change in real time, after the driverless forklift trolley reaches the preset position, this application detects whether there is a deviation in the placement position of the goods to be picked up, and further re-determines the coordinates of the picking point. On this basis, this solution further designs a genetic algorithm based on Bessel curves, which is responsible for planning the picking route from the preset position to the coordinates of the picking point, enabling the driverless forklift to complete the picking task in the case of deviation in the position of the goods to be picked up, and realizing the application of the driverless forklift to the picking scenario where the positions of goods change in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a schematic structural diagram of a path planning device in the hardware operating environment related to the solution of the embodiment of this application;

[0040] Figure 2 is a schematic flowchart of the first embodiment of the path planning method of this application;

[0041] Figure 3 is a flowchart of the genetic algorithm of the first embodiment of the path planning method of this application;

[0042] Figure 4 is a schematic diagram of a driverless forklift picking up goods in the third embodiment of the path planning method of this application;

[0043] Figure 5 is a schematic diagram of the functional modules of the first embodiment of the path planning device of this application.

[0044] The realization, functional features and advantages of the purpose of this application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0046] Refer to Figure 1 , Figure 1 is a schematic structural diagram of a path planning device in the hardware operating environment related to the solution of the embodiment of this application.

[0047] As Figure 1As shown in the figure, the path planning device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wireless-Fidelity (WI-FI) interface). The memory 1005 may be a high-speed Random Access Memory (RAM) or a stable Non-Volatile Memory (NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0048] Those skilled in the art can understand that Figure 1 the structure shown in does not constitute a limitation on the path planning device, and it may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0049] As Figure 1 shown, in the memory 1005 as a storage medium, there may be included an operating system, a data storage module, a network communication module, a user interface module, and a path planning program.

[0050] In Figure 1 the path planning device shown, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with users; the processor 1001 and the memory 1005 in the path planning device of the present application may be set in the path planning device. The path planning device calls the path planning program stored in the memory 1005 through the processor 1001 and executes the path planning method provided by the embodiments of the present application.

[0051] The embodiments of the present application provide a path planning method. Referring to Figure 2 , Figure 2 it is a schematic flowchart of the first embodiment of a path planning method of the present application.

[0052] In this embodiment, the path planning method includes:

[0053] Step S10: When the driverless forklift reaches the preset position, detect whether there is a deviation in the placement position of the goods to be picked up. The preset position is the pause position when the driverless forklift is ready to pick up goods.

[0054] Step S20: If so, re-determine the pick-up point coordinates according to the placement position.

[0055] Specifically, in order to make the driverless forklift applicable to the scenario where the position of the goods changes in real time, after the driverless forklift reaches the preset position, this application detects whether there is a deviation in the placement position of the goods to be picked up. If there is a deviation in the position of the goods to be picked up due to the arbitrary placement of the manual forklift, the pick-up point coordinates are further re-determined. In order to detect the placement position of the goods to be picked up and thus determine the pick-up point coordinates, a position detection device capable of sensing the position of the goods to be picked up is required. The position detection device described in this embodiment is non-contact, including but not limited to, video acquisition devices, optical imaging devices, lidar, millimeter wave radar, inertial measurement devices, etc.

[0056] Optionally, when the position detection device is an optical imaging device, the optical imaging device can be a depth camera, and the depth camera can detect the depth distance of the captured space. By obtaining the distance of each point in the image from the camera and adding the two-dimensional coordinates of the point in the 2D image, the three-dimensional space coordinates of each point in the image can be obtained. After taking a photo of the goods to be picked up when the driverless forklift reaches the preset position, the relative position between the placement position of the goods to be picked up and the driverless forklift can be determined, and the coordinates of the pick-up point in the world coordinate system can be determined by using the camera imaging principle and coordinate system conversion.

[0057] Optionally, when the displacement detection device is a lidar, the lidar is composed of a laser transmitter, an optical receiver, a turntable and an information processing system, etc. The laser transmitter converts the electrical pulse into an optical pulse to emit a detection signal to the target, and then compares the received signal (target echo) reflected from the target with the transmitted signal. After appropriate processing by the processor, relevant information about the goods to be picked up can be obtained, such as the distance, azimuth, height, speed, attitude, and even shape of the goods to be picked up from the driverless forklift. Further comprehensive analysis can obtain the pick-up point coordinates.

[0058] Step S30: Use the genetic algorithm to plan the pick-up route for the driverless forklift to reach the pick-up point coordinates from the preset position.

[0059] Specifically, the genetic algorithm is a randomized search method evolved by drawing on the evolutionary laws in the biological world (the survival-of-the-fittest and the genetic mechanism of natural selection). Its main features are that it directly operates on structural objects without the limitations of derivative calculation and function continuity; it has inherent implicit parallelism and better global optimization capabilities; it uses a probabilistic optimization method that can automatically obtain and guide the optimization search space, adaptively adjust the search direction, and does not require definite rules. This application uses the genetic algorithm for the control points of planning the route for the unmanned forklift to reach the picking point. Refer to Figure 3 , Figure 3 which is the flowchart of the genetic algorithm for the first embodiment of the path planning method of this application.

[0060] Furthermore, the step S30 includes:

[0061] Step S31: Obtain an initial population based on Bezier curves;

[0062] Step S32: Continuously perform selection iterations on the initial population until the fitness of the optimal individual reaches a given threshold to obtain the final population;

[0063] Step S33: Decode the individuals in the final population to obtain the target control points, and the curve fitted by the target control points is the picking route.

[0064] Specifically, since the genetic algorithm is a search algorithm generated by the theory of evolution and genetic mechanism, a lot of knowledge of biological genetics will be used in this algorithm. The following are some term explanations to be used in this embodiment: A chromosome can also be called a genotype individual, and a certain number of individuals form a population, and the number of individuals in the population is called the population size. The degree of adaptation of each individual to the environment is called fitness. In order to reflect the adaptability of the chromosome, a function that can measure each chromosome in the problem is introduced, called the fitness function. This function calculates the probability of an individual being used in the population.

[0065] The process of obtaining the initial population is actually the process of parameterizing the actual problem. After several genetic iterations of the initial population, the optimal result selected by the fitness function can be decoded to obtain the solution of the actual problem.

[0066] The genetic iteration includes selection, crossover, and mutation operations. Selection operation: Apply the selection operator to the population. The purpose of selection is to directly inherit the optimized individuals to the next generation or generate new individuals through paired crossover and then inherit them to the next generation. The selection operation is based on the fitness evaluation of individuals in the population. Crossover operation: Apply the crossover operator to the population. The crossover operator plays a core role in the genetic algorithm. Mutation operation: Apply the mutation operator to the population. That is, make changes to the gene values at certain gene loci of the individual strings in the population.

[0067] In the theory of evolution, fitness represents the adaptability of an individual to the environment and also represents the ability of the individual to reproduce offspring. The fitness function of the genetic algorithm, also called the evaluation function, is an index used to judge the quality of individuals in the population, and it is evaluated according to the objective function of the problem to be solved.

[0068] In the search and evolution process, the genetic algorithm generally does not require other external information. It only uses the evaluation function to evaluate the quality of individuals or solutions and uses it as the basis for subsequent genetic operations. Since in the genetic algorithm, the fitness function needs to compare and sort and calculate the selection probability based on this, the value of the fitness function should be positive. Thus, in many cases, it is necessary to map the objective function into a fitness function in the form of maximizing and with non-negative function values.

[0069] The design of the fitness function mainly meets the following conditions:

[0070] (a)Single-valued, continuous, non-negative, maximizing

[0071] (b)Reasonable, consistent

[0072] (c)Small computational amount

[0073] (d)Strong versatility.

[0074] In specific applications, the design of the fitness function should be determined in combination with the requirements of the problem to be solved. The design of the fitness function directly affects the performance of the genetic algorithm. The fitness function adopted in this embodiment is the sum of the squares of the curvatures of all fitting points on the Bessel curve. Let F represent the fitness function. Assume that there are n fitting points on the Bessel curve fitted by five control points obtained after decoding the k-th group of individuals in the T-th generation population. The curvature of the curve at the i-th fitting point is ,then the fitness function of this individual is

[0075] Assume that there are t groups of individuals in the T-th generation after selection, crossover, and mutation. Then the probability that the k-th ( )group of individuals is selected during inheritance is

[0076] Eliminate the (t - 20) groups with relatively small probabilities from the t groups of individuals in the T-th generation population, and the remaining 20 groups of individuals form the (T + 1)-th generation population.

[0077] The condition for ending the genetic algorithm is set to

[0078] .

[0079] When the fitness of the optimal individual reaches a given threshold, or when the fitness of the optimal individual and the population fitness no longer increase, or when the number of iterations reaches a preset number of generations, the algorithm terminates.

[0080] The curve fitted by the control points after decoding the individuals that meet the conditions is the picking route.

[0081] Step S40: Control the driverless forklift to reach the picking point coordinates according to the picking route to complete the picking. When the driverless forklift reaches the picking point coordinates according to the picking route, the body posture of the driverless forklift is consistent with the pallet of the goods to be picked.

[0082] In this embodiment, in order to make the driverless forklift applicable to the scenario where the position of the goods changes in real time, after the driverless forklift reaches the preset position, it detects whether there is a deviation in the placement position of the goods to be picked, and further re-determines the picking point coordinates. On this basis, this embodiment further designs a genetic algorithm based on the Bezier curve, which is responsible for planning the route from the preset position to the picking point coordinates, enabling the driverless forklift to complete the picking task in the case of deviation of the position of the goods to be picked, and realizing the picking scenario where the driverless forklift is applicable to the real-time change of the goods position.

[0083] Further, based on the above embodiment, a second embodiment of the present application is provided, and the step S31 includes:

[0084] Step S34: Obtain the initial individuals based on the Bezier curve;

[0085] Step S35: Set the initial population size to the first preset number;

[0086] Further, the step S34 includes:

[0087] Step S50: Select the preset position and the picking point coordinates as the first control point and the last control point of the Bezier curve;

[0088] Step S51: Insert a second preset number of control points between the first control point and the last control point, and the coordinates of the second preset number of control points are randomly obtained;

[0089] Step S52: Encode all the control points of the Bezier curve in sequence to obtain the initial individuals.

[0090] Further, step S51 includes:

[0091] Step S53: Set the penultimate control point and the last control point to be on the same straight line, and the direction of the straight line is perpendicular to the front surface of the tray, so that when the driverless forklift reaches the coordinates of the picking point, the body posture of the driverless forklift is consistent with the tray of the goods to be picked.

[0092] Step S54: Set that the second preset number of control points are all within the circle with the line connecting the first control point and the last control point as the diameter, so as to reduce the number of iterations. Among them, the second control point is the inner point of the first control point and the third control point.

[0093] Specifically, in this embodiment, the driverless forklift is a driverless forklift, which includes a vehicle body and a tray. A total of five control points are set, and the second preset number is 3.

[0094] After the driverless forklift reaches the preset position, the current coordinates of the driverless forklift and the picking point coordinates fed back by the position detection device are used as the first control point and the fifth control point of the Bezier curve;

[0095] The second, third, and fourth control points are inserted between the first control point and the fifth control point of the Bezier curve. The coordinates of the three inserted control points are randomly obtained, but follow the following principles: ① To make the body posture of the driverless forklift consistent with the tray when reaching the end point, the fourth and fifth control points need to be on the same straight line, and this straight line passes through the parking point (i.e., the fifth control point), and the direction of the straight line is perpendicular to the front surface of the tray; ② To reduce the number of iterations, the second control point is the inner point of the first and third control points, and the three inserted control points are all within the circle with the line connecting the first and fifth control points as the diameter.

[0096] Encode the five control points of the Bezier curve in sequence to obtain the initial individual;

[0097] Assume that the current coordinates of the driverless forklift are , and the picking point coordinates fed back by the position detection device are , these two points are the first and fifth control points, and the direction of the parking point is denoted as , and the coordinates of the three inserted control points are respectively denoted as 、 、 , take

[0098]

[0099] , then , . Represented by 8-bit binary coding symbols respectively , , different encodings can be obtained respectively, and the corresponding relationships during parameter encoding are as follows: kinds of different encodings, and the corresponding relationships during parameter encoding are:

[0100] ,

[0101] ,

[0102] ,

[0103] ……,

[0104] .

[0105]

[0106] Similarly, randomly select three control points that meet the constraints of ① and ②, and encode them according to the above corresponding relationships to obtain a group of initial individuals.

[0107] Correspondingly, the decoding function is

[0108]

[0109] Step S36: Repeat the step of obtaining the initial individuals for the number of times of the preset quantity to obtain an initial population of the first preset quantity.

[0110] Repeat the above steps 20 times to obtain an initial population with a population size of 20.

[0111] In this embodiment, in order to make the driverless forklift applicable to the scenario where the cargo position changes in real time, a genetic algorithm is used to design the picking route, and the method is simple and easy to implement.

[0112] Furthermore, based on the above embodiment, referring to Figure 4 , a third embodiment of the present application is provided, and after step S40, it includes:

[0113] Step S41: When the driverless forklift reaches the picking point coordinates, control the driverless forklift to pick up the goods to be picked;

[0114] Step S42: When the driverless forklift completes picking up the goods, control the driverless forklift to return to the preset position according to the picking route.

[0115] Specifically, in this embodiment, the position detection device is a depth camera, the application scenario is picking up goods, and the preset position is the visual detection point. Referring to Figure 4 , Figure 4Schematic diagram of an automated forklift picking up goods for the third embodiment of the path planning method of this application. The numbers 1 to 6 respectively represent an automated forklift, a depth camera, the starting point of the picking route, the picking route, the ending point of the picking route, and goods. The automated forklift's autonomous picking process is as follows:

[0116] The automated forklift arrives at the visual inspection point along the route planned by the scheduling system; the vision module triggers the depth camera to take a photo, obtains the position of the goods based on the point cloud image, and calculates the coordinates of the picking stop point; the control module plans a picking path line based on the Bezier curve using the genetic algorithm according to the vehicle's current coordinates and the picking point coordinates; the automated forklift arrives at the picking point along the autonomously planned path line to complete the picking task; the automated forklift returns to the visual inspection point along the original route; the automated forklift arrives at the goods dropping point along the route planned by the scheduling system.

[0117] In this embodiment, by arriving at the visual inspection point to trigger the depth camera to determine the picking point coordinates and using the genetic algorithm to plan the route for the automated forklift to reach the picking point, the risk of the automated forklift picking up goods incorrectly and colliding with the goods caused by inaccurate placement of the manually placed goods is avoided.

[0118] In addition, an embodiment of this application also proposes a path planning device. Refer to Figure 5 , Figure 5 Schematic diagram of the functional modules of the first embodiment of the path planning device of this application. The path planning device includes:

[0119] Detection module 10, used to detect whether there is a deviation in the placement position of the goods to be picked up when the automated forklift arrives at a preset position, and the preset position is the pause position when the automated forklift is ready to pick up goods;

[0120] Determination module 20, used to, if so, re-determine the picking point coordinates according to the placement position;

[0121] Planning module 30, used to plan the picking route of the automated forklift from the preset position to the picking point coordinates using the genetic algorithm;

[0122] Control module 40, used to control the automated forklift to reach the picking point coordinates according to the picking route to complete the picking. Among them, when the automated forklift reaches the picking point coordinates according to the picking route, the body posture of the automated forklift is consistent with the tray of the goods to be picked up.

[0123] Among them, the specific embodiments executed by each module in the path planning device of this application are basically the same as those of each embodiment of the above path planning method, and will not be elaborated here.

[0124] In addition, an embodiment of this application also proposes a readable storage medium.

[0125] A path planning program is stored on the readable storage medium of the present application. When the path planning program is executed by a processor, the steps of the path planning method described above are implemented.

[0126] Among them, the specific embodiments in which the path planning program stored in the readable storage medium of the present application is executed by the processor are basically the same as those of the above path planning method embodiments, and will not be elaborated here.

[0127] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or system. Without further limitation, the element defined by the statement "including a path planning" does not exclude the existence of additional identical elements in the process, method, article or system including the element.

[0128] The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0129] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0130] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A path planning method, characterized in that, The path planning method includes the following steps: When the driverless forklift reaches a preset position, it detects whether there is a deviation in the placement position of the goods to be picked up. The preset position is the pause position when the driverless forklift is ready to pick up the goods; If so, re-determine the coordinates of the picking point according to the placement position; Use the genetic algorithm to plan the picking route for the driverless forklift to reach the coordinates of the picking point from the preset position; Control the driverless forklift to reach the coordinates of the picking point according to the picking route to complete the picking. Among them, the second-to-last control point and the last control point of the picking route are on the same straight line, and the direction of the straight line is perpendicular to the front surface of the pallet of the goods to be picked up, so that when the driverless forklift reaches the coordinates of the picking point according to the picking route, the body posture of the driverless forklift is consistent with the pallet.

2. The path planning method according to claim 1, characterized in that, The step of using the genetic algorithm to plan the picking route for the driverless forklift to reach the coordinates of the picking point from the preset position includes: Obtain an initial population based on Bezier curves; Continuously perform selection iteration on the initial population until the fitness of the optimal individual reaches a given threshold to obtain the final generation population; Decode the individuals of the final generation population to obtain target control points, and the curve fitted by the target control points is the picking route.

3. The path planning method according to claim 2, characterized in that, The step of obtaining an initial population based on Bezier curves includes: Obtain an initial individual based on the Bezier curve; Set the initial population size to a first preset number, and repeat the step of obtaining the initial individual for the number of times of the preset number to obtain an initial population of the first preset number.

4. The path planning method according to claim 3, characterized in that, The step of obtaining an initial individual based on the control points of the Bezier curve includes: Select the preset position and the coordinates of the picking point as the first control point and the last control point of the Bezier curve; Insert a second preset number of control points between the first control point and the last control point, and the coordinates of the second preset number of control points are randomly obtained; Encode all the control points of the Bezier curve in sequence to obtain an initial individual.

5. The path planning method according to claim 4, characterized in that, The step of inserting a second preset number of control points between the first control point and the last control point, and the coordinates of the second preset number of control points are randomly obtained further includes: Set that the second-to-last control point and the last control point of the Bezier curve are on the same straight line, and the direction of the straight line is perpendicular to the front surface of the pallet, so that when the driverless forklift reaches the coordinates of the picking point, the body posture of the driverless forklift is consistent with the pallet of the goods to be picked up.

6. The path planning method according to claim 4, characterized in that, The step of inserting a second preset number of control points between the first control point and the last control point, and the coordinates of the second preset number of control points are randomly obtained further includes: Set that the second preset number of control points are all within the circle with the line connecting the first control point and the last control point as the diameter to reduce the number of iterations, where the second control point is the inner point of the first control point and the third control point.

7. The path planning method according to claim 1, characterized in that, After the step of controlling the driverless forklift to reach the coordinates of the picking point according to the picking route to complete the picking includes: After the driverless forklift reaches the coordinates of the picking point, control the driverless forklift to pick up the goods to be picked. After the driverless forklift completes picking up the goods, control the driverless forklift to return to the preset position according to the picking route.

8. A path planning device, characterized in that, The device includes: A detection module, configured to detect whether there is a deviation in the placement position of the goods to be picked when the driverless forklift reaches the preset position, where the preset position is the pause position when the driverless forklift is ready to pick up the goods; A determination module, configured to, if so, re-determine the coordinates of the picking point according to the placement position; A planning module, configured to use a genetic algorithm to plan a picking route for the driverless forklift to reach the coordinates of the picking point from the preset position; A control module, configured to control the driverless forklift to reach the coordinates of the picking point according to the picking route to complete picking up the goods, wherein the second-to-last control point and the last control point of the picking route are located on the same straight line, and the direction of the straight line is perpendicular to the front surface of the pallet of the goods to be picked, so that when the driverless forklift reaches the coordinates of the picking point according to the picking route, the body posture of the driverless forklift is consistent with the pallet.

9. A path planning device, characterized in that, The device includes: a memory, a processor, and a path planning program stored on the memory and executable on the processor, where the path planning program is configured to implement the steps of the path planning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A path planning program is stored on the computer-readable storage medium, and when the path planning program is executed by a processor, it implements the steps of the path planning method according to any one of claims 1 to 7.

Images