Forklift pallet automatic fork picking method, device, computer equipment and storage medium
By acquiring pallet pose information to construct a coordinate system, generating a planned path and selecting a collision-free path, the problem of fork collisions with pallets caused by manual pallet placement is solved, and safe picking by unmanned forklifts is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN HAIXING ZHIJIA TECH CO LTD
- Filing Date
- 2023-10-26
- Publication Date
- 2026-07-21
AI Technical Summary
In existing technologies, due to errors in manually placing pallets, the forks of forklifts are prone to colliding with the pallets during forklift operations, which can prevent the operation from being completed or even cause safety accidents.
By acquiring the pallet's pose information, a target coordinate system is constructed, multiple planned paths are generated, the positional relationship between the forks and the pallet is determined, and a collision-free target path is selected to avoid collision risks.
It enables unmanned forklifts to safely pick up pallets in different positions, avoiding collisions between the forks and pallets and ensuring smooth operation.
Smart Images
Figure CN117208814B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of intelligent vehicle technology, specifically to a method, apparatus, computer equipment, and storage medium for automatically picking up pallets from a forklift. Background Technology
[0002] With the continuous development and iteration of intelligent and digital technologies, the level of automation in on-site operations of engineering vehicles is also increasing, and unmanned forklift operations in industrial parks have become a current development trend. Unmanned forklifts are intelligent industrial vehicles that can autonomously complete path following and loading / unloading tasks without human operation, and their automated loading / unloading is a very important part of the entire operation process.
[0003] The specific implementation method is as follows: the vehicle is located by laser / vision sensors, and the navigation positioning guides the vehicle to the target location. The vision sensor is used to obtain the target pallet pose to realize the automatic pallet picking action.
[0004] Currently, in most work scenarios, pallets are generally placed manually. Due to human error or factors such as factory management level, the placement posture of the pallet often deviates significantly from the ideal posture. Using only visual sensors to obtain the actual posture of the pallet to assist in path planning may not be able to fully meet the forklift requirements of all scenarios. In some scenarios where the pallet is significantly deviated, the forklift may collide with the pallet during the forklift operation, causing production accidents.
[0005] Therefore, the current method of manually placing pallets is prone to the risk of collision between the forks and the pallet, which may prevent the pallet picking operation from being completed or even cause safety accidents. Summary of the Invention
[0006] In view of this, the present disclosure provides a method, apparatus, computer equipment and storage medium for automatic pallet picking by forklifts, in order to solve the problem that the current method of manually placing pallets is prone to the risk of collision between the forks and the pallet, which may lead to the failure of pallet picking operations or even cause safety accidents.
[0007] In a first aspect, this disclosure provides a method for automatically picking up a forklift pallet, the method comprising:
[0008] Upon receiving the instruction information that the target forklift will automatically pick up the pallet, obtain the pallet's position information;
[0009] Construct the target coordinate system based on the tray's pose information;
[0010] Based on the target forklift's initial positioning information and target coordinate system, generate multiple planned paths for the target forklift to travel.
[0011] Based on the planned path and target coordinate system, determine the positional relationship between the forks of the target forklift and the pallet;
[0012] The target path is selected from the planned path based on the positional relationship. The target path is the path that enables the forklift to automatically pick up the pallet.
[0013] In this embodiment of the disclosure, the pallet's pose information is obtained by acquiring the instruction information for the target forklift to automatically pick up the pallet; and a target coordinate system is constructed based on the pallet's pose information.
[0014] Based on the first positioning information of the target forklift and the target coordinate system, multiple planned paths for the target forklift are generated. Based on the planned paths and the target coordinate system, the positional relationship between the forklift's forks and the pallet is determined. Based on the positional relationship, a target path is selected from the planned paths, whereby the target forklift automatically picks up the pallet. This embodiment of the disclosure constructs a target coordinate system based on the pallet's pose information, then obtains a planned path based on the target forklift's current positioning information and the target coordinate system. It determines whether the planned path can achieve safe operation and selects the target path that can achieve safe operation. This avoids the collision risk caused by space and pallet pose limitations, solving the problem in related technologies where manual pallet placement easily leads to the risk of forklift collisions with the pallet, making pallet picking operations impossible.
[0015] In one optional implementation, a target coordinate system is constructed based on the tray's pose information, including:
[0016] Based on the pallet's position information, determine the perpendicular line of the pallet in the preset direction;
[0017] Construct the target coordinate system using the vertical line as a reference line.
[0018] In one optional implementation, based on the first positioning information of the target forklift and the target coordinate system, multiple planned paths for the target forklift are generated, including:
[0019] The first positioning information of the target forklift is converted into the target coordinate system to determine the initial starting point and initial ending point of the target forklift's movement. The initial starting point is the first positioning information, and the initial ending point is the critical point at which the forks of the target forklift can be aligned with the pallet for correct insertion.
[0020] Based on the initial starting point and initial ending point, obtain multiple planned paths generated by the target forklift in the target coordinate system.
[0021] In this embodiment of the disclosure, by obtaining the initial starting point and multiple initial ending points when the target forklift is traveling, and then using a polynomial fitting method to construct a polynomial, multiple planned paths are generated for subsequent verification of the feasibility of the paths.
[0022] In one optional implementation, determining the positional relationship between the forks and the pallet based on the planned path and the target coordinate system includes:
[0023] Select candidate routes from the planned routes whose travel distance is less than a preset threshold;
[0024] Obtain the movement trajectory of the forks of the target forklift during its journey along the candidate path;
[0025] Transform the movement trajectory of the forks into the target coordinate system to determine the positional relationship between the forks and the pallet.
[0026] In this embodiment of the disclosure, the movement trajectory of the fork tip during the vehicle's tracking process is predicted by planning the path and using a vehicle kinematics model, and it is determined whether the trajectory of the fork tip poses a risk of collision with the pallet, thereby verifying the feasibility of the path.
[0027] In one optional implementation, selecting the target path from the planned paths based on location relationships includes:
[0028] If the positional relationship indicates that there is no collision between the forks and the pallet, then the candidate path is taken as the target path;
[0029] If the positional relationship indicates a collision between the forks and the pallet, then obtain the remaining paths in the planned path besides the candidate paths;
[0030] Select the target path from the remaining paths;
[0031] If no target path is selected from the remaining paths, a splicing segment is generated based on the initial starting point, the initial ending point, and the second positioning information of the tray. The splicing segment includes a curve composed of the initial starting point and the initial ending point, and a straight line composed of the initial ending point and the second positioning information.
[0032] Determine the target path based on the splicing lines.
[0033] In this embodiment of the disclosure, the strategy determines whether the pallet can be picked up based on the current pose of the forklift. If not, the current pose of the forklift is changed to obtain a better initial pose for planning.
[0034] In one alternative implementation, selecting the target path from the remaining paths includes:
[0035] The path to be executed is selected from the remaining paths based on the cost function;
[0036] The positional relationship between the forks and the pallet is determined based on the path to be executed until no collision occurs between the forks and the pallet. The path to be executed without collision is then taken as the target path.
[0037] In this embodiment of the disclosure, if the current path predicts that a collision between the forks and the pallet may occur, the planned path is selected again to avoid the failure of the forklift operation due to pallet position deviation.
[0038] In one optional implementation, determining the target path based on the splicing segment includes:
[0039] The target forklift is reversed based on the splicing line segment. The initial starting point and initial ending point of the target forklift are adjusted. The multiple planned paths generated by the target forklift in the target coordinate system are obtained from the steps and the loop is started until the target path is obtained. The loop ends, so that the target forklift can automatically pick up the pallet.
[0040] In this embodiment of the disclosure, if the current path predicts that a collision between the forks and the pallet may occur, the current vehicle position is adjusted to give it a more planned starting position, so as to avoid the failure of the forklift operation due to the pallet position deviation.
[0041] Secondly, this disclosure provides an apparatus for automatically picking up pallets from a forklift, the apparatus comprising:
[0042] The acquisition module is used to acquire the pallet's position information when the target forklift automatically picks up the pallet.
[0043] The construction module is used to construct the target coordinate system based on the pose information of the pallet;
[0044] The generation module is used to generate multiple planned paths for the target forklift based on the target forklift's initial positioning information and the target coordinate system.
[0045] The determination module is used to determine the positional relationship between the forks of the target forklift and the pallet based on the planned path and the target coordinate system;
[0046] The selection module is used to select the target path from the planned path based on the positional relationship. The target path is the path that enables the forklift to automatically pick up the pallet.
[0047] Thirdly, this disclosure provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the forklift pallet automatic picking method described in the first aspect or any corresponding embodiment.
[0048] Fourthly, this disclosure provides a computer-readable storage medium storing computer instructions for causing a computer to execute the method for automatically picking up a forklift pallet according to the first aspect or any corresponding embodiment described above. Attached Figure Description
[0049] To more clearly illustrate the technical solutions in the specific embodiments of this disclosure or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0050] Figure 1 This is a flowchart illustrating a method for automatically picking up pallets from a forklift according to some embodiments of the present disclosure;
[0051] Figure 2 This is a schematic diagram of the inter-module connection for automatic pallet picking by a forklift according to some embodiments of the present disclosure;
[0052] Figure 3 This is a complete flowchart illustrating a method for automatically picking up a forklift pallet according to some embodiments of the present disclosure;
[0053] Figure 4 This is a structural block diagram of a forklift pallet automatic lifting device according to some embodiments of the present disclosure;
[0054] Figure 5 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present disclosure. Detailed Implementation
[0055] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.
[0056] With the continuous development and iteration of intelligent and digital technologies, the level of automation in on-site operations of engineering vehicles is also increasing, and unmanned forklift operations in industrial parks have become a current development trend. Unmanned forklifts are intelligent industrial vehicles that can autonomously complete path following and loading / unloading tasks without human operation, and their automated loading / unloading is a very important part of the entire operation process.
[0057] Forklifts must not only ensure that the lateral error between the vehicle and the pallet is within a certain range when picking up pallets, but also ensure that the forks are fully aligned with the insertion holes before entering them to guarantee safe picking. General path planning algorithms usually consider the length and width of the vehicle body, but the body structure of a forklift differs significantly from that of a typical vehicle. As part of the vehicle body, the forks have a unique structure and cannot be simply regarded as a common quadrilateral body structure. Therefore, path planning and collision avoidance functions cannot effectively handle the collision risks brought about by this special structure.
[0058] Different pallet placement errors result in different planned paths. If the pallets are close together and the angle and position are offset, the working area is generally small, while the fork length is generally more than 1.2 meters. Furthermore, the forklift's positioning information cannot intuitively reflect the position of the fork tip. Therefore, there is a risk of the fork colliding with the pallet during the forklift's lifting process, which may prevent the pallet lifting operation from being completed or even cause a safety accident.
[0059] At present, in most work scenarios, pallets are usually placed manually. Due to human error or factors such as factory management level, there is a risk of forks colliding with pallets, which can prevent pallet picking operations from being completed or even cause safety accidents.
[0060] To address the aforementioned problems, according to an embodiment of this disclosure, a method for automatically picking up pallets from a forklift is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0061] This embodiment provides a method for automatically picking up pallets using a forklift. Figure 1 This is a flowchart of a method for automatically picking up a forklift pallet according to an embodiment of the present disclosure, such as... Figure 1 As shown, this method can be applied to server testing, and the method process includes the following steps:
[0062] Step S101: If the instruction information for the target forklift to automatically pick up the pallet is obtained, the position information of the pallet is obtained.
[0063] Step S102: Construct the target coordinate system based on the pose information of the pallet;
[0064] Step S103: Based on the first positioning information of the target forklift and the target coordinate system, generate multiple planned paths for the target forklift to travel.
[0065] Step S104: Determine the positional relationship between the forks of the target forklift and the pallet based on the planned path and the target coordinate system;
[0066] Step S105: Select the target path from the planned path according to the positional relationship, where the target path is the path for the target forklift to automatically pick up the pallet.
[0067] Optionally, such as Figure 2 As shown in this embodiment, the automatic pallet retrieval method for forklifts comprises at least the following units: a decision control module, a pallet pose detection module, a forklift positioning module, a path planning module, and a chassis control module. The operation instruction issuing module issues a retrieval command; the decision control module issues sub-commands for the operation; the pallet pose detection module acquires the pallet pose information through sensors; the positioning module acquires the current forklift pose; the path planning module plans a path based on the current actual pallet pose; and the chassis control module travels to the operation point to perform the pallet retrieval operation based on the planned path and feedback from the positioning module.
[0068] Therefore, for the server, the first step is to obtain the instruction information from the decision control module to automatically pick up the pallet by the target forklift. At the recognition point, the pallet pose detection module obtains the actual pose information of the pallet through the sensor.
[0069] The pose information of the path planning module tray is used to construct a target coordinate system, such as the SL coordinate system.
[0070] The path planning module performs path sampling in the SL coordinate system based on the target forklift's first positioning information (i.e., current positioning information) and forms several planned paths for the target forklift to travel through polynomial fitting.
[0071] Then, based on the planned path and the SL coordinate system, the positional relationship between the two forks at the front of the target forklift and the pallet is obtained, such as whether there is a risk of collision or not.
[0072] Then, based on these positional relationships, the target path for the forklift to automatically fork into the pallet is selected from multiple planned paths to achieve the target path for picking up the pallet.
[0073] In this embodiment of the disclosure, the pallet's pose information is obtained by acquiring the instruction information for the target forklift to automatically pick up the pallet; and a target coordinate system is constructed based on the pallet's pose information.
[0074] Based on the first positioning information of the target forklift and the target coordinate system, multiple planned paths for the target forklift are generated. Based on the planned paths and the target coordinate system, the positional relationship between the forklift's forks and the pallet is determined. Based on the positional relationship, a target path is selected from the planned paths, whereby the target forklift automatically picks up the pallet. This embodiment of the disclosure constructs a target coordinate system based on the pallet's pose information, then obtains a planned path based on the target forklift's current positioning information and the target coordinate system. It determines whether the planned path can achieve safe operation and selects the target path that can achieve safe operation. This avoids the collision risk caused by space and pallet pose limitations, solving the problem in related technologies where manual pallet placement easily leads to the risk of forklift collisions with the pallet, making pallet picking operations impossible.
[0075] In some optional implementations, a target coordinate system is constructed based on the tray's pose information, including:
[0076] Based on the pallet's position information, determine the perpendicular line of the pallet in the preset direction;
[0077] Construct the target coordinate system using the vertical line as a reference line.
[0078] Optionally, during pallet loading operations, the target forklift acquires the actual position and orientation information of the pallet through sensors, including coordinates x, y and heading angle; then, using the vertical line in the preset direction of the pallet, such as the positive direction, as a reference line, it constructs the SL coordinate system.
[0079] In some optional implementations, multiple planned paths for the target forklift are generated based on the target forklift's initial positioning information and the target coordinate system, including:
[0080] The first positioning information of the target forklift is converted into the target coordinate system to determine the initial starting point and initial ending point of the target forklift's movement. The initial starting point is the first positioning information, and the initial ending point is the critical point at which the forks of the target forklift can be aligned with the pallet for correct insertion.
[0081] Based on the initial starting point and initial ending point, obtain multiple planned paths generated by the target forklift in the target coordinate system.
[0082] Optionally, after obtaining the initial positioning information of the target forklift, the server transforms it into the target coordinate system, then plans the initial pose, and determines the initial starting point and initial ending point of the target forklift's movement. It can be understood that the initial starting point is the current position of the target forklift, and the initial ending point is the critical point at which the forklift's forks can be correctly inserted into the pallet's slots (because as long as the forklift's forks reach this critical point, the forklift can pick up the pallet, so the forklift's forks only need to reach the initial ending point).
[0083] Then, according to the SL coordinate system, sampling is performed in the vertical direction of the tray at a fixed step size, and multiple sampling points are selected. These sampling points are then used as initial endpoints (it should be noted that the critical points mentioned above are also included in the sampling points). Based on the initial starting point and multiple initial endpoints, a preset number of polynomials (e.g., 5 times) are constructed through polynomial fitting, thereby generating multiple planned paths formed by the initial starting point and multiple initial endpoints.
[0084] In this embodiment of the disclosure, by obtaining the initial starting point and multiple initial ending points when the target forklift is traveling, and then using a polynomial fitting method to construct a polynomial, multiple planned paths are generated for subsequent verification of the feasibility of the paths.
[0085] In some alternative implementations, the positional relationship between the forks and the pallet is determined based on the planned path and the target coordinate system, including:
[0086] Select candidate routes from the planned routes whose travel distance is less than a preset threshold;
[0087] Obtain the movement trajectory of the forks of the target forklift during its journey along the candidate path;
[0088] Transform the movement trajectory of the forks into the target coordinate system to determine the positional relationship between the forks and the pallet.
[0089] Optionally, the path with the shortest travel distance in the planned path is selected. The selection method can be to find a path with a travel distance less than a preset threshold as a candidate path. Then, combined with the vehicle kinematics model, that is, based on the vehicle structure parameters of the target forklift and the path information of the candidate path, the vehicle body direction and the position of the fork tip when the target forklift travels to each coordinate point can be known. Then, the motion trajectory of the two fork tips during the travel of the target forklift on the candidate path is predicted. The motion trajectory of the fork tips is transformed into the SL coordinate system to determine the positional relationship between the fork and the pallet, and to determine whether the fork collides with the pallet during the travel of the forklift.
[0090] In this embodiment of the disclosure, the movement trajectory of the fork tip during the vehicle's tracking process is predicted by planning the path and using a vehicle kinematics model, and it is determined whether the trajectory of the fork tip poses a risk of collision with the pallet, thereby verifying the feasibility of the path.
[0091] In some optional implementations, the target path is selected from the planned paths based on location relationships, including:
[0092] If the positional relationship indicates that there is no collision between the forks and the pallet, then the candidate path is taken as the target path;
[0093] If the positional relationship indicates a collision between the forks and the pallet, then obtain the remaining paths in the planned path besides the candidate paths;
[0094] Select the target path from the remaining paths;
[0095] If no target path is selected from the remaining paths, a splicing segment is generated based on the initial starting point, the initial ending point, and the second positioning information of the tray. The splicing segment includes a curve composed of the initial starting point and the initial ending point, and a straight line composed of the initial ending point and the second positioning information.
[0096] Determine the target path based on the splicing lines.
[0097] Optionally, if no collision occurs between the forks and the pallet, the candidate path with the shortest path is directly used as the target path to achieve stable and safe pallet picking. If a collision occurs between the forks and the pallet, and the current sampled path cannot pick up the pallet, the second-best path among the remaining paths in the planned path (excluding the candidate paths) is selected as the target path.
[0098] If no target path can be selected from the remaining paths, meaning that collisions cannot be avoided with any of the currently planned paths, then the target path is determined using a spliced segment obtained by combining an RS curve and a straight line. The RS curve is a curve composed of an initial starting point (as the curve's starting point) and an initial ending point (as the curve's ending point; here, the initial ending point can only be the critical point where the forks can be aligned with the pallet for correct insertion). The straight line is a straight line segment composed of the initial ending point (as the line's starting point) and the pallet's second positioning information (as the line's ending point).
[0099] Then, based on the splicing segments, a better starting pose of the forklift is obtained, and thus the target path is obtained.
[0100] In this embodiment of the disclosure, the strategy determines whether the pallet can be picked up based on the current pose of the forklift. If not, the current pose of the forklift is changed to obtain a better initial pose for planning.
[0101] In some alternative implementations, selecting the target path from the remaining paths includes:
[0102] The path to be executed is selected from the remaining paths based on the cost function;
[0103] The positional relationship between the forks and the pallet is determined based on the path to be executed until no collision occurs between the forks and the pallet. The path to be executed without collision is then taken as the target path.
[0104] Optionally, a cost function is constructed to evaluate the path. The evaluation items include multiple cost items such as path length, curvature, lateral change rate, and lateral movement. The remaining paths are evaluated using the cost function, and the remaining paths are arranged in ascending order of cost value obtained from the cost function. The smaller the cost value, the higher the priority.
[0105] Cost function = k1 × length + k2 × maximum curvature + k3 × maximum lateral rate of change + k4 × maximum lateral range, where k1, k2, k3, and k4 are all customizable weight values.
[0106] Select the highest priority path from the remaining paths, then determine the positional relationship between the forks and the pallet based on the path to be executed. Sort by priority and select the paths to be executed in a loop until no collision occurs between the forks and the pallet. The path to be executed that has not collided is taken as the target path.
[0107] In this embodiment of the disclosure, if the current path predicts that a collision between the forks and the pallet may occur, the planned path is selected again to avoid the failure of the forklift operation due to pallet position deviation.
[0108] In some alternative implementations, determining the target path based on the splicing segment includes:
[0109] The target forklift is reversed based on the splicing line segment. The initial starting point and initial ending point of the target forklift are adjusted. The multiple planned paths generated by the target forklift in the target coordinate system are obtained from the steps and the loop is started until the target path is obtained. The loop ends, so that the target forklift can automatically pick up the pallet.
[0110] Optionally, after obtaining the splicing segment obtained by stitching RS curves and straight lines, the target forklift reverses according to the splicing segment, readjusts the initial starting point and initial ending point corresponding to the target forklift's movement, obtains a better starting point pose, and starts looping from the multiple planned paths generated by the target forklift in the target coordinate system obtained in the step, resampling and predicting until a target path that meets the conditions is found, and the loop ends, thus achieving stable pallet safe picking.
[0111] In this embodiment of the disclosure, if the current path predicts that a collision between the forks and the pallet may occur, the current vehicle position is adjusted to give it a more planned starting position, so as to avoid the failure of the forklift operation due to the pallet position deviation.
[0112] In some alternative implementations, such as Figure 3 As shown, Figure 3 This is a schematic diagram of the complete process of a method for automatically picking up pallets from a forklift according to some embodiments of the present disclosure. The specific process includes the following:
[0113] Obtain the actual pose information of the pallet; construct the SL coordinate system;
[0114] Obtain the vehicle's current location information;
[0115] The planned path is obtained by sampling the path based on the current positioning information and the SL coordinate system;
[0116] Predict the fork movement trajectory based on the planned path and SL coordinate system;
[0117] Determine if the forks collide with the pallet;
[0118] If no collision occurs, the path is published; if a collision occurs, the remaining paths are obtained, the suboptimal path is selected from the remaining paths, and then the process is repeated cyclically starting from the predicted fork movement trajectory.
[0119] If collisions cannot be avoided on the remaining paths, use RS curves and straight lines to stitch together the vehicle and reverse to obtain a better starting point pose. After the vehicle reaches the reverse position, repeat the above steps to sample and plan the path until a suitable planned path is found.
[0120] This embodiment also provides an automatic pallet-grabbing device for forklifts, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0121] This embodiment provides a device for automatically picking up pallets from a forklift, such as... Figure 4 As shown, it includes:
[0122] The acquisition module 401 is used to acquire the pallet's position information when the target forklift automatically picks up the pallet.
[0123] Module 402 is used to construct the target coordinate system based on the pose information of the pallet;
[0124] The generation module 403 is used to generate multiple planned paths for the target forklift based on the first positioning information of the target forklift and the target coordinate system;
[0125] The determination module 404 is used to determine the positional relationship between the forks of the target forklift and the pallet based on the planned path and the target coordinate system;
[0126] The selection module 405 is used to select the target path from the planned path based on the positional relationship, wherein the target path is the path that enables the target forklift to automatically pick up the pallet.
[0127] In some alternative implementations, building module 402 includes:
[0128] The first determining unit is used to determine the perpendicular line of the pallet in a preset direction based on the pallet's pose information.
[0129] The building unit is used to construct the target coordinate system using the vertical line as a reference line.
[0130] In some alternative implementations, the generation module 403 includes:
[0131] The second determining unit is used to convert the first positioning information of the target forklift into the target coordinate system and determine the initial starting point and initial ending point of the target forklift's travel. The initial starting point is the first positioning information, and the initial ending point is the critical point at which the forks of the target forklift can be aligned with the pallet to achieve correct insertion.
[0132] The first acquisition unit is used to acquire multiple planned paths generated by the target forklift in the target coordinate system based on the initial starting point and the initial ending point.
[0133] In some alternative implementations, the determining module 404 includes:
[0134] The first selection unit is used to select candidate paths from the planned paths whose travel distance is less than a preset threshold.
[0135] The second acquisition unit is used to acquire the movement trajectory of the forks of the target forklift during its journey along the candidate path;
[0136] The third determining unit is used to convert the movement trajectory of the forks into the target coordinate system and determine the positional relationship between the forks and the pallet.
[0137] In some alternative implementations, the selection module 405 includes:
[0138] The setting unit is used to select the candidate path as the target path if the positional relationship indicates that there is no collision between the forks and the pallet.
[0139] The third acquisition unit is used to acquire the remaining paths in the planned path other than the candidate paths if the positional relationship indicates that a collision has occurred between the forks and the pallet.
[0140] The second selection unit is used to select the target path from the remaining paths;
[0141] The generation unit is used to generate a splicing segment based on the initial starting point, the initial ending point, and the second positioning information of the tray if no target path is selected from the remaining paths. The splicing segment includes a curve composed of the initial starting point and the initial ending point and a straight line composed of the initial ending point and the second positioning information.
[0142] The fourth determining unit is used to determine the target path based on the splicing segment.
[0143] In some alternative implementations, the second selection unit includes:
[0144] The selection submodule is used to select the path to be executed from the remaining paths based on the cost function;
[0145] The configuration submodule is used to determine the positional relationship between the forks and the pallet based on the path to be executed, until no collision occurs between the forks and the pallet, and the path to be executed without collision is taken as the target path.
[0146] In some optional implementations, the fourth determining unit includes:
[0147] The adjustment submodule is used to reverse the target forklift based on the splicing segment, adjust the initial starting point and initial ending point of the target forklift when it is moving, and start looping from the multiple planned paths generated by the target forklift in the target coordinate system obtained from the steps until the target path is obtained, and then the loop ends, so as to realize the automatic pallet picking by the target forklift.
[0148] In this embodiment, the automatic pallet-grabbing device for forklifts is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.
[0149] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.
[0150] This disclosure also provides a computer device having the above-described features. Figure 4 The device shown is an automatic pallet-grabbing device for forklifts.
[0151] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of this disclosure, such as... Figure 5 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 5 Take a processor 10 as an example.
[0152] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.
[0153] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.
[0154] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device as shown by a landing page for an app. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0155] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.
[0156] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.
[0157] This disclosure also provides a computer-readable storage medium in which the methods described in this disclosure can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium after being downloaded over a network. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium may be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium may also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code that, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.
[0158] Although embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A method for automatically picking up pallets using a forklift, characterized in that, The method includes: Upon receiving the instruction information that the target forklift will automatically pick up the pallet, the pallet's position and orientation information is obtained; Based on the pose information of the tray, construct a target coordinate system; Based on the first positioning information of the target forklift and the target coordinate system, multiple planned paths for the target forklift to travel are generated; Based on the planned path and the target coordinate system, determine the positional relationship between the forks of the target forklift and the pallet; A target path is selected from the planned paths based on the positional relationship, wherein the target path is the path through which the target forklift automatically picks up the pallet; The step of constructing a target coordinate system based on the pose information of the tray includes: Based on the position information of the tray, determine the perpendicular line of the tray in the preset direction; The target coordinate system is constructed using the vertical line as a reference line; Selecting the target path from the planned path based on the positional relationship includes: If the positional relationship indicates that no collision has occurred between the forks and the pallet, then the candidate path is taken as the target path; If the positional relationship indicates a collision between the forks and the pallet, then obtain the remaining paths in the planned path besides the candidate paths; Select the target path from the remaining paths; If the target path is not selected from the remaining paths, a splicing segment is generated based on the initial starting point, the initial ending point, and the second positioning information of the tray. The splicing segment includes a curve composed of the initial starting point and the initial ending point, and a straight line composed of the initial ending point and the second positioning information. The target path is determined based on the splicing line segment; Selecting the target path from the remaining paths includes: The path to be executed is selected from the remaining paths based on the cost function; A cost function is constructed to evaluate the path, and the evaluation items include path length, maximum curvature, maximum lateral rate of change, and maximum lateral distance. The remaining paths are then evaluated using the cost function, and the remaining paths are arranged in ascending order of cost value obtained from the cost function. Cost function = k1 × length + k2 × maximum curvature + k3 × maximum lateral rate of change + k4 × maximum lateral distance, where k1, k2, k3, and k4 are user-defined weight values. The positional relationship between the forks and the pallet is determined based on the path to be executed until no collision occurs between the forks and the pallet. The path to be executed without collision is then taken as the target path. Based on the first positioning information of the target forklift and the target coordinate system, multiple planned paths for the target forklift are generated, including: The first positioning information of the target forklift is converted into the target coordinate system to determine the initial starting point and initial ending point of the target forklift's travel. The initial starting point is the first positioning information, and the initial ending point is the critical point at which the forks of the target forklift can be aligned with the pallet for correct insertion. Based on the initial starting point and the initial ending point, obtain multiple planned paths generated by the target forklift in the target coordinate system; Determining the target path based on the spliced segment includes: The target forklift is retracted according to the splicing line segment, the initial starting point and the initial ending point corresponding to the target forklift's movement are adjusted, and the step of obtaining multiple planned paths generated by the target forklift in the target coordinate system is executed until the target path is obtained, and the loop ends, so that the target forklift can automatically pick up the pallet.
2. The method according to claim 1, characterized in that, Determining the positional relationship between the forks and the pallet based on the planned path and the target coordinate system includes: Select candidate paths from the planned paths whose travel distance is less than a preset threshold; Obtain the movement trajectory of the forks of the target forklift during its journey along the candidate path; The movement trajectory of the forks is converted into the target coordinate system to determine the positional relationship between the forks and the pallet.
3. A device for automatically picking up pallets from a forklift, characterized in that, The device includes: The acquisition module is used to acquire the position information of the pallet when the instruction information of the target forklift to automatically pick up the pallet is received. A construction module is used to construct a target coordinate system based on the pose information of the tray; The generation module is used to generate multiple planned paths for the target forklift to travel based on the first positioning information of the target forklift and the target coordinate system; The determination module is used to determine the positional relationship between the forks of the target forklift and the pallet based on the planned path and the target coordinate system; The selection module is used to select a target path from the planned path according to the positional relationship, wherein the target path is the path that enables the target forklift to automatically pick up the pallet; The step of constructing a target coordinate system based on the pose information of the tray includes: Based on the position information of the tray, determine the perpendicular line of the tray in the preset direction; The target coordinate system is constructed using the vertical line as a reference line; Selecting the target path from the planned path based on the positional relationship includes: If the positional relationship indicates that no collision has occurred between the forks and the pallet, then the candidate path is taken as the target path; If the positional relationship indicates a collision between the forks and the pallet, then obtain the remaining paths in the planned path besides the candidate paths; Select the target path from the remaining paths; If the target path is not selected from the remaining paths, a splicing segment is generated based on the initial starting point, the initial ending point, and the second positioning information of the tray. The splicing segment includes a curve composed of the initial starting point and the initial ending point, and a straight line composed of the initial ending point and the second positioning information. The target path is determined based on the splicing line segment; Selecting the target path from the remaining paths includes: The path to be executed is selected from the remaining paths based on the cost function; A cost function is constructed to evaluate the path, and the evaluation items include path length, maximum curvature, maximum lateral rate of change, and maximum lateral distance. The remaining paths are then evaluated using the cost function, and the remaining paths are arranged in ascending order of cost value obtained from the cost function. Cost function = k1 × length + k2 × maximum curvature + k3 × maximum lateral rate of change + k4 × maximum lateral distance, where k1, k2, k3, and k4 are user-defined weight values. The positional relationship between the forks and the pallet is determined based on the path to be executed until no collision occurs between the forks and the pallet. The path to be executed without collision is then taken as the target path. Based on the first positioning information of the target forklift and the target coordinate system, multiple planned paths for the target forklift are generated, including: The first positioning information of the target forklift is converted into the target coordinate system to determine the initial starting point and initial ending point of the target forklift's travel. The initial starting point is the first positioning information, and the initial ending point is the critical point at which the forks of the target forklift can be aligned with the pallet for correct insertion. Based on the initial starting point and the initial ending point, obtain multiple planned paths generated by the target forklift in the target coordinate system; Determining the target path based on the spliced segment includes: The target forklift is retracted according to the splicing line segment, the initial starting point and the initial ending point corresponding to the target forklift's movement are adjusted, and the step of obtaining multiple planned paths generated by the target forklift in the target coordinate system is executed until the target path is obtained, and the loop ends, so that the target forklift can automatically pick up the pallet.
4. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for automatically picking up a forklift pallet as described in any one of claims 1 to 2.
5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method of automatically picking up a forklift pallet as described in any one of claims 1 to 2.