AGV forklift positioning and navigation method and system based on visual identification

Abstract

The invention relates to a positioning and navigation method and system of an AGV forklift based on visual identification, and relates to the field of forklift intelligent control technology, and the method comprises the following steps: obtaining a visual identification image; judging whether external obstacle features exist or not according to the visual identification image; if the external obstacle feature exists, determining an external obstacle point according to the external obstacle feature, and determining a required driving road section according to the current position and the end position point of the forklift; judging whether the external obstacle point is located on the required driving road section or not; if the external obstacle point is located on the required driving road section, a required avoiding point is determined according to the external obstacle characteristics, a path replacement road section is constructed according to the current position of the forklift, the required avoiding point and the end position point, and the path replacement road section is used for replacing and updating the required driving road section so as to control the forklift to move along the updated forklift driving path. The forklift truck has the effect that the forklift truck can execute the transportation task conveniently.

Description

Technical Field

[0001] The present application relates to the field of forklift intelligent control technology, and in particular to a positioning and navigation method and system for an AGV forklift based on visual recognition. Background Art

[0002] AGV forklift is the application of automatic guided vehicle technology in the forklift field. It is a forklift equipment that can travel automatically and does not require manual driving. Instead, it completes the material handling task through pre-set programs, navigation systems and sensors. Therefore, it has been widely used in logistics warehousing, manufacturing workshops and other fields. Among them, because visual recognition technology has the advantages of low cost, strong adaptability and rich information, it provides effective technical support for AGV forklift.

[0003] In the related technology, AGV forklifts generally apply visual recognition technology to obstacle avoidance processing, and detect obstacles on the driving path through visual sensors. When the corresponding obstacles are detected, corresponding avoidance measures are taken to bypass the obstacles.

[0004] In the above-mentioned related technologies, when the AGV forklift is close to an obstacle for avoidance, the forklift needs to adjust its movement posture to a large extent. Not only does it need to wait for the forklift to adjust its movement posture, but the overall movement of the forklift is also difficult, which makes it inconvenient for the forklift to perform transportation tasks. There is still room for improvement. Summary of the invention

[0005] In order to facilitate the forklift to perform transportation tasks, the present application provides a positioning and navigation method and system for an AGV forklift based on visual recognition.

[0006] In the first aspect, the present application provides a positioning and navigation method for an AGV forklift based on visual recognition, which adopts the following technical solution: A positioning and navigation method for an AGV forklift based on visual recognition, comprising: Obtain visual recognition images, forklift travel path, and forklift current location; The forklift driving path is divided into a plurality of straight driving sections according to a preset transport space diagram, and the straight driving section including the current position of the forklift is defined as the current section, and the end position point and the moving direction of the section are determined on the current section; Determine the clear road section image in the preset image record library according to the current position of the forklift and the moving direction of the road section; Compare the clear road section image with the visual recognition image to determine whether there are external obstacle features; If there is no external obstacle feature, the current forklift is controlled to continue moving along the current road section; If there are external obstacle features, the external obstacle point is determined according to the external obstacle features, and the required driving section is determined according to the current position and the end position of the forklift; Determine whether the external obstacle point is on the required driving section; If the external obstacle point is not on the required driving section, the current forklift is controlled to continue moving along the current section; If the external obstacle point is on the required driving section, the required avoidance point is determined according to the external obstacle characteristics, and a path replacement section is constructed according to the current position of the forklift, the required avoidance point and the end position point, and the path replacement section is replaced and updated with the required driving section to control the forklift to move along the updated forklift driving path.

[0007] Optionally, if the external obstacle point is on the required driving section, the positioning and navigation method of the AGV forklift based on visual recognition also includes: On the preset time axis, a unit interval with a width of a preset unit time length is established with the current time point as the front end point; Control the forklift to continue moving along the current road section within the unit interval and continuously acquire visual recognition images, and re-determine the external obstacle point corresponding to the external obstacle feature based on the visual recognition image; Determine the obstacle moving distance based on any two external obstacle points in the unit interval; Determine whether there is a situation where the obstacle moving distance is greater than the preset action distance; If there is no obstacle whose moving distance is greater than the action distance, the required avoidance point is determined according to the characteristics of the external obstacle after the unit interval, and the forklift driving path is updated; If the obstacle moving distance is greater than the action distance, the current forklift is controlled to continue moving along the current road section.

[0008] Optionally, if there is a situation where the obstacle moving distance is greater than the action distance, the positioning and navigation method of the AGV forklift based on visual recognition preferably includes: Determine whether the external obstacle feature is a preset transport forklift feature; If the external obstacle feature is not a transport forklift feature, the current forklift is controlled to continue moving along the current road section; If the external obstacle feature is a transport forklift feature, the forklift presence point of each transport forklift is obtained in the preset task scheduling library; Calculate the distance between points according to the forklift existence points and external obstacle points, and determine the point distance with the smallest value according to the preset sorting rules, and define the transport forklift corresponding to the point distance with the smallest value as the obstructing forklift; Determine the obstructing task path according to the obstructing forklift in the task scheduling library, and determine the real-time existence point of the obstructing forklift at each time point according to the obstructing task path; Determine the simulated existence point of the current forklift at each time point according to the forklift's driving path and the forklift's current position; Determine whether there is a situation where the real-time existing point and the simulated existing point overlap on the current road section; If there is no situation where the real-time existing point and the simulated existing point overlap on the current road section, the current forklift is controlled to continue moving along the current road section; If there is a situation where the real-time existence point and the simulated existence point overlap on the current road section, the required avoidance point is determined based on the characteristics of the transport forklift.

[0009] Optionally, after the distance between the points is determined, the positioning and navigation method of the AGV forklift based on visual recognition also includes: Determine whether there are at least two forklift points with the same and minimum distance between them; If there are not at least two forklift points with the same and minimum distance between points, the obstructing forklift is determined according to the forklift points corresponding to the minimum distance between points; If there are at least two forklift presence points with the same and minimum distance between them, the forklift execution posture of the forklift corresponding to each forklift presence point is obtained according to the task scheduling library, and the forklift obstruction posture is determined according to the characteristics of the transport forklift; Comparing the forklift execution posture and the forklift obstruction posture to determine the posture similarity ratio; The posture similarity ratio with the largest value is determined according to the sorting rule, and the obstructing forklift is determined according to the forklift existence point corresponding to the posture similarity ratio with the largest value.

[0010] Optionally, the step of determining the required avoidance point according to the characteristics of the transport forklift includes: The point where the real-time existing point and the simulated existing point overlap on the current road section is defined as the meeting point; Get the model and specifications of the forklift that is blocking the forklift; Determine the required avoidance width corresponding to the forklift model and specification based on the preset parameter matching relationship; A virtual moving line segment is constructed according to the current position of the forklift and the meeting point, and an avoidance line perpendicular to the virtual moving line segment is constructed at the meeting point; Move the meeting point in any direction of the avoidance line by the required avoidance width to determine the required avoidance point.

[0011] Optionally, after the avoidance line is determined, the positioning and navigation method of the AGV forklift based on visual recognition further includes: Determine whether the end position point coincides with the path endpoint on the forklift's driving path; If the end position coincides with the path endpoint on the forklift's driving path, the meeting point is moved in any direction of the avoidance line by the required avoidance width to determine the required avoidance point; If the end position point does not coincide with the path endpoint on the forklift's driving path, the straight driving section on the forklift's driving path that is after the current section is defined as the subsequent driving section, and the subsequent driving direction is determined based on the subsequent driving section; The meeting point is moved in both directions of the avoidance line by the required avoidance width to determine the simulated avoidance point, and the direction of the latter part of the avoidance is determined according to the simulated avoidance point and the end position point; The direction angle is determined according to the subsequent driving direction and the direction of the rear section of the avoidance, and the direction angle with the smallest value is determined according to the sorting rules, and the simulated avoidance point corresponding to the direction angle with the smallest value is defined as the required avoidance point.

[0012] In the second aspect, the present application provides a positioning and navigation system for an AGV forklift based on visual recognition, which adopts the following technical solution: A positioning and navigation system for an AGV forklift based on visual recognition, comprising: An acquisition module is used to acquire visual recognition images, forklift driving paths, and the current position of the forklift; A processing module, connected to the acquisition module and the judgment module, for storing and processing information; A judgment module, connected with the acquisition module and the processing module, for judging the information; The processing module divides the forklift driving path into a plurality of straight driving sections according to a preset transportation space diagram, defines the straight driving section including the current position of the forklift as the current section, and determines the end position point and the moving direction of the section on the current section; The processing module determines the clear road section image in a preset image record library according to the current position of the forklift and the moving direction of the road section; The processing module compares the features of the clear road section image with the visual recognition image so that the judgment module can judge whether there are external obstacle features; If the judging module determines that there is no external obstacle feature, the processing module controls the current forklift to continue moving along the current road section; If the judgment module determines that there are external obstacle features, the processing module determines the external obstacle point according to the external obstacle features, and determines the required driving section according to the current position and the end position of the forklift; The judgment module judges whether the external obstacle point is on the required driving section; If the judgment module determines that the external obstacle point is not on the required driving section, the processing module controls the current forklift to continue moving along the current section; If the judgment module determines that the external obstacle point is on the required driving section, the processing module determines the required avoidance point according to the external obstacle characteristics, and constructs a path replacement section according to the current position of the forklift, the required avoidance point and the end position point, and replaces and updates the required driving section with the path replacement section to control the forklift to move along the updated forklift driving path.

[0013] In a third aspect, the present application provides a computer storage medium capable of storing corresponding programs, which has the feature of facilitating a forklift to perform a transportation task, and adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any of the above-mentioned positioning and navigation methods for an AGV forklift based on visual recognition.

[0014] In summary, the present application includes at least one of the following beneficial technical effects: 1. During the movement of the forklift, the visual recognition technology can be used to determine the obstacle in front, so that when the forklift detects the existence of an obstacle at a long distance, the forklift can immediately adjust the moving angle. At this time, the forklift can more conveniently avoid the obstacle, making it easier for the forklift to perform the transportation task; 2. When analyzing obstacle situations, the encounter between two forklifts can be comprehensively analyzed so that forklift avoidance control can be performed in special situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of the positioning and navigation method of the AGV forklift based on visual recognition.

[0016] Figure 2 It is a module flow chart of the positioning and navigation method of AGV forklift based on visual recognition. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-Figure 2 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0018] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0019] The present application embodiment discloses a positioning and navigation method for an AGV forklift based on visual recognition, referring to Figure 1 The method flow of the positioning and navigation method of the AGV forklift based on visual recognition includes the following steps: Step S100: Acquire a visual recognition image, a forklift driving path, and a current position of the forklift.

[0020] The visual recognition image is an image acquired by a visual sensor installed on the forklift to acquire images of the road in front of the forklift. The forklift driving path is the driving path that the forklift needs to move when performing the current task. The forklift task can be analyzed to determine that the current position of the forklift, that is, the position point when the forklift acquires the visual recognition image, can be obtained by installing a positioning device on the forklift.

[0021] Step S101: splitting the forklift's driving path into a plurality of straight driving sections according to a preset transport space diagram, defining the straight driving section including the forklift's current position as the current section, and determining the end position point and the section moving direction on the current section.

[0022] The transport space map is a space map of the space where the forklift is currently located, such as a warehouse distribution map. The transport space map records the relative positions of each shelf and the road. The straight driving sections are the straight driving sections in the forklift's driving path. The current section is defined to determine the section where the forklift is currently moving, which is convenient for analyzing obstacle conditions. The end position point is the end point on the current section that the forklift has not yet moved to, and the section moving direction is the moving direction of the forklift when it moves on the current section.

[0023] Step S102: determining a clear road section image in a preset image record library according to the current position of the forklift and the moving direction of the road section.

[0024] The image record library is a database that stores images of various position points, including images that can be obtained when there are no obstacles on the road ahead in the space corresponding to the transportation space diagram when the forklift is at any position and facing any direction, and clear road section images, that is, images that can be obtained when there are no obstacles ahead when the forklift is at the current position of the forklift facing the direction of movement of the road section.

[0025] Step S103: performing feature comparison between the clear road section image and the visual recognition image to determine whether there are external obstacle features.

[0026] The feature comparison method is to determine whether there is a feature in the visual recognition image that is not present in the image of the unobstructed road section. The feature is the external obstacle feature. The purpose of the judgment is to determine whether there is a possibility that an obstacle will hinder the current forklift.

[0027] Step S1031: If there is no external obstacle feature, the current forklift is controlled to continue moving along the current road section.

[0028] When there is no external obstacle feature, it means that there is no obstacle in front of the forklift, and the forklift can be controlled to continue moving.

[0029] Step S1032: If there are external obstacle features, the external obstacle point is determined according to the external obstacle features, and the required driving section is determined according to the current position and the end position of the forklift.

[0030] When there are external obstacle features, it means that there may be obstacles that will hinder the current forklift, and further analysis is needed at this time; the external obstacle point is the location point of the external obstacle feature, and the distance and relative direction between the external obstacle feature and the forklift can be determined by obtaining the image of the external obstacle feature in the image, so that the external obstacle point can be effectively determined; the required driving section is the section that the current forklift needs to travel from the current position of the forklift to the end position point.

[0031] Step S104: Determine whether the external obstacle point is on the required driving section.

[0032] The purpose of the judgment is to know whether the obstacle ahead will hinder the forklift.

[0033] Step S1041: If the external obstacle point is not on the required driving section, the current forklift is controlled to continue moving along the current section.

[0034] When the external obstacle point is not on the required driving section, it means that the obstacle in front will not hinder the current forklift, and the forklift can be controlled to move normally.

[0035] Step S1042: If the external obstacle point is on the required driving section, the required avoidance point is determined according to the external obstacle characteristics, and a path replacement section is constructed according to the current position of the forklift, the required avoidance point and the end position point, and the path replacement section is replaced and updated with the required driving section to control the forklift to move along the updated forklift driving path.

[0036] When the external obstacle point is on the required driving section, it means that the obstacle ahead will hinder the forklift, and an avoidance operation is required at this time; the required avoidance point is the point to which the forklift needs to move when avoiding the obstacle. The width value of the obstacle in the width direction of the current section can be determined by the external obstacle feature, and then the external obstacle point is moved in the width direction by the corresponding width value to determine the required avoidance point. The method for determining the avoidance point is similar to step S600-step S602, and will not be repeated here; the path replacement section is a section that enables the forklift to avoid the external obstacle feature, that is, the section from the current position of the forklift to the required avoidance point and then to the end position point, wherein the movement between the points is a linear movement, and the forklift can be moved normally by updating the forklift driving path by using the path replacement section; at this time, when the forklift finds the obstacle ahead at a farther position, the forklift only needs to adjust a smaller movement angle to avoid the obstacle, so that the adjustment difficulty of the forklift is relatively small, which is convenient for the forklift to execute the transportation task.

[0037] If the external obstacle point is on the required driving section, the positioning and navigation method of the AGV forklift based on visual recognition also includes: Step S200: establishing a unit interval with a width of a preset unit time length on a preset time axis with the current time point as the front end point.

[0038] When the external obstacle point is on the required driving section, the obstacle may be a staff member. At this time, the detected obstruction is caused by the movement of the staff, and there will be no continuous obstruction. Therefore, no avoidance operation is required for this situation, and it is necessary to analyze this situation; the time axis is a coordinate axis formed by the combination of various time points. The left side of the coordinate axis is defined as the front, and the right side is defined as the rear. The unit time is the fixed time set by the staff. Establishing a unit interval can facilitate the determination of the situation of external obstacles within the unit time, which is convenient for subsequent analysis.

[0039] Step S201: Control the forklift to continue moving along the current road section within the unit interval and continuously acquire visual recognition images, and re-determine the external obstacle point corresponding to the external obstacle feature based on the visual recognition image.

[0040] Controlling the forklift to continue moving and visually identifying the situation of external obstacles can facilitate subsequent analysis.

[0041] Step S202: Determine the obstacle moving distance according to any two external obstacle points in the unit section.

[0042] The obstacle moving distance is the straight-line distance between two external obstacle points.

[0043] Step S203: Determine whether the obstacle moving distance is greater than the preset action distance.

[0044] The action distance is the minimum obstacle moving distance that needs to be reached when the obstacle determined by the staff moves. The purpose of the judgment is to know whether there is an obstacle moving, so as to determine whether the current obstacle will continue to hinder the current forklift.

[0045] Step S2031: If there is no obstacle moving distance greater than the action distance, then after the unit section, the required avoidance point is determined according to the external obstacle characteristics, and the forklift driving path is updated.

[0046] When there is no situation where the obstacle moving distance is greater than the action distance, it means that there is no situation where the obstacle will move away by itself. At this time, the forklift can perform the avoidance operation normally.

[0047] Step S2032: If there is a situation where the obstacle moving distance is greater than the action distance, the current forklift is controlled to continue moving along the current road section.

[0048] When there is a situation where the obstacle moving distance is greater than the action distance, it means that the obstacle in front is a movable obstacle. At this time, the obstacle may move by itself when the forklift approaches the obstacle. Therefore, it is sufficient to control the movement of the forklift normally without performing an avoidance operation. It should be noted that this forklift also has a forced avoidance mechanism, that is, when the distance between the forklift and the external obstacle is less than the preset approaching distance value, the forklift will immediately perform an avoidance operation. The specific measures for forced avoidance are set by the staff according to the actual situation, and do not create points for this application, so they will not be elaborated here.

[0049] If there is a situation where the obstacle moving distance is greater than the action distance, the positioning and navigation method of the AGV forklift based on visual recognition is best including: Step S300: Determine whether the external obstacle feature is a preset transport forklift feature.

[0050] The transport forklift feature is a feature that can be detected when the forklift is an obstacle. The purpose of the judgment is to know whether the current external movable obstacle is the remaining forklifts that are performing transportation processing in the transport space.

[0051] Step S3001: If the external obstacle feature is not a transport forklift feature, the current forklift is controlled to continue moving along the current road section.

[0052] When the external obstacle feature is not a transport forklift feature, it means that the external obstacle is not a forklift. At this time, the current forklift can be controlled normally to move.

[0053] Step S3002: If the external obstacle feature is a transport forklift feature, then the forklift presence point of each transport forklift is obtained from a preset task scheduling library.

[0054] When the external obstacle feature is a transport forklift feature, it means that the external obstacle is a forklift. At this time, the subsequent movement of the forklift may still hinder the current forklift action, which requires further analysis; the forklift existence point is the position point where each forklift that is performing the corresponding task needs to be in theory at the current time point. The task scheduling library is a database that records the transport forklift and the corresponding tasks. The tasks to be performed include the path to be moved and the corresponding movement rules, including driving speed, turning speed, etc.

[0055] Step S301: Calculate the distance between points based on forklift points and external obstacle points, and determine the point distance with the smallest value based on a preset sorting rule, and define the transport forklift corresponding to the point distance with the smallest value as the obstructing forklift.

[0056] The point-to-point distance is the distance between the forklift existence point and the external obstacle point. The sorting rule is a method set by the staff to sort the numerical values, such as the bubble method. The point-to-point distance with the smallest value can be determined through the sorting rule, which means that the forklift at the forklift existence point corresponding to the point-to-point distance is the forklift that hinders the current forklift. It is defined as an obstructing forklift to distinguish different transport forklifts for subsequent analysis.

[0057] Step S302: determining an obstructing task path in the task scheduling library according to the obstructing forklift, and determining the real-time existence point of the obstructing forklift at each time point according to the obstructing task path.

[0058] The obstruction task path is a path that prevents the forklift from traveling when executing the current task, and the real-time existence point is a position point that the obstruction forklift will reach at each time point when executing the current task.

[0059] Step S303: determining the simulated presence point of the current forklift at each time point according to the forklift's travel path and the forklift's current position.

[0060] The simulated existence point is the position point that the current forklift will be at at each time point after starting from the current position of the forklift.

[0061] Step S304: Determine whether there is a situation where a real-time existing point and a simulated existing point overlap on the current road section.

[0062] The purpose of the judgment is to find out whether the forklifts will encounter each other, so as to determine whether early avoidance is required.

[0063] Step S3041: If there is no overlap between the real-time existing point and the simulated existing point on the current road section, the current forklift is controlled to continue moving along the current road section.

[0064] When there is no overlap between the real-time existing point and the simulated existing point on the current road section, it means that there is no situation where the forklift will meet on the current road section. At this time, the forklift can be controlled to move normally.

[0065] Step S3042: If there is a situation where the real-time existing point and the simulated existing point overlap on the current road section, the required avoidance point is determined according to the characteristics of the transport forklift.

[0066] When the real-time existence point and the simulated existence point overlap on the current road section, it means that forklifts will meet on the current road section. At this time, advance avoidance processing is required. Therefore, the corresponding required avoidance point is determined according to the characteristics of the transport forklift for subsequent avoidance operations. The method for determining the required avoidance point is the method recorded in steps S600-S602.

[0067] After the distance between the points is determined, the positioning and navigation method of the AGV forklift based on visual recognition also includes: Step S400: Determine whether there are at least two forklift points with the same and minimum distance between them.

[0068] The purpose of the judgment is to find out whether there are multiple forklifts that are more consistent with the current obstacle, so as to more accurately determine the only obstructing forklift.

[0069] Step S4001: If there are not at least two forklift points with the same and minimum distance between points, then the obstructing forklift is determined according to the forklift points corresponding to the minimum distance between points.

[0070] When there are no forklift points with at least two points having the same and minimum distance between them, it means that there is only one forklift that meets the requirements, and the obstructing forklift can be determined normally.

[0071] Step S4002: If there are at least two forklift presence points with the same and minimum distance between them, the forklift execution posture of the forklift corresponding to each forklift presence point is obtained according to the task scheduling library, and the forklift obstruction posture is determined according to the transport forklift characteristics.

[0072] When there are at least two forklift presence points with the same and smallest distance between them, it means that multiple forklifts are relatively close to the external obstacle point, and they are all likely to be forklifts that hinder the current forklift and need further analysis; the forklift execution posture is the moving posture of the forklift at the determined forklift presence point, and the posture includes the moving direction, the height of the cargo lifted by the forklift, etc. The forklift obstruction posture is the moving posture of the acquired transport forklift characteristics, and the posture also includes the moving direction, the height of the cargo lifted by the forklift, etc.

[0073] Step S401: Compare the forklift execution posture and the forklift obstruction posture to determine the posture similarity ratio.

[0074] The posture similarity ratio is the similarity value of the two forklifts. When the degree of overlap between the forklift execution posture and the forklift obstruction posture is higher, the corresponding posture similarity ratio is also larger.

[0075] Step S402: determining the posture similarity ratio with the largest value according to the sorting rule, and determining the obstructing forklift according to the forklift existence point corresponding to the posture similarity ratio with the largest value.

[0076] The sorting rule can be used to determine the posture similarity ratio with the largest value, that is, the forklift corresponding to the posture similarity ratio is most similar to the external obstacle feature, that is, the forklift is an obstructing forklift.

[0077] The steps for determining the required avoidance points based on the characteristics of the transport forklift include: Step S500: define the location point where the real-time existing point and the simulated existing point overlap on the current road section as a meeting point.

[0078] Define meeting points to identify locations where forklifts may meet for subsequent analysis.

[0079] Step S501: Obtain the model and specifications of the forklift that is blocking the forklift.

[0080] The forklift model specifications are the forklift models that hinder the forklift.

[0081] Step S502: Determine the required avoidance width corresponding to the forklift model and specification according to a preset parameter matching relationship.

[0082] The required avoidance width is the width value that needs to be moved in the width direction when performing avoidance processing on a forklift of a forklift model and specification. Forklifts of different forklift models and specifications have different forklift parameters, so the corresponding required avoidance widths are also different. The parameter matching relationship between the two is entered and stored in advance by the staff.

[0083] Step S503: constructing a virtual moving line segment according to the current position of the forklift and the meeting point, and constructing an avoidance line perpendicular to the virtual moving line segment at the meeting point.

[0084] The virtual moving line segment is a line segment formed by the current position of the forklift and the meeting point as two end points, and the avoidance line is a line on which the path that the forklift needs to move when performing an avoidance operation is located.

[0085] Step S504: Move the meeting point in any direction of the avoidance line by the required avoidance width to determine the required avoidance point.

[0086] By moving the meeting point along the avoidance line by the required avoidance width, the position point at which the forklift can effectively avoid the obstructing forklift can be determined. At this time, the determined required avoidance point can meet the forklift avoidance requirement.

[0087] After the avoidance line is determined, the positioning and navigation method of the AGV forklift based on visual recognition also includes: Step S600: determining whether the end position point coincides with a path endpoint on the forklift driving path.

[0088] The purpose of the judgment is to know whether the current road section is the last straight section, that is, to determine whether the subsequent forklift needs to perform a turning operation.

[0089] Step S6001: If the end position point coincides with the path endpoint on the forklift driving path, the meeting point is moved in any direction of the avoidance line by the required avoidance width to determine the required avoidance point.

[0090] When the end position coincides with the end point of the forklift's driving path, it means that the subsequent forklift will not turn. At this time, a direction can be randomly selected to determine the required avoidance point.

[0091] Step S6002: If the end position point does not coincide with the path endpoint on the forklift's driving path, a straight driving section on the forklift's driving path following the current section is defined as a subsequent driving section, and a subsequent driving direction is determined based on the subsequent driving section.

[0092] When the end position point does not coincide with the path endpoint on the forklift's driving path, it means that the forklift has to move to the next straight driving section. At this time, the forklift still needs to turn after reaching the end position point. Therefore, how to facilitate the forklift to turn at the end position point is a problem that needs to be solved at present, which requires further analysis; define the subsequent driving section to determine the execution driving section that needs to turn later, and the subsequent driving direction is the moving direction of the forklift when moving on the subsequent driving section.

[0093] Step S601: The meeting point is moved in two directions of the avoidance line by the required avoidance width to determine a simulated avoidance point, and the latter avoidance direction is determined according to the simulated avoidance point and the end position point.

[0094] Determine the simulated avoidance point to mark the position that may be the required avoidance point, so as to facilitate subsequent analysis; the avoidance rear end direction is the direction in which the forklift moves after reaching the simulated avoidance point, that is, the direction in which the simulated avoidance point points to the end position point.

[0095] Step S602: Determine the direction angle according to the subsequent driving direction and the direction of the rear section of the avoidance, and determine the direction angle with the smallest value according to the sorting rules, and define the simulated avoidance point corresponding to the direction angle with the smallest value as the required avoidance point.

[0096] The direction angle is the angle between the subsequent driving direction and the direction of the rear section of the avoidance. The direction angle with the smallest value can be determined through the sorting rules. That is, the angle that needs to be adjusted when the forklift reaches the end position is the smallest, that is, the adjustment difficulty of the forklift is the smallest. At this time, the corresponding simulated avoidance point is defined as the required avoidance point to facilitate the subsequent movement control of the forklift.

[0097] Reference Figure 2 Based on the same inventive concept, an embodiment of the present invention provides a positioning and navigation system for an AGV forklift based on visual recognition, comprising: An acquisition module is used to acquire visual recognition images, forklift driving paths, and the current position of the forklift; A processing module, connected to the acquisition module and the judgment module, for storing and processing information; A judgment module, connected with the acquisition module and the processing module, for judging the information; The processing module divides the forklift driving path into a plurality of straight driving sections according to a preset transportation space diagram, defines the straight driving section including the current position of the forklift as the current section, and determines the end position point and the moving direction of the section on the current section; The processing module determines the clear road section image in a preset image record library according to the current position of the forklift and the moving direction of the road section; The processing module compares the features of the clear road section image with the visual recognition image so that the judgment module can judge whether there are external obstacle features; If the judging module determines that there is no external obstacle feature, the processing module controls the current forklift to continue moving along the current road section; If the judgment module determines that there are external obstacle features, the processing module determines the external obstacle point according to the external obstacle features, and determines the required driving section according to the current position and the end position of the forklift; The judgment module judges whether the external obstacle point is on the required driving section; If the judgment module determines that the external obstacle point is not on the required driving section, the processing module controls the current forklift to continue moving along the current section; If the judgment module determines that the external obstacle point is on the required driving section, the processing module determines the required avoidance point according to the external obstacle characteristics, and constructs a path replacement section according to the current position of the forklift, the required avoidance point and the end position point, and replaces and updates the required driving section with the path replacement section to control the forklift to move along the updated forklift driving path; The obstacle situation analysis module is used to analyze and process the specific situation of obstacles ahead; The forklift encounter analysis module is used to analyze and process the situation where the obstacle in front is other forklifts; An obstructing forklift screening module is used to screen multiple forklifts that meet the requirements to determine a unique obstructing forklift; The required avoidance point determination module is used to determine the required avoidance point so that the forklift can effectively perform avoidance processing; The module for accurately determining the required avoidance points is used to determine the more appropriate required avoidance points so that the forklift can be more conveniently controlled to move later.

[0098] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0099] An embodiment of the present invention provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executes a positioning and navigation method for an AGV forklift based on visual recognition.

[0100] Computer storage media include, for example, various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

Claims

1. A positioning and navigation method for an AGV forklift based on visual recognition, characterized in that: include: Obtain visual recognition images, forklift travel path, and forklift current location; The forklift driving path is divided into a plurality of straight driving sections according to a preset transport space diagram, and the straight driving section including the current position of the forklift is defined as the current section, and the end position point and the moving direction of the section are determined on the current section; Determine the clear road section image in the preset image record library according to the current position of the forklift and the moving direction of the road section; Compare the clear road section image with the visual recognition image to determine whether there are external obstacle features; If there is no external obstacle feature, the current forklift is controlled to continue moving along the current road section; If there are external obstacle features, the external obstacle point is determined according to the external obstacle features, and the required driving section is determined according to the current position and the end position of the forklift; Determine whether the external obstacle point is on the required driving section; If the external obstacle point is not on the required driving section, the current forklift is controlled to continue moving along the current section; If the external obstacle point is on the required driving section, the required avoidance point is determined according to the external obstacle characteristics, and a path replacement section is constructed according to the current position of the forklift, the required avoidance point and the end position point, and the path replacement section is replaced and updated with the required driving section to control the forklift to move along the updated forklift driving path.

2. The positioning and navigation method of an AGV forklift based on visual recognition according to claim 1 is characterized in that: If the external obstacle point is on the required driving section, the positioning and navigation method of the AGV forklift based on visual recognition also includes: On the preset time axis, a unit interval with a width of a preset unit time length is established with the current time point as the front end point; Control the forklift to continue moving along the current road section within the unit interval and continuously acquire visual recognition images, and re-determine the external obstacle point corresponding to the external obstacle feature based on the visual recognition image; Determine the obstacle moving distance based on any two external obstacle points in the unit interval; Determine whether there is a situation where the obstacle moving distance is greater than the preset action distance; If there is no obstacle whose moving distance is greater than the action distance, the required avoidance point is determined according to the characteristics of the external obstacle after the unit interval, and the forklift driving path is updated; If the obstacle moving distance is greater than the action distance, the current forklift is controlled to continue moving along the current road section.

3. The positioning and navigation method of an AGV forklift based on visual recognition according to claim 2 is characterized in that: If there is a situation where the obstacle moving distance is greater than the action distance, the positioning and navigation method of the AGV forklift based on visual recognition is best including: Determine whether the external obstacle feature is a preset transport forklift feature; If the external obstacle feature is not a transport forklift feature, the current forklift is controlled to continue moving along the current road section; If the external obstacle feature is a transport forklift feature, the forklift presence point of each transport forklift is obtained in the preset task scheduling library; Calculate the distance between points according to the forklift existence points and external obstacle points, and determine the point distance with the smallest value according to the preset sorting rules, and define the transport forklift corresponding to the point distance with the smallest value as the obstructing forklift; Determine the obstructing task path according to the obstructing forklift in the task scheduling library, and determine the real-time existence point of the obstructing forklift at each time point according to the obstructing task path; Determine the simulated existence point of the current forklift at each time point according to the forklift's driving path and the forklift's current position; Determine whether there is a situation where the real-time existing point and the simulated existing point overlap on the current road section; If there is no situation where the real-time existing point and the simulated existing point overlap on the current road section, the current forklift is controlled to continue moving along the current road section; If there is a situation where the real-time existence point and the simulated existence point overlap on the current road section, the required avoidance point is determined based on the characteristics of the transport forklift.

4. The positioning and navigation method of an AGV forklift based on visual recognition according to claim 3 is characterized in that: After the distance between the points is determined, the positioning and navigation method of the AGV forklift based on visual recognition also includes: Determine whether there are at least two forklift points with the same and minimum distance between them; If there are not at least two forklift points with the same and minimum distance between points, the obstructing forklift is determined according to the forklift points corresponding to the minimum distance between points; If there are at least two forklift presence points with the same and minimum distance between them, the forklift execution posture of the forklift corresponding to each forklift presence point is obtained according to the task scheduling library, and the forklift obstruction posture is determined according to the characteristics of the transport forklift; Comparing the forklift execution posture and the forklift obstruction posture to determine the posture similarity ratio; The posture similarity ratio with the largest value is determined according to the sorting rule, and the obstructing forklift is determined according to the forklift existence point corresponding to the posture similarity ratio with the largest value.

5. The positioning and navigation method of an AGV forklift based on visual recognition according to claim 3 is characterized in that: The steps for determining the required avoidance points based on the characteristics of the transport forklift include: The point where the real-time existing point and the simulated existing point overlap on the current road section is defined as the meeting point; Get the model and specifications of the forklift that is blocking the forklift; Determine the required avoidance width corresponding to the forklift model and specification based on the preset parameter matching relationship; A virtual moving line segment is constructed according to the current position of the forklift and the meeting point, and an avoidance line perpendicular to the virtual moving line segment is constructed at the meeting point; Move the meeting point in any direction of the avoidance line by the required avoidance width to determine the required avoidance point.

6. The positioning and navigation method of an AGV forklift based on visual recognition according to claim 5, characterized in that: After the avoidance line is determined, the positioning and navigation method of the AGV forklift based on visual recognition also includes: Determine whether the end position point coincides with the path endpoint on the forklift's driving path; If the end position coincides with the path endpoint on the forklift's driving path, the meeting point is moved in any direction of the avoidance line by the required avoidance width to determine the required avoidance point; If the end position point does not coincide with the path endpoint on the forklift's driving path, the straight driving section on the forklift's driving path that is after the current section is defined as the subsequent driving section, and the subsequent driving direction is determined based on the subsequent driving section; The meeting point is moved in both directions of the avoidance line by the required avoidance width to determine the simulated avoidance point, and the direction of the latter part of the avoidance is determined according to the simulated avoidance point and the end position point; The direction angle is determined according to the subsequent driving direction and the direction of the rear section of the avoidance, and the direction angle with the smallest value is determined according to the sorting rules, and the simulated avoidance point corresponding to the direction angle with the smallest value is defined as the required avoidance point.

7. A positioning and navigation system for AGV forklift based on visual recognition, characterized in that: include: An acquisition module is used to acquire visual recognition images, forklift driving paths, and the current position of the forklift; A processing module, connected to the acquisition module and the judgment module, for storing and processing information; A judgment module, connected with the acquisition module and the processing module, for judging the information; The processing module divides the forklift driving path into a plurality of straight driving sections according to a preset transportation space diagram, defines the straight driving section including the current position of the forklift as the current section, and determines the end position point and the moving direction of the section on the current section; The processing module determines the clear road section image in a preset image record library according to the current position of the forklift and the moving direction of the road section; The processing module compares the features of the clear road section image with the visual recognition image so that the judgment module can judge whether there are external obstacle features; If the judging module determines that there is no external obstacle feature, the processing module controls the current forklift to continue moving along the current road section; If the judgment module determines that there are external obstacle features, the processing module determines the external obstacle point according to the external obstacle features, and determines the required driving section according to the current position and the end position of the forklift; The judgment module judges whether the external obstacle point is on the required driving section; If the judgment module determines that the external obstacle point is not on the required driving section, the processing module controls the current forklift to continue moving along the current section; If the judgment module determines that the external obstacle point is on the required driving section, the processing module determines the required avoidance point according to the external obstacle characteristics, and constructs a path replacement section according to the current position of the forklift, the required avoidance point and the end position point, and replaces and updates the required driving section with the path replacement section to control the forklift to move along the updated forklift driving path.

8. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 6.

Images