CN118568999B - Intelligent storage handling equipment quality control system - Google Patents
Intelligent storage handling equipment quality control system Download PDFInfo
- Publication number
- CN118568999B CN118568999B CN202411038070.6A CN202411038070A CN118568999B CN 118568999 B CN118568999 B CN 118568999B CN 202411038070 A CN202411038070 A CN 202411038070A CN 118568999 B CN118568999 B CN 118568999B
- Authority
- CN
- China
- Prior art keywords
- obstacle
- quality
- path planning
- obstacle recognition
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/163—Programme controls characterised by the control loop learning, adaptive, model based, rule based expert control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
- B25J9/1666—Avoiding collision or forbidden zones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/30—Post-processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
Abstract
The invention discloses an intelligent warehousing and transportation equipment quality control system, which particularly relates to the technical field of warehousing and transportation equipment management, and comprises a basic equipment analysis module, a simulation test analysis module and an environment support resource management module, wherein the basic equipment analysis module, the simulation test analysis module and the environment support resource management module are used for acquiring the quality of data acquisition equipment and the quality of communication equipment of a warehousing and transportation environment; performing simulation test to obtain the performance of the obstacle recognition model and the path planning model in a simulation environment, and analyzing to obtain the obstacle recognition model quality evaluation index and the path planning model quality evaluation index; the analysis results based on the basic equipment analysis module and the simulation test analysis module obtain the reliability coefficient of the environment support resources, and corresponding measures are taken based on the reliability coefficient of the environment support resources, so that the problems of insufficient reliability and low efficiency of the conveying system caused by the fact that key components in the quality control system of the conventional warehouse conveying equipment do not operate in an optimal state are solved.
Description
Technical Field
The invention relates to the technical field of warehouse handling equipment management, in particular to a quality control system of intelligent warehouse handling equipment.
Background
The intelligent warehouse handling equipment should be provided with an intelligent path planning and obstacle avoidance algorithm to avoid collision with obstacles. By combining sensor data and obstacle avoidance algorithm, the warehouse handling equipment can detect and respond to the obstacle in real time, and select a proper path to bypass the obstacle so as to realize safe and efficient handling operation.
The existing quality control system of the warehouse handling equipment is characterized in that after warehouse environment data and cargo data are collected, the warehouse environment data and the cargo data are transmitted to a warehouse handling equipment center control platform, after the warehouse handling equipment center control platform recognizes obstacle information of a warehouse environment through an obstacle recognition model according to the received collected environment data and cargo data, the obstacle information and the cargo information are input into a path planning model to obtain path information of the warehouse handling equipment, the path information is transmitted to an execution end of the warehouse handling equipment, and the warehouse handling equipment is used for grabbing, transferring and placing cargoes based on the path information and the cargo information to finish handling operation of the cargoes.
The quality of the storage and conveying equipment is not separated from the reliability of the quality of collected data, the reliability of the obstacle recognition model and the reliability of the path planning model, and when the conventional storage and conveying system is in actual use, the problem that key components in the quality control system of the storage and conveying equipment do not operate in an optimal state, so that the reliability of the conveying system is insufficient and the efficiency is low still caused; for example, in the operation process of the existing warehouse handling equipment, the operation efficiency is reduced and handling errors are increased possibly due to the environment support resource quality problem, the obstacle recognition model and the abnormal path planning model.
Based on the method, the quality control system of the intelligent warehouse handling equipment is provided, and the operation efficiency and the operation quality of the warehouse handling equipment are improved by analyzing the environmental support resources of the warehouse handling equipment and the quality of an algorithm model.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a quality control system of intelligent warehouse handling equipment, which is used for monitoring and evaluating the quality of data acquisition, obstacle recognition models, path planning models and data communication resources in real time through an environment supporting resource management module, so that the key components are ensured to run in an optimal state, the reliability and the efficiency of the whole handling system are improved, and the problems in the background technology are solved.
In order to achieve the above purpose, the present invention provides the following technical solutions: an intelligent warehouse handling equipment quality control system, comprising:
The basic equipment analysis module is used for acquiring the quality of data acquisition equipment and the quality of communication equipment in the warehouse and carrying environment, analyzing to obtain a quality stability index Zs of the data acquisition equipment and a communication transmission quality stability index Zt, and transmitting the data acquisition equipment quality stability index Zs and the communication transmission quality stability index Zt to the environment support resource management module;
The simulation test analysis module is used for performing simulation test, obtaining the performance of the obstacle recognition model and the path planning model in a simulation environment, analyzing to obtain an obstacle recognition model quality evaluation index Zm and a path planning model quality evaluation index Lm, and transmitting the obstacle recognition model quality evaluation index Zm and the path planning model quality evaluation index Lm to the environment support resource management module;
The environment support resource management module is used for jointly analyzing the quality stability index Zs, the communication transmission quality stability index Zt, the obstacle recognition model quality evaluation index Zm and the path planning model quality evaluation index Lm of the data acquisition equipment to obtain an environment support resource reliability coefficient HZ, and taking corresponding measures based on the environment support resource reliability coefficient.
Preferably, the quality of the data acquisition device for each time period is recorded as SJ i, i represents the number of the time period, i is an integer from 1 to n, SJ 0 represents the preset quality of the data acquisition device, and the method is as followsCalculating to obtain a quality stability index Zs of the data acquisition equipment; the quality of the communication equipment in each time period is recorded as SC i, the SC 0 is used for representing the preset quality of the communication equipment, and the formula is adoptedCalculating to obtain a communication transmission quality stability index Zt;
preferably, the process of obtaining the obstacle recognition model quality assessment index Zm and the path planning model quality assessment index Lm includes the steps of:
Step S11, designing a scene: according to the operation scene and the environmental characteristics of the actual warehousing and transportation equipment, designing an obstacle scene in simulation software, and creating a virtual model of the warehousing and transportation equipment;
Step S12, writing an algorithm: writing corresponding codes or scripts according to the principle and the implementation thought of the obstacle recognition algorithm and the path planning algorithm to obtain an obstacle recognition model and a path planning model;
Step S13, setting a test scene: setting scene parameters of obstacle recognition simulation tests and scene parameters of path planning simulation tests;
Step S14, running a simulation test and recording data: running a simulation test and recording data in the simulation test process to obtain a simulation test result of the obstacle recognition model and a simulation test result of the path planning model;
step S15, analyzing simulation test results: the balance fraction, the obstacle recognition time deviation degree and the obstacle positioning accuracy of the obstacle recognition model are jointly analyzed to obtain an obstacle recognition model quality evaluation index Zm; and jointly analyzing the path length deviation degree, the normal traffic rate of the path and the path planning time deviation degree of the path planning model to obtain the path planning model quality evaluation index Lm.
Preferably, the model is mass analyzed by an obstacle recognition modelCalculating to obtain a quality evaluation index Zm of the obstacle recognition model, wherein alpha 1、α2 and alpha 3 respectively represent the proportionality coefficients of the various items, alpha 1+α2+α3 =1.0, fs represents the balance score of the obstacle recognition model for recognizing the obstacle, sp represents the deviation degree of the obstacle recognition time, and Zd represents the positioning accuracy of the obstacle; quality analysis model through path planning modelAnd calculating a path planning model quality evaluation index Lm, wherein beta 1 represents an influence factor of the path length deviation degree, beta 2 represents an influence factor of the path planning time deviation degree, beta 1+β2 =1.0, lc represents the path length deviation degree of the path planning model, lt represents the normal traffic rate of the path, and Ls represents the path planning time deviation degree.
Preferably, the quality stability index of the data acquisition equipment, the communication transmission quality stability index, the obstacle recognition model quality evaluation index and the path planning model quality evaluation index form a first-level feature set; the data acquisition equipment quality stability index, the communication transmission quality stability index and the obstacle recognition model quality evaluation index are interacted with each other to complete feature fusion, so that a secondary feature set is formed; the intersection of the primary feature set and the secondary feature set forms a comprehensive feature set; screening feature factors related to the reliability of the environment support resources from the comprehensive feature set by using a principal component analysis method, and matching weight coefficients for the feature factors; the value of each characteristic factor is multiplied by the corresponding weight coefficient and then summed to obtain a weighted summation result; and calculating the ratio of the weighted sum result to the weighted coefficient sum to obtain the environment support resource reliability coefficient HZ.
Preferably, when the reliability coefficient HZ of the environment supporting resources is smaller than the preset value HZ 0, indicating that the environment supporting resources of the warehouse transporting equipment are abnormal, giving an early warning to a user to pause the execution of the warehouse transporting task, prompting the user to pay attention to the environment supporting resources, analyzing the reasons of the abnormality of the environment supporting resources, optimizing the data acquisition device, the communication equipment, the obstacle recognition model and the path planning model until the reliability coefficient HZ of the environment supporting resources is larger than or equal to the preset value HZ 0, and recovering the execution of the warehouse transporting task; when the reliability coefficient HZ of the environment supporting resources is more than or equal to the preset value HZ 0, the environment supporting resources of the warehouse handling equipment are normal, and no measures are needed.
Preferably, the system further comprises an obstacle recognition correction module and a path planning correction module, wherein the obstacle recognition correction module is used for obtaining corrected balance scores xu_Fs, obstacle recognition time deviation degrees xu_Sp and obstacle positioning accuracy xu_zd; the path planning correction module is used for obtaining corrected path length deviation degree xu_lc and corrected path planning time deviation degree xu_ls, matching corresponding correction coefficients for each obstacle recognition simulation test according to scene complexity parameters of the obstacle recognition simulation test, and correcting balance scores of obstacle recognition models for recognizing obstacles, obstacle recognition time deviation degree and obstacle positioning accuracy through weighted summation and averaging to obtain corrected balance scores xu_fs, obstacle recognition time deviation degree xu_Sp and obstacle positioning accuracy xu_zd.
Preferably, s is used for representing the number of the obstacle recognition simulation test, the number is an integer from 1 to q, and the balance score, the obstacle recognition time deviation degree and the obstacle positioning accuracy of the s-th obstacle recognition simulation test are respectively marked as Fs_s, sp_s and zd_s; by the formulaCalculating to obtain a corrected balance score xu_Fs; by the formulaCalculating to obtain corrected obstacle recognition time deviation degree xu_Sp; by the formulaAnd calculating to obtain corrected barrier positioning accuracy xu_zd, wherein yz_s represents a correction coefficient of the s-th barrier identification simulation test.
Preferably, the correction coefficient acquisition mode of the s-th obstacle recognition simulation test is as follows:
By the formula Calculating to obtain scene complexity parameters ZH s of the s-th obstacle recognition simulation test, wherein Lux represents ambient illumination intensity, le represents illumination uniformity, cs represents obstacle area, and ζ represents obstacle type influence factors; the value range of the illumination uniformity is 0 to 1, and the closer the illumination uniformity is to 1, the better the illumination uniformity is;
By the formula And calculating to obtain the correction coefficient of the s-th obstacle recognition simulation test as yz_s.
Preferably, according to the scene complexity parameter of the path planning simulation test, the path length deviation degree and the path planning time deviation degree of the path planning model are corrected by weighting and summing to average the correction coefficient corresponding to each path planning simulation test, and the corrected path length deviation degree xu_lc and the corrected path planning time deviation degree xu_ls are obtained.
Preferably, t is used to represent the number of the path planning simulation test, the value is an integer from 1 to p, and the path length deviation degree and the path planning time deviation degree of the t-th path planning simulation test are respectively recorded as lc_t and ls_t; by the formulaCalculating to obtain a corrected path length deviation degree xu_lc; by the formulaAnd calculating the corrected path planning time deviation degree xu_ls, wherein yl_t represents the correction coefficient of the t-th path planning simulation test.
Preferably, the correction coefficient obtaining mode of the t-th path planning simulation test is as follows:
By the formula Calculating to obtain scene complexity parameters LH t of a t-th path planning simulation test, wherein Cm represents the number of obstacles, cs represents the area of the obstacle and FL represents the distribution discrete coefficient of the obstacle;
By the formula And calculating to obtain a correction coefficient of the t-th path planning simulation test as yl_t.
Preferably, the corrected balance score xu_Fs, the obstacle recognition time deviation degree xu_Sp and the obstacle positioning accuracy xu_Zd are used for replacing Fs, sp and Zd, and the obstacle recognition model quality evaluation index Zm is obtained through calculation of the obstacle recognition model quality analysis model; and replacing Lc and Ls with the corrected path length deviation xu_lc and the corrected path planning time deviation xu_ls, and calculating by a path planning model quality analysis model to obtain a path planning model quality evaluation index Lm.
Preferably, the system also comprises a warehouse handling equipment execution end analysis module and a warehouse handling execution end management module;
the storage handling equipment execution end analysis module acquires the condition of the storage handling equipment execution end, analyzes to obtain a basic operation evaluation index ZJp and an instruction execution stability index ZLw, and jointly analyzes the basic operation evaluation index ZJp and the instruction execution stability index ZLw to obtain a storage handling equipment execution end risk coefficient RZF;
And the warehouse carrying execution end management module is used for taking corresponding measures based on the risk coefficient RZF of the warehouse carrying equipment execution end, such as screening abnormal warehouse carrying equipment execution ends.
Preferably, the system further comprises a supervision resource allocation module, wherein the supervision resource demand coefficient of each warehouse handling equipment is calculated based on the risk coefficient of the warehouse handling equipment execution end and the environment support resource reliability coefficient, and supervision resources for the warehouse handling equipment are allocated based on the supervision resource demand coefficient.
The invention has the technical effects and advantages that:
The quality control system of the warehouse handling equipment acquires the quality of data acquisition equipment and the quality of communication equipment of the warehouse handling environment; performing simulation test to obtain the performance of the obstacle recognition model and the path planning model in a simulation environment, and analyzing to obtain the obstacle recognition model quality evaluation index and the path planning model quality evaluation index; the analysis results based on the basic equipment analysis module and the simulation test analysis module obtain the reliability coefficient of the environment support resources, and corresponding measures are taken based on the reliability coefficient of the environment support resources, so that the problems of insufficient reliability and low efficiency of the conveying system caused by the fact that key components in the quality control system of the conventional warehouse conveying equipment do not operate in an optimal state are solved.
According to the quality control system for the warehouse handling equipment, provided by the invention, the virtual simulation environment is built by using the simulation software or tools, the path planning algorithm and the obstacle avoidance algorithm of the warehouse handling equipment are verified and evaluated, the performance of the obstacle recognition model and the path planning model can be evaluated at lower cost and risk, and the improvement and optimization can be performed according to the evaluation result.
According to the quality control system of the warehouse handling equipment, the corrected balance score xu_Fs, the obstacle recognition time deviation degree xu_Sp and the obstacle positioning accuracy xu_Zd are obtained by matching the corresponding correction coefficients for each simulation test according to the scene complexity parameters, and the corrected obstacle recognition model quality evaluation index is obtained based on the corrected balance score, the corrected time deviation degree and the corrected obstacle recognition time deviation degree, so that a user can be helped to know the operation quality of an actual obstacle recognition model; and obtaining the corrected path length deviation degree xu_lc and the corrected path planning time deviation degree xu_ls to obtain a corrected path planning model quality evaluation index, so that a user can be helped to know the running quality of an actual path planning model.
According to the quality control system for the warehouse handling equipment, provided by the invention, the abnormal warehouse handling equipment execution end can be found and screened out in time through the calculation of the handling execution end risk coefficient, so that potential risks are prevented, and the safety and stability of handling operation are ensured.
Drawings
FIG. 1 is a schematic diagram of the quality control system of a warehouse handling equipment based on environmental support resource management according to the present invention.
FIG. 2 is a flow chart of the simulation test analysis of the present invention.
Fig. 3 is a schematic working diagram of a quality control system of a warehouse handling equipment based on a correction module according to the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the application, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
Embodiment 1 referring to the working schematic diagram of the quality control system of the warehouse handling equipment based on the environment supporting resource management of fig. 1, the present invention provides an intelligent warehouse handling equipment quality control system as shown in fig. 1, comprising:
The basic equipment analysis module is used for acquiring the quality of data acquisition equipment and the quality of communication equipment in the warehouse and carrying environment, analyzing to obtain a quality stability index Zs of the data acquisition equipment and a communication transmission quality stability index Zt, and transmitting the data acquisition equipment quality stability index Zs and the communication transmission quality stability index Zt to the environment support resource management module;
In the embodiment of the present invention, it should be further explained that the quality of the data acquisition device for each time period is recorded as SJ i, i represents the number of the time period, i is an integer from 1 to n, SJ 0 represents the preset quality of the data acquisition device, and the formula is used for the data acquisition device Calculating to obtain a quality stability index Zs of the data acquisition equipment; the quality of the communication equipment in each time period is obtained and recorded as SC i, the SC 0 is used for representing the preset quality of the communication equipment, and the formula is adoptedAnd calculating to obtain the communication transmission quality stability index Zt.
In the embodiment of the invention, the quality of the data acquisition equipment represents the degree that the accuracy, the integrity, the consistency and the timeliness of the data acquired by the data acquisition equipment meet the preset standard; the quality of the communication equipment represents the degree that the transmission efficiency, the transmission reliability, the anti-interference capability and the transmission delay of the communication equipment meet preset standards; the embodiment of the invention does not limit the specific types of the quality of the data acquisition equipment and the quality of the communication equipment, and a user can select the data acquisition equipment and the communication equipment according to actual conditions.
The simulation test analysis module is used for performing simulation test, obtaining the performance of the obstacle recognition model and the path planning model in a simulation environment, analyzing to obtain an obstacle recognition model quality evaluation index Zm and a path planning model quality evaluation index Lm, and transmitting the obstacle recognition model quality evaluation index Zm and the path planning model quality evaluation index Lm to the environment support resource management module;
referring to the simulation test analysis flow chart of fig. 2, in the simulation test analysis module, a simulation environment is built, performances of the obstacle recognition model and the path planning model in the simulation environment are obtained, and a process of obtaining the obstacle recognition model quality evaluation index Zm and the path planning model quality evaluation index Lm includes the following steps:
Step S11, designing a scene: according to the operation scene and the environmental characteristics of the actual warehousing and transportation equipment, designing an obstacle scene in simulation software, and creating a virtual model of the warehousing and transportation equipment;
The method comprises the steps of describing, inputting collected warehouse environment data into the type and the position of an output obstacle of an obstacle recognition model; inputting the acquired obstacle information and cargo information into a roadbed planning model, and outputting path information of a storage handling equipment virtual model;
Step S12, writing an algorithm: writing corresponding codes or scripts according to the principle and the implementation thought of the obstacle recognition algorithm and the path planning algorithm to obtain an obstacle recognition model and a path planning model;
Step S13, setting a test scene: setting scene parameters of obstacle recognition simulation tests and scene parameters of path planning simulation tests;
the scene parameters of the obstacle recognition simulation test comprise illumination intensity, illumination uniformity, obstacle area and obstacle type of the scene; the scene parameters of the path planning simulation test comprise the initial position, the target position, the number of obstacles between the initial position and the target position, the area of the obstacles and the discrete coefficient of the distribution of the obstacles of the virtual model of the warehouse handling equipment;
Step S14, running a simulation test and recording data: running a simulation test and recording data in the simulation test process to obtain a simulation test result of the obstacle recognition model and a simulation test result of the path planning model;
The simulation test result of the obstacle recognition model includes: the obstacle recognition model recognizes the balance score, the obstacle recognition time deviation degree and the obstacle positioning accuracy of the obstacle; the simulation test result of the path planning model comprises: path length deviation of the path planning model, normal traffic rate of the path and path planning time deviation.
Step S15, analyzing simulation test results: the balance fraction, the obstacle recognition time deviation degree and the obstacle positioning accuracy of the obstacle recognition model are jointly analyzed to obtain an obstacle recognition model quality evaluation index Zm; and jointly analyzing the path length deviation degree, the normal traffic rate of the path and the path planning time deviation degree of the path planning model to obtain the path planning model quality evaluation index Lm.
In the description supplement, simulation software or tools are used for constructing a simulation environment in simulation test analysis, and in the process of analyzing a path planning model based on an obstacle recognition model, proper simulation software or tools such as MATLAB, ROS (robot operating system) and Gazebo, coppeliaSim are selected according to requirements and algorithm characteristics; selecting a suitable sensor, such as a laser radar, a camera, an ultrasonic sensor, to acquire data of the surrounding environment; the reliability of path planning and obstacle avoidance algorithms is verified by providing different types of obstacles, such as ceilings, walls, shelves, cargo, uneven ground, overhead wires, furniture, other moving objects.
In the embodiment of the present invention, it is further explained that the balance score of the obstacle recognition model for recognizing the obstacle is obtained by: based on FN, TP, FP, TN for identifying the obstacle, obtaining a balance score Fs of the obstacle identified by the obstacle identification model; the obstacle recognition time deviation Sp is an index for measuring the time accuracy of the obstacle recognition model in recognizing the obstacle, and is the deviation degree between the time required for the obstacle recognition model to recognize the obstacle and the expected recognition time; the obstacle positioning accuracy Zd is an index for describing the position judgment accuracy degree of the obstacle recognition model when recognizing the obstacle, reflects the accuracy of the obstacle recognition model when determining the actual position of the obstacle, and represents the deviation degree between the position coordinate of the obstacle recognition model output recognition and the coordinate deviation of the actual recognition obstacle.
FN is illustrated as representing a false negative, i.e. a situation where the obstacle recognition model erroneously predicts a positive sample as a negative sample; TP represents a real case, i.e., a case where the obstacle recognition model correctly predicts a positive sample as a positive sample; FP represents false positives, i.e. the situation where the obstacle recognition model erroneously predicts a negative sample as a positive sample; TN represents true negatives, i.e., the situation where the obstacle recognition model correctly predicts the negative sample as a negative sample.
In the embodiment of the present invention, it needs to be further explained that the obtaining manner of the path length deviation Lc is as follows: when the path planning model outputs planning path information according to the input obstacle and cargo information, calculating a path length deviation Lc based on a difference between the output length of the planning path and a theoretical shortest or optimal path length; the normal pass rate Lt of the path refers to the proportion of successful passing of the warehouse handling equipment according to the planned path information; the path planning time deviation Ls refers to the deviation degree between the time required for the path planning model to output the planned path and the expected planning time.
It should be further explained in the embodiments of the present invention that the model is mass-analyzed by the obstacle recognition modelCalculating to obtain a quality evaluation index Zm of the obstacle recognition model, wherein alpha 1、α2 and alpha 3 respectively represent the proportionality coefficients of the various items, alpha 1+α2+α3 =1.0, fs represents the balance score of the obstacle recognition model for recognizing the obstacle, sp represents the deviation degree of the obstacle recognition time, and Zd represents the positioning accuracy of the obstacle; quality analysis model through path planning modelAnd calculating a path planning model quality evaluation index Lm, wherein beta 1 represents an influence factor of the path length deviation degree, beta 2 represents an influence factor of the path planning time deviation degree, beta 1+β2 =1.0, lc represents the path length deviation degree of the path planning model, lt represents the normal traffic rate of the path, and Ls represents the path planning time deviation degree.
The environment support resource management module is used for jointly analyzing the quality stability index Zs, the communication transmission quality stability index Zt, the obstacle recognition model quality evaluation index Zm and the path planning model quality evaluation index Lm of the data acquisition equipment to obtain an environment support resource reliability coefficient HZ, and taking corresponding measures based on the environment support resource reliability coefficient.
In the embodiment of the invention, it is further explained that the environment support resource reliability coefficient HZ is obtained through calculation of the environment support resource reliability analysis model, and corresponding measures are adopted based on the relation between the environment support resource reliability coefficient HZ and the preset value HZ 0.
In a further design, the data acquisition equipment quality stability index, the communication transmission quality stability index, the obstacle recognition model quality evaluation index and the path planning model quality evaluation index form a first-level feature set;
The data acquisition equipment quality stability index, the communication transmission quality stability index and the obstacle recognition model quality evaluation index are interacted with each other to complete feature fusion, so that a secondary feature set is formed;
the intersection of the primary feature set and the secondary feature set forms a comprehensive feature set;
Screening feature factors related to the reliability of the environment support resources from the comprehensive feature set by using a principal component analysis method, and matching weight coefficients for the feature factors; and multiplying the value of each characteristic factor with the corresponding weight coefficient, summing, and calculating the ratio of the value to the sum of the weight coefficients to obtain the environment support resource reliability coefficient.
Illustratively, when the feature factors obtained by screening are STz1, STz2, STz, …, and the corresponding weight coefficients are wz1, wz2, …, the resource reliability analysis model is supported by the environment,
And calculating to obtain the environment support resource reliability coefficient HZ.
Exemplary, when the characteristic factors obtained by screening areCorresponding weight coefficients are marked as w11, w12, w13 and w14, and the resource reliability analysis model is supported through the environmentAnd calculating to obtain the environment support resource reliability coefficient HZ.
Exemplary, when the characteristic factors obtained by screening areCorresponding weight coefficients are marked as w21, w22, w23 and w24, and the resource reliability analysis model is supported through the environmentAnd calculating to obtain the environment support resource reliability coefficient HZ.
In the embodiment of the invention, when the reliability coefficient HZ of the environment supporting resources is smaller than the preset value HZ 0, indicating that the environment supporting resources of the warehouse handling equipment are abnormal, giving an early warning to a user to pause the execution of the warehouse handling task, prompting the user to pay attention to the environment supporting resources, analyzing the reasons of the abnormality of the environment supporting resources, optimizing a data acquisition device, a communication device, an obstacle recognition model and a path planning model until the reliability coefficient HZ of the environment supporting resources is larger than or equal to the preset value HZ 0, and recovering the execution of the warehouse handling task; when the reliability coefficient HZ of the environment supporting resources is more than or equal to the preset value HZ 0, the environment supporting resources of the warehouse handling equipment are normal, and no measures are needed.
The advantages are that: by constructing a virtual simulation environment by using simulation software or tools, the path planning algorithm and the obstacle avoidance algorithm of the warehouse handling equipment are verified and evaluated, the performance of the obstacle recognition model and the path planning model can be evaluated at lower cost and risk, and the improvement and optimization can be performed according to the evaluation result.
In the embodiment of the invention, in order to improve the reliability of the simulation test result, under the condition that the quality of the data acquisition equipment and the quality of the communication equipment are normal, the simulation test is carried out for a plurality of times, and then the average is taken to obtain the simulation test result of the obstacle recognition model; and under the condition that the quality of the data acquisition equipment, the quality of the communication equipment and the obstacle recognition model are normal, carrying out simulation test for a plurality of times, and averaging to obtain a simulation test result of the path planning model.
Referring to the working schematic diagram of the quality control system of the warehouse handling equipment based on the correction module of fig. 3, in a further design, the system further comprises a barrier identification correction module and a path planning correction module, wherein the barrier identification correction module is used for obtaining a corrected balance score xu_fs, a barrier identification time deviation xu_sp and barrier positioning accuracy xu_zd; the path planning correction module is used for obtaining corrected path length deviation degree xu_lc and corrected path planning time deviation degree xu_ls.
In a further design, according to scene complexity parameters of the obstacle recognition simulation test, matching corresponding correction coefficients for each obstacle recognition simulation test, and carrying out weighted summation averaging to correct balance scores, obstacle recognition time deviation degrees and obstacle positioning accuracy of the obstacle recognition model recognition obstacles to obtain corrected balance scores xu_Fs, obstacle recognition time deviation degrees xu_Sp and obstacle positioning accuracy xu_zd.
For example, s is used for representing the number of the obstacle recognition simulation test, the number is an integer from 1 to q, and the balance score, the obstacle recognition time deviation degree and the obstacle positioning accuracy of the s-th obstacle recognition simulation test are respectively marked as Fs_s, sp_s and zd_s; by the formulaCalculating to obtain a corrected balance score xu_Fs; by the formulaCalculating to obtain corrected obstacle recognition time deviation degree xu_Sp; by the formulaAnd calculating to obtain corrected barrier positioning accuracy xu_zd, wherein yz_s represents a correction coefficient of the s-th barrier identification simulation test.
In further design, according to scene complexity parameters of the path planning simulation test, matching corresponding correction coefficients for each path planning simulation test, and carrying out weighted summation to average the path length deviation degree and the path planning time deviation degree of the path planning model so as to obtain corrected path length deviation degree xu_lc and corrected path planning time deviation degree xu_ls.
For example, t is used to represent the number of the path planning simulation test, the value is an integer from 1 to p, and the path length deviation degree and the path planning time deviation degree of the t-th path planning simulation test are respectively recorded as lc_t and ls_t; by the formulaCalculating to obtain a corrected path length deviation degree xu_lc; by the formulaAnd calculating the corrected path planning time deviation degree xu_ls, wherein yl_t represents the correction coefficient of the t-th path planning simulation test.
In the embodiment of the invention, it is further explained that the correction coefficient acquisition mode of the s-th obstacle recognition simulation test is as follows:
By the formula Calculating to obtain scene complexity parameters ZH s of the s-th obstacle recognition simulation test, wherein Lux represents ambient illumination intensity, lux 0 represents preset ambient illumination intensity, le represents illumination uniformity, cs represents obstacle area, and ζ represents obstacle type influence factors; the value range of the illumination uniformity Le is 0 to 1, and the closer the illumination uniformity is to 1, the better the illumination uniformity is;
By the formula And calculating to obtain the correction coefficient of the s-th obstacle recognition simulation test as yz_s.
In the embodiment of the invention, it is further explained that the correction coefficient acquisition mode of the t-th path planning simulation test is as follows:
By the formula Calculating to obtain scene complexity parameters LH t of a t-th path planning simulation test, wherein Cm represents the number of obstacles, cs represents the area of the obstacle and FL represents the distribution discrete coefficient of the obstacle;
By the formula And calculating to obtain a correction coefficient of the t-th path planning simulation test as yl_t.
In a further design, using the corrected balance score xu_Fs, the obstacle recognition time deviation degree xu_Sp and the obstacle positioning accuracy xu_Zd to replace Fs, sp and Zd, and calculating to obtain an obstacle recognition model quality evaluation index Zm through an obstacle recognition model quality analysis model; and replacing Lc and Ls with the corrected path length deviation xu_lc and the corrected path planning time deviation xu_ls, and calculating by a path planning model quality analysis model to obtain a path planning model quality evaluation index Lm.
The method has the advantages that the corresponding correction coefficient is matched for each simulation test according to the scene complexity parameter, the corrected balance score xu_Fs, the obstacle recognition time deviation degree xu_Sp and the obstacle positioning accuracy xu_Zd are obtained, the corrected obstacle recognition model quality evaluation index is obtained based on the corrected balance score, the corrected time deviation degree and the corrected obstacle recognition time deviation degree, and the user can be helped to know the running quality of an actual obstacle recognition model; and obtaining the corrected path length deviation degree xu_lc and the corrected path planning time deviation degree xu_ls to obtain a corrected path planning model quality evaluation index, so that a user can be helped to know the running quality of an actual path planning model.
In embodiment 2, the background illustrates that the execution end of the warehouse handling device generates an execution instruction according to the path information and the cargo information, and based on the execution instruction, realizes accurate grabbing of the cargo, and moves the grabbed cargo to an expected position according to a preset speed for placement.
The embodiment of the present invention is different from embodiment 1 in that it further includes:
The storage handling equipment execution end analysis module is used for obtaining the storage handling equipment execution end condition, analyzing to obtain a basic operation evaluation index ZJp and an instruction execution stability index ZLw, and jointly analyzing the basic operation evaluation index ZJp and the instruction execution stability index ZLw to obtain a storage handling equipment execution end risk coefficient RZF;
And the warehouse carrying execution end management module is used for taking corresponding measures based on the risk coefficient RZF of the warehouse carrying equipment execution end, such as screening abnormal warehouse carrying equipment execution ends.
In the embodiment of the invention, after the storage handling equipment executing end executes the grabbing, moving and placing operations for a plurality of times, the grabbing quality stability parameter Zq, the moving accuracy parameter Yd and the placing and positioning accuracy parameter Fd are obtained by analyzing the executing condition,
The grasping quality stability parameter Zq, the moving accuracy parameter Yd and the placement positioning accuracy parameter Fd are analyzed in a combined mode to obtain a basic operation quality index ZJp;
Illustratively, the correlation formula is as follows:
Wherein γ1 is a grasping quality influence factor, γ2 is a moving quality influence factor, and γ3 is a placement quality influence factor;
In the embodiment of the present invention, it should be further explained that the grasping quality stability parameter Zq refers to: the ratio of the number of times the storage carrying equipment executing end successfully grabs the goods to the total number of attempts; the movement accuracy parameter Yd refers to the movement speed control precision of the storage carrying equipment executing end, and the actual measured speed is divided by a set value to calculate the movement speed control precision; the placement positioning accuracy parameter Fd refers to the acceleration of the goods after the goods are placed by the execution end of the storage and conveying equipment, and the acceleration of the goods is monitored through the inclination sensor installed on the goods or the conveying equipment.
The embodiment of the invention needs to be further explained, namely, analyzing the behavior of the storage carrying equipment execution end after receiving the execution instruction to obtain the instruction response speed Zx and the instruction completion degree parameter Zw; by the formulaAn instruction execution stability index ZLw is calculated, where Zx 0 represents a preset instruction response speed.
In the embodiment of the invention, it is further explained that the instruction response speed Zx refers to the time required from the start of response to the actual execution of the action after the handling execution end receives the operation instruction, and the instruction response speed Zx measures the response sensitivity and the execution efficiency of the handling execution end; the instruction completion degree parameter Zw is obtained by the following steps: and carrying out instruction execution test on the carrying execution end by utilizing automatic test, simulating various operation instructions of the carrying execution end, automatically recording the execution result of the carrying execution end, and evaluating the instruction completion degree parameter of the equipment by comparing the difference between the test result and the expected result.
In the embodiment of the invention, the risk coefficient RZF of the execution end of the storage handling equipment is obtained based on the joint analysis of the following formula,
Wherein k1 and k2 are weight coefficients, and k 1 2+k2 2 =1 based on user settings, and 0.ltoreq.k1.ltoreq.k2.ltoreq.1.
In the embodiment of the invention, it is further explained that when the risk coefficient RZF of the execution end of the storage and conveying equipment exceeds the preset value RZ 0, the execution end of the storage and conveying equipment is indicated to be abnormal, the storage and conveying equipment is marked as abnormal storage and conveying equipment, the execution of the storage and conveying task is warned and suspended to a user, the user is prompted to pay attention to the execution end of the storage and conveying equipment, the cause of the abnormality of the execution end of the storage and conveying is analyzed, and a motor, a grabbing clamp and a positioning device of the execution end are optimized until the risk coefficient ZF of the conveying and conveying is more than or equal to the preset value ZF 0; when the risk coefficient RZF of the execution end of the storage and conveying equipment does not exceed the preset value RZ 0, the execution end of the storage and conveying equipment is normal, and no measures are needed.
The advantages are that: through the calculation of the risk coefficient of the carrying execution end, the abnormal carrying execution end of the warehouse carrying equipment can be found and screened in time, so that potential risks are prevented, and the safety and stability of carrying operation are ensured.
Embodiment 3 is different from embodiment 2 in that the embodiment of the present invention further includes:
the monitoring resource allocation module is used for calculating the monitoring resource demand coefficient of each storage handling device based on the risk coefficient of the storage handling device execution end and the environment supporting resource reliability coefficient, and allocating the monitoring resource for the storage handling device based on the monitoring resource demand coefficient.
Illustratively, by the formulaAnd the supervision resource demand coefficient GX of each warehouse conveying device is represented, wherein xq1 and xq2 represent influence coefficients, xq1 represents an environment support resource influence coefficient, xq2 represents an execution end influence coefficient of the warehouse conveying device, xq1 is more than 0 and less than 1, xq2 is more than 0 and less than 1, and xq1+xq2=1.0.
The advantages are that: according to the real-time data, the supervision resource demand coefficient GX of each warehouse handling device is obtained, and the environment support resource management strategy and supervision resource allocation are dynamically adjusted based on the supervision resource demand coefficient GX so as to adapt to the demands of different situations, and the management flexibility and efficiency are improved.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (9)
1. The utility model provides an intelligent storage handling equipment quality management and control system which characterized in that includes:
The basic equipment analysis module is used for acquiring the quality of data acquisition equipment and the quality of communication equipment in the warehouse and carrying environment, analyzing to obtain a quality stability index Zs of the data acquisition equipment and a communication transmission quality stability index Zt, and transmitting the data acquisition equipment quality stability index Zs and the communication transmission quality stability index Zt to the environment support resource management module; the quality of the data acquisition equipment in each time period is recorded as SJ i, i represents the number of the time period, i is an integer from 1 to n, SJ 0 represents the preset quality of the data acquisition equipment, and the formula is adopted Calculating to obtain a quality stability index Zs of the data acquisition equipment; the quality of the communication equipment in each time period is recorded as SC i, the SC 0 is used for representing the preset quality of the communication equipment, and the formula is adoptedCalculating to obtain a communication transmission quality stability index Zt;
The simulation test analysis module is used for performing simulation test, obtaining the performance of the obstacle recognition model and the path planning model in a simulation environment, analyzing to obtain an obstacle recognition model quality evaluation index Zm and a path planning model quality evaluation index Lm, and transmitting the obstacle recognition model quality evaluation index Zm and the path planning model quality evaluation index Lm to the environment support resource management module; quality analysis model through obstacle recognition model Calculating to obtain a quality evaluation index Zm of the obstacle recognition model, wherein alpha 1、α2 and alpha 3 respectively represent the proportionality coefficients of the various items, alpha 1+α2+α3 =1.0, fs represents the balance score of the obstacle recognition model for recognizing the obstacle, sp represents the deviation degree of the obstacle recognition time, and Zd represents the positioning accuracy of the obstacle; quality analysis model through path planning modelCalculating to obtain a path planning model quality evaluation index Lm, wherein β 1 represents an influence factor of a path length deviation degree, β 2 represents an influence factor of a path planning time deviation degree, β 1+β2 =1.0, lc represents a path length deviation degree of the path planning model, lt represents a normal traffic rate of the path, and Ls represents a path planning time deviation degree;
The environment support resource management module is used for jointly analyzing the quality stability index Zs, the communication transmission quality stability index Zt, the obstacle recognition model quality evaluation index Zm and the path planning model quality evaluation index Lm of the data acquisition equipment to obtain an environment support resource reliability coefficient HZ, and taking corresponding measures based on the environment support resource reliability coefficient; comprising the following steps:
The data acquisition equipment quality stability index, the communication transmission quality stability index, the obstacle recognition model quality evaluation index and the path planning model quality evaluation index form a primary feature set; the data acquisition equipment quality stability index, the communication transmission quality stability index and the obstacle recognition model quality evaluation index are interacted with each other to complete feature fusion, so that a secondary feature set is formed; the intersection of the primary feature set and the secondary feature set forms a comprehensive feature set; screening feature factors related to the reliability of the environment support resources from the comprehensive feature set by using a principal component analysis method, and matching weight coefficients for the feature factors; the value of each characteristic factor is multiplied by the corresponding weight coefficient and then summed to obtain a weighted summation result; and calculating the ratio of the weighted sum result to the weighted coefficient sum to obtain the environment support resource reliability coefficient HZ.
2. The quality control system of intelligent warehouse handling equipment as set forth in claim 1, wherein the balance score of the obstacle recognition model recognition obstacle is obtained by: based on FN, TP, FP, TN for identifying the obstacle, obtaining a balance score Fs of the obstacle identified by the obstacle identification model; the obstacle recognition time deviation Sp is an index for measuring the time accuracy of the obstacle recognition model in recognizing the obstacle, and is the deviation degree between the time required for the obstacle recognition model to recognize the obstacle and the expected recognition time; the obstacle positioning accuracy Zd is an index for describing the position judgment accuracy degree of the obstacle recognition model when recognizing the obstacle, reflects the accuracy of the obstacle recognition model when determining the actual position of the obstacle, and represents the deviation degree between the position coordinates of the obstacle recognition model output recognition and the coordinate deviations of the actual recognition obstacle, and FN represents false negative, namely the situation that the obstacle recognition model erroneously predicts a positive sample as a negative sample; TP represents a real case, i.e., a case where the obstacle recognition model correctly predicts a positive sample as a positive sample; FP represents false positives, i.e. the situation where the obstacle recognition model erroneously predicts a negative sample as a positive sample; TN represents true negative, i.e. the situation that the obstacle recognition model correctly predicts the negative sample as negative sample; the path length deviation Lc is obtained by: when the path planning model outputs planning path information according to the input obstacle and cargo information, calculating a path length deviation Lc based on a difference between the output length of the planning path and a theoretical shortest or optimal path length; the normal pass rate Lt of the path refers to the proportion of successful passing of the warehouse handling equipment according to the planned path information; the path planning time deviation Ls refers to the deviation degree between the time required for the path planning model to output the planned path and the expected planning time.
3. The intelligent warehouse handling equipment quality control system according to claim 1, wherein the balance score xu_fs, the obstacle recognition time deviation xu_sp and the obstacle positioning accuracy xu_zd of the obstacle recognition model are obtained by correcting the balance score, the obstacle recognition time deviation and the obstacle positioning accuracy of the obstacle recognition model by weighting and summing and averaging according to the scene complexity parameter of the obstacle recognition simulation test and matching the corresponding correction coefficient for each obstacle recognition simulation test; replacing Fs, sp and Zd with the corrected balance score xu_Fs, the obstacle recognition time deviation degree xu_Sp and the obstacle positioning accuracy xu_zd; calculating to obtain a quality evaluation index Zm of the obstacle recognition model through the quality analysis model of the obstacle recognition model; and replacing Lc and Ls with the corrected path length deviation xu_lc and the corrected path planning time deviation xu_ls, and calculating by a path planning model quality analysis model to obtain a path planning model quality evaluation index Lm.
4. The intelligent warehouse handling equipment quality control system according to claim 3, wherein s is used for representing the number of the obstacle recognition simulation test, the number is an integer from 1 to q, and the balance score, the obstacle recognition time deviation degree and the obstacle positioning accuracy of the s-th obstacle recognition simulation test are respectively marked as Fs_s, sp_s and zd_s; by the formulaCalculating to obtain a corrected balance score xu_Fs; by the formulaCalculating to obtain corrected obstacle recognition time deviation degree xu_Sp; by the formulaAnd calculating to obtain corrected barrier positioning accuracy xu_zd, wherein yz_s represents a correction coefficient of the s-th barrier identification simulation test.
5. The intelligent warehouse handling equipment quality control system as set forth in claim 4, wherein the correction factor of the s-th obstacle recognition simulation test is obtained by:
By the formula Calculating to obtain scene complexity parameters ZH s of the s-th obstacle recognition simulation test, wherein Lux represents ambient illumination intensity, le represents illumination uniformity, cs represents obstacle area, and ζ represents obstacle type influence factors; the value range of the illumination uniformity is 0 to 1, and the closer the illumination uniformity is to 1, the better the illumination uniformity is;
By the formula And calculating to obtain the correction coefficient of the s-th obstacle recognition simulation test as yz_s.
6. The intelligent warehouse handling equipment quality control system according to claim 5, wherein the path length deviation and the path planning time deviation of the path planning model are corrected by weighting and averaging according to the scene complexity parameter of the path planning simulation test and the correction coefficient corresponding to each path planning simulation test, so as to obtain the corrected path length deviation xu_lc and the corrected path planning time deviation xu_ls.
7. The quality control system of intelligent warehouse handling equipment according to claim 6, wherein t is used for representing the number of the path planning simulation test, the number is an integer from 1 to p, and the path length deviation and the path planning time deviation of the t-th path planning simulation test are respectively recorded as lc_t and ls_t; by the formulaCalculating to obtain a corrected path length deviation degree xu_lc; by the formulaAnd calculating the corrected path planning time deviation degree xu_ls, wherein yl_t represents the correction coefficient of the t-th path planning simulation test.
8. The intelligent warehouse handling equipment quality control system of claim 7, wherein the correction factor for the t-th path planning simulation test is obtained by:
By the formula Calculating to obtain scene complexity parameters LH t of a t-th path planning simulation test, wherein Cm represents the number of obstacles, cs represents the area of the obstacle and FL represents the distribution discrete coefficient of the obstacle;
By the formula And calculating to obtain a correction coefficient of the t-th path planning simulation test as yl_t.
9. The intelligent warehouse management and control system of claim 8, further comprising a warehouse management module, and a supervisory resource allocation module,
The storage handling equipment execution end analysis module acquires the condition of the storage handling equipment execution end, analyzes to obtain a basic operation evaluation index ZJp and an instruction execution stability index ZLw, and jointly analyzes the basic operation evaluation index ZJp and the instruction execution stability index ZLw to obtain a storage handling equipment execution end risk coefficient RZF;
The warehouse carrying execution end management module is used for taking corresponding measures based on the risk coefficient RZF of the warehouse carrying equipment execution end and screening abnormal warehouse carrying equipment execution ends;
the monitoring resource allocation module is used for calculating the monitoring resource demand coefficient of each storage handling device based on the risk coefficient of the storage handling device execution end and the environment supporting resource reliability coefficient, and allocating the monitoring resource for the storage handling device based on the monitoring resource demand coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411038070.6A CN118568999B (en) | 2024-07-31 | 2024-07-31 | Intelligent storage handling equipment quality control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411038070.6A CN118568999B (en) | 2024-07-31 | 2024-07-31 | Intelligent storage handling equipment quality control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118568999A CN118568999A (en) | 2024-08-30 |
| CN118568999B true CN118568999B (en) | 2024-09-27 |
Family
ID=92478526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411038070.6A Active CN118568999B (en) | 2024-07-31 | 2024-07-31 | Intelligent storage handling equipment quality control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118568999B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119204899B (en) * | 2024-11-28 | 2025-03-11 | 济宁市海富电子科技有限公司 | Material warehouse center transportation path planning system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116257086A (en) * | 2023-02-24 | 2023-06-13 | 中国人民解放军总参谋部第六十研究所 | An Unmanned Helicopter Perception and Obstacle Avoidance Simulation System |
| CN117232517A (en) * | 2023-09-01 | 2023-12-15 | 华北电力大学（保定） | Multi-mobile industrial robot path planning method for storage scene in power industry |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020021126A1 (en) * | 2018-07-27 | 2020-01-30 | Embotech Ag | Method for steering a vehicle and apparatus therefor |
-
2024
- 2024-07-31 CN CN202411038070.6A patent/CN118568999B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116257086A (en) * | 2023-02-24 | 2023-06-13 | 中国人民解放军总参谋部第六十研究所 | An Unmanned Helicopter Perception and Obstacle Avoidance Simulation System |
| CN117232517A (en) * | 2023-09-01 | 2023-12-15 | 华北电力大学（保定） | Multi-mobile industrial robot path planning method for storage scene in power industry |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118568999A (en) | 2024-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118568999B (en) | Intelligent storage handling equipment quality control system | |
| CN112579464A (en) | Verification method, device and equipment of automatic driving algorithm and storage medium | |
| CN114578839B (en) | Unmanned aerial vehicle path calculation system and method based on big data | |
| CN116759355B (en) | Wafer transmission control method and system | |
| CN117935453B (en) | Port machine remote control method and system based on binocular camera | |
| CN107175659B (en) | Robot obstacle avoidance method and device | |
| CN110443399B (en) | Intelligent scheduling method for aviation rescue of vehicle accident | |
| CN118350593A (en) | Intelligent construction method, system, equipment and medium for modular integrated building | |
| CN117688838A (en) | UAV autonomy assessment methods, systems and electronic equipment based on knowledge graph | |
| RU2503985C2 (en) | Method for two-level control of equipment and system for realising said method | |
| CN115762025A (en) | Intelligent early warning method and system for communication optical cable | |
| CN118605538B (en) | Multi-source-based target data collaborative processing method and system | |
| CN109977884B (en) | Target following method and device | |
| CN118428631A (en) | Cooperative control method and system for disaster sensing and emergency rescue | |
| CN116307534B (en) | Engineering measurement data processing method based on cloud computing | |
| CN114661057A (en) | Intelligent bionic biped inspection robot | |
| CN114993315A (en) | A route planning method for unmanned underwater vehicle in complex environment for military application | |
| CN114415726A (en) | Unmanned aerial vehicle obstacle avoidance control system and method based on image analysis | |
| CN117389937B (en) | Calculation method of obstacle avoidance data of vehicle, computer and readable storage medium | |
| CN118347506B (en) | Intelligent underground danger avoiding method and system based on AI technology | |
| CN119132115B (en) | Traffic control system based on drone operation safety | |
| RU2486564C1 (en) | Method of double-level adaptive control and system of control for its realisation | |
| CN119519156B (en) | Intelligent power plant joint inspection system and method based on video AI and robot | |
| CN117921680B (en) | Mechanical arm path planning method and system | |
| CN118870324A (en) | A UAV swarm security authentication method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |