A system and method for identifying cargo status in cargo space based on laser radar

By using IoT devices using lidar and RFID sensors in small flexible warehousing, combined with ant colony algorithm and k-means clustering algorithm, efficient and accurate monitoring of the cargo status of the cargo space is achieved, and the cargo space in the existing technology is solved The problem of difficult-to-manage state exceptions improves management efficiency and accuracy.

CN118365250BActive Publication Date: 2024-11-12WAYZIM TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410788629.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-19
Publication Date
2024-11-12
Estimated Expiration
2044-06-19

AI Technical Summary

Technical Problem

In the management of small flexible warehousing, it is difficult to effectively monitor and manage abnormal cargo space status, and there are uncontrollable factors that lead to efficiency and cost limitations.

Method used

The IoT devices based on lidar and RFID sensors are used for real-time monitoring, and the storage area is divided and goods are allocated through ant colony algorithm and k-means clustering algorithm, and the location fingerprint positioning is used to improve the recognition efficiency and accuracy of cargo status of cargo space sex.

Benefits of technology

It improves the efficiency and accuracy of the identification of goods status in the cargo space, reduces the occurrence of abnormalities caused by human factors, and reduces operating costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118365250B_ABST
    Figure CN118365250B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of cargo management, and discloses a system and method for identifying the status of cargo in cargo spaces based on laser radar. The method installs an Internet of Things device in a storage area that needs to be identified and performs real-time monitoring, and at the same time abstractly defines the storage area that needs to be identified, the shelves in the storage area, and each cargo space in the shelves, and divides the storage area based on the abstract definition of the storage area that needs to be identified, the shelves in the storage area, and each cargo space in the shelves, as well as the types of items in the storage area, and at the same time, distributes each cargo after entering the warehouse through an ant colony algorithm, distributes the cargo after entering the warehouse to the corresponding cargo space, and accurately locates each cargo space through position fingerprint positioning for the cargo after entering the warehouse, and inquires about the status of the cargo at the corresponding location, thereby improving the efficiency and accuracy of identifying the status of the cargo space.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of cargo management, and in particular to a system and method for identifying the status of cargo in a cargo space based on laser radar. Background Art

[0002] Large-scale logistics warehouse cargo spaces are mainly managed by the WCS system. However, for small-scale flexible warehouses, the system's warehouse management software is not applicable. If you only rely on existing programs for simple cargo space management, it is not safe and reliable to record the cargo space status through task logic, and it cannot rule out the possibility that uncontrollable factors caused by human factors may cause the cargo space status to be abnormal. Therefore, a real-time cargo space detection function is added on the basis of the handling system to avoid such abnormalities.

[0003] The existing Chinese patent application CN113673923A users send a login request to the business platform by scanning the code; the business platform establishes a task list and the user fills in the cargo information; the user changes the cargo transportation information on the business platform, and the transportation information includes "in transit" and "in warehouse"; when the transportation information is "in transit", the business platform issues an acquisition instruction; the acquisition terminal obtains the status data and GPS positioning of the cargo; the processing terminal extracts the status data obtained by the acquisition terminal, and calculates the status data according to the preset calculation model to obtain the status value; the status value is compared and analyzed with the preset status threshold to obtain the status information of the cargo; the status information is stored to form an information report; the transmission terminal sends the information report and GPS positioning to the business platform for the user to view. This application has the function of enabling people to know the status of the cargo and the cause of damage in real time, but it still needs to be continuously optimized in terms of efficiency and cost and has certain limitations. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a system and method for identifying the status of cargo in a cargo space based on laser radar, which has the advantages of high efficiency and high accuracy, and solves the problem of abnormal cargo space status caused by uncontrollable factors.

[0005] In order to solve the technical problem that the above uncontrollable factors cause the cargo space status to be abnormal, the present invention provides the following technical solutions:

[0006] The present invention discloses a method for identifying the status of cargo in a cargo space based on laser radar, which specifically comprises the following steps:

[0007] S1. Install IoT devices in the storage areas that need to be identified, and use the installed IoT devices to monitor the storage areas that need to be identified in real time;

[0008] The installed IoT devices include: LiDAR and RFID sensors;

[0009] S2. Abstractly define the storage area to be identified, the shelves in the storage area, and each cargo position in the shelves. Specifically, perform spatial planning on the coordinate positions of the shelves and each cargo position in the shelves.

[0010] S3, based on the abstract definition of the storage area to be identified, the shelves in the storage area, each cargo position in the shelves, and the types of items in the storage area, the storage area is divided to obtain the divided storage area;

[0011] S4. Based on the divided storage areas, each incoming cargo is allocated to the corresponding cargo location using the ant colony algorithm;

[0012] S5. For the goods after storage, each cargo position is accurately located by location fingerprint positioning, and the status of the goods at the corresponding location is queried.

[0013] The present invention installs Internet of Things devices in storage areas that need to be identified and conducts real-time monitoring, and at the same time abstractly defines the storage areas that need to be identified, the shelves in the storage areas, and each cargo position in the shelves, and divides the storage areas based on the abstract definitions of the storage areas that need to be identified, the shelves in the storage areas, and each cargo position in the shelves and the types of items in the storage areas. At the same time, each warehoused cargo is allocated through an ant colony algorithm, and the warehoused cargo is allocated to the corresponding cargo position. For the warehoused cargo, each cargo position is accurately located by position fingerprint positioning, and the status of the corresponding located cargo is queried, thereby improving the efficiency and accuracy of identifying the status of cargo in the cargo position.

[0014] Preferably, the abstract definition of the storage area to be identified, the shelves in the storage area, and each cargo location in the shelves comprises the following steps:

[0015] A number with a unique identifier is set based on the storage area location. The number is associated with the storage area location, and the location of the storage area to be identified is uniquely determined according to the set number;

[0016] Set the two-dimensional coordinates of the central reference shelf in the storage area to be identified as (X0, Y0), the three-dimensional coordinates of the central reference cargo position on the central reference shelf as (X0, Y0, Z0), set the length direction of the shelf, i.e. the left and right direction, as the X direction, the width direction of the shelf, i.e. the front and back direction, as the Y direction, and the height direction of the shelf as the Z direction; and set the front and back spacing of the shelf to L1, the left and right spacing to L2, the shelf length to W1, the shelf width to W2, the height interval of each shelf layer to H1, set multiple rows of cargo positions on each layer of the shelf, and the row distance between the cargo positions is D1;

[0017] Then the two-dimensional coordinates of the shelves around the reference shelf can be set as:

[0018] The coordinates of the shelf in front of the reference shelf (X0, Y0+W2+L1), the coordinates of the shelf behind the reference shelf (X0, Y0-W2-L1);

[0019] The coordinates of the shelf to the right of the reference shelf (X0+W1+L2,Y0), the coordinates of the shelf to the left of the reference shelf (X0-W1-L2,Y0);

[0020] And so on, plan the coordinates of all shelves;

[0021] Similarly, the three-dimensional coordinates of the storage locations around the center reference storage location of the reference shelf can be set as:

[0022] The coordinates of the cargo position to the right of the reference cargo position on the same shelf (X0+D1, Y0, Z0), and the coordinates of the cargo position to the left of the reference cargo position (X0-D1, Y0, Z0);

[0023] The coordinates of the upper cargo position corresponding to the reference cargo position on the same shelf (X0, Y0, Z0+H1), and the coordinates of the lower cargo position corresponding to the reference cargo position (X0, Y0, Z0-H1);

[0024] And so on, plan the coordinates of all cargo locations on all shelves.

[0025] The present invention completes the abstract definition of shelves and cargo spaces in a storage area by setting a unique identification number for the storage area location and limiting the distance within the storage area to be identified, thereby improving the efficiency of identifying the status of cargo in the storage area.

[0026] Preferably, the division of the storage area based on the abstract definition of the storage area to be identified, the shelves in the storage area, each cargo space in the shelves, and the types of items in the storage area comprises the following steps:

[0027] S31. Classify the goods to be stored by using k-means clustering algorithm;

[0028] S32. Calculate the proportion of goods that need to be stored in each category, and divide the storage area based on the calculated proportion of goods that need to be stored in each category.

[0029] Preferably, the classifying of the goods to be stored by using the k-means clustering algorithm comprises the following steps:

[0030] S311, multiple goods to be stored are classified as a category data set according to their category attributes, and one of the goods to be stored is regarded as a category data point, and k of the goods to be stored are selected as k initial clustering centers. The selected initial clustering centers have centralized typicality, and each clustering center is set as a category of goods;

[0031] S312, calculating the distance between each initial cluster center and each data point, and assigning the data point to the cargo category represented by the cluster center closest to the data point based on the calculated distance between each initial cluster center and each data point;

[0032] The distance between each initial cluster center and each data point The calculation formula is as follows:

[0033]

[0034] in, represents the similarity distance between the initial cluster center i and the data point j, represents the horizontal coordinate of the initial cluster center i, represents the ordinate of the initial cluster center i, represents the horizontal coordinate of data point j, Represents the ordinate of data point j;

[0035] S313, when all data points are assigned, the mean of all data in the cargo category is calculated, and the calculated mean is used as a new cluster center;

[0036] S314, reallocating based on the calculated new cluster centers;

[0037] S315. Repeat steps S312-S314 until the cluster center of the cargo category no longer changes, then stop clustering and output the clustering results, which include cargo category, the quantity of cargo in each cargo category, and the cluster center.

[0038] Preferably, the calculating the proportion of goods to be stored in each category and dividing the storage area based on the calculated proportion of goods to be stored in each category comprises the following steps:

[0039] The calculation formula for the proportion of goods that need to be stored in each category is as follows:

[0040]

[0041] in, Representation classification The proportion of goods Representation classification The quantity of goods, Indicates the total quantity of goods;

[0042] Based on the calculated proportion of goods in each category, the storage area is allocated an area corresponding to each category.

[0043] The present invention classifies the goods to be stored by using the k-means clustering algorithm, and calculates the distance between the initial cluster center and each data point through continuous iteration. The classification of various types of goods is completed in a way. At the same time, by calculating the proportion of each type of goods, the area corresponding to the proportion of each category is allocated in the storage area, which improves the efficiency of identifying the status of goods in the cargo space.

[0044] Preferably, the method of allocating each warehoused cargo by using an ant colony algorithm based on the divided storage areas includes the following steps:

[0045] S41. Based on the shelves in the divided storage area, define a weighted graph with M nodes ,in Represents a collection of storage location nodes in a storage area =1,2,3,...,n; Represents the path between the storage location nodes in the storage area, and sets the distance between the storage location node e in the storage area and the storage location node f in the storage area to ;

[0046] S42, calculating the shortest path based on ant colony algorithm;

[0047] S43. Based on the shortest path calculated by the ant colony algorithm, each cargo that needs to be stored in the warehouse is allocated to the corresponding cargo location node, and the stored cargo type and the allocated cargo location coordinates are combined into an array and stored in the database.

[0048] Preferably, the shortest path calculation based on the ant colony algorithm comprises the following steps:

[0049] Set the number of ants in the ant colony to h, and set the pheromone concentration on the connection path between the cargo node e in the storage area and the cargo node f in the storage area at time t to ;

[0050] At the initial moment, the pheromone concentration on the connection path between the cargo nodes in each storage area is the same. , is the pheromone concentration on the connection path between the cargo location nodes in each storage area at the initial moment;

[0051] Ant , the next city to visit is determined according to the pheromone concentration on the connection path between the cargo nodes in each storage area. represents the ant at time t From the probability of the cargo location node e in the storage area and the cargo location node f in the storage area, the transfer probability formula is as follows:

[0052]

[0053] in, is the heuristic function, , represents the ant's expectation degree from the cargo location node e in the storage area to the cargo location node f in the storage area, It represents the distance between the storage location node e and the storage location node f in the storage area. is the heuristic function, , represents the ant's expectation degree from the cargo location node e in the storage area to the cargo location node s in the storage area, It represents the distance between the storage location node e and the storage location node s in the storage area. Represents ants The collection of storage location nodes in the storage area to be accessed, is the pheromone importance factor, is the importance factor of the heuristic function, represents the pheromone concentration between the cargo location node e in the storage area and the cargo location node s in the storage area at time t;

[0054] Based on the transition probability formula, the solution space is constructed and each ant is randomly placed in the cargo location nodes in different storage areas. , based on the transition probability formula, calculate the next storage location node to be visited in the storage area until all ants have visited all storage location nodes in the storage area, and at the same time calculate the path length D of each ant;

[0055] Set the number of iterations of the algorithm and update the pheromone concentration on the connection path between the cargo nodes in each storage area;

[0056] After reaching the set number of iterations, the calculation is terminated and the shortest path connecting the storage location nodes in each storage area is output.

[0057] The present invention uses an ant colony algorithm to find the shortest path connecting the cargo location nodes in each storage area, and saves the goods of different categories after entering the warehouse based on the calculated shortest path, thereby improving the efficiency of identifying the cargo location and storing the goods.

[0058] Preferably, the method of accurately locating each cargo position of the goods after storage by means of location fingerprint positioning and querying the status of the goods located correspondingly comprises the following steps:

[0059] S51, establishing a location fingerprint through offline sampling;

[0060] An RFID sensor is installed in each cargo location in all cargo location nodes. When there are goods in the cargo location, the RFID sensor of the cargo location is activated;

[0061] Randomly select r cargo location as a reference point among all cargo location nodes, collect the receivable RFID sensor signal at each reference point through the laser radar, and determine the collection range of the laser radar based on the collected receivable RFID sensor signal;

[0062] After receiving the RFID sensor signal, the laser radar stores a set of triplet data including the location coordinates of the cargo location, the RFID sensor signal, and the device number of the RFID sensor signal into a database;

[0063] A set of triplet data is set as a location fingerprint;

[0064] S52, establishing a location fingerprint through online real-time sampling based on the determined collection range of the laser radar;

[0065] Install a laser radar in each partition of the storage area that needs to be identified. The installed laser radar collects the status of each activated RFID sensor in the current partition in real time, and creates a location fingerprint online and saves it to the database;

[0066] When goods enter or leave the warehouse, the LiDAR will update the location fingerprint in the database in real time;

[0067] S53, by inputting the location coordinates of the cargo space allocated by the ant colony algorithm for each cargo after entering the warehouse in step S4, and querying the status of the corresponding cargo type based on the allocated cargo space location coordinates to determine whether it is in the warehouse;

[0068] The laser radar will match the location fingerprint of the assigned cargo location in the database. If the match is successful, it means that the cargo type is in the warehouse. If the match fails, it means that the cargo type is not in the warehouse.

[0069] The present invention establishes a location fingerprint based on the way that the laser radar collects RFID sensor signals through offline sampling, and determines the collection range of the laser radar. At the same time, based on the determined collection range of the laser radar, online real-time sampling is performed to establish the location fingerprint. By inputting the cargo type, the location coordinates of the cargo position assigned to the corresponding cargo type are queried, and the status of the corresponding cargo type is queried based on the assigned cargo position coordinates, and the status of the cargo in the cargo position is judged, thereby improving the accuracy of identifying the status of the cargo in the cargo position.

[0070] The present invention discloses a system for identifying the status of cargo in cargo spaces based on laser radar, comprising: a laser radar, an RFID sensor, a database, a storage area division module and a cargo warehousing module;

[0071] The laser radar is used to collect RFID sensor signals in the monitoring area in real time and distinguish the RFID sensor signals based on signal strength;

[0072] The RFID sensor is used to send RFID sensor signals in real time;

[0073] The database is used to store the location fingerprint data collected and constructed by the laser radar;

[0074] The storage area division module is used to divide the storage area based on the type and quantity of goods;

[0075] The cargo warehousing module is used to calculate the shortest path to distribute the cargo to the corresponding cargo location.

[0076] Compared with the prior art, the present invention provides a system and method for identifying the status of cargo in cargo space based on laser radar, which has the following beneficial effects:

[0077] 1. The invention installs IoT devices in storage areas that need to be identified and conducts real-time monitoring, while abstractly defining the storage areas that need to be identified, the shelves in the storage areas, and each cargo position in the shelves, and divides the storage areas based on the abstract definitions of the storage areas that need to be identified, the shelves in the storage areas, and each cargo position in the shelves, as well as the types of items in the storage areas. At the same time, each warehoused cargo is allocated through an ant colony algorithm, and the warehoused cargo is allocated to the corresponding cargo position. For the warehoused cargo, each cargo position is accurately located through position fingerprint positioning, and the status of the corresponding located cargo is queried, thereby improving the efficiency and accuracy of identifying the status of cargo in the cargo position.

[0078] 2. The invention completes the abstract definition of the shelves in the storage area by setting a unique identification number for the storage area location and limiting the distance within the storage area to be identified, thereby improving the efficiency of identifying the status of goods in the storage area.

[0079] 3. The invention classifies the goods to be stored by using the k-means clustering algorithm, and calculates the distance between the initial cluster center and each data point through continuous iteration. The classification of various types of goods is completed in a way. At the same time, by calculating the proportion of each type of goods, the area corresponding to the proportion of each category is allocated in the storage area, which improves the efficiency of identifying the status of goods in the cargo space.

[0080] 4. The invention uses an ant colony algorithm to find the shortest path connecting the cargo location nodes in each storage area, and saves the goods of different categories after entering the warehouse based on the calculated shortest path, thereby improving the efficiency of identifying cargo location storage.

[0081] 5. The invention establishes a location fingerprint by offline sampling based on the laser radar collecting RFID sensor signals and determines the collection range of the laser radar. At the same time, the location fingerprint is established based on the online real-time sampling determined based on the collection range of the laser radar. By inputting the cargo location coordinates assigned by the ant colony algorithm and querying the status of the corresponding cargo type based on the assigned cargo location coordinates, the status of the cargo in the cargo location is judged, thereby improving the accuracy of identifying the status of the cargo in the cargo location. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 The figure is a schematic diagram of the structure of the process of the method for identifying the status of cargo in cargo space based on laser radar of the present invention. DETAILED DESCRIPTION

[0083] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0084] The present invention discloses a method for identifying the status of cargo in a cargo space based on laser radar, which specifically comprises the following steps:

[0085] S1. Install IoT devices in the storage areas that need to be identified, and use the installed IoT devices to monitor the storage areas that need to be identified in real time;

[0086] The installed IoT devices include: LiDAR and RFID sensors;

[0087] S2. Abstractly define the storage area to be identified, the shelves in the storage area, and each cargo position in the shelves. Specifically, perform spatial planning on the coordinate positions of the shelves and each cargo position in the shelves.

[0088] The abstract definition of the storage area to be identified, the shelves in the storage area, and each shelf in the shelf includes the following steps:

[0089] A number with a unique identifier is set based on the storage area location. The number is associated with the storage area location, and the location of the storage area to be identified is uniquely determined according to the set number;

[0090] Set the two-dimensional coordinates of the central reference shelf in the storage area to be identified as (X0, Y0), the three-dimensional coordinates of the central reference cargo position on the central reference shelf as (X0, Y0, Z0), set the length direction of the shelf, i.e. the left and right direction, as the X direction, the width direction of the shelf, i.e. the front and back direction, as the Y direction, and the height direction of the shelf as the Z direction; and set the front and back spacing of the shelf to L1, the left and right spacing to L2, the shelf length to W1, the shelf width to W2, the height interval of each shelf layer to H1, set multiple rows of cargo positions on each layer of the shelf, and the row distance between the cargo positions is D1;

[0091] Then the two-dimensional coordinates of the shelves around the reference shelf can be set as:

[0092] The coordinates of the shelf in front of the reference shelf (X0, Y0+W2+L1), the coordinates of the shelf behind the reference shelf (X0, Y0-W2-L1);

[0093] The coordinates of the shelf to the right of the reference shelf (X0+W1+L2,Y0), the coordinates of the shelf to the left of the reference shelf (X0-W1-L2,Y0);

[0094] And so on, plan the coordinates of all shelves;

[0095] Similarly, the three-dimensional coordinates of the storage locations around the center reference storage location of the reference shelf can be set as:

[0096] The coordinates of the cargo position to the right of the reference cargo position on the same shelf (X0+D1, Y0, Z0), and the coordinates of the cargo position to the left of the reference cargo position (X0-D1, Y0, Z0);

[0097] The coordinates of the upper cargo position corresponding to the reference cargo position on the same shelf (X0, Y0, Z0+H1), and the coordinates of the lower cargo position corresponding to the reference cargo position (X0, Y0, Z0-H1);

[0098] And so on, plan the coordinates of all cargo locations on all shelves;

[0099] S3, based on the abstract definition of the storage area to be identified, the shelves in the storage area, each cargo position in the shelves, and the types of items in the storage area, the storage area is divided to obtain the divided storage area;

[0100] Based on the abstract definition of the storage area to be identified, the shelves in the storage area, each cargo location in the shelves, and the types of items in the storage area, the division of the storage area includes the following steps:

[0101] S31. Classify the goods to be stored by using k-means clustering algorithm;

[0102] S311. Multiple goods to be stored are taken as a category data set according to their category attributes, and one good to be stored is taken as a category data point. K representative goods to be stored are selected as k initial clustering centers. The selected initial clustering centers have centralized typicality (central typicality is equivalent to representativeness, representing the main clustering categories of multiple goods, such as representing categories of goods with a proportion of more than 5% or even more than 15%). Each clustering center is set as a category of goods. The setting of the category data set can refer to the warehouse item classification manual in the prior art.

[0103] S312, calculating the distance between each initial cluster center and each data point, and assigning the data point to the cargo category represented by the cluster center closest to the data point based on the calculated distance between each initial cluster center and each data point;

[0104] The distance between each initial cluster center and each data point The calculation formula is as follows:

[0105]

[0106] in, represents the similarity distance between the initial cluster center i and the data point j, represents the horizontal coordinate of the initial cluster center i, represents the ordinate of the initial cluster center i, represents the horizontal coordinate of data point j, Represents the ordinate of data point j;

[0107] S313, when all data points are assigned, the mean of all data in the cargo category is calculated, and the calculated mean is used as a new cluster center;

[0108] S314, reallocating based on the calculated new cluster centers;

[0109] S315, repeating steps S312-S314 until the cluster center of the cargo category no longer changes, the clustering stops, and the clustering results are output, the clustering results including: cargo category, the quantity of cargo in each cargo category, and the cluster center;

[0110] S32, calculating the proportion of goods that need to be stored in each category, and dividing the storage area based on the calculated proportion of goods that need to be stored in each category;

[0111] The calculation formula for the proportion of goods that need to be stored in each category is as follows:

[0112]

[0113] in, Representation classification The proportion of goods Representation classification The quantity of goods, Indicates the total quantity of goods;

[0114] Furthermore, based on the calculated proportion of goods in each category, an area corresponding to the proportion of each category is allocated in the storage area;

[0115] S4. Based on the divided storage areas, each incoming cargo is allocated to the corresponding cargo location using the ant colony algorithm;

[0116] Based on the divided storage areas, the ant colony algorithm is used to allocate each incoming cargo, including the following steps:

[0117] S41. Based on the shelves in the divided storage area, define a weighted graph with M nodes ,in Represents a collection of storage location nodes in a storage area =1,2,3,...,n; Represents the path between the storage location nodes in the storage area, and sets the distance between the storage location node e in the storage area and the storage location node f in the storage area to ;

[0118] S42, calculating the shortest path based on ant colony algorithm;

[0119] Set the number of ants in the ant colony to h, and set the pheromone concentration on the connection path between the cargo node e in the storage area and the cargo node f in the storage area at time t to ;

[0120] It is assumed that the pheromone concentration on the connection path between the cargo location nodes in each storage area is the same at the initial moment. , is the pheromone concentration on the connection path between the cargo location nodes in each storage area at the initial moment;

[0121] Ant , the next city to visit is determined according to the pheromone concentration on the connection path between the cargo nodes in each storage area. represents the ant at time t From the probability of the cargo location node e in the storage area and the cargo location node f in the storage area, the transfer probability formula is as follows:

[0122]

[0123] in, is the heuristic function, , represents the ant's expectation degree from the cargo location node e in the storage area to the cargo location node f in the storage area, It represents the distance between the storage location node e and the storage location node f in the storage area. is the heuristic function, , represents the ant's expectation degree from the cargo location node e in the storage area to the cargo location node s in the storage area, It represents the distance between the storage location node e and the storage location node s in the storage area. Represents ants The collection of storage location nodes in the storage area to be accessed, is the pheromone importance factor, is the importance factor of the heuristic function, represents the pheromone concentration between the cargo location node e in the storage area and the cargo location node s in the storage area at time t;

[0124] Based on the transition probability formula, the solution space is constructed and each ant is randomly placed in the cargo location nodes in different storage areas. , based on the transition probability formula, calculate the next storage location node to be visited in the storage area until all ants have visited all storage location nodes in the storage area, and at the same time calculate the path length D of each ant;

[0125] Set the number of iterations of the algorithm and update the pheromone concentration on the connection path between the cargo nodes in each storage area;

[0126] After reaching the set number of iterations, the calculation is terminated and the shortest path connecting the cargo location nodes in each storage area is output;

[0127] S43, based on the shortest path calculated by the ant colony algorithm, each cargo that needs to be stored in the warehouse is allocated to the corresponding cargo location node, and the type of stored cargo and the coordinates of the allocated cargo location are combined into an array and stored in the database;

[0128] S5. For the goods after storage, each cargo position is accurately located by location fingerprint positioning, and the status of the goods at the corresponding location is queried;

[0129] For the goods after storage, each cargo position is accurately located by location fingerprint positioning, and the status of the goods at the corresponding location is queried, including the following steps:

[0130] S51, establishing a location fingerprint through offline sampling;

[0131] An RFID sensor is installed in each cargo location in all cargo location nodes. When there are goods in the cargo location, the RFID sensor of the cargo location is activated;

[0132] Randomly select r cargo location as a reference point among all cargo location nodes, collect the receivable RFID sensor signal at each reference point through the laser radar, and determine the collection range of the laser radar based on the collected receivable RFID sensor signal;

[0133] Furthermore, after receiving the RFID sensor signal, the laser radar stores a set of triplet data including the location coordinates of the cargo location, the RFID sensor signal, and the device number of the RFID sensor signal into a database;

[0134] A set of triplet data is set as a location fingerprint;

[0135] S52, establishing a location fingerprint through online real-time sampling based on the determined collection range of the laser radar;

[0136] Install a laser radar in each partition of the storage area that needs to be identified. The installed laser radar collects the status of each activated RFID sensor in the current partition in real time, and creates a location fingerprint online and saves it to the database;

[0137] When goods enter or leave the warehouse, the LiDAR will update the location fingerprint in the database in real time;

[0138] S53, by inputting the location coordinates of the cargo space allocated by the ant colony algorithm for each cargo after entering the warehouse in step S4, and querying the status of the corresponding cargo type based on the allocated cargo space location coordinates to determine whether it is in the warehouse;

[0139] The laser radar will match the assigned cargo location with the location fingerprint in the database. If the match is successful, it means that the cargo type is in the warehouse. If the match fails, it means that the cargo type is not in the warehouse.

[0140] The present invention discloses a system for identifying the status of cargo in cargo spaces based on laser radar, comprising: a laser radar, an RFID sensor, a database, a storage area division module and a cargo warehousing module;

[0141] The laser radar is used to collect RFID sensor signals in the monitoring area in real time and distinguish the RFID sensor signals based on signal strength;

[0142] The RFID sensor is used to send RFID sensor signals in real time;

[0143] The database is used to store the location fingerprint data collected and constructed by the laser radar;

[0144] The storage area division module is used to divide the storage area based on the type and quantity of goods;

[0145] The cargo warehousing module is used to calculate the shortest path to distribute the cargo to the corresponding cargo location.

[0146] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for identifying cargo status of cargo space based on laser radar, characterized in that: The following steps are involved: S1. Install IoT devices in the storage areas that need to be identified, and use the installed IoT devices to monitor the storage areas that need to be identified in real time; The installed IoT devices include: LiDAR and RFID sensors; S2. Abstractly define the storage area to be identified, the shelves in the storage area, and each cargo position in the shelves. Specifically, perform spatial planning on the coordinate positions of the shelves and each cargo position in the shelves. The abstract definition of the storage area to be identified, the shelves in the storage area, and each cargo location in the shelves includes the following steps: A number with a unique identifier is set based on the storage area location. The number is associated with the storage area location, and the location of the storage area to be identified is uniquely determined according to the set number; Set the two-dimensional coordinates of the central reference shelf in the storage area to be identified as (X0, Y0), the three-dimensional coordinates of the central reference cargo position on the central reference shelf as (X0, Y0, Z0), set the length direction of the shelf, i.e. the left and right direction, as the X direction, the width direction of the shelf, i.e. the front and back direction, as the Y direction, and the height direction of the shelf as the Z direction; and set the front and back spacing of the shelf to L1, the left and right spacing to L2, the shelf length to W1, the shelf width to W2, the height interval of each shelf layer to H1, set multiple rows of cargo positions on each layer of the shelf, and the row distance between the cargo positions is D1; Then the two-dimensional coordinates of the shelves around the reference shelf can be set as: The coordinates of the shelf in front of the reference shelf (X0, Y0+W2+L1), the coordinates of the shelf behind the reference shelf (X0, Y0-W2-L1); The coordinates of the shelf to the right of the reference shelf (X0+W1+L2,Y0), the coordinates of the shelf to the left of the reference shelf (X0-W1-L2,Y0); And so on, plan the coordinates of all shelves; Similarly, the three-dimensional coordinates of the storage locations around the center reference storage location of the reference shelf can be set as: The coordinates of the right side of the reference location on the same shelf (X0+D1,Y0,Z0), and the coordinates of the left side of the reference location (X0-D1,Y0,Z0); The coordinates of the upper level location corresponding to the reference location on the same shelf (X0, Y0, Z0+H1), and the coordinates of the lower level location corresponding to the reference location (X0, Y0, Z0-H1); And so on, plan the coordinates of all cargo locations on all shelves; S3, based on the abstract definition of the storage area to be identified, the shelves in the storage area, each cargo position in the shelves, and the types of items in the storage area, the storage area is divided to obtain the divided storage area; S4. Based on the divided storage areas, each incoming cargo is allocated to the corresponding cargo location using the ant colony algorithm; S5. For the goods after storage, each cargo position is accurately located by location fingerprint positioning, and the status of the goods at the corresponding location is queried; The method of accurately locating each cargo position of the goods after storage by means of location fingerprint positioning and querying the status of the goods located correspondingly includes the following steps: S51, establishing a location fingerprint through offline sampling; An RFID sensor is installed in each cargo location in all cargo location nodes. When there are goods in the cargo location, the RFID sensor of the cargo location is activated; Randomly select r cargo location as a reference point among all cargo location nodes, collect the receivable RFID sensor signal at each reference point through the laser radar, and determine the collection range of the laser radar based on the collected receivable RFID sensor signal; After receiving the RFID sensor signal, the laser radar stores a set of triplet data including the location coordinates of the cargo location, the RFID sensor signal, and the device number of the RFID sensor signal into a database; A set of triplet data is set as a location fingerprint; S52, establishing a location fingerprint through online real-time sampling based on the determined collection range of the laser radar; Install a laser radar in each partition of the storage area that needs to be identified. The installed laser radar collects the status of each activated RFID sensor in the current partition in real time, and creates a location fingerprint online and saves it to the database; When goods enter or leave the warehouse, the LiDAR will update the location fingerprint in the database in real time; S53, by inputting the location coordinates of the cargo space allocated by the ant colony algorithm for each cargo after entering the warehouse in step S4, and querying the status of the corresponding cargo type based on the allocated cargo space location coordinates to determine whether it is in the warehouse; The laser radar will match the location fingerprint of the assigned cargo location in the database. If the match is successful, it means that the cargo type is in the warehouse. If the match fails, it means that the cargo type is not in the warehouse.

2. The method for identifying cargo status in cargo space based on laser radar according to claim 1, characterized in that: The division of the storage area based on the abstract definition of the storage area to be identified, the shelves in the storage area, each cargo position in the shelves, and the types of items in the storage area includes the following steps: S31. Classify the goods to be stored by using k-means clustering algorithm; S32. Calculate the proportion of goods that need to be stored in each category, and divide the storage area based on the calculated proportion of goods that need to be stored in each category.

3. The method for identifying cargo status in cargo space based on laser radar according to claim 2, characterized in that: The classification of the goods to be stored by the k-means clustering algorithm includes the following steps: S311, multiple goods to be stored are grouped as a category data set according to their category attributes, one item to be stored is grouped as a category data point, k representative items to be stored are selected as k initial clustering centers, and each clustering center is set as a category of goods; S312, calculating the distance between each initial cluster center and each data point, and assigning the data point to the cargo category represented by the cluster center closest to the data point based on the calculated distance between each initial cluster center and each data point; The distance between each initial cluster center and each data point The calculation formula is as follows: in, represents the similarity distance between the initial cluster center i and the data point j, represents the horizontal coordinate of the initial cluster center i, represents the ordinate of the initial cluster center i, represents the horizontal coordinate of data point j, Represents the ordinate of data point j; S313, when all data points are assigned, the mean of all data in the cargo category is calculated, and the calculated mean is used as a new cluster center; S314, reallocating based on the calculated new cluster centers; S315. Repeat steps S312-S314 until the cluster center of the cargo category no longer changes, then stop clustering and output the clustering results, which include: cargo category, the quantity of cargo in each cargo category, and the cluster center.

4. The method for identifying cargo status in cargo space based on laser radar according to claim 2, characterized in that: The calculating the proportion of goods to be stored in each category and dividing the storage area based on the calculated proportion of goods to be stored in each category includes the following steps: The calculation formula for the proportion of goods that need to be stored in each category is as follows: in, Representation classification The proportion of goods Representation classification The quantity of goods, Indicates the total quantity of goods; Based on the calculated proportion of goods in each category, the storage area is allocated an area corresponding to each category.

5. The method for identifying cargo status in cargo space based on laser radar according to claim 1, characterized in that: The method of allocating each warehoused cargo by using an ant colony algorithm based on the divided storage area includes the following steps: S41. Based on the shelves and cargo locations in the divided storage area, define a weighted graph with M nodes ,in Represents a collection of storage location nodes in a storage area =1,2,3,...,n; Represents the path between the storage location nodes in the storage area, and sets the distance between the storage location node e in the storage area and the storage location node f in the storage area to ; S42, calculating the shortest path based on ant colony algorithm; S43. Based on the shortest path calculated by the ant colony algorithm, each cargo that needs to be stored in the warehouse is allocated to the corresponding cargo location node, and the stored cargo type and the allocated cargo location coordinates are combined into an array and stored in the database.

6. The method for identifying cargo status in cargo space based on laser radar according to claim 5, characterized in that: The shortest path calculation based on the ant colony algorithm comprises the following steps: Set the number of ants in the ant colony to h, and set the pheromone concentration on the connection path between the cargo node e in the storage area and the cargo node f in the storage area at time t to ; At the initial moment, the pheromone concentration on the connection path between the cargo nodes in each storage area is the same. , is the pheromone concentration on the connection path between the cargo location nodes in each storage area at the initial moment; Ant , =1,2,...,h, the next city to visit is determined according to the pheromone concentration on the connection path between the cargo nodes in each storage area. represents the ant at time t From the probability of the cargo location node e in the storage area and the cargo location node f in the storage area, the transfer probability formula is as follows: in, is the heuristic function, , represents the ant's expectation degree from the cargo location node e in the storage area to the cargo location node f in the storage area, It represents the distance between the storage location node e and the storage location node f in the storage area. is the heuristic function, , represents the ant's expectation degree from the cargo location node e in the storage area to the cargo location node s in the storage area, It represents the distance between the storage location node e and the storage location node s in the storage area. Represents ants The collection of storage location nodes in the storage area to be accessed, is the pheromone importance factor, is the importance factor of the heuristic function, represents the pheromone concentration between the cargo location node e in the storage area and the cargo location node s in the storage area at time t; Based on the transition probability formula, the solution space is constructed and each ant is randomly placed in the cargo location nodes in different storage areas. , based on the transition probability formula, calculate the next storage location node to be visited in the storage area until all ants have visited all storage location nodes in the storage area, and at the same time calculate the path length D of each ant; Set the number of iterations of the algorithm and update the pheromone concentration on the connection path between the cargo nodes in each storage area; After reaching the set number of iterations, the calculation is terminated and the shortest path connecting the storage location nodes in each storage area is output.

7. A system for implementing the method for identifying cargo status of cargo space based on laser radar as described in any one of claims 1 to 6, characterized in that: Includes LiDAR, RFID sensor, database, storage area division module and goods warehousing module; The laser radar is used to collect RFID sensor signals in the monitoring area in real time and distinguish the RFID sensor signals based on signal strength; The RFID sensor is used to send RFID sensor signals in real time; The database is used to store the location fingerprint data collected and constructed by the laser radar; The storage area division module is used to divide the storage area based on the type and quantity of goods; The cargo warehousing module is used to calculate the shortest path to distribute the cargo to the corresponding cargo location.

Citation Information

Cited By

  • Warehousing shelf management method and system based on logistics intelligent search

    CN121616205A