Single-piece separation method and system for express delivery sorting
Through dynamic DWS components and sorting path optimization technology, the problems of low degree of express sorting and low efficiency in the existing technology are solved, and the overall efficiency and automation level of express sorting are improved.
Patent Information
- Application Number
- CN202411095626.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-12
AI Technical Summary
In the prior art, the separation of express delivery single-pieces mainly depends on the robot to sort according to preset procedures, resulting in low global express delivery sorting efficiency.
By introducing dynamic DWS components to obtain cargo weight, size, barcode and motion speed information in real time, and combine warehouse calibration number, handling robot model and sorting port passage information to optimize the sorting path, optimize the sorting path to achieve single-piece Separation and transport.
The full process automation from the cargo entering the conveyor belt to the separation and handling of single-pieces is realized, which improves sorting efficiency and automation level and reduces sorting time.
Smart Images

Figure CN118616338B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of material handling, and in particular to a single piece separation method and system for express delivery sorting. Background Art
[0002] By separating express items, express items can be arranged reasonably to facilitate the subsequent sorting of express items. Currently, express item separation is performed by a robot arm according to a preset program to automatically separate the express items in the conveying direction and in the left and right directions at specific intervals to facilitate subsequent sorting. Although automation has been achieved, the disadvantage is that it is limited to the automation of the step of express item separation, and does not take into account improving the overall express sorting efficiency. Summary of the invention
[0003] The present application provides a single-piece separation method for express sorting, aiming to solve the technical problem that in the prior art, express single-piece separation is mainly performed by a robot arm according to a preset program, which is limited to the separation of express single pieces and has a low overall express sorting efficiency.
[0004] In view of the above problems, the present application provides a single piece separation method and system for express sorting.
[0005] The first aspect disclosed in the present application provides a single-piece separation method for express sorting, the method comprising: when the goods enter the conveyor belt, obtaining the weight information, size information, barcode information and movement speed information of the goods through the dynamic DWS component; matching the goods with the warehouse according to the barcode information of the goods, and obtaining the warehouse calibration number information; matching the goods with the handling robot according to the weight information and the size information of the goods, and obtaining the model information of the handling robot; predicting the movement of the goods according to the movement speed information of the goods, obtaining the time information of the movement trajectory, matching the time in combination with the position information of the sorting port, and obtaining the time information of the sorting port passing; optimizing the sorting path according to the warehouse calibration number information, the model information of the handling robot and the time information of the sorting port passing, obtaining the optimized path for single-piece separation, and performing single-piece separation and handling of the goods.
[0006] The second aspect disclosed in the present application provides a single-piece separation system for express sorting, the system is used for the above-mentioned single-piece separation method for express sorting, the system comprises: a cargo information acquisition module, the cargo information acquisition module is used to obtain cargo weight information, cargo size information, cargo barcode information and cargo movement speed information through a dynamic DWS component when the cargo enters the conveyor belt; a warehouse matching module, the warehouse matching module is used to match the cargo to the warehouse according to the cargo barcode information, and obtain the warehouse calibration number information; a robot matching module, the robot matching module is used to match the cargo to the warehouse according to the cargo barcode information, and obtain the warehouse calibration number information. The cargo weight information and the cargo size information are used to match the cargo handling robot to obtain the handling robot model information; a time matching module is used to predict the movement of the cargo according to the cargo movement speed information, obtain the movement trajectory time information, and perform time matching in combination with the sorting port position information to obtain the sorting port passing time information; a sorting path optimization module is used to optimize the sorting path according to the warehouse calibration number information, the handling robot model information and the sorting port passing time information, obtain the single-piece separation optimization path, and perform single-piece separation and handling of the cargo.
[0007] According to a third aspect disclosed in the present application, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any step of the first aspect disclosed in the present application is implemented.
[0008] The fourth aspect disclosed in the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the first aspect disclosed in the present application.
[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0010] By introducing the dynamic DWS component, accurate information such as the weight, size, barcode, and movement speed of the goods can be obtained in real time, realizing the automation of the entire process from the goods entering the conveyor belt to the separation and transportation of individual pieces, thereby improving the sorting efficiency; the sorting path is optimized according to the warehouse calibration number, the model of the handling robot, and the time information of the sorting port, and the optimal sorting path is determined. Through the comprehensive planning of the sorting path, the sorting efficiency can be effectively improved and the sorting time can be reduced. In summary, the single-piece separation method for express sorting solves the problems of low sorting automation and low sorting efficiency in the prior art by introducing the dynamic DWS component and combining the sorting path optimization, thereby improving the overall efficiency and automation level of express sorting.
[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] Figure 1 A schematic flow chart of a method for separating single items for express delivery sorting provided in an embodiment of the present application;
[0013] Figure 2 A schematic diagram of the structure of a single-piece separation system for express sorting provided in an embodiment of the present application;
[0014] Figure 3 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application.
[0015] Explanation of reference numerals: cargo information acquisition module 10 , cargo warehouse matching module 20 , robot matching module 30 , time matching module 40 , sorting path optimization module 50 . DETAILED DESCRIPTION
[0016] The embodiment of the present application provides a single-piece separation method for express sorting, which solves the technical problem that in the prior art, express single-piece separation is mainly performed by a robot arm according to a pre-set program, which is limited to the separation of express single pieces and has low global express sorting efficiency.
[0017] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0018] like Figure 1 As shown, an embodiment of the present application provides a single-piece separation method for express sorting, the method comprising:
[0019] When the goods enter the conveyor belt, the dynamic DWS component obtains the goods weight information, goods size information, goods barcode information and goods movement speed information;
[0020] The dynamic DWS (Dimension Weight System) component is an integrated information collection device, including a cargo weight receiving module, a cargo volume recognition module, a barcode information receiving module, and a cargo speed recognition module. When the cargo enters the conveyor belt, the cargo weight receiving module interacts with the weight sensor on the conveyor belt to obtain the cargo weight information; the cargo volume recognition module interacts with the multi-directional industrial camera deployed on the conveyor belt to obtain the multi-directional image information of the cargo for recognition, thereby generating cargo size information; the barcode information receiving module responds to the cargo electronic tag and receives the cargo barcode information; the cargo speed recognition module interacts with the conveyor belt control end to receive the cargo movement speed information. The acquired information is integrated through the dynamic DWS component for subsequent sorting and handling operations.
[0021] Matching the goods to the warehouse according to the barcode information of the goods to obtain the warehouse calibration number information;
[0022] Parse the barcode of the goods read, extract the barcode information, obtain the pre-set database, which contains the correspondence between the barcode and the warehouse calibration number, and query the database according to the barcode information of the current goods to obtain the corresponding warehouse calibration number information. This number is used to identify the unique identifier of the warehouse. This ensures that in the subsequent sorting process, the goods can be accurately allocated to the correct warehouse.
[0023] Matching the cargo to a handling robot according to the cargo weight information and the cargo size information to obtain the handling robot model information;
[0024] Obtain the capability parameters of different handling robots, such as the maximum load weight, the range of sizes that can be handled, etc. These parameters are determined according to the robot design file. Define the intervals of different capability levels according to the robot capability parameters, and formulate a matching strategy. For example, a greedy algorithm is used to prioritize the capability level that is closest to the weight and size of the goods to minimize resource waste. For each cargo, according to its weight and size information, based on the matching strategy, select the most suitable robot capability level. After determining the robot capability level, return the robot model information corresponding to the level.
[0025] Predict the movement of the goods according to the movement speed information of the goods, obtain the time information of the movement trajectory, and perform time matching in combination with the position information of the sorting port to obtain the time information of the sorting port passing;
[0026] The obtained cargo movement speed information is used to predict the cargo movement trajectory. Specifically, the cargo movement trajectory time information on the conveyor belt is obtained based on the real-time position and speed of the cargo and the conveyor belt travel track information. The sorting port position information is obtained based on the conveyor belt design information, including its position on the conveyor belt and its position relative to the conveyor belt. The predicted movement trajectory time information is matched with the sorting port position information to determine the time information when the cargo passes through the sorting port, which includes the time point when the cargo arrives at the sorting port.
[0027] The sorting path is optimized according to the warehouse calibration number information, the transport robot model information and the sorting port passing time information, and the single-piece separation optimization path is obtained to separate and transport the goods individually.
[0028] Use the warehouse calibration number information to determine the target warehouse location information where the goods need to be sorted as the path end point; use the handling robot model information to determine the parking position information of the handling robot as the path starting point. Combine the path starting point and path end point, as well as the sorting port passing time information, and use the path planning algorithm to calculate the optimal sorting path. This optimal path combines the starting point, end point and sorting port passing time information. The specific optimization process will be described in detail in the subsequent steps, so I will not go into details here. Based on the optimal path, control the handling robot to start the sorting task, take the goods from the conveyor belt and transport them to the target warehouse according to the path.
[0029] Furthermore, when the goods enter the conveyor belt, the dynamic DWS component obtains the goods weight information, goods size information, goods barcode information and goods movement speed information, including:
[0030] The dynamic DWS component includes a barcode information receiving module, a cargo weight receiving module, a cargo volume identification module, and a cargo speed identification module;
[0031] Wherein, the barcode information receiving module is used to respond to the goods electronic label and receive the goods barcode information;
[0032] Wherein, the cargo weight receiving module is used to interact with the weight sensor deployed on the conveyor belt to receive the cargo weight information;
[0033] The cargo volume recognition module is used to interact with the multi-directional industrial camera deployed on the conveyor belt, obtain multi-directional image information of the cargo for recognition, and generate the cargo size information, wherein the cargo size information includes cargo length information, cargo width information and cargo height information, and the multi-directional information includes at least the top of the conveyor belt, the left side of the conveyor belt, and the right side of the conveyor belt;
[0034] The cargo speed identification module is used to interact with the conveyor belt control end to receive the cargo movement speed information.
[0035] The dynamic DWS component includes a barcode information receiving module, a cargo weight receiving module, a cargo volume identification module, and a cargo speed identification module.
[0036] Among them, the implementation of the barcode information receiving module can adopt various technologies, including laser scanning, image recognition, RFID (radio frequency identification), etc. When the goods are transported by the conveyor belt, the barcode information receiving module scans the barcode information on the goods. These barcodes are printed on the goods by labels and contain the unique identification code of the goods. After reading the barcode information, the module decodes it for further processing. By identifying the barcode information, each cargo can be accurately tracked and identified, thereby ensuring that the cargo can be correctly sorted and processed.
[0037] The main function of the cargo weight receiving module is to interact with the weight sensor on the conveyor belt and receive the weight information of the cargo in real time. Through this module, the weight data of each cargo can be obtained. When the cargo enters the conveyor belt and passes through the weight sensor, the sensor detects the weight of the cargo and transmits this data to the cargo weight receiving module. By obtaining the weight of the cargo in real time, the cargo can be sorted and processed according to the weight information to ensure that each cargo is delivered correctly.
[0038] The main function of the cargo volume recognition module is to use the multi-directional industrial camera deployed on the conveyor belt to obtain image information of the cargo at multiple angles. The multi-directional cameras include at least above the conveyor belt, on the left side of the conveyor belt, and on the right side of the conveyor belt, so as to obtain images of the cargo in multiple directions such as above, on the left side and on the right side of the conveyor belt, and recognize these images to determine the size information of the cargo.
[0039] When the goods enter the conveyor belt and pass through the multi-directional industrial camera, the camera captures images of the goods in multiple directions, such as above, on the left and on the right side of the conveyor belt. The cargo volume recognition module uses this image information, image processing and computer vision technology to identify the goods and determine their size information, which includes the length, width and height of the goods.
[0040] The main function of the cargo speed identification module is to interact with the control end of the conveyor belt and receive the cargo movement speed information in real time. Through this module, the real-time movement speed of the cargo on the conveyor belt can be obtained. When the cargo moves on the conveyor belt, the conveyor belt control end controls the movement speed of the conveyor belt. The cargo speed identification module obtains the real-time movement speed information of the conveyor belt by interacting with the control end, thereby obtaining the cargo movement speed information. By obtaining the movement speed of the cargo in real time, the arrival time of the cargo can be predicted and time matching can be performed to accurately deliver the cargo to the destination.
[0041] Furthermore, the cargo volume recognition module is used to interact with the multi-directional industrial camera deployed on the conveyor belt, obtain multi-directional image information of the cargo for recognition, and generate the cargo size information, including:
[0042] Obtaining industrial camera acquisition status information, wherein the industrial camera acquisition status information includes a first camera acquisition angle and a first camera deployment position, a second camera acquisition angle and a second camera deployment position, and finally an N-th camera acquisition angle and an N-th camera deployment position, where N is an integer and N≥3;
[0043] Traversing the first camera acquisition angle, the second camera acquisition angle, and the conveyor belt deployment area of the Nth camera acquisition angle, and taking the intersection, obtaining the first intersection position, the second intersection position, and the Nth intersection position;
[0044] According to the first camera deployment position, the second camera deployment position, and up to the Nth camera deployment position, compare with the first intersection position, the second intersection position, and up to the Nth intersection position to obtain a first acquisition distance, a second acquisition distance, and up to the Nth acquisition distance;
[0045] Through the image scale analysis model, the first acquisition distance and the first camera control parameter, the second acquisition distance and the second camera control parameter, and up to the Nth acquisition distance and the Nth camera control parameter are processed respectively to obtain a first scale, a second scale, and up to the Nth scale, where the scale represents the reduction ratio of the image and the real object;
[0046] The multi-directional image information of the cargo is recognized according to the first scale, the second scale, and up to the Nth scale to generate the cargo size information.
[0047] First, determine the number N of industrial cameras deployed on the conveyor belt. N ≥ 3 means that there are at least 3 cameras, covering at least the top, left side, and right side of the conveyor belt.
[0048] Obtain the deployment position and collection angle of the industrial camera. For example, take the cargo collection position as the reference (origin) to establish a rectangular coordinate system with the horizontal direction as the x-axis and the vertical direction as the y-axis. For each industrial camera, determine its position coordinates in the established rectangular coordinate system, obtain the first camera deployment position, the second camera deployment position, and so on until the Nth camera deployment position.
[0049] Based on the rectangular coordinate system, determine the angle of each industrial camera relative to the cargo collection position, that is, obtain the angle of the position coordinates of each industrial camera relative to the origin of the established rectangular coordinate system. The angle can be the angle relative to the x-axis, and obtain the first camera collection angle, the second camera collection angle, until the Nth camera collection angle.
[0050] For each camera, its acquisition angle is vertically projected onto the conveyor belt to determine the vertical mapping position of the camera on the conveyor belt. This can be done through angle calculation in geometry to obtain the position of intersection with the conveyor belt. This position is marked on the coordinate axis to obtain the position coordinate of the intersection position on the x-axis. Each camera is traversed to obtain the first intersection position, the second intersection position, and so on until the Nth intersection position.
[0051] For each camera, its deployment position, intersection position and cargo collection position (origin) form a right triangle. The length of the right angle side is determined by calculating the coordinate difference between the deployment position and the intersection position. The camera collection angle is the angle opposite to the right angle side. Using trigonometric functions, the hypotenuse of the right angle is calculated, that is, the length of the right angle side divided by the tangent value of the collection angle. The hypotenuse is the collection distance from the camera deployment position to the cargo collection position. For each industrial camera, repeat the above steps to obtain the first collection distance, the second collection distance, and the Nth collection distance.
[0052] Prepare a training data set, including the acquisition distance between the camera and the object when acquiring the image, and the camera control parameter information, such as focal length, and the scale of the image. The scale is the reduction ratio between the acquired image and the real object. The training data set can be obtained through simulation or laboratory experiments.
[0053] Construct a BP neural network model. The input layer of the neural network includes the acquisition distance between the camera and the object, as well as the camera control parameters, and the output includes the scale of the image. Determine the hidden layer structure and activation function of the neural network, initialize the weights and biases, and use the prepared data set to train the neural network model. During the training process, use the back propagation algorithm to update the weights and biases of the neural network to minimize the error between the predicted distance and the actual distance. Through iterative training, the neural network gradually learns the scale information in the image and adjusts the control parameters to more accurately represent the actual scale until the convergence conditions are met, such as reaching the preset number of iterations, or the accuracy meets the preset accuracy threshold, and outputs the image scale analysis model.
[0054] The trained image scale parsing model processes the acquisition distance and control parameters of each camera according to the learned content to obtain the scaling ratio between the image and the real object, that is, the first scale, the second scale, and so on to the Nth scale.
[0055] The acquired multi-directional images are semantically segmented, and a deep learning model, such as a semantic segmentation network, such as U-Net, can be used to segment the images and clearly extract the boundaries of the goods. For the first camera, in the first image after semantic segmentation, the bounding box of the goods is identified, and the size information of the goods in the first image is obtained by using image processing technology, such as contour detection or bounding box detection. The extracted image size information is enlarged according to the first scale corresponding to the first image. The scale maps the pixel size in the image to the physical size in the real world, and the actual size information of the goods is obtained, which can be length, width, height, etc. Repeat the above steps for the images collected by each camera until all images are processed, and integrate the actual size information collected by all cameras to obtain the complete size information of the goods.
[0056] Furthermore, the movement of the goods is predicted according to the movement speed information of the goods to obtain the time information of the movement trajectory, and the time is matched in combination with the position information of the sorting port to obtain the time information of the sorting port passing, including:
[0057] Obtaining the real-time location information of the cargo, combining the cargo movement speed information with the conveyor belt travel track information for matching, and obtaining the movement track time information;
[0058] The sorting port position information is obtained and matched with the conveyor belt travel track information to obtain the intersection track position information;
[0059] The passing time information of the sorting port is obtained according to the intersection trajectory position information and the movement trajectory time information.
[0060] The conveyor belt travel track information describes the movement path of the conveyor belt, which can be a straight or curved track. Taking the starting point of the conveyor belt as the reference and the initial movement direction of the conveyor belt as the x-axis, a second coordinate system is established, and the conveyor belt travel track is mapped to the second coordinate system. Sensors are used to obtain the position of the goods on the conveyor belt in real time, and the position is mapped to the travel track of the second coordinate system to obtain the real-time position coordinates of the goods.
[0061] The goods move forward at a constant speed on the conveyor belt. According to the real-time position and movement speed of the goods and the travel track of the conveyor belt, the time it takes for the goods to reach any point on the movement track of the conveyor belt can be calculated. Specifically, any point on the track is taken as the target position, and the real-time position coordinates are subtracted from the target position coordinates to obtain the length of the travel distance. The length of the travel distance is divided by the movement speed of the goods to obtain the time required for the goods to reach the target position, and then the time point when the goods reach the target position is obtained, and this time point is recorded as the moment information of the movement track passing the target position.
[0062] The position information of each sorting port is obtained. The position information may be relative to the starting point of the conveyor belt. The position information of the sorting port is matched with the travel track information of the conveyor belt, that is, the position of the sorting port is mapped to the aforementioned second coordinate system, and the intersection position between the position of the sorting port and the travel track of the conveyor belt is obtained.
[0063] The intersection trajectory position is used as the aforementioned target position, and the motion trajectory time acquisition process is repeated, that is, according to the movement speed of the goods, the time required for the goods to move from the real-time position to the intersection trajectory position is calculated, so as to obtain the time point when the goods move from the real-time position to the sorting port, and record this time point as the moment information when the goods pass through the sorting port.
[0064] Furthermore, the sorting path is optimized according to the warehouse calibration number information, the handling robot model information and the sorting port passing time information to obtain a single piece separation optimization path, and the goods are separated and transported individually, including:
[0065] According to the cargo warehouse calibration number information, the cargo warehouse deployment location information is obtained, and the sorting port number set of the sorting port passing time information is traversed to perform distance analysis and sort from near to far to obtain the sorting result of the first sorting port;
[0066] According to the model information of the transport robot, the parking position information of the robot is obtained, the sorting port number set is traversed to perform distance analysis and sorted from near to far to obtain the sorting result of the second sorting port;
[0067] According to the sorting result of the first sorting port and the sorting result of the second sorting port, a comprehensive distance analysis is performed on the sorting port number set and the sorting is performed from small to large to obtain a third sorting port sorting result;
[0068] sorting the sorting results of the third sorting port according to the passing time information of the sorting port to obtain the sorting results of the fourth sorting port;
[0069] The first sorting port in the sorting result of the fourth sorting port is extracted and set as the target sorting port for path matching to obtain the single-piece separation optimization path.
[0070] Establish a third coordinate system that covers the entire factory area, including the warehouse location, sorting port location, robot location, and the travel path between them. According to the warehouse calibration number information, search the corresponding database, which contains the warehouse deployment location information corresponding to each calibration number, map the warehouse deployment location to the third coordinate system, and obtain the warehouse location coordinates. Traverse the sorting port number set of the sorting port passing time information, map each sorting port position to the third coordinate system, and obtain multiple sorting port position coordinates. According to the warehouse location coordinates and multiple sorting port location coordinates, calculate the distance between each sorting port and the warehouse. In the absence of obstacles, the distance is a straight-line distance.
[0071] The calculated distances are associated with the corresponding sorting port numbers and stored as a set of key-value pairs. These key-value pairs are sorted in ascending order according to the size of the distances, that is, they are sorted from near to far to obtain the sorting result of the first sorting port. In this sorting, the sorting port with the closest distance is at the front and the one with the farthest distance is at the back.
[0072] According to the model information of the handling robot, a pre-stored database is queried, which contains the parking position information corresponding to each robot model. The robot can be parked at its standby point, charging point and other designated positions, wherein the robot parking position has a one-to-one corresponding road to each sorting port, and each road has a corresponding distance.
[0073] The sorting port number set is traversed, and for each sorting port coordinate, its distance from the robot parking position is obtained, and the obtained distance is associated with the corresponding sorting port number, and sorted in ascending order according to the size of the distance, that is, sorted from near to far according to the distance, to obtain the second sorting port sorting result.
[0074] For each sorting port, obtain its first serial number in the sorting result of the first sorting port and its second serial number in the sorting result of the second sorting port, add the first serial number and the second serial number, the smaller the sum is, the closer the comprehensive distance of the sorting port is, sort the sum results from small to large, and obtain the sorting result of the third sorting port.
[0075] The information on the time when the goods pass through each sorting port is obtained. This information records the time when the goods pass through each sorting port. According to the robot's estimated departure time and the robot's movement speed, as well as the distance between the robot and each sorting port, the time when the robot passes through each sorting port is calculated as the robot's arrival time.
[0076] Traverse the sorting results of the third sorting port, and for each sorting port, compare the sorting port passing time with the robot arrival time. If the robot arrival time is earlier than the sorting port passing time, keep the sorting port; otherwise, discard the sorting port. Sort the sorting ports that have passed the sorting according to their order in the sorting results of the third sorting ports to obtain the sorting results of the fourth sorting port.
[0077] The first sorting port is obtained from the sorting result of the fourth sorting port, that is, the first sorting port in the sorting result, and the first sorting port is used as the target sorting port. The path is matched with the current position of the transport robot. There is a corresponding running track between the transport robot and each sorting port, which is similar to the road in human traffic.
[0078] Use a path planning algorithm, such as the shortest path algorithm, to calculate the optimal path from the current position of the transport robot to the target sorting port. Combine the speed of the transport robot, the current state of the robot, and possible obstacles to search for the optimal path. Based on the results of path matching, obtain the optimal path from the current position of the transport robot to the target sorting port. This path is the single-piece separation optimization path, which guides the transport robot on how to move to sort the goods to the target sorting port.
[0079] Furthermore, sorting the sorting results of the third sorting port according to the passing time information of the sorting port to obtain the sorting results of the fourth sorting port includes:
[0080] Obtaining the estimated departure time information and robot movement speed information of the transport robot model information;
[0081] Traversing the sorting results of the third sorting port, performing running distance matching in combination with the parking position information of the robot, and obtaining a running distance set, wherein the running distance set corresponds to the sorting results of the third sorting port one by one;
[0082] Traversing the running distance set, calibrating the arrival time according to the estimated departure time information and the robot movement speed information, and obtaining an arrival time set;
[0083] The third sorting port sorting result is sorted according to the arrival time set and the sorting port passing time information to obtain the fourth sorting port sorting result.
[0084] Monitor the status of the handling robots in real time based on the handling robot model information. Idle handling robots will start tasks according to the received instructions. Record the idle status of each handling robot and the estimated departure time information, that is, the time when the robot accepts a new task and starts. Record the movement speed information of each handling robot, including linear speed and angular speed. The movement speed varies according to the robot model and current environmental conditions, so it needs to be configured and recorded for each robot.
[0085] The robot parking position has a one-to-one corresponding road with each sorting port, and each road has a corresponding distance. The sorting results of the third sorting port are traversed, and for each sorting port, the running distance with the robot parking position is found to obtain a running distance set. Each item in the running distance set corresponds to a sorting port and corresponds one-to-one with the sorting results of the third sorting port.
[0086] Traverse the running distance set, which contains the distance between each sorting port and the robot's parking position. For each sorting port, the running time of the robot to reach the sorting port can be calculated based on the distance between it and the robot's parking position and the robot's movement speed. The expected departure time plus the running time can be obtained to obtain the expected arrival time. Pair each sorting port with its corresponding expected arrival time to form an arrival time set. Each item in the arrival time set corresponds to a sorting port, and its value represents the time when the robot is expected to arrive at the sorting port.
[0087] Traverse the sorting results of the third sorting port, and for each sorting port, compare the arrival time set with the sorting port passing time, and check whether the arrival time of the sorting port is earlier than the sorting port passing time. If so, it means that the time when the robot arrives at the sorting port is earlier than the time when the goods arrive at the sorting port, then the sorting port is added to the sorting results of the fourth sorting port; otherwise, the sorting port is discarded. Repeat the above steps until all the sorting results of the third sorting port are traversed. After screening, the sorting port list obtained is the sorting result of the fourth sorting port.
[0088] Further, sorting the sorting result of the third sorting port according to the arrival time set and the passing time information of the sorting port to obtain the sorting result of the fourth sorting port includes:
[0089] When the arrival time of any sorting port in the third sorting port sorting result is earlier than the sorting port passing time, the time interval length is obtained;
[0090] Determine whether the time interval is greater than or equal to a waiting time threshold;
[0091] If it is greater than or equal to, delete the sorting port, otherwise, select the sorting port;
[0092] When the arrival time of any sorting port in the third sorting port sorting result is later than the passing time of the sorting port, the sorting port is deleted to obtain the fourth sorting port sorting result.
[0093] Traverse the sorting results of the third sorting port, and for each sorting port, compare its arrival time and the time it passes through the sorting port. If the arrival time of the sorting port is earlier than the time it passes through the sorting port, it means that the preliminary judgment is reasonable and further judgment is needed. Calculate the time difference between the arrival time and the time it passes. The difference is the time interval length.
[0094] The waiting time threshold is a pre-set value, which indicates the maximum waiting time allowed for the robot during the sorting process. It can be set according to the actual situation and specific needs. The time interval of each sorting port is compared with the set waiting time threshold. If the time interval is greater than or equal to the waiting time threshold, the waiting time is considered to be too long and the sorting port is deleted; if the time interval is less than the waiting time threshold, the waiting time is considered to be within an acceptable range and the sorting port is retained.
[0095] For each sorting port, if the arrival time of the sorting port is later than the passing time of the sorting port, the sorting port is directly deleted from the list. Combined with the sorting ports deleted in the previous step, the list of the remaining sorting ports is the sorting result of the fourth sorting port.
[0096] In summary, the single-item separation method for express sorting provided in the embodiment of the present application has the following technical effects:
[0097] 1. By introducing the dynamic DWS component, accurate information such as the weight, size, barcode and movement speed of the goods can be obtained in real time, realizing the automation of the entire process from the goods entering the conveyor belt to the single-piece separation and transportation, thereby improving the sorting efficiency;
[0098] 2. Optimize the sorting path according to the warehouse calibration number, handling robot model and sorting port passing time information to determine the optimal sorting path. Through comprehensive planning of the sorting path, the sorting efficiency can be effectively improved and the sorting time can be reduced.
[0099] In summary, the single-piece separation method for express sorting solves the problems of low sorting automation and low sorting efficiency in the prior art by introducing a dynamic DWS component and combining it with sorting path optimization, thereby improving the overall efficiency and automation level of express sorting.
[0100] Based on the same inventive concept as the single-piece separation method for express sorting in the aforementioned embodiment, Figure 2 As shown, the present application provides a single-piece separation system for express sorting, the system comprising:
[0101] A cargo information acquisition module 10, which is used to obtain cargo weight information, cargo size information, cargo barcode information and cargo movement speed information through a dynamic DWS component when the cargo enters the conveyor belt;
[0102] A cargo warehouse matching module 20, the cargo warehouse matching module 20 is used to match the cargo warehouse according to the cargo barcode information to obtain the cargo warehouse calibration number information;
[0103] A robot matching module 30, wherein the robot matching module 30 is used to match the cargo handling robot to the cargo according to the cargo weight information and the cargo size information, and obtain the handling robot model information;
[0104] A time matching module 40, which is used to predict the movement of the goods according to the movement speed information of the goods, obtain the time information of the movement trajectory, and perform time matching in combination with the sorting port position information to obtain the time information of the sorting port passing;
[0105] The sorting path optimization module 50 is used to optimize the sorting path according to the warehouse calibration number information, the transport robot model information and the sorting port passing time information, obtain the single-piece separation optimization path, and carry out single-piece separation and transportation of the goods.
[0106] Furthermore, the system also includes a dynamic DWS component:
[0107] The dynamic DWS component includes a barcode information receiving module, a cargo weight receiving module, a cargo volume identification module, and a cargo speed identification module;
[0108] Wherein, the barcode information receiving module is used to respond to the goods electronic label and receive the goods barcode information;
[0109] Wherein, the cargo weight receiving module is used to interact with the weight sensor deployed on the conveyor belt to receive the cargo weight information;
[0110] The cargo volume recognition module is used to interact with the multi-directional industrial camera deployed on the conveyor belt, obtain multi-directional image information of the cargo for recognition, and generate the cargo size information, wherein the cargo size information includes cargo length information, cargo width information and cargo height information, and the multi-directional information includes at least the top of the conveyor belt, the left side of the conveyor belt, and the right side of the conveyor belt;
[0111] The cargo speed identification module is used to interact with the conveyor belt control end to receive the cargo movement speed information.
[0112] Furthermore, the system further includes a cargo size information generation module to perform the following operation steps:
[0113] Obtaining industrial camera acquisition status information, wherein the industrial camera acquisition status information includes a first camera acquisition angle and a first camera deployment position, a second camera acquisition angle and a second camera deployment position, and finally an N-th camera acquisition angle and an N-th camera deployment position, where N is an integer and N≥3;
[0114] Traversing the first camera acquisition angle, the second camera acquisition angle, and the conveyor belt deployment area of the Nth camera acquisition angle, and taking the intersection, obtaining the first intersection position, the second intersection position, and the Nth intersection position;
[0115] According to the first camera deployment position, the second camera deployment position, and up to the Nth camera deployment position, compare with the first intersection position, the second intersection position, and up to the Nth intersection position to obtain a first acquisition distance, a second acquisition distance, and up to the Nth acquisition distance;
[0116] Through the image scale analysis model, the first acquisition distance and the first camera control parameter, the second acquisition distance and the second camera control parameter, and up to the Nth acquisition distance and the Nth camera control parameter are processed respectively to obtain a first scale, a second scale, and up to the Nth scale, where the scale represents the reduction ratio of the image and the real object;
[0117] The multi-directional image information of the cargo is recognized according to the first scale, the second scale, and up to the Nth scale to generate the cargo size information.
[0118] Furthermore, the system further includes a sorting port passing time information acquisition module to perform the following operation steps:
[0119] Obtaining the real-time location information of the cargo, combining the cargo movement speed information with the conveyor belt travel track information for matching, and obtaining the movement track time information;
[0120] The sorting port position information is obtained and matched with the conveyor belt travel track information to obtain the intersection track position information;
[0121] The passing time information of the sorting port is obtained according to the intersection trajectory position information and the movement trajectory time information.
[0122] Furthermore, the system further includes a single-piece separation optimization path generation module to perform the following operation steps:
[0123] According to the cargo warehouse calibration number information, the cargo warehouse deployment location information is obtained, and the sorting port number set of the sorting port passing time information is traversed to perform distance analysis and sort from near to far to obtain the sorting result of the first sorting port;
[0124] According to the model information of the transport robot, the parking position information of the robot is obtained, the sorting port number set is traversed to perform distance analysis and sorted from near to far to obtain the sorting result of the second sorting port;
[0125] According to the sorting result of the first sorting port and the sorting result of the second sorting port, a comprehensive distance analysis is performed on the sorting port number set and the sorting is performed from small to large to obtain a third sorting port sorting result;
[0126] sorting the sorting results of the third sorting port according to the passing time information of the sorting port to obtain the sorting results of the fourth sorting port;
[0127] The first sorting port in the sorting result of the fourth sorting port is extracted and set as the target sorting port for path matching to obtain the single-piece separation optimization path.
[0128] Furthermore, the system further includes a sorting port sorting result generation module to perform the following operation steps:
[0129] Obtaining the estimated departure time information and robot movement speed information of the transport robot model information;
[0130] Traversing the sorting results of the third sorting port, performing running distance matching in combination with the parking position information of the robot, and obtaining a running distance set, wherein the running distance set corresponds to the sorting results of the third sorting port one by one;
[0131] Traversing the running distance set, calibrating the arrival time according to the estimated departure time information and the robot movement speed information, and obtaining an arrival time set;
[0132] The third sorting port sorting result is sorted according to the arrival time set and the sorting port passing time information to obtain the fourth sorting port sorting result.
[0133] Furthermore, the system further includes a fourth sorting port sorting result acquisition module to perform the following operation steps:
[0134] When the arrival time of any sorting port in the third sorting port sorting result is earlier than the sorting port passing time, the time interval length is obtained;
[0135] Determine whether the time interval is greater than or equal to a waiting time threshold;
[0136] If it is greater than or equal to, delete the sorting port, otherwise, select the sorting port;
[0137] When the arrival time of any sorting port in the third sorting port sorting result is later than the passing time of the sorting port, the sorting port is deleted to obtain the fourth sorting port sorting result.
[0138] Through the above-mentioned detailed description of a single-piece separation method for express sorting in this specification, those skilled in the art can clearly know a single-piece separation system for express sorting in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0139] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the processor of the computer device is used to provide computing and control capabilities; the memory of the computer device includes a non-volatile storage medium and an internal memory, wherein the non-volatile storage medium stores an operating system, a computer program and a database, and the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium; the network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a single-piece separation method for express sorting.
[0140] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0141] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0142] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A single piece separation method for express sorting, characterized in that: The method comprises: When the goods enter the conveyor belt, the dynamic DWS component obtains the goods weight information, goods size information, goods barcode information and goods movement speed information; Matching the goods to the warehouse according to the barcode information of the goods to obtain the warehouse calibration number information; Matching the cargo to a handling robot according to the cargo weight information and the cargo size information to obtain the handling robot model information; Predict the movement of the goods according to the movement speed information of the goods, obtain the time information of the movement trajectory, and perform time matching in combination with the position information of the sorting port to obtain the time information of the sorting port passing; According to the warehouse calibration number information, the handling robot model information and the sorting port passing time information, the sorting path is optimized to obtain the single-piece separation optimization path, and the goods are separated and transported individually; Among them, the sorting path optimization is performed according to the warehouse calibration number information, the handling robot model information and the sorting port passing time information, and the single-piece separation optimization path is obtained to separate and transport the goods individually, including: According to the cargo warehouse calibration number information, the cargo warehouse deployment location information is obtained, and the sorting port number set of the sorting port passing time information is traversed to perform distance analysis and sort from near to far to obtain the sorting result of the first sorting port; According to the model information of the transport robot, the parking position information of the robot is obtained, the sorting port number set is traversed to perform distance analysis and sorted from near to far to obtain the sorting result of the second sorting port; According to the sorting result of the first sorting port and the sorting result of the second sorting port, a comprehensive distance analysis is performed on the sorting port number set and the sorting is performed from small to large to obtain a third sorting port sorting result; sorting the sorting results of the third sorting port according to the passing time information of the sorting port to obtain the sorting results of the fourth sorting port; Extracting the first sorting port in the sorting result of the fourth sorting port, setting it as the target sorting port for path matching, and obtaining the single-piece separation optimization path; The step of sorting the sorting results of the third sorting port according to the passing time information of the sorting port to obtain the sorting results of the fourth sorting port includes: Obtaining the estimated departure time information and robot movement speed information of the transport robot model information; Traversing the sorting results of the third sorting port, performing running distance matching in combination with the parking position information of the robot, and obtaining a running distance set, wherein the running distance set corresponds to the sorting results of the third sorting port one by one; Traversing the running distance set, calibrating the arrival time according to the estimated departure time information and the robot movement speed information, and obtaining an arrival time set; The third sorting port sorting result is sorted according to the arrival time set and the sorting port passing time information to obtain the fourth sorting port sorting result.
2. The method according to claim 1, characterized in that When the goods enter the conveyor belt, the dynamic DWS component obtains the goods weight information, goods size information, goods barcode information and goods movement speed information, including: The dynamic DWS component includes a barcode information receiving module, a cargo weight receiving module, a cargo volume identification module, and a cargo speed identification module; Wherein, the barcode information receiving module is used to respond to the goods electronic label and receive the goods barcode information; Wherein, the cargo weight receiving module is used to interact with the weight sensor deployed on the conveyor belt to receive the cargo weight information; The cargo volume recognition module is used to interact with the multi-directional industrial camera deployed on the conveyor belt, obtain multi-directional image information of the cargo for recognition, and generate the cargo size information, wherein the cargo size information includes cargo length information, cargo width information and cargo height information, and the multi-directional information includes at least the top of the conveyor belt, the left side of the conveyor belt, and the right side of the conveyor belt; The cargo speed identification module is used to interact with the conveyor belt control end to receive the cargo movement speed information.
3. The method according to claim 2, characterized in that The cargo volume recognition module is used to interact with the multi-directional industrial camera deployed on the conveyor belt, obtain multi-directional image information of the cargo for recognition, and generate the cargo size information, including: Obtaining industrial camera acquisition status information, wherein the industrial camera acquisition status information includes a first camera acquisition angle and a first camera deployment position, a second camera acquisition angle and a second camera deployment position, and finally an N-th camera acquisition angle and an N-th camera deployment position, where N is an integer and N≥3; Traversing the first camera acquisition angle, the second camera acquisition angle, and the conveyor belt deployment area of the Nth camera acquisition angle, and taking the intersection, obtaining the first intersection position, the second intersection position, and the Nth intersection position; According to the first camera deployment position, the second camera deployment position, and up to the Nth camera deployment position, compare with the first intersection position, the second intersection position, and up to the Nth intersection position to obtain a first acquisition distance, a second acquisition distance, and up to the Nth acquisition distance; Through the image scale analysis model, the first acquisition distance and the first camera control parameter, the second acquisition distance and the second camera control parameter, and up to the Nth acquisition distance and the Nth camera control parameter are processed respectively to obtain a first scale, a second scale, and up to the Nth scale, where the scale represents the reduction ratio of the image and the real object; The multi-directional image information of the cargo is recognized according to the first scale, the second scale, and up to the Nth scale to generate the cargo size information.
4. The method according to claim 1, characterized in that Predicting the movement of the goods according to the movement speed information of the goods, obtaining the time information of the movement trajectory, and performing time matching in combination with the position information of the sorting port to obtain the time information of the sorting port passing, including: Obtaining the real-time location information of the cargo, combining the cargo movement speed information with the conveyor belt travel track information for matching, and obtaining the movement track time information; The sorting port position information is obtained and matched with the conveyor belt travel track information to obtain the intersection track position information; The passing time information of the sorting port is obtained according to the intersection trajectory position information and the movement trajectory time information.
5. The method according to claim 1, characterized in that Sorting the third sorting port sorting result according to the arrival time set and the sorting port passing time information to obtain the fourth sorting port sorting result, including: When the arrival time of any sorting port in the third sorting port sorting result is earlier than the sorting port passing time, the time interval length is obtained; Determine whether the time interval is greater than or equal to a waiting time threshold; If it is greater than or equal to, delete the sorting port, otherwise, select the sorting port; When the arrival time of any sorting port in the third sorting port sorting result is later than the passing time of the sorting port, the sorting port is deleted to obtain the fourth sorting port sorting result.
6. A single-piece separation system for express sorting, characterized in that: A system for implementing a single-piece separation method for express sorting according to any one of claims 1 to 5, the system comprising: A cargo information acquisition module, which is used to obtain cargo weight information, cargo size information, cargo barcode information and cargo movement speed information through a dynamic DWS component when the cargo enters the conveyor belt; A warehouse matching module, the warehouse matching module is used to match the goods with the warehouse according to the barcode information of the goods to obtain the warehouse calibration number information; A robot matching module, wherein the robot matching module is used to match the cargo handling robot to the cargo according to the cargo weight information and the cargo size information, and obtain the handling robot model information; A time matching module, which is used to predict the movement of the goods according to the movement speed information of the goods, obtain the time information of the movement trajectory, and perform time matching in combination with the sorting port position information to obtain the time information of the sorting port passing; The sorting path optimization module is used to optimize the sorting path according to the warehouse calibration number information, the handling robot model information and the sorting port passing time information, obtain the single-piece separation optimization path, and carry out single-piece separation and transportation of the goods.
7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the processor implements the steps of a single-piece separation method for express sorting as described in any one of claims 1 to 5.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a single piece separation method for express sorting described in any one of claims 1 to 5 are implemented.
