CN117465874A - Automatic cargo inspection method and device - Google Patents

Abstract

The invention discloses an automatic cargo inspection device which comprises an inspection module, a storage matching module and a scheduling module, wherein the inspection module comprises an inspection AMR, a data transmission device, a telescopic support frame, a camera component and a motor component, the inspection AMR is provided with the telescopic support frame, the inspection AMR is connected with the data transmission device, and the data transmission device is also connected with the motor component and used for controlling the motor component; the telescopic support frame is connected with the camera component; the storage module comprises a goods shelf, a standardized container and a ground grid; the scheduling module is used for scheduling the AMR. Based on the device, the invention also provides an automatic cargo inspection method. Compared with the prior art, the invention has the beneficial effects that: the invention can enable the inspection of the warehouse goods to be automatic, help other links in the supply chain to know the goods state, and make corresponding decisions and arrangements in time, thereby improving the response capability and cooperativity of the whole supply chain.

Description

Automatic cargo inspection method and device

Technical Field

The invention relates to the technical field of intelligent storage, in particular to an automatic cargo inspection method and an automatic cargo inspection device.

Background

With the rapid development of modern industry, the demands of the manufacturing industry field for production efficiency and quality control are increasing. In the cigarette industry, ensuring the quality and consistency of finished cigarette products is critical to maintaining market competitiveness. Cargo inspection is an indispensable part of the quality control process. However, the conventional manual cargo inspection method has the problems of low efficiency, easy error, difficulty in realizing full coverage and the like. Specifically, due to the fact that warehouse standardized containers are stacked neatly, the traditional manual inspection has the problems of missing inspection, re-inspection, false inspection and the like. In addition, some standardized containers in warehouses are placed at high locations, making it difficult for workers to fully cover. Moreover, this tedious, single inspection task can also greatly reduce the work efficiency of the staff.

The existing automatic cargo inspection equipment has the defects that the existing automatic cargo inspection equipment can release manual work, but the existing automatic cargo inspection equipment also has the main defects that the real-time adjustment capacity of a scheduling scheme of the automatic cargo inspection equipment is poor, and once unexpected conditions occur, the inspection robot is easy to idle or conflict, so that the preset working efficiency cannot be achieved. In order to solve the problem of insufficient adjustment capacity of the scheduling scheme, in the actual use process, enough time is often reserved for each link, so that the conventional automatic cargo inspection equipment can smoothly complete the work in the working process, but time and efficiency are sacrificed.

Therefore, there is an urgent need to develop an automated inspection method and an automated inspection device capable of efficiently and accurately completing the inspection task. Thereby improving the production efficiency and the quality control level.

In view of the above drawbacks, the present inventors have finally achieved the present invention through long-time studies and practices.

Disclosure of Invention

In view of the above, in order to realize efficient inspection, the invention provides an automatic cargo inspection method, which comprises the following steps:

step S1, a scheduling module generates a patrol task instruction and sends the patrol task instruction to a data transmission device;

s2, the data transmission device sends a control instruction to the AMR, and the data transmission device determines the moving height of the camera according to the number of shelf layers in the inspection task;

s3, starting the AMR to go to the appointed position, starting the ground grid positioning by the AMR to determine whether the AMR reaches the appointed position, and then, enabling the AMR to reach the appointed position area;

s4, the data transmission device controls the motor assembly to act, and the motor assembly adjusts the height of the telescopic support frame and the height of the camera;

s5, shooting by a camera, and enabling the routing inspection AMR to start moving according to routing inspection path information in routing inspection task instructions and two-dimensional code information on a ground grid;

s6, executing the same-area same-layer priority inspection strategy;

step S7, after the scanning of the standardized containers on the same layer is finished, starting the motor assembly and adjusting the camera to the height of the next layer so as to continue shooting and inspection;

s8, if all the shelves in the current area are scanned, the AMR is moved to another area, and the scanning is continuously started;

and step S9, repeating the steps S5 to S8 until the shelves and standardized containers in all areas are scanned.

Preferably, during the process of executing the patrol task by the patrol AMR, the scheduling module generates a new constraint and scheduling scheme according to the information from the patrol AMR, and then re-executes step S1.

Preferably, the scheduling module uses DQNThe algorithm is solved recursively to obtain a feasible scheduling scheme, and Q (s in the DQN algorithm _t ,a _t ) The calculation method is as follows:

where rt represents the instant prize at time t, when the target is reached, rt is 50, the collision or timeout event rt is-10,representing the probability of transitioning to state st +1 with the current state st and action at determined,the maximum reward value obtained by taking different actions in the state st+1 is represented, gamma is a discount factor, and the influence degree of future rewards on the current action of the AMR is represented; q(s) _t ,a _t ) The updated formula of (2) is:

wherein, alpha is learning rate, and the value range is alpha epsilon [0,1]; gamma is a discount factor and represents the influence degree of future rewards on the current action of the AMR patrol.

Preferably, the scheduling module gives the instant reward function of the patrol AMR:

when the patrol AMR reaches the target point, the instant rewarding function value is C1, when the patrol AMR collides, the instant rewarding function value is C2, and under other conditions, the instant rewarding function value is K x cos theta/d, wherein K is an hyper-parameter, gamma is an included angle between a vector n1 pointing to the target point position from the position of the patrol AMR before the patrol AMR acts and a direction vector n2 before and after the patrol AMR acts, and d is a distance between the position of the AMR and the target point position.

Preferably, the scheduling module adopts a scheduling strategy for waiting for a conflict point under a multi-AMR system, the scheduling strategy is to simulate and inspect the extra operation time of AMR passing through the conflict point, adopts an Eerlon distribution model, and assumes that the probability of collision in the process of inspecting n shelves is beta, and a preset collision allowance time formula is as follows: t0=β×n×m×y, where m is the number of collision points passed by the patrol AMR and y is the average of the additional working time.

The invention also provides an automatic cargo inspection device which is used for the automatic cargo inspection method and comprises an inspection module, a storage matching module and a scheduling module.

Preferably, the inspection module comprises an inspection AMR, a data transmission device, a telescopic supporting frame, a camera component and a motor component, wherein the telescopic supporting frame is arranged on the inspection AMR, the inspection AMR is connected with the data transmission device, and the data transmission device is also connected with the motor component and used for controlling the motor component; the telescopic support frame is connected with the camera component; the storage module comprises a goods shelf, a standardized container and a ground grid; the scheduling module is used for decomposing the inspection task into a plurality of inspection AMRs and planning the running route of the inspection AMRs.

Preferably, the motor assembly includes a first motor for driving the telescopic support frame 3 and a second motor for driving the camera assembly.

Preferably, the telescopic support frame comprises a frame body, a telescopic bracket and a first transmission device, wherein the first transmission device is connected with the first motor, and the first transmission device is also connected with the telescopic bracket; the telescopic bracket is arranged on the frame body, and the frame body is arranged on the AMR; the camera assembly comprises a camera and a second transmission device, and the second transmission device is respectively connected with the second motor and the camera.

Preferably, the standardized container is placed on the goods shelf, a first two-dimensional code is arranged on the standardized container, a second two-dimensional code is arranged on the goods shelf, and a third two-dimensional code is arranged on the ground grid.

Compared with the prior art, the method and the device provided by the invention have the following beneficial effects:

the camera capable of moving up and down can shoot the two-dimensional code on the side surface of the standardized container so as to acquire the related information of the goods. Standardized bins may be stacked on shelves and the camera may read one layer of bin information at a time. Every two rows of shelves are a group, the inspection device makes a circle, and the inspection task of the goods on one layer of the two rows of shelves can be completed. And after the height of the camera is adjusted, the cargo box information of other layers can be read. Aiming at a multi-AMR inspection scene, the scheduling module solves a feasible AMR scheduling scheme set based on an DQN algorithm, selects a scheme which can meet the minimum time, and improves the AMR utilization rate as much as possible. The invention can enable the inspection of the warehouse goods to be automatic, help other links in the supply chain to know the goods state, and make corresponding decisions and arrangements in time, thereby improving the response capability and cooperativity of the whole supply chain.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic side view of an automatic cargo inspection device according to a first embodiment of the present invention;

FIG. 2 is a schematic view showing a front view of a pallet and a standardized container according to a first embodiment of the present invention;

FIG. 3 is a top view of the warehouse;

fig. 4 is a flowchart of an automatic cargo inspection method according to a first embodiment of the present invention.

Reference numerals:

AMR1, data transmission device 2, scalable braced frame 3, flexible area 4, first motor 5, second motor 6, camera 7, goods shelves 8, standardized packing box 9, first two-dimensional code 10, second two-dimensional code 11 and third two-dimensional code 12 are patrolled and examined.

Detailed Description

The above and further technical features and advantages of the present invention are described in more detail below with reference to the accompanying drawings.

In the description of the present invention, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" is at least two unless explicitly defined otherwise.

In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; may be mechanically connected, may be electrically connected or may be in communication with each other; either directly or indirectly, through intermediaries, or both, may be in communication with each other or in interaction with each other, unless expressly defined otherwise. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention.

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

In order to illustrate the technical scheme of the invention, the following description is made by specific examples.

Example 1

As shown in fig. 1 to 3, the invention provides an automatic cargo inspection device, which comprises an inspection module, a warehouse matching module and a dispatching module.

The inspection module comprises an inspection AMR1 (autonomous mobile robot), a data transmission device 2, a telescopic support frame 3, a camera assembly and a motor assembly.

The inspection AMR1 is provided with a telescopic supporting frame 3, and the inspection AMR1 is connected with the data transmission device 2. The data transmission device 2 is also connected with the motor assembly for controlling the motor assembly.

The motor assembly comprises a first motor 5 and a second motor 6. The first motor 5 is used to drive the telescopic support frame 3. The second motor 6 is used to drive the camera assembly.

The telescopic support frame 3 comprises a frame body, a telescopic bracket and a first transmission. The first transmission device is connected with the first motor 5, and the first transmission device is also connected with the telescopic bracket. The telescopic bracket is arranged on the frame body, and the frame body is arranged on the inspection AMR1. The first motor 5 adjusts the height and posture of the telescopic bracket by driving the first transmission device, and can also directly or indirectly adjust the height and posture of the camera 7. Preferably, the first transmission is a chain.

In addition, when an obstacle exists at the high position of certain positions of the corridor, the data transmission device 2 obtains the obstacle position and then drives the first motor 5 to adjust the height and the posture of the telescopic support frame 3 so as to avoid touching the obstacle.

The camera assembly is connected with the telescopic bracket. Movement of the telescopic support can drive movement of the camera assembly. The camera assembly comprises a camera 7 and a second actuator. The second transmission device is respectively connected with the second motor 6 and the camera 7. The second motor 6 enables the camera 7 to move up and down by driving the second transmission. Preferably, the second transmission means is a telescopic belt 4.

The camera 7 is used to capture and identify two-dimensional code information on the shelves and standardized containers.

Preferably, the first motor 5 is provided at a side of the telescopic support frame 3. The first motor 5 is used to adjust the telescoping of the support frame.

Preferably, the second motor 6 is provided at the bottom of the telescopic support frame 3. The second motor 6 can control the up and down movement of the camera 7 to accommodate different levels of shelves.

Preferably, the telescopic support frame 3 is located right above the inspection AMR1, and the telescopic support frame 3 is telescopic, which is used to avoid high obstacles in the warehouse.

Preferably, the patrol AMR is preferably embedded AMR, and the duration is 6 to 8 hours. The patrol AMR1 can acquire its current position in the warehouse by identifying the identifier embedded on the floor grid. The patrol AMR1 can adjust its own orientation and position.

Preferably, the data transmission device is installed on the inspection AMR1, and is abutted against the telescopic supporting frame 3, and is used for driving the motor assembly and sending information shot by the camera, and receiving task requirements sent by the dispatching system.

The warehouse module comprises shelves 8, standardized containers 9 and floor grids.

The standardized container 9 is placed on a shelf 8, and a second two-dimensional code 11 is arranged on the shelf 8. The second two-dimensional code 11 records the shelf identification and the position information, and the specifications of the stored standardized cargo box. The standardized container 9 is also provided with a first two-dimensional code 10. The first two-dimensional code 10 includes information about the goods. The shelves and standardized containers are the target objects that the inspection device needs to identify and process. The ground is divided into a goods shelf area and a corridor area, the corridor area is provided with a ground grid, and a third two-dimensional code 12 is attached to the center of the ground grid. The third two-dimensional code 12 is used for guiding the movement path of the patrol AMR1. The two-dimensional code in the ground grid can be read by a bottom camera of the AMR1, so that accurate positioning and navigation are realized. The patrol AMR1 can precisely adjust the advancing direction and distance by using the third two-dimensional code 12 on the ground grid identified by itself.

Preferably, the second two-dimensional code 11 is provided on a side of the shelf 8. The first two-dimensional code 10 is arranged outside the standardized container 9. The ground grid is a square grid. The racks 8 are used to store standardized containers 9, and the racks 8 can be stacked up to 3 floors. At most 2 standardized containers are placed in each column in each layer of the goods shelf, and 3 layers of standardized containers can be placed on one goods shelf. The second two-dimensional code 11 is attached to the pillar of the shelf 8.

Preferably, the standardized containers have several gauges, each gauge having fixed length, width and height parameters. Containers of different sizes are stored on different shelves. The standardized container is used for storing finished goods, is placed on the goods shelf 8, and is externally stuck with a two-dimensional code containing goods information at a fixed height.

The scheduling module is used for decomposing the patrol task to a plurality of patrol AMR1 and planning the running route of the patrol AMR1.

The patrol AMR1 is the core of the device, which is capable of autonomous movement and performing patrol tasks. Other components are mounted on the patrol AMR1, and path planning and obstacle avoidance are performed through an autonomous navigation system.

The camera 7 is used for shooting two-dimensional codes on the goods shelves and standardized containers. The position of the camera 7 can be adjusted according to the task.

The data transmission device 2 is used for data exchange and communication with other systems. Through the data transmission device, the automatic cargo inspection device can receive task instructions, send inspection data and the like.

Preferably, according to the automatic cargo inspection device of the present invention, the steering accuracy of the inspection AMR1 is within ±10mm, and the stopping accuracy is within ±20 mm.

Preferably, the standardized containers are placed in at most 3 layers, each layer has at most two rows, and each row has at most 5.

Preferably, the pasting precision of the first two-dimensional code 10 on the standardized container 9 is within +/-5 mm.

Preferably, the telescoping accuracy of the telescoping support frame is within ±30 mm.

Preferably, the accuracy of the camera 7 on the telescopic support frame 3 is within ±2 mm.

The working process of the automatic cargo inspection device in the embodiment is as follows:

the automatic cargo inspection device starts to operate, and the scheduling module sends out an inventory task instruction. These task instructions include coordinates of the start and end positions, and the shelf levels (e.g., 1, 2, 3 levels) that need to be checked.

The data transmission device 2 determines the moving height of the camera 7 according to these task instructions to ensure that the camera can accurately shoot the required shelf information.

The data transmission device 2 further transmits an instruction to the autonomous mobile robot (inspection AMR 1), and when the inspection AMR1 reaches a specified position, the data transmission device 2 adjusts the height of the camera by driving the motor assembly. Thus, the camera can start shooting tasks.

In the whole inspection shooting process, the inspection AMR1 performs navigation and positioning according to the information of the third two-dimensional code 12 on the ground grid. At the same time, the camera 7 starts shooting two-dimensional code information on the shelves 8 and standardized boxes 9. The two-dimensional codes contain relevant information of goods, such as product codes, batch information and the like.

Once the automatic cargo inspection device completes the scanning task on the bottommost layer, the motor assembly is started, and the camera 7 is adjusted to a height suitable for the next work to continue the shooting work. The camera starts to capture the two-dimensional code on the second-layer shelf and recognize and record the two-dimensional code.

The data transmission device 2 is used for collecting and collating data shot by the camera. The data transmission device 2 can determine the goods information of each shelf by performing processing such as de-duplication and debug on the scanned data, and generate an inventory result.

Finally, the data transmission device 2 returns the inventory result to the scheduling module for viewing and processing by warehouse management personnel. The AMR-based automatic warehouse cargo inspection device realizes an automatic cargo checking process, improves the efficiency and reduces the occurrence of human errors. Meanwhile, due to the adoption of the telescopic supporting frame and the camera navigation system, the device can be suitable for various complex scenes, and brings convenience and accuracy to warehouse management.

As shown in fig. 4, the present invention further provides an automatic cargo inspection method, which includes the steps of:

step S1, a scheduling module generates a patrol task instruction and sends the patrol task instruction to a data transmission device 2;

step S2, the data transmission device 2 sends a control instruction to the inspection AMR1, and the data transmission device 2 determines the moving height of the camera 7 according to the number of shelf layers in the inspection task;

s3, starting the inspection AMR1 to go to a designated position, starting the ground grid positioning by the inspection AMR1 to determine whether the designated position is reached, and then enabling the inspection AMR1 to reach a designated position area;

s4, the data transmission device 2 controls the motor assembly to act, and the motor assembly adjusts the height of the telescopic support frame and the height of the camera;

s5, the camera 7 starts shooting, and the patrol AMR1 starts moving according to patrol path information in patrol task instructions and two-dimensional code information on a ground grid;

s6, executing the same-area same-layer priority inspection strategy;

step S7, after the scanning of the standardized containers on the same layer is finished, starting the motor assembly and adjusting the camera 7 to the height of the next layer so as to continue shooting and inspection;

s8, if all the shelves in the current area are scanned, the AMR1 is moved to another area, and the scanning is continuously started;

and step S9, repeating the steps S5 to S8 until the shelves and standardized containers in all areas are scanned.

Preferably, step S10 is continued after step S9 is performed.

In step S10, the data transmission device 2 processes the scan data from the camera 7 and returns the processed scan data to the scheduling module.

The processing of the scanning data is to process the goods data of the corresponding goods shelf, including the operations of de-duplication, debugging and the like.

The scheduling module needs to perform first scheduling, the first scheduling needs to determine the time required for finishing inspection according to a collision-free path on the premise that all shelves are full according to the number of the existing shelves in the warehouse, and the allowance time brought by interference factors is added to generate first time constraint.

In the process of executing the patrol task by the patrol AMR1, the scheduling module generates a new constraint and scheduling scheme according to the information from the patrol AMR1, and then re-executes step S1. The scheduling module converts the new scheduling scheme into a patrol task instruction and synchronizes the patrol task instruction to each patrol AMR1. The scheduling scheme designates the starting point, the routes of each stage and the ending point of each inspection AMR1 operation and the shelf layer to be checked. The patrol AMR1 then performs a new task according to the new scheduling scheme.

In order to cope with the conflict of the trolley, reasonable allowance time is set, and a scheduling module adopts a scheduling strategy of waiting for conflict points under a multi-AMR system. In order to simulate the additional working time of AMR passing through the conflict point, an Ellang distribution model is adopted, and the probability of conflict in the process of inspecting n shelves is assumed to be beta. The preset conflict allowance time formula is: t0=β×n×m×y, where m is the number of collision points passed by the patrol AMR1, and y is the average value of the additional working time.

Because some shelves are empty, part of the AMR1 inspection speed is higher, if the AMR1 inspection speed is completely according to an initial scheme, the AMR inspection speed is idle, and the like, therefore, the constraint condition is modified and updated according to time constraint, and a model is solved again, and a scheduling scheme with high AMR inspection utilization rate and minimum inspection time is selected as a new scheduling scheme.

And the scheduling module uses a DQN algorithm to carry out recursion solution according to constraint conditions such as the inspection time of goods in each warehouse, the quantity of the inspected AMR1 and the like, so as to obtain a feasible scheduling scheme to meet the constraint conditions.

Specifically, for the DQN algorithm, Q (s _t ,a _t ) Based on the bellman equation, the maximum Q value for the next state is added to the current prize to update the Q value for the current state. By continuously and iteratively updating the Q value table, the intelligent agent gradually learns the optimal behavior strategy, thereby obtaining the maximum benefit in a complex environment. Q(s) _t ,a _t ) The calculation method is as follows:

wherein r is _t Representing instant rewards at time t, r when the target is reached _t 50, case r of collision or timeout _t Is in the form of-10 a,is represented in the current state s _t And action a _t Transition to state s with determination _t+1 Is a function of the probability of (1),represented in state s _t+1 The maximum prize value that can be obtained by taking different actions. Gamma is a discount factor representing the extent to which future rewards affect the current actions of the mobile robot. Q(s) _t ,a _t ) The updated formula of (c) is given by,

wherein, alpha is learning rate, and the value range is alpha epsilon [0,1]; gamma is a discount factor representing the extent to which future rewards affect the current actions of the mobile robot.

The instant rewarding function is an important part of the path planning based on reinforcement learning, and the setting quality of the instant rewarding function can directly influence the effect of patrol planning and the convergence condition of the network. In the reward function of the traditional DQN algorithm, the patrol AMR1 can acquire a reward value except when reaching a target point and programming fails, and can not acquire instant and effective feedback in other states. Although it isThe patrol AMR1 can still plan the path sought by training, but this process typically requires a large number of rounds and the planned path is often not optimal. Thus, the present invention redesigns the bonus function. The reward obtained when the patrol AMR1 reaches the target point is C1, the reward obtained when the patrol AMR1 collides is C2, and the reward obtained by the robot under other conditions is K.times.cos theta/d. Wherein K is an superparameter, θ is an included angle between a vector n1 pointing from the AMR position to the target point position before the AMR acts and a direction vector n2 before and after the robot acts, and d is a distance between the AMR position and the target point position.The larger the indication direction deviation from the target point, the smaller the reward; the farther from the target point, the smaller the reward.

In step S6, the same-area same-layer priority inspection strategy includes:

step S60, if the standardized container 9 to be inspected is reserved on the shelf in the same area and on the same layer, the AMR1 is inspected to inspect the shelf in the same area preferentially without adjusting the height of the camera;

in step S61, if the standardized containers on the same floor are scanned, but there are other shelves on the same floor, the inspection AMR1 winds around another row to continue inspecting the shelf on the floor.

The automatic cargo inspection method and device provided by the invention have the beneficial effects that:

the camera 7 is mounted on a support frame and is movable up and down. The camera 7 is used for shooting two-dimensional codes on the side surface of the standardized cargo box so as to acquire relevant information of cargoes. Standardized containers 9 can be stacked on the goods shelves 8, and the camera can read container information of one layer after one travel; every two rows of shelves are a group, and the inspection device makes a circle, so that the inspection task of one-layer goods of the two rows of shelves can be completed; the container information of other layers can be read after the height of the camera is adjusted; aiming at a multi-AMR inspection scene, the scheduling module solves a feasible AMR scheduling scheme set based on an DQN algorithm, selects a scheme which can meet the minimum time, and improves the AMR utilization rate as much as possible. The invention can enable the inspection of the warehouse goods to be automatic, help other links in the supply chain to know the goods state, and make corresponding decisions and arrangements in time, thereby improving the response capability and cooperativity of the whole supply chain.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims (10)

1. An automatic cargo inspection method is characterized by comprising the following steps:

step S1, a scheduling module generates a patrol task instruction and sends the patrol task instruction to a data transmission device;

s2, the data transmission device sends a control instruction to the AMR, and the data transmission device determines the moving height of the camera according to the number of shelf layers in the inspection task;

s3, starting the AMR to go to the appointed position, starting the ground grid positioning by the AMR to determine whether the AMR reaches the appointed position, and then, enabling the AMR to reach the appointed position area;

s4, the data transmission device controls the motor assembly to act, and the motor assembly adjusts the height of the telescopic support frame and the height of the camera;

s5, shooting by a camera, and enabling the routing inspection AMR to start moving according to routing inspection path information in routing inspection task instructions and two-dimensional code information on a ground grid;

s6, executing the same-area same-layer priority inspection strategy;

step S7, after the scanning of the standardized containers on the same layer is finished, starting the motor assembly and adjusting the camera to the height of the next layer so as to continue shooting and inspection;

s8, if all the shelves in the current area are scanned, the AMR is moved to another area, and the scanning is continuously started;

and step S9, repeating the steps S5 to S8 until the shelves and standardized containers in all areas are scanned.

2. The method according to claim 1, wherein the scheduling module generates new constraint and scheduling scheme based on information from the inspection AMR during the execution of the inspection task by the inspection AMR, and then re-executes step S1.

3. An automated cargo inspection method according to claim 2, wherein the scheduling module recursively solves using a DQN algorithm to obtain a viable scheduling scheme, Q (s _t ,a _t ) The calculation method is as follows:

wherein r is _t Representing instant rewards at time t, r when the target is reached _t 50, case r of collision or timeout _t Is in the form of-10 a,is represented in the current state s _t And action a _t Transition to state s with determination _t+1 Is a function of the probability of (1),represented in state s _t+1 When different actions are adopted, the maximum reward value obtained is adopted, gamma is a discount factor and represents future rewards to patrol AMR current actionsThe degree of influence; q(s) _t ,a _t ) The updated formula of (2) is:

wherein, alpha is learning rate, and the value range is alpha epsilon [0,1]; gamma is a discount factor and represents the influence degree of future rewards on the current action of the AMR patrol.

4. An automatic cargo inspection method according to claim 3, wherein the scheduling module gives an instantaneous prize function to the inspection AMR of:

when the patrol AMR reaches the target point, the instant rewarding function value is C1, when the patrol AMR collides, the instant rewarding function value is C2, and under other conditions, the instant rewarding function value is K x cos theta/d, wherein K is an hyper-parameter, theta is an included angle between a vector n1 pointing to the target point position from the position of the patrol AMR before the patrol AMR acts and a direction vector n2 before and after the patrol AMR acts, and d is a distance between the position of the patrol AMR and the target point position.

5. The automatic cargo inspection method according to claim 1, wherein the scheduling module adopts a scheduling strategy for waiting for a conflict point under a multi-AMR system, the scheduling strategy is to simulate additional operation time for the inspection AMR to pass through the conflict point, an ellang distribution model is adopted, and a collision probability is assumed to be β in the process of inspecting n shelves, and a collision allowance time formula is preset as follows: t0=β×n×m×y, where m is the number of collision points passed by the patrol AMR and y is the average of the additional working time.

6. An automatic cargo inspection device, characterized in that it is used for executing an automatic cargo inspection method according to any one of claims 1-5, and comprises an inspection module, a warehouse matching module and a dispatching module.

7. The automatic cargo inspection device according to claim 6, wherein the inspection module comprises an inspection AMR, a data transmission device, a telescopic support frame, a camera assembly and a motor assembly, the inspection AMR is provided with the telescopic support frame, the inspection AMR is connected with the data transmission device, and the data transmission device is further connected with the motor assembly for controlling the motor assembly; the telescopic support frame is connected with the camera component; the storage module comprises a goods shelf, a standardized container and a ground grid; the scheduling module is used for decomposing the inspection task into a plurality of inspection AMRs and planning the running route of the inspection AMRs.

8. The automated cargo inspection device of claim 7, wherein the motor assembly comprises a first motor for driving the telescoping support frame 3 and a second motor for driving the camera assembly.

9. The automated cargo inspection device of claim 8, wherein the telescoping support frame comprises a frame body, a telescoping support, and a first transmission, the first transmission coupled to the first motor, the first transmission further coupled to the telescoping support; the telescopic bracket is arranged on the frame body, and the frame body is arranged on the AMR; the camera assembly comprises a camera and a second transmission device, and the second transmission device is respectively connected with the second motor and the camera.

10. The automated cargo inspection device of claim 7, wherein the standardized container is placed on the shelf, a first two-dimensional code is provided on the standardized container, a second two-dimensional code is provided on the shelf, and a third two-dimensional code is provided on the ground grid.