Clamping object storage method, storage system and storage device

Abstract

The invention relates to the technical field of smart home, and discloses a clamped object storage method, storage system and storage device. The method comprises the steps that the size of an object to be stored, the space size of a storage area and the relative position of the object to be stored and the storage area are obtained; the relative position of the to-be-stored object and the storage area is judged, and a first result is obtained; comparing the size of the object to be stored with the space size of the storage area to obtain a second result; and fusing the first result and the second result, and outputting a storage instruction for the intelligent storage equipment based on the fused result. The storage in-place rate and the success rate are improved, the equipment adaptability is enhanced, meanwhile, damage to clamped objects and equipment is avoided, and the use safety is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart home, in particular to a clamping object storage method, a storage system and a storage device. BACKGROUND

[0002] With the rapid development of smart home and industrial automation technology, automated storage equipment is increasingly widely used in fields such as home, warehousing, and logistics. Such equipment realizes automatic grabbing, carrying, and storage of various objects through the coordinated action of mechanical arms and clamps, effectively improving storage efficiency and reducing labor costs, meeting people's demand for efficient and convenient life and production methods. In the actual operation process of automated storage equipment, the form, size, and material of the objects to be stored vary significantly. For example, socks, towels, and paperboard have different sizes, softness, and structural characteristics, which puts high requirements on the adaptability and storage accuracy of the equipment. Currently, existing automated storage technology generally has the following technical pain points when dealing with different types of clamping objects: 1. For flexible and deformable objects (such as socks and towels), existing technology often directly grabs a part of the object to move it. If the size of the object (such as length or area) exceeds the opening size of the storage space, the object may be stuck or partially exposed outside the storage area during placement, resulting in storage failure. Although theoretically, the object can be folded, existing systems lack a complete technical solution for actively and intelligently folding the object online before the "grabbing-placing" process. How to guide the mechanical arm to complete a series of complex operations such as "recognition-grabbing-folding-reconfirmation" through the coordination of vision and force feedback is a technical bottleneck for realizing automated storage.

[0003] 2. For the relevance of grabbing posture and placing posture: existing technology usually considers grabbing and placing of objects as two relatively independent steps. The system may be able to successfully grab the object, but the position and direction of grabbing (for example, grabbing one end of a long stick) may cause the object to present a high height or an unfavorable posture when moving above the storage area, making it difficult to place it in the limited vertical space. Existing systems lack a closed-loop mechanism for real-time judgment and dynamic adjustment of the "feasibility of placing the object in the current grabbing state" before placing. When it is judged as unfeasible, the system cannot autonomously decide whether to change the grabbing point, fold, or adjust the object's direction, resulting in interruption or failure of the operation process.

[0004] 3. Insufficient fault tolerance for storage results: After the article is placed in the storage area, it is often found that the article does not completely enter the storage area due to the flexibility, collision or position deviation of the article (for example, part of it is still on the edge of the storage box). The existing technology mostly considers that "loosening the clamping jaw" means that the task is completed, and lacks the ability to check and remedy the final state of the storage result. This leads to low reliability and neatness of storage.

[0005] In summary, the existing automatic storage system has obvious shortcomings in intelligence, adaptability and robustness in processing, and cannot flexibly adopt strategies such as "folding first and then placing" or "adjusting the posture and then placing" when facing size-mismatched articles. It also lacks fault tolerance capability for "final correction" when the task is close to completion. SUMMARY

[0006] The purpose of the present application is to overcome the technical shortcomings of the existing automatic storage equipment in the size adaptation preprocessing of clamped objects and the storage in-place rate guarantee, which makes it difficult to meet the efficient and accurate storage needs of diversified clamped objects. The present application provides a clamped object storage method, a storage system and a storage device. The present application improves the storage in-place rate and success rate, enhances the adaptability of the equipment, and at the same time, avoids damage to the clamped object and the equipment, and ensures the safety of use.

[0007] To achieve the above purpose, the first aspect of the present application provides a clamped object storage method, which is applied to an intelligent storage device. The method comprises: obtaining the size of the object to be stored, the space size of the storage area, and the relative position of the object to be stored and the storage area; judging the relative position of the object to be stored and the storage area to obtain a first result; comparing the size of the object to be stored with the space size of the storage area to obtain a second result; fusing the first result and the second result, and outputting a storage instruction for the intelligent storage device based on the fused result.

[0008] Preferably, the camera of the intelligent storage device recognizes the object to be stored and the storage area.

[0009] Preferably, the camera is a binocular camera.

[0010] Preferably, the first result includes any of the following: the object to be stored has been stored completely; the object to be stored has not been stored; the object to be stored has not completely entered the storage area.

[0011] Preferably, the second result includes any of the following: The dimensions of the items to be stored must meet the storage requirements of the storage area. The dimension of the item to be stored in one direction is greater than or equal to the dimension of the storage area; The area of ​​the item to be stored is larger than the size of the storage area and is flat; The item to be stored must be larger than the storage area and be non-woven, non-foldable, and not clampable in the center.

[0012] Preferably, the first result and the second result are fused, and a storage instruction for the smart storage device is output based on the fused result, including: For items that are not yet stored but whose size meets the storage conditions of the storage area, the robotic arm controlling the intelligent storage adjusts the gripper to pick up the items and adjusts it to the placement posture, and then places the items into the storage area.

[0013] Preferably, the method further includes fusing the first result and the second result, and outputting a storage instruction for the smart storage device based on the fused result, and also includes: If an item to be stored is not stored and its dimension in one direction is larger than the storage area, it is determined that it needs to be folded. The robotic arm controlling the smart storage device adjusts the gripper to hold one end of the item to be stored, and uses a force sensor to determine whether the gripping was successful: if the gripping fails, it tries again; if the gripping is successful, it adjusts the posture of the robotic arm so that the gripper reaches the other end of the item to be stored in preparation for folding the item. After the camera recognizes that the gripper has reached the other end of the item to be stored, it controls the gripper to release, and uses a force sensor to determine whether the release was successful: if the release fails, it tries to release again; if the release is successful, it re-acquires the size of the item to be stored and the second result; if the second result is not "the size of the item to be stored meets the storage conditions of the storage area", it is determined that it needs to be folded; if the second result is "the size of the item to be stored meets the storage conditions of the storage area", it controls the robotic arm to adjust the gripper to grasp the folded surface of the item to be stored and adjust it to the placement posture, and determines whether the current height of the item to be stored meets the placement height; if the height meets the height, the item to be stored is placed in the storage area; if the height does not meet the height, the gripper's gripping direction is adjusted or it is folded again.

[0014] Preferably, the method further includes fusing the first result and the second result, and outputting a storage instruction for the smart storage device based on the fused result, and also includes: For items that are not stored, have an area larger than the storage area, and are flat, determine the center of the item to be clamped. The robotic arm controlling the intelligent storage adjusts the gripper to hold the center of the item to be stored, and uses a force sensor to determine whether the gripping was successful: if the gripping fails, it tries again; if the gripping is successful, it adjusts the robotic arm to the placement position. Determine if the current height of the item to be stored meets the placement height requirement: if the height does not meet the requirement, the item needs to be folded; if the height meets the requirement, the item is placed in the storage area.

[0015] Preferably, the method further includes fusing the first result and the second result, and outputting a storage instruction for the smart storage device based on the fused result, and also includes: For items that are not stored, are non-woven, cannot be folded, and cannot be clamped in the center, determine which end of the item to be stored should be clamped. The robotic arm controlling the intelligent storage adjusts the gripper to hold one end of the item to be stored, and uses a force sensor to determine whether the gripping was successful: if the gripping fails, it tries again; if the gripping is successful, it adjusts the robotic arm to the placement position. Determine if the current height of the item to be stored meets the placement height requirement: if the height meets the requirement, place the item into the storage area; if the height does not meet the requirement, control the grippers to release the item. The force sensor determines whether the release was successful: if the release fails, it is attempted again; if the release is successful, the robotic arm of the intelligent storage system is controlled to adjust the gripper to hold the other end of the item to be stored. The force sensor determines whether the gripping was successful: if the gripping fails, it is tried again; if the gripping is successful, the robotic arm is adjusted to the placement position. Determine if the current height of the item to be stored meets the placement height requirement: If the height meets the requirement, place the item into the storage area; if the height does not meet the requirement, continue to adjust the grippers to hold the item in different directions until the placement height is met.

[0016] Preferably, the method further includes verifying the state after storage: if the item to be stored is completely inside the storage area, the storage operation is completed; otherwise, it is determined that the gripper push-in operation is performed, the robotic arm is controlled to adjust its posture to move the gripper directly below the item to be stored and retract it, the robotic arm is controlled to adjust its posture upward and push the item to be stored into the storage area through the gripper. When the gripper is aligned with the highest point of the storage area, the camera identifies whether the item to be stored has completely entered the storage area: if so, the storage operation is complete; otherwise, the gripper push-in operation is repeated.

[0017] A second aspect of the present invention provides a clamping object storage system for performing the above-described clamping object storage method.

[0018] A third aspect of the present invention provides a clamping object storage device for performing the above-described clamping object storage method, or the clamping object storage device includes the above-described clamping object storage system.

[0019] According to the above technical solution, this invention enables robots to intelligently select the optimal pre-storage processing strategy based on the actual situation (size, shape) of the items, just like humans, through visual perception and logical judgment, greatly improving the system's versatility and intelligence. A force sensor is introduced to confirm the gripping and releasing actions, and combined with a visual verification and adjustment mechanism after storage, a complete "perception-decision-execution-verification-correction" closed loop is formed, significantly improving the success rate and reliability of the entire storage task. Simultaneously, differentiated processing procedures are designed for different types of items (flexible long objects, flat objects, and hard objects), enabling the robot to cope with various complex storage scenarios and breaking through the limitation of existing technologies that only handle a single type of object. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating a method for storing clamped objects according to one embodiment of the present invention. Figure 2 This is a logical schematic diagram of a clamping object storage method according to one embodiment of the present invention. Detailed Implementation

[0021] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0022] In this invention, unless otherwise stated, directional terms such as "up," "down," "left," and "right" included in the terminology represent the orientation of the term in its normal use or are common terms understood by those skilled in the art, and should not be regarded as limitations on the term.

[0023] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0024] First, this invention provides a method for storing clamped objects, which is applied to intelligent storage devices, such as robot vacuum cleaners. Specifically, as... Figure 1 As shown, the method includes: Obtain the dimensions of the item to be stored, the size of the storage area, and the relative position of the item to be stored to the storage area; Determine the relative position of the items to be stored and the storage area to obtain the initial result; Compare the dimensions of the items to be stored with the size of the storage area to obtain a second result; The first and second results are merged, and storage instructions for the smart storage device are output based on the merged result.

[0025] In this embodiment, to achieve precise, automated, and intelligent storage operations, preferably, the intelligent storage device uses a camera to identify the items to be stored and the storage area. Through image recognition via the camera, the intelligent storage device can determine the specific location (X, Y coordinates) of the items within the camera's field of view and identify the category of the items. This is crucial for subsequent decision-making, as different items require different gripping strategies. For example, the opening range and gripping force of the grippers are completely different when gripping a book and a ball. The camera's recognition of shape and size guides the robotic arm to select the optimal gripping point and control the optimal gripping force to prevent damage to the items. Simultaneously, the camera can capture the posture of the items—whether they are upright, lying down, or tilted—and then adopt different gripping methods accordingly. Such accurate posture estimation ensures that the grippers approach and grasp at the correct angle, avoiding slippage or failure and improving the success rate of gripping. While identifying the items to be stored, the storage area is also identified and located. Through positioning and spatial perception, combined with navigation and path planning, precise placement of the items to be stored is achieved.

[0026] Furthermore, in this field, monocular cameras can only provide two-dimensional planar images (X-axis and Y-axis), showing where objects are located but struggling to accurately determine their distance from the camera (Z-axis). Binocular cameras, by mimicking the parallax principle of the human eye, can calculate the depth information of each pixel, generating depth maps or point cloud data to reconstruct a three-dimensional scene. Based on this three-dimensional scene, precise 3D positioning of the object can be achieved, enabling more reliable object recognition and segmentation, as well as accurate pose estimation. Simultaneously, for the storage area, binocular cameras can deepen the understanding of the three-dimensional spatial structure, optimize obstacle avoidance and path planning, and achieve more accurate placement feasibility assessments. Therefore, in this embodiment, binocular cameras are preferred.

[0027] Specifically, in one implementation, the first result includes any of the following: The items to be stored have been stored. Items awaiting storage have not been stored. The item to be stored has not fully entered the storage area. The second result includes any of the following: The dimensions of the items to be stored must meet the storage requirements of the storage area. The dimension of the item to be stored in one direction is greater than or equal to the dimension of the storage area; The area of ​​the item to be stored is larger than the size of the storage area and is flat; The item to be stored must be larger than the storage area and be non-woven, non-foldable, and not clampable in the center.

[0028] The first and second results are then merged, and based on the merged result, storage instructions are output to the smart storage device for specific operational control, including the following storage scenarios (see...). Figure 2 ): In the first scenario, if the item to be stored is not yet stored but its size meets the storage requirements of the storage area, the robotic arm controlling the intelligent storage adjusts the gripper to pick up the item and adjusts it to the placement position, then places the item into the storage area.

[0029] In the second scenario, if the item to be stored is not stored and its size in one direction is larger than the size of the storage area, it is determined that it needs to be folded. The robotic arm controlling the smart storage device adjusts the gripper to hold one end of the item to be stored, and uses a force sensor to determine whether the gripping was successful. If the gripping fails, it tries again. If the gripping is successful, the robotic arm posture is adjusted so that the gripper reaches the other end of the item to be stored in preparation for folding the item. After the camera recognizes that the gripper has reached the other end of the item to be stored, it controls the gripper to release, and uses a force sensor to determine whether the release was successful: if the release fails, it tries to release again; if the release is successful, it re-acquires the size of the item to be stored and the second result; if the second result is not "the size of the item to be stored meets the storage conditions of the storage area", it is determined that it needs to be folded; if the second result is "the size of the item to be stored meets the storage conditions of the storage area", it controls the robotic arm to adjust the gripper to grasp the folded surface of the item to be stored and adjust it to the placement posture, and determines whether the current height of the item to be stored meets the placement height; if the height meets the height, the item to be stored is placed in the storage area; if the height does not meet the height, the gripper's gripping direction is adjusted or it is folded again.

[0030] In the third case, for items that are not stored, have an area larger than the storage area, and are flat, the center of the item to be stored is determined. The robotic arm controlling the intelligent storage adjusts the gripper to hold the center of the item to be stored, and uses a force sensor to determine whether the gripping was successful: if the gripping fails, it tries again; if the gripping is successful, it adjusts the robotic arm to the placement position. Determine if the current height of the item to be stored meets the placement height requirement: if the height does not meet the requirement, the item needs to be folded; if the height meets the requirement, the item is placed in the storage area.

[0031] In the fourth case, for items that are not stored and are non-woven, cannot be folded, and cannot be clamped in the center, it is determined that one end of the item to be stored should be clamped. The robotic arm controlling the intelligent storage adjusts the gripper to hold one end of the item to be stored, and uses a force sensor to determine whether the gripping was successful: if the gripping fails, it tries again; if the gripping is successful, it adjusts the robotic arm to the placement position. Determine if the current height of the item to be stored meets the placement height requirement: if the height meets the requirement, place the item into the storage area; if the height does not meet the requirement, control the grippers to release the item. The force sensor determines whether the release was successful: if the release fails, it is attempted again; if the release is successful, the robotic arm of the intelligent storage system is controlled to adjust the gripper to hold the other end of the item to be stored. The force sensor determines whether the gripping was successful: if the gripping fails, it is tried again; if the gripping is successful, the robotic arm is adjusted to the placement position. Determine if the current height of the item to be stored meets the placement height requirement: If the height meets the requirement, place the item into the storage area; if the height does not meet the requirement, continue to adjust the grippers to hold the item in different directions until the placement height is met.

[0032] Furthermore, in this embodiment, the method also includes verifying the state after storage: if the item to be stored is completely inside the storage area, the storage operation is completed; otherwise, it is determined that a gripper push-in operation is to be performed, the robotic arm is controlled to adjust its posture to move the gripper directly below the item to be stored and retract it, the robotic arm is controlled to adjust its posture upward and push the item to be stored into the storage area through the gripper. When the gripper is aligned with the highest point of the storage area, the camera identifies whether the item to be stored has completely entered the storage area: if so, the storage operation is complete; otherwise, the gripper push-in operation is repeated.

[0033] In actual operation, such as Figure 1 As shown, this logic diagram fully illustrates the workflow of the present invention, which is mainly divided into two stages: 1. Adaptive processing before storage Starting with identifying the item, the first step is to determine whether its size requires processing.

[0034] If processing is required, three different processing strategy sub-processes are initiated based on the item type (flexible long and narrow objects, large and flat objects, and rigid objects). All three strategy sub-processes use "whether the placement conditions are met" as the core judgment, forming a closed-loop decision-making process that ensures the item is adjusted to its optimal state before placement.

[0035] One-way folding strategy: Repeat the "fold-measure-judgment" process until the size meets the standard.

[0036] Center grabbing strategy: make a judgment once, and if the height is not met, switch to the collapse strategy.

[0037] Multi-directional attempt strategy: Repeat the process of "attempt to grab - judge height - change direction" until a grabbing posture that meets the conditions is found.

[0038] All strategies ultimately converge on the "prepare to insert the clamped item" step.

[0039] 2. Correction and adjustment after storage After the items are placed, the task does not end immediately. Instead, it enters a fault-tolerant closed loop of "verification-execution-re-verification." This means that the camera checks whether the items are completely inside the storage area. If not, an alignment process is initiated, and the check is repeated until the task is perfectly completed.

[0040] The following provides two specific embodiments to illustrate the technical solution of the present invention in detail: Example 1: Storing Socks First, the camera identifies the socks to be stored and measures their length as L. The host determines that L is greater than the storage area length threshold L_max; The host computer initiates a one-way folding strategy, controlling the robotic arm to grip one end of the sock with its gripper. The force sensor detects that the clamping force has reached the threshold, confirming successful gripping. The host computer plans a path and controls the robotic arm to move one end of the sock above the other end and then lower it to complete one fold. Once the gripper releases, the force sensor detects the disappearance of the force, confirming successful release. At this point, the camera measures again, and the length of the folded sock is approximately L' / 2; the host determines that L' is less than L_max, thus meeting the storage conditions; The host computer controls a robotic arm to grip the middle of a folded sock and move it above the storage box. Before placing it in, the host computer uses a camera to estimate the height of the sock currently being gripped. If it determines that the height is less than the height of the box, it will then proceed with the placement. After being placed inside, the camera detected that one corner of the sock was draped over the edge of the box and had not completely fallen in. At this point, the host immediately initiates the alignment and correction process: the control robotic arm moves the open gripper to below the overhang angle, then closes the gripper and gently lifts it upwards, pushing the sock completely into the box; Double-check until you are sure the storage is complete.

[0041] Example 2: Storing Cardboard First, the camera detects the cardboard and measures its dimensions; the host determines that its area is too large and cannot be folded (the camera can identify this as "non-woven fabric" through AI). The host computer initiates a multi-directional trial strategy to control the robotic arm to grip the long side of the cardboard; At this point, the main unit calculates that if the cardboard is placed in this position, its height will exceed the height of the storage box. Immediately, the host computer commands the robotic arm to release the cardboard and then re-grip the short side of the cardboard; The calculation was repeated, and the cardboard was still placed too high. The host computer then commanded the cardboard to change direction and try to clamp a corner to tilt the cardboard. Calculations showed that the projection height in the tilted position met the placement requirements; the host then controlled the robotic arm to successfully place the cardboard into the storage box in this position.

[0042] The above examples fully demonstrate the powerful adaptability and wide applicability of this method.

[0043] The present invention also provides a clamping object storage system for performing the above-described clamping object storage method. The clamping object storage system may include: The host is used to process data, execute decision-making logic, and send control commands. A dual-lens camera, connected to the main unit, is used to identify and locate items to be stored, and to measure their three-dimensional dimensions (area, height). The robotic arm, controlled by the host computer, can move within the working area; Grippers, mounted at the end of a robotic arm, are used to grasp and release items; Force sensors, integrated into the grippers, are used to detect the clamping force between the grippers and the object to determine whether the gripping or releasing action is successful.

[0044] The host is configured to perform the following steps: S1: Adaptive folding and posture adjustment before storage Identification and Judgment: The system uses a dual-lens camera to identify items to be stored and measures their dimensions. The measurements are compared to preset storage area size thresholds to determine whether the items need to be disposed of.

[0045] Decision-making and execution: Based on the size determination results, the host selects different processing strategies: A. One-way folding strategy (suitable for long, flexible materials such as socks): a. Control the robotic arm to grip one end of the item, and the force sensor confirms that the grip is tight; b. Control the robotic arm to move and transport the clamped end of the item to the vicinity of the other end, completing one fold; c. Release the gripper; the force sensor confirms the release. d. Measure the dimensions of the folded item again using the binocular camera; if the dimensions meet the requirements, proceed with the subsequent storage; if not, repeat the folding process.

[0046] B. Center-grabbing and judgment strategy (suitable for large, flat, flexible materials such as towels): a. Control the central area where the robotic arm directly grips the item; b. After successful gripping, simulate or calculate the projected height of the item in the current posture; c. Determine if the height is less than the opening height of the storage area; if so, proceed with storage directly; if not, trigger the folding strategy A mentioned above.

[0047] C. Multi-directional trial strategy (applicable to rigid, non-foldable materials such as cardboard): a. Control one end of the robotic arm that grips the item; b. Determine whether the placement height of the item exceeds the limit under the current clamping posture; c. If the height requirement is not met, release the item, change the clamping direction (e.g., clamp the other end or the other side), and clamp again, and re-evaluate the height; repeat this process until a clamping direction that meets the height requirement is found.

[0048] Final storage execution: For items processed through any of the above strategies, the host computer controls the robotic arm to transport them to the storage area and place them inside.

[0049] S2: Correction and adjustment after storage Storage status verification: After the gripper releases the item, the main unit again uses the binocular camera on the robotic arm to identify whether the item has completely entered the storage area.

[0050] Alignment execution: If the item is detected as not fully inserted (e.g., partially hanging), then: a. Control the robotic arm to adjust its posture and move the gripper directly below the suspended part of the object; b. Retract the gripper to position it below the item; c. Control the robotic arm to move upwards, using the grippers to "push" or "lift" the item into the storage area. During this process, an RGB-D camera can also be used to determine whether the grippers are aligned with the highest point of the storage area to confirm the completion of the action.

[0051] Loop verification: After alignment, verify the item status again until it is confirmed that it has completely entered the storage area.

[0052] Furthermore, the present invention also provides a clamping object storage device for performing the above-described clamping object storage method, or the clamping object storage device includes the above-described clamping object storage system. The basic structure, connection, and operation control method of the clamping object storage device are the same as or similar to the above-described clamping object storage system, and will not be described again here.

[0053] In summary, this invention, through visual perception and logical judgment, enables robots to intelligently select the optimal pre-processing strategy for storage based on the actual conditions (size, shape) of the items, much like humans do, greatly improving the system's versatility and intelligence. The introduction of force sensors to confirm gripping and releasing actions, combined with a post-storage visual verification and alignment mechanism, forms a complete "perception-decision-execution-verification-correction" closed loop, significantly improving the success rate and reliability of the entire storage task. Furthermore, differentiated processing procedures are designed for different types of items (flexible long objects, flat objects, and hard objects), enabling the robot to handle various complex storage scenarios and overcoming the limitations of existing technologies that only process a single type of object.

[0054] The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings; however, the present invention is not limited thereto. Within the scope of the inventive concept, various simple modifications can be made to the technical solutions of the present invention, including combinations of various specific technical features in any suitable manner. To avoid unnecessary repetition, the present invention will not describe the various possible combinations separately. However, these simple modifications and combinations should also be considered as the content disclosed in the present invention and are all within the protection scope of the present invention.

Claims

1. A method for storing clamped objects, characterized in that, The clamping and storage method is applied to intelligent storage devices, and the method includes: Obtain the dimensions of the item to be stored, the size of the storage area, and the relative position of the item to be stored to the storage area; The relative position of the item to be stored and the storage area is determined to obtain a first result; The dimensions of the item to be stored are compared with the size of the storage area to obtain a second result; The first result and the second result are fused together, and a storage instruction for the smart storage device is output based on the fused result.

2. The method for storing clamped objects according to claim 1, characterized in that, The camera of the smart storage device identifies the item to be stored and the storage area.

3. The method for storing clamped objects according to claim 2, characterized in that, The camera is a binocular camera.

4. The method for storing clamped objects according to claim 1, characterized in that, The first result includes any one of the following: The items to be stored have been stored; The items to be stored were not stored; The item to be stored was not fully placed in the storage area.

5. The method for storing clamped objects according to claim 4, characterized in that, The second result includes any one of the following: The dimensions of the items to be stored meet the storage requirements of the storage area. The dimension of the item to be stored in a certain direction is greater than or equal to the dimension of the storage area; The area of ​​the item to be stored is larger than the size of the storage area and is flat; The item to be stored is larger than the storage area and is not made of fabric, cannot be folded, and cannot be clamped in the center.

6. The method for storing clamped objects according to claim 5, characterized in that, The first result and the second result are fused, and a storage instruction for the smart storage device is output based on the fused result, including: If the item to be stored is not stored and its size meets the storage conditions of the storage area, the robotic arm of the intelligent storage system adjusts its gripper to pick up the item and adjusts it to a placement position, and then places the item into the storage area.

7. The method for storing clamped objects according to claim 6, characterized in that, The method further includes fusing the first result and the second result, and outputting a storage instruction for the smart storage device based on the fused result. If the item to be stored is not stored and its dimension in a certain direction is larger than the storage area dimension, it is determined that it needs to be folded. The robotic arm of the intelligent storage device adjusts its gripper to hold one end of the item to be stored, and uses a force sensor to determine whether the gripping was successful. If the gripping fails, it tries again. If the gripping is successful, the robotic arm's posture is adjusted so that the gripper reaches the other end of the item to be stored in preparation for folding it. After the camera recognizes that the gripper has reached the other end of the item to be stored, it controls the gripper to release and uses the force sensor to determine whether the release was successful: if the release fails, it tries to release again; if the release is successful, it re-acquires the size of the item to be stored and the second result; if the second result is not "the size of the item to be stored meets the storage conditions of the storage area", it is determined that it needs to be folded; if the second result is "the size of the item to be stored meets the storage conditions of the storage area", it controls the robotic arm to adjust the gripper to grasp the folded surface of the item to be stored and adjust it to the placement posture, and determines whether the current height of the item to be stored meets the placement height; if the height meets the height, it places the item to be stored in the storage area; if the height does not meet the height, it adjusts the gripping direction of the gripper or folds it again.

8. The method for storing clamped objects according to claim 7, characterized in that, The method further includes fusing the first result and the second result, and outputting a storage instruction for the smart storage device based on the fused result. For an item to be stored that is not stored, has an area larger than the storage area, and is flat, determine to clamp the center of the item to be stored. The robotic arm controlling the intelligent storage adjusts the gripper to hold the center of the item to be stored, and determines whether the gripping is successful through a force sensor: if the gripping fails, the gripping is attempted again; if the gripping is successful, the robotic arm is adjusted to the placement posture. Determine if the current height of the item to be stored meets the placement height requirement: if the height does not meet the requirement, it is determined that the item to be stored needs to be folded; if the height meets the requirement, the item to be stored is placed in the storage area.

9. The method for storing clamped objects according to claim 8, characterized in that, The method further includes fusing the first result and the second result, and outputting a storage instruction for the smart storage device based on the fused result. For an item to be stored that is not stored and is non-woven, cannot be folded, and cannot be clamped in the center, determine one end of the item to be stored to be clamped. The robotic arm controlling the intelligent storage adjusts the gripper to hold one end of the item to be stored, and uses a force sensor to determine whether the gripping was successful: if the gripping fails, it tries again; if the gripping is successful, it adjusts the robotic arm to the placement position. Determine if the current height of the item to be stored meets the placement height requirement: if the height meets the requirement, place the item to be stored into the storage area; if the height does not meet the requirement, control the grippers to release the item to be stored. The force sensor determines whether the release was successful: if the release fails, the release attempt is repeated; if the release is successful, the robotic arm of the intelligent storage system is controlled to adjust the gripper to hold the other end of the item to be stored. The force sensor determines whether the gripping was successful: if the gripping fails, the gripping is attempted again; if the gripping is successful, the robotic arm is adjusted to the placement position. Determine whether the current height of the item to be stored meets the placement height requirement: if the height meets the requirement, place the item to be stored into the storage area; if the height does not meet the requirement, continue to adjust the grippers to hold the item in different directions until the placement height is met.

10. The method for storing clamped objects according to claim 9, characterized in that, The method also includes verifying the state after storage: if the item to be stored is completely inside the storage area, the storage operation is completed; otherwise, it is determined that a gripper push-in operation is to be performed, the robotic arm is controlled to adjust its posture to move the gripper directly below the item to be stored and retract it, the robotic arm is controlled to adjust its posture upward and push the item to be stored into the storage area through the gripper; When the gripper is aligned with the highest point of the storage area, the camera identifies whether the item to be stored has completely entered the storage area: if so, the storage operation is complete; otherwise, the gripper push-in operation is repeated.

11. A clamping and storage system, characterized in that, Used to perform the clamp storage method according to any one of claims 1-10.

12. A clamping and storing device, characterized in that, The device is used to perform the clamping object storage method according to any one of claims 1-10, or the clamping object storage device includes the clamping object storage system according to claim 11.

Images