Commodity selecting and carrying device based on image recognition

Abstract

The commodity selecting and carrying device comprises a left supporting frame and a right supporting frame, a connecting plate is arranged between the left supporting frame and the right supporting frame, the left supporting frame and the right supporting frame are the same in structure and are symmetrically arranged in a mirror image mode, a left guide rail is arranged on the upper end face of the left supporting frame, and a right guide rail is arranged on the upper end face of the right supporting frame. A carrying frame is arranged between the left guide rail and the right guide rail, a driving motor is arranged on the carrying frame, guide wheels are driven by the driving motor to move on the left guide rail and the right guide rail, a clamping claw is arranged on the carrying frame, a camera is installed on the lower side of the carrying frame, and the camera assists the clamping claw in clamping and carrying. Compared with the prior art, the device has obvious advantages and innovations in a commodity carrying and selecting mechanism for self-service vending. The mechanical arm is characterized in that a supporting frame, a connecting plate and a guide rail system which are arranged in a mirror image mode form the mechanical arm capable of moving flexibly, and a traditional fixed type mechanical arm or a conveying belt system is mostly used in the prior art.

Description

Technical Field

[0001] The utility model belongs to the field of unmanned vending, and in particular relates to a commodity selection and transport device based on image recognition. Background Art

[0002] At present, the product picking and handling devices based on image recognition are mainly used in unmanned convenience stores, warehousing and logistics centers and other scenarios. Such devices usually combine computer vision, deep learning and robotic arm control technology to achieve automatic identification, picking and handling of goods. Although this technology initially attracted much attention due to Amazon's vigorous promotion, it also faces many challenges and limitations.

[0003] The commodity handling system based on image recognition requires a large amount of high-quality image data for training to achieve a high recognition rate. At present, the commodity picking and handling devices based on image recognition are mainly used in scenes such as unmanned convenience stores and containers. Such devices usually combine computer vision, robotic arm control technology, etc. to realize the recognition, grasping and handling of commodities. However, the existing technology currently relies mainly on artificial intelligence technology, especially the progress of computer vision and natural language processing. By using cameras, sensors and other equipment, the location and type of goods can be identified and tracked to achieve the current unmanned vending technology. The process of picking and handling commodities often relies on traditional robotic arms and conveyor belt systems. Although these systems have achieved automation to a certain extent, they still have many limitations and shortcomings. First of all, the traditional robotic arms are limited in operation accuracy, especially when handling irregularly shaped or small-sized commodities, errors are prone to occur, resulting in damage to commodities or failure to pick. In addition, the range of motion and flexibility of the robotic arms are limited by their mechanical structure, and they cannot adapt to the diverse placement of commodities and complex shelf layouts.

[0004] Although conveyor belt systems perform well in the continuous transport of goods, their fixed layout makes it difficult to adapt to dynamically changing shelf configurations and product types. The maintenance cost of conveyor belt systems is also relatively high, and when a failure occurs, the operation of the entire system will be seriously affected. In addition, conveyor belt systems pose a greater risk when handling fragile or valuable goods, as the goods are easily hit or squeezed during the conveyance process.

[0005] In existing unmanned vending systems, the application of image recognition technology is not yet widespread, and there are many challenges in actual operation. The image recognition system needs to process a large amount of visual data, which requires extremely high computing power and algorithm accuracy. In a complex retail environment, factors such as light changes and product occlusion will affect the accuracy of image recognition. In addition, the deployment and maintenance costs of the image recognition system are relatively high, requiring a professional technical team to regularly update and optimize.

[0006] The existing unmanned vending system has obvious technical bottlenecks in the selection and handling of goods, which are mainly reflected in insufficient operating accuracy, poor flexibility, high maintenance costs, and limited application of image recognition technology. In order to overcome these shortcomings, it is necessary to develop a new type of commodity selection and handling device based on image recognition, which should have high-precision operating capabilities, flexible movement mechanisms, low maintenance costs, and powerful image recognition technology support to achieve more efficient and reliable unmanned vending services. Therefore, there is an urgent need for a commodity selection and handling device based on image recognition. Utility Model Content

[0007] The utility model proposes a commodity picking and handling device based on image recognition, which solves the technical problems of commodity handling and picking in the process of unmanned vending. By using a mirror-designed support frame, a guide rail system, and a camera and a clamping claw, the device sets a symmetrical support frame, guide rail and handling frame, combined with a drive motor and a camera, to solve the technical problems of positioning accuracy, operational flexibility and visually assisted clamping in commodity picking and handling.

[0008] The technical solution of the utility model is implemented as follows: a commodity picking and carrying device based on image recognition includes a connecting plate arranged between a left support frame and a right support frame, the left support frame and the right support frame have the same structure and are symmetrically mirrored, a left guide rail is arranged on the upper end face of the left support frame, and a right guide rail is arranged on the upper end face of the right support frame, a carrying frame is arranged between the left guide rail and the right guide rail, a driving motor is arranged on the carrying frame, and the guide wheels are driven by the driving motor to move on the left guide rail and the right guide rail, a clamping claw is arranged on the carrying frame, and a camera is installed on the lower side of the carrying frame, and the clamping claw is assisted by the camera to perform clamping and carrying.

[0009] Compared with the existing technology, the device has obvious advantages and innovations in the handling and picking mechanism of goods in unmanned vending. Its highlight is that a flexible and movable robotic arm is constructed through a mirror-set support frame, connecting plate and guide rail system, while the existing technology mostly uses traditional fixed robotic arms or conveyor belt systems. The new robotic arm designed by the device has higher operating accuracy and flexibility. Unlike traditional robotic arms, it can achieve wider coverage and precise positioning through mirror-set support frames and guide rails, and is particularly suitable for the handling of goods of various shapes and sizes. In addition, this design has strong adaptability and can achieve precise clamping and handling under complex layouts through the coordination of cameras and clamping claws, while existing technologies are often unable to cope with complex scenes. The device also optimizes the commodity identification and handling process through computer vision technology. By installing a camera on the lower side of the handling frame, visual assistance can be provided to the clamping claw, improving the identification and clamping failure problems that are prone to occur in traditional robotic arms. This visual assistance system can adjust the clamping position in real time to ensure that the handling process is more robust and controllable.

[0010] Compared with existing technologies, this device brings innovation to the field of unmanned vending. It integrates the use of mirror-set robotic arms, computer vision and guide rail systems to achieve higher-precision operations, better flexibility and a more reliable visual assistance system, providing an efficient and accurate solution for unmanned vending scenarios.

[0011] As a preferred embodiment, the support rod on the lower side of the left support frame parallel to the left guide rail and the support rod on the lower side of the right support frame parallel to the right guide rail are both provided with slide grooves, and auxiliary brackets are provided on the left and right sides of the transport frame to match the slide grooves.

[0012] As a preferred embodiment, the connecting plate arranged between the left support frame and the right support frame is symmetrically arranged on the front and rear sides of the left and right support frames, and the connecting plate is used to assist in limiting the moving position of the clamping claw.

[0013] As a preferred embodiment, limit baffles are provided on both the front and rear sides of the left guide rail and the right guide rail, and the moving position of the transport rack is limited by the limit baffles.

[0014] As a preferred embodiment, the transport frame includes a driving motor, a clamping claw, an auxiliary bracket, a telescopic plate and a connecting cross plate, the driving motor is arranged at the outer end of the connecting cross plate facing the left guide rail, the auxiliary bracket is arranged on the inner edges of the left and right guide rails on the left and right sides of the connecting cross plate, a telescopic plate is arranged on the lower end surface of the middle part of the connecting cross plate, and a plurality of clamping claws are horizontally arranged on the telescopic plate away from the connecting cross plate.

[0015] After adopting the above technical solution, the beneficial effect of the utility model is that by using a mirror-set support frame and guide rail system, combined with the precise control of the drive motor and guide wheel, the device can achieve accurate positioning and handling of the goods. This high-precision operation capability reduces the risk of damage to the goods during handling and improves the reliability of the overall operation. The design of the device allows the transport frame to move freely on the left and right rails. This flexibility enables the device to adapt to goods of different sizes and shapes, as well as a variety of shelf layouts. This flexibility is not available in traditional fixed robotic arms or conveyor belt systems. By installing a camera on the lower side of the transport frame, the device can use computer vision technology to assist the gripping claws in identifying and gripping goods. This visual assistance system improves the accuracy of commodity identification and reduces the possibility of misoperation, thereby improving handling efficiency. The automated nature of the device reduces the need for manual participation, especially in unmanned vending scenarios during peak hours or 24-hour operation, which can significantly reduce labor costs and improve operational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the utility model or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the utility model. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0017] Figure 1 It is a schematic diagram of the overall structure of the utility model.

[0018] In the figure, 1-left support frame; 11-slide slot, 2-right support frame; 3-connecting plate; 4-left guide rail; 5-right guide rail; 6-transport frame; 61-driving motor, 62-clamping claw, 63-auxiliary bracket, 64-telescopic plate, 65-connecting cross plate, 7-limit baffle. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the utility model to clearly and completely describe the technical solutions in the embodiments of the utility model. Obviously, the described embodiments are only part of the embodiments of the utility model, not all of the embodiments. Based on the embodiments of the utility model, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the utility model.

[0020] Example:

[0021] like Figure 1 As shown, a commodity picking and handling device based on image recognition includes a connecting plate 3 arranged between a left support frame 1 and a right support frame 2, the left support frame 1 and the right support frame 2 have the same structure and are symmetrically mirrored, a left guide rail 4 is arranged on the upper end surface of the left support frame 1, and a right guide rail 5 is arranged on the upper end surface of the right support frame 2, a handling frame 6 is arranged between the left guide rail 4 and the right guide rail 5, a driving motor 61 is arranged on the handling frame 6, and the guide wheel is driven by the driving motor 61 to move on the left guide rail 4 and the right guide rail 5, a clamping claw 62 is arranged on the handling frame 6, and a camera is installed on the lower side of the handling frame 6, and the clamping claw 62 is assisted by the camera to perform clamping and handling.

[0022] The product selection and handling device based on image recognition realizes accurate identification, picking and handling of products through the support frame, guide rail system and intelligent robotic arm set in mirror image. Its working principle and process can be summarized as the following steps:

[0023] Image recognition and product positioning: The device uses a camera installed on the lower side of the transport rack and combines computer vision technology to identify and locate the products on the shelf. The camera captures the product image and uses the image recognition-based product selection and transport device to identify and locate the products on the shelf. The working principle and workflow of the device are as follows: The device constructs a stable mechanical structure through the symmetrical mirror setting of the left support frame 1 and the right support frame 2, and the fixation of the connecting plate 3. The setting of the left guide rail 4 and the right guide rail 5 enables the transport rack 6 to move freely in the horizontal direction. This design provides a wide operating space and flexibility, which is significantly different from the fixed or limited range of movement of the robot arm in the prior art. The drive motor 61 on the transport rack 6 drives the guide wheel to move on the left guide rail 4 and the right guide rail 5, thereby realizing the precise position control of the transport rack. This driving method not only improves the positioning accuracy, but also enhances the response speed and operating efficiency of the device. In contrast, the robot arm or conveyor belt system in the prior art often has limitations in positioning and moving speed.

[0024] The design of the clamping claw 62 enables the device to adapt to commodities of different shapes and sizes. With the visual assistance of the camera, the clamping claw can more accurately identify the position and shape of the commodity, thereby achieving precise clamping. This visual assistance system is rarely used in the prior art, and it greatly improves the accuracy and reliability of commodity selection and handling.

[0025] At the beginning of the workflow, the camera first scans and identifies the goods on the shelf. The identification results are analyzed by the image processing algorithm to determine the specific location of the goods and the best clamping point. Then, the drive motor 61 is started to control the transport frame 6 to move to the location of the target goods. The clamping claw 62 adjusts the clamping angle and strength according to the visual feedback of the camera to ensure that the goods are firmly clamped. Finally, the transport frame 6 moves the goods to the designated location, such as the checkout counter or packaging area, completing the entire transport process.

[0026] Compared with existing technologies, this device achieves more efficient and accurate product selection and handling by integrating image recognition, precise drive and flexible clamping technology. Its working principle and workflow not only improve the level of automation of operations, but also optimize the user experience and reduce the need for manual intervention. This innovative design and functional combination gives the device significant technical advantages and market potential in the field of unmanned vending.

[0027] The support rod on the lower side of the left support frame 1 parallel to the left guide rail 4 and the support rod on the lower side of the right support frame 2 parallel to the right guide rail 5 are both provided with a slide groove 11, and auxiliary brackets 63 are provided on the left and right sides of the transport frame 6 to match the slide groove 11. The device introduces a matching mechanism of the slide groove and the auxiliary bracket in the structural design, further enhancing the overall stability and accuracy. By providing slide grooves on the lower sides of the left and right support frames and cooperating with the auxiliary brackets on both sides of the transport frame, the device improves various performances.

[0028] The combination of the slide and auxiliary bracket provides more stable support and guidance for the transport rack. This design can effectively reduce the shaking and swaying of the robot arm, making the device more stable during precise operations. Compared with existing technologies, this new stabilization mechanism can ensure positioning accuracy during operation, especially when handling small or irregularly shaped goods, and can provide more secure support.

[0029] The setting of the slide provides a smoother and more accurate moving path for the transport rack. Through the sliding matching of the auxiliary bracket and the slide, the movement of the transport rack is more stable, which can avoid the shaking or jamming caused by the structural limitations of the traditional robot arm during the movement. This design improves the overall response speed and accuracy of the device, making the picking and placement of goods smoother.

[0030] Through the structural design of the slide and auxiliary bracket, the device enhances the lateral expansion capability. Unlike the existing fixed mechanical arm, this expandable structure allows the device to adjust the width and coverage of the transport frame according to actual needs. This modular design not only improves the flexibility of the device, but also has significant mechanical structure and stability compared with the prior art. Compared with the prior art, the device has obvious innovations and advantages in structural design and functional realization. First, by setting a support rod parallel to the guide rail on the lower side of the left support frame 1 and the right support frame 2, and setting a slide 11 on the support rod, this design increases the stability and carrying capacity of the device. The setting of the slide 11 enables the transport frame 6 to match the slide 11 through the auxiliary bracket 63, so as to maintain stability during the movement. This structural design is not common in the prior art. It provides additional support and guidance to ensure the stability and accuracy of the transport frame during the movement.

[0031] The matching design of the auxiliary bracket 63 and the slide 11 enhances the mobility and positioning accuracy of the transport rack 6. This design allows the transport rack to be more accurately positioned and adjusted on the left and right rails, while the mechanical arms or transport devices in the prior art often lack such a fine adjustment mechanism. Through the matching of the auxiliary bracket and the slide, the transport rack can reach the target position more accurately, which is crucial to improving the efficiency of commodity selection and transportation.

[0032] This structural design also improves the adaptability and expandability of the device. The arrangement of the chute 11 and the auxiliary bracket 63 enables the device to adapt to commodities of different sizes and weights, while also providing space for possible functional expansion and technical upgrades in the future. This flexibility and expandability are not available in many fixed or single-function devices in the prior art.

[0033] The connecting plate 3 arranged between the left support frame 1 and the right support frame 2 is symmetrically arranged on the front and rear sides of the left and right support frames, and the moving position of the clamping claw 62 is limited by the connecting plate 3. The symmetrical arrangement of the connecting plate 3 provides a more stable support structure for the device. By symmetrically arranging the connecting plate 3 on the front and rear sides of the left and right support frames, the overall structure of the device is more balanced and stable. This design helps to reduce the shaking and swaying of the device during operation, and improves the operation accuracy and stability. In contrast, the connecting plate design in the prior art is often simpler and may not be able to provide the same structural support and stability. The setting of the connecting plate 3 provides more accurate restriction and guidance for the moving position of the clamping claw 62. The clamping claw 62 needs to maintain an accurate position and angle during the handling process to ensure that the clamping and release of the goods can be accurate and correct. With the assistance of the connecting plate 3, the moving range of the clamping claw 62 is effectively limited and regulated, avoiding unnecessary swinging and deviation during operation. This design improves the accuracy and reliability of the device when clamping and carrying goods. The symmetrical arrangement of the connecting plate 3 also provides more convenience for the maintenance and debugging of the device. Since the connecting plates 3 are symmetrically arranged on the front and rear sides of the left and right support frames, during the maintenance and debugging of the device, technicians can more conveniently adjust and calibrate the moving position of the clamping claws 62. This design helps to improve the maintainability and debuggability of the device and reduce the complexity and cost of daily maintenance work.

[0034] The left guide rail 4 and the right guide rail 5 are both provided with limit baffles 7 on both the front and rear sides, and the moving position of the transport rack 6 is limited by the limit baffles 7. The left guide rail 4 and the right guide rail 5 are both provided with limit baffles 7 on both the front and rear sides, and the moving position of the transport rack 6 is limited by the limit baffles 7. This design has significant innovation and advantages compared with the prior art.

[0035] The setting of the limit baffle 7 provides more precise control and restriction for the moving position of the transport frame 6. During operation, the transport frame 6 needs to move precisely on the left and right guide rails to ensure that the clamping and transportation of the goods can be accurate and correct. Through the setting of the limit baffle 7, the device can accurately sense the limit of the moving position during the movement, avoid unnecessary movement beyond the range, and improve the reliability and stability of the operation. In contrast, the guide rail limit design in the prior art may be relatively simple and may not necessarily provide the same fine position control and protection.

[0036] The setting of the limit baffle 7 provides more safety for the device. During the handling process, the limit baffle 7 can effectively prevent the handling frame 6 from moving beyond the range due to operational errors or other reasons, avoiding the risk of collision or damage of the robot arm with other equipment or goods. This design improves the safety and reliability of the device during operation and reduces the probability of accidents.

[0037] The setting of the limit baffle 7 also provides more convenience for the maintenance and debugging of the device. Since the limit baffle 7 can accurately limit the moving range of the transport frame 6, during the maintenance and debugging of the device, the technician can more conveniently adjust and calibrate the moving position of the transport frame 6. This design helps to improve the maintainability and debuggability of the device and reduce the complexity and cost of daily maintenance work.

[0038] The transport frame 6 includes a driving motor 61, a clamping claw 62, an auxiliary bracket 63, a telescopic plate 64 and a connecting cross plate 65. The connecting cross plate 65 is provided with a driving motor 61 at the outer end of the side facing the left guide rail 4. The auxiliary bracket 63 is arranged on the inner edges of the left and right guide rails on the left and right sides of the connecting cross plate 65. The lower end surface of the middle part of the connecting cross plate 65 is provided with a telescopic plate 64. The telescopic plate 64 is horizontally provided with a plurality of clamping claws 62 on the side away from the connecting cross plate 65. The setting of the driving motor 61 provides a powerful driving system for the transport frame 6. By setting the driving motor 61 on the connecting cross plate 65, it is possible to directly provide power for the movement of the transport frame 6, ensuring that the entire device can be operated efficiently and accurately. The mechanical arm in the prior art often uses a simple motor or pneumatic system. In terms of driving capability and response speed, the structural design of the transport frame 6 includes a driving motor 61, a clamping claw 62, an auxiliary bracket 63, a telescopic plate 64 and a connecting cross plate 65. This design has significant innovation and advantages compared with the prior art.

[0039] The structural design of the transport frame 6 provides a more stable support and connection for the device through the setting of the connecting cross plate 65. A driving motor 61 is set at the outer end of the connecting cross plate 65 facing the left guide rail 4. This design enables the driving motor to more directly control the movement of the transport frame, improving the response speed and accuracy of the operation. In contrast, the transport frame design in the prior art may be more decentralized and may not be able to provide the same structural support and power transmission efficiency.

[0040] The auxiliary bracket 63 is arranged on the inner edge of the left and right guide rails on the left and right sides of the connecting cross plate 65, providing a more stable support and guidance for the transport rack. The close fit between the auxiliary bracket 63 and the guide rail makes the transport rack more stable during movement, reducing the error caused by loose or unstable structure. This design improves the overall response speed and accuracy of the device, making the picking and placement of goods smoother.

[0041] The arrangement of the telescopic plate 64 and the clamping claw 62 provides the device with more flexible operation capabilities. A plurality of clamping claws 62 are horizontally arranged on the side of the telescopic plate 64 away from the connecting horizontal plate 65. This design enables the clamping claws to be adjusted according to the size and shape of the goods, thereby improving the adaptability and operational flexibility of the device to different goods. In contrast, the clamping claw design in the prior art may be more fixed and may not provide the same operational flexibility and adaptability.

[0042] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A commodity picking and transporting device based on image recognition, characterized in that: The invention comprises a connecting plate (3) arranged between a left support frame (1) and a right support frame (2); the left support frame (1) and the right support frame (2) have the same structure and are symmetrically arranged in a mirror image; the upper end surface of the left support frame (1) is provided with a left guide rail (4); the upper end surface of the right support frame (2) is provided with a right guide rail (5); a transport frame (6) is arranged between the left guide rail (4) and the right guide rail (5); a driving motor (61) is arranged on the transport frame (6); the driving motor (61) drives the guide wheel to move on the left guide rail (4) and the right guide rail (5); a clamping claw (62) is arranged on the transport frame (6); a camera is installed on the lower side of the transport frame (6); the camera assists the clamping claw (62) to perform clamping and transport.

2. The commodity selection and handling device based on image recognition according to claim 1, characterized in that: A slide groove (11) is provided on the support rod on the lower side of the left support frame (1) and parallel to the left guide rail (4) and on the support rod on the lower side of the right support frame (2) and parallel to the right guide rail (5), and auxiliary brackets (63) are provided on the left and right sides of the transport frame (6) to match the slide groove (11).

3. The commodity selection and handling device based on image recognition as claimed in claim 1, characterized in that: The connecting plate (3) arranged between the left support frame (1) and the right support frame (2) is symmetrically arranged on the front and rear sides of the left and right support frames, and the connecting plate (3) assists in limiting the moving position of the clamping claw (62).

4. The commodity selection and handling device based on image recognition as claimed in claim 1, characterized in that: Limit baffles (7) are provided on both the front and rear sides of the left guide rail (4) and the right guide rail (5), and the moving position of the transport rack (6) is limited by the limit baffles (7).

5. The commodity selection and handling device based on image recognition as claimed in claim 1, characterized in that: The transport frame (6) comprises a driving motor (61), a clamping claw (62), an auxiliary bracket (63), a telescopic plate (64) and a connecting transverse plate (65); the driving motor (61) is arranged at the outer end of the connecting transverse plate (65) facing the left guide rail (4); the auxiliary bracket (63) is arranged at the inner edges of the left and right guide rails on both sides of the connecting transverse plate (65); the telescopic plate (64) is arranged at the lower end surface of the middle part of the connecting transverse plate (65); and a plurality of clamping claws (62) are horizontally arranged on the telescopic plate (64) away from the connecting transverse plate (65).

Images