A machine vision agricultural exoskeleton robot detector device and method

Abstract

The present disclosure relates to the technical field of agricultural exoskeleton, and in particular to a machine vision agricultural exoskeleton robot detector device and method. The present disclosure provides a machine vision agricultural exoskeleton robot detector device, including a lower limb exoskeleton unit, an image acquisition device, and an analysis and control device. The lower limb exoskeleton unit includes a thigh exoskeleton and a calf exoskeleton. The thigh exoskeleton is connected to the calf exoskeleton through a knee joint assisting member, and the knee joint assisting member is used to provide assistance when the thigh exoskeleton and the calf exoskeleton are relatively flexed; the image acquisition device is used to collect images around the user and transmit the images to the control device. The image acquisition device includes a detector body and at least four image acquisition members, which are arranged on the detector body. The detector body is connected to the thigh exoskeleton through a joint, and the joint is used to provide external assistance during the flexion movement of the user's lower limbs. Through the above technical solution, agricultural production efficiency can be improved and work intensity can be reduced.

Description

Technical Field

[0001] The present disclosure relates to the technical field of agricultural exoskeletons, and in particular to a machine vision agricultural exoskeleton robot detector device and a method of using the same. Background Art

[0002] With the continuous advancement of science and technology, exoskeleton robot assistance technology has been applied to many fields, but traditional exoskeleton robots cannot be used on a large scale in agriculture due to their high price and heavy weight. Nowadays, agricultural workers are seriously aging. In some hilly and mountainous areas with heavy physical labor and steep terrain, elderly agricultural workers and women who lack strength find it extremely difficult to perform agricultural operations, with low production efficiency and certain operational risks.

[0003] It is an urgent problem to study an agricultural exoskeleton power-assisting device with low cost, simple structure and easy operation. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a machine vision agricultural exoskeleton robot detector device, including a lower limb exoskeleton unit, an image acquisition device and an analysis and control device, wherein:

[0005] The lower limb exoskeleton unit includes a thigh exoskeleton and a calf exoskeleton, the thigh exoskeleton is connected to the calf exoskeleton via the knee joint assisting member, the knee joint assisting member is used to provide assisting force when the thigh exoskeleton and the calf exoskeleton are relatively flexed, the knee joint assisting member includes a first elastic connecting rod and a first compression spring, one end of the first elastic connecting rod is arranged in the thigh exoskeleton, and the other end is arranged in the calf exoskeleton, the first compression spring is arranged in the knee joint assisting member, and the first compression spring abuts between the first elastic connecting rod and the inner wall of the knee joint assisting member close to the lower limb exoskeleton unit;

[0006] The image acquisition device is used to acquire user action images and / or surrounding scene images and transmit the images to the control device, the image acquisition device comprises a detector body and at least four image acquisition components, the image acquisition components are arranged on the detector body, and the detector body is connected to the thigh exoskeleton through a joint;

[0007] The joint assembly is used to provide external assistance when the user's lower limbs move. The joint assembly includes a driving device and a rotating part. The rotating part includes a driving gear and a driven gear. The driving gear is arranged in the joint assembly, and the driven gear is arranged in the lower limb exoskeleton unit. The driving gear is meshed and connected with the driven gear.

[0008] The driving device drives the driving gear to rotate after the analysis and control device issues a motion instruction;

[0009] The analysis and control device is used to convert the collected images into a variety of motion instructions, and the multiple motion instructions respectively correspond to preset torque values ​​to control the driving device to provide external assistance.

[0010] Optionally, the detector body is annular and is worn on the waist of a user. A mounting groove is provided on the detector body, four of the mounting grooves are arranged along the circumference of the detector body, and the image acquisition device is arranged in the mounting groove.

[0011] Optionally, the movement instructions include squatting picking instructions, bending over picking instructions, reaching out picking instructions, and twisting waist operation instructions, wherein:

[0012] The torque value of the driving device when receiving the squatting and picking instruction is 2200N;

[0013] The torque value of the driving device when receiving the bending and picking instruction is 2050N;

[0014] The torque value of the driving device when receiving the reaching-out picking instruction is 950N;

[0015] The torque value of the driving device when receiving the waist twisting operation instruction is 1980N.

[0016] Optionally, the image acquisition component includes a camera and a deformation part, and the camera is connected to the detector body through the deformation part.

[0017] Optionally, the image acquisition component includes a camera and a micro pan-tilt platform, and the camera is connected to the detector body via the micro pan-tilt platform.

[0018] Optionally, it is characterized in that the joint pair also includes a connecting component, which includes a second elastic connecting rod and a second compression spring, the joint pair and the lower limb exoskeleton unit are connected via the second elastic connecting rod, the second compression spring is arranged in the joint pair, and the second compression spring abuts between the second elastic connecting rod and the inner wall of the joint pair close to the lower limb exoskeleton unit.

[0019] Optionally, the analysis and control device is further provided with a team forming module, and the team forming module is used to form a team with other users and can share the image information collected by the image acquisition device with each other.

[0020] A method for using the above-mentioned machine vision agricultural exoskeleton robot detector device is characterized by comprising the following steps:

[0021] Step 1: 3 to 5 machine vision agricultural exoskeleton robot detector devices are formed into a group through a machine vision algorithm, and the machine vision agricultural exoskeleton robot detector device is bound to the user to achieve pairing of the device and the user;

[0022] Step 2: Press the team formation button, and the analysis and control device will search for other machine vision agricultural exoskeleton robot detector devices to form a team. At this time, the other image acquisition devices will provide auxiliary decision-making for themselves, obtain the movement information of their wearers, cover each other, and provide information to each other.

[0023] Optionally, in step one, the network group between the multiple machine vision agricultural exoskeleton robot detector devices adopts a distance method, with the closest vision being the main method.

[0024] Optionally, in step 2, after multiple machine vision agricultural exoskeleton robot detector devices perform team image sharing, if the network group signal is blocked for more than two seconds, the user will be prompted that the shared image of multiple agricultural exoskeleton robot detector devices uses the nearest device as the sharing target.

[0025] Compared with the prior art, the beneficial effects of the present disclosure are: the machine vision agricultural exoskeleton robot detector device provided by the embodiment of the present disclosure provides external assistance when the user's legs are flexed by setting a lower limb exoskeleton unit and provides external assistance when the user walks by setting a joint, so that the user can improve production efficiency and the difficulty of load-bearing agricultural operations; the operator's movement mode is observed by the image acquisition device and sent to the analysis and control device to form a motion command, thereby achieving accurate matching of the external assistance value and the operation item and intensity. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0027] In order to more clearly illustrate the embodiments of the present invention 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0028] Figure 1 A schematic diagram of the structure of the present invention worn on the body of an operator;

[0029] Figure 2 It is a schematic diagram of the structure of the joint-attached thigh exoskeleton disclosed in the present invention;

[0030] Figure 3It is a schematic diagram of the structure of the thigh exoskeleton, calf exoskeleton and knee joint assisting member disclosed in the present invention;

[0031] Figure 4 A schematic diagram of a plurality of the present disclosures teaming up to influence collection devices to collect images from each other.

[0032] Among them, 1-lower limb exoskeleton unit; 11-thigh exoskeleton; 12-knee joint assisting part; 121-first elastic connecting rod; 122-first compression spring; 13-calf exoskeleton; 2-image acquisition device; 21-detector body; 22-image acquisition part; 3-analysis and control device; A-joint; C-camera; D-deformation part; 41-driving device; E-second elastic connecting rod; F-second compression spring; G-driving gear; H-driven gear. DETAILED DESCRIPTION

[0033] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0034] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0035] Exoskeleton robot assistance technology has been applied to many fields, but traditional exoskeleton robots cannot be used on a large scale in agriculture due to their high price and heavy weight. Nowadays, agricultural workers are seriously aging. In some hilly and mountainous areas with heavy physical labor and steep terrain, elderly agricultural workers and women who lack strength find it extremely difficult to perform agricultural operations, with low production efficiency and certain operational risks.

[0036] Based on this, the disclosed embodiment provides a machine vision agricultural exoskeleton robot detector device, which provides external assistance for agricultural workers during work, improves production efficiency and reduces work intensity.

[0037] The following is a detailed description of the machine vision agricultural exoskeleton robot detector device through specific facts:

[0038] Reference Figures 1 to 2As shown, the present disclosure provides a machine vision agricultural exoskeleton robot detector device, including a lower limb exoskeleton unit 1, an image acquisition device 2 and an analysis and control device 3, wherein the lower limb exoskeleton unit 1 of the present disclosure is correspondingly worn on both lower limbs, and the embodiment of the present disclosure is described according to a unilateral structure, and the other side is the same as the unilateral structure, the lower limb exoskeleton unit 1 includes a thigh exoskeleton 11 and a calf exoskeleton 13, the thigh exoskeleton 11 is connected to the calf exoskeleton 13 through a knee joint assisting member 12, and when the operator performs a knee flexion action, the knee joint assisting member 12 is used to provide when the thigh exoskeleton 11 and the calf exoskeleton 13 are relatively flexed. Assisting, the main structure of the knee joint assisting member 12 has certain bending performance and elasticity. For example, the knee joint assisting member 12 includes a first elastic connecting rod 221 and a first compression spring 222. One end of the first elastic connecting rod 221 is arranged in the thigh exoskeleton 11, and the other end is arranged in the calf exoskeleton 13. The first compression spring 222 is arranged in the knee joint assisting member 12, and the first compression spring 222 abuts between the first elastic connecting rod 221 and the inner wall of the knee exoskeleton member 22 close to the lower limb exoskeleton unit 1. In another embodiment of the present disclosure, the knee joint assisting member 12 can use a rotating electromagnet;

[0039] The image acquisition device disclosed in the present invention is used to collect images around the user and transmit the images to the control device 3. The principle of the image acquisition device 2 is a well-known technology in the art, which is to collect the operator's working actions, such as the action of collecting citrus. The action has an image comparison ratio stored in the analysis and control device 3 in advance. The image collected by the image acquisition device 2 is compared with the pre-stored comparison ratio image in the analysis and control device 3. After the comparison is consistent, a response instruction will be issued. The image comparison and analysis module is implemented by the well-known technology in the art and will not be repeated here. The image acquisition device 2 includes a detector body 21. The detector body 21 is preferably annular, preferably elliptical, and can also be set to other shapes such as rectangle. The present invention specifically selects an elliptical ring to adapt to the human body structure and be worn on the user's waist. At least four mounting grooves are set on the detector body 21. The four mounting grooves are evenly arranged along the circumference of the detector body 21, and the image acquisition component 22 is arranged in the mounting groove; further, the mounting groove can also be a sliding groove arranged along the periphery of the detector body 21. The image acquisition component 22 is slidably connected to the mounting groove, and can be fixed with a buckle after sliding to the specified position.

[0040] The present invention provides at least four image acquisition components 22, which correspond to the front, back, left and rear directions of the user respectively. In order to be able to read the surrounding image information more accurately, the number of image acquisition components 22 can also be increased. The image acquisition component 22 includes a camera C and a deformation part D. The camera C is connected to the detector body 21 through the deformation part D. The deformation part can be a metal soft connection with shaping ability. Furthermore, the image acquisition component 22 can also be provided with a micro gimbal. The camera is connected to the detector body 21 through the micro gimbal. The micro gimbal can automatically adjust the angle of the camera under a certain rule, and the user can be saved from manually adjusting the camera.

[0041] The detector body 21 of the present invention is connected to the thigh exoskeleton 11 through the joint A, and the joint A is used to provide external assistance during the flexion movement of the user's lower limbs. Furthermore, the joint A of the present invention includes a driving device 41, a rotating part and a connecting component, and the connecting component includes a second elastic connecting rod E and a second compression spring F. The joint A and the lower limb exoskeleton unit 1 are connected through the second elastic connecting rod E. The preferred second elastic connecting rod F can be a spring lever or a metal connecting rod that can bend and rebound at the connection between the joint A and the thigh exoskeleton 11. The present invention specifically uses a spring lever, and the second compression spring F is arranged on the joint A. The second compression spring F is in contact with the inner wall of the second elastic connecting rod E and the joint A near the lower limb exoskeleton unit 1. When the joint A of the present invention does not provide external assistance, the second elastic connecting piece E is bent by the operator's leg movements during walking and applies pressure to the second compression spring F, which plays a role in assisting movement and buffering the pressure of the lower limbs. Furthermore, the deformation of the second compression spring F is 5.2 cm and the torque is 93 kg to better produce the effect of assisting movement. If the deformation and torque are too small, the auxiliary effect is not obvious; if the deformation and torque are too large, it will be inconvenient for the operator to walk.

[0042] The rotating part of the present invention plays the role of active external assistance. The rotating part includes a driving gear G and a driven gear H. The driving gear G is arranged in the joint pair A, and the driven gear H is arranged in the lower limb exoskeleton unit 1, and the driving gear G is meshed and connected with the driven gear H. When no active external assistance is provided, the driving gear G and the driven gear H can also rotate, and their rotational energy is generated by the operator's own walking; when active external assistance is required, the driving device 41 drives the driving gear G to rotate to provide external assistance under the motion command of the analysis control device 3.

[0043] The analysis and control device 3 of the present disclosure is used to convert the collected images into motion instructions, control the joint A to provide external assistance, and the analysis and control device 3 is also provided with a team system, which is used to form a team with other users and can share the image information collected by the image acquisition device 2 with each other, wherein the motion instructions of the analysis and control device 3 include squatting picking instructions, bending picking instructions, reaching picking instructions, and twisting waist operation instructions, and the image information collected by the image acquisition device 2 is converted into motion instructions by the analysis and control device 3 to facilitate matching the most appropriate assistance intensity, wherein,

[0044] When the driving device receives the squat picking instruction, the torque value is 2200N;

[0045] When the driving device receives the bending and picking instruction, the torque value is 2050N;

[0046] When the driving device receives the reaching-out-to-pick instruction, the torque value is 950N;

[0047] When the drive device receives the twisting operation instruction, the torque value is 1980N.

[0048] The present disclosure also provides a method for using the above-mentioned machine vision agricultural exoskeleton robot detector device, comprising the following steps:

[0049] Step 1: Group 3 to 5 machine vision agricultural exoskeleton robot detector devices through machine vision algorithms, bind the machine vision agricultural exoskeleton robot detector devices to users, and achieve pairing between the devices and users.

[0050] Step 2: Press the team formation button, and the analysis and control device will search for other machine vision agricultural exoskeleton robot detector devices to form a team. At this time, other image acquisition devices will provide auxiliary decision-making for themselves, obtain the motion information of their wearers, cover each other, and provide information to each other.

[0051] In step 1, the network group between multiple machine vision agricultural exoskeleton robot detector devices adopts the distance method, with the closest vision as the main method.

[0052] In step 2, when multiple machine vision agricultural exoskeleton robot detector devices are teamed up to share images, the user will be prompted if the network group signal is blocked for more than two seconds.

[0053] In step two, the shared images of multiple machine vision agricultural exoskeleton robot detector devices take the nearest equipment as the sharing target, so that multiple users wearing the settings disclosed in the present invention can take care of each other, share image information, and realize field group operations, which is in line with the actual characteristics of a large group of people working in hilly and mountainous areas. The acquisition device 2 receives images of environmental characteristics in the manner described above, such as stone obstructions, gullies, steep slopes, etc., and the analysis and control device 3 also pre-stores comparative images of environmental abnormalities, and there are different corresponding comparative image groups according to different terrains; exemplarily, when a team of multiple people conducts agricultural operations in a hilly and mountainous area, the acquisition images shared by the team members, such as capturing a steep slope, are matched with the captured image by the analysis and control module 3. If it is verified that the comparison is consistent with the pre-stored comparative image, the drive device 41 is controlled to generate power to help go uphill. Further, in order to analyze the misoperation of the control device 3, when the comparison is consistent with the comparative image, the operator is first prompted whether to provide power. If power is required, it can be confirmed by setting a voice function or a button.

[0054] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A machine vision agricultural exoskeleton robot detector device, characterized in that: It comprises a lower limb exoskeleton unit (1), an image acquisition device (2) and an analysis and control device (3), wherein: The lower limb exoskeleton unit (1) comprises a thigh exoskeleton (11) and a calf exoskeleton (13), wherein the thigh exoskeleton (11) is connected to the calf exoskeleton (13) via a knee joint assisting member (12), wherein the knee joint assisting member (12) is used to provide assistance when the thigh exoskeleton (11) and the calf exoskeleton (13) are relatively flexed, and the knee joint assisting member (12) comprises a first elastic connecting rod (121) and a first compression spring (122), wherein one end of the first elastic connecting rod (121) is arranged in the thigh exoskeleton (11), and the other end is arranged in the calf exoskeleton (13), and the first compression spring (122) is arranged in the knee joint assisting member (12), and the first compression spring (122) abuts between the first elastic connecting rod (121) and the inner wall of the knee joint assisting member (12) close to the lower limb exoskeleton unit (1); The image acquisition device (2) is used to acquire user action images and / or surrounding scene images and transmit the images to the control device (3); the image acquisition device (2) comprises a detector body (21) and at least four image acquisition components (22); the image acquisition components (22) are arranged on the detector body (21); and the detector body (21) is connected to the thigh exoskeleton (11) via a joint (A); The joint assembly (A) is used to provide external assistance when the user's lower limbs move. The joint assembly (A) comprises a driving device (41) and a rotating part. The rotating part comprises a driving gear (G) and a driven gear (H). The driving gear (G) is arranged in the joint assembly (A), and the driven gear (H) is arranged in the lower limb exoskeleton unit (1). The driving gear (G) is meshedly connected with the driven gear (H). The joint support (A) further comprises a connection assembly, the connection assembly comprising a second elastic connection rod (E) and a second compression spring (F), the joint support (A) and the lower limb exoskeleton unit (1) are connected via the second elastic connection rod (E), the second compression spring (F) is arranged in the joint support (A), and the second compression spring (F) abuts between the second elastic connection rod (E) and an inner wall of the joint support (A) close to the lower limb exoskeleton unit (1); The driving device (41) drives the driving gear (G) to rotate after the analysis and control device issues a motion instruction; The analysis and control device (3) is used to convert the collected images into a plurality of motion instructions, and the plurality of motion instructions respectively correspond to preset torque values ​​to control the driving device (41) to provide external assistance; The movement instructions include squatting picking instructions, bending over picking instructions, reaching out picking instructions, and twisting waist operation instructions, wherein: The torque value of the driving device (41) when receiving the squatting picking instruction is 2200N; The torque value of the driving device (41) when receiving the bending and picking instruction is 2050N; The torque value of the driving device (41) when receiving the reaching-out picking instruction is 950N; The driving device (41) receives a torque value of 1980N when receiving a waist-twisting operation instruction; The analysis and control device (3) is also provided with a team forming module, and the team forming module is used to form a team with other users and can share the image information collected by the image collecting device (2) with each other.

2. The machine vision agricultural exoskeleton robot detector device according to claim 1, characterized in that: The detector body (21) is annular and is worn on the waist of a user. The detector body (21) is provided with a mounting groove, four of which are arranged along the circumference of the detector body (21), and the image acquisition component (22) is arranged in the mounting groove.

3. The machine vision agricultural exoskeleton robot detector device according to claim 1, characterized in that: The image acquisition component (22) comprises a camera (C) and a deformation portion (D), and the camera (C) is connected to the detector body (21) via the deformation portion (D).

4. The machine vision agricultural exoskeleton robot detector device according to claim 1, characterized in that: The image acquisition component (22) comprises a camera and a micro-pan platform, and the camera is connected to the detector body (21) via the micro-pan platform.

5. A method for using the machine vision agricultural exoskeleton robot detector device according to any one of claims 1 to 4, characterized in that: The following steps are included: Step 1: 3 to 5 machine vision agricultural exoskeleton robot detector devices are formed into a group through a machine vision algorithm, and the machine vision agricultural exoskeleton robot detector device is bound to the user to achieve pairing of the device and the user; Step 2: Press the team formation button, and the analysis and control device will search for other machine vision agricultural exoskeleton robot detector devices to form a team. At this time, the other image acquisition devices will provide auxiliary decision-making for themselves, obtain the motion information of their wearers, cover each other, and provide information to each other.

6. The networking operation method of the machine vision agricultural exoskeleton robot detector device according to claim 5 is characterized in that: In the step 1, the network group between the multiple machine vision agricultural exoskeleton robot detector devices adopts the distance method, with the closest vision as the main method.

7. The networking operation method of the machine vision agricultural exoskeleton robot detector device according to claim 5 is characterized in that: In step 2, when multiple machine vision agricultural exoskeleton robot detector devices share images in a team, if the network group signal is blocked for more than two seconds, the user will be prompted that the shared images of multiple agricultural exoskeleton robot detector devices use the nearest device as the sharing target.

Images