Mature fruit picking method

Abstract

The invention relates to a mature fruit picking method which comprises the following steps: presetting a pre-picking position of a mechanical arm and a pre-picking posture of an end effector according to growth characteristics of fruits; acquiring an image of a to-be-picked fruit, and analyzing and detecting to obtain position information and attitude information of a mature fruit stalk under a camera coordinate system; the position information of the mature fruit stalks in a depth camera coordinate system is converted into the position information in a mechanical arm base coordinate system, path planning is carried out, and an auxiliary picking middle point, a shearing position and an auxiliary rollback middle point are determined; the mechanical arm moves to an auxiliary picking middle point from a pre-picking position along a planned path, adjusts the angle of the end effector, then linearly moves to a shearing position, shears and clamps the mature fruits through the end effector, and linearly retreats to an auxiliary retreating middle point along an original path; and moving to a preset release position to release the picked mature fruits to finish picking. Compared with the prior art, the picking success rate and efficiency are improved.

Description

Technical Field

[0001] The invention relates to the technical field of fruit picking, in particular to a method for picking ripe fruits. Background Art

[0002] Fruit picking is the most time-consuming and labor-intensive part of fruit production. The labor required during fruit harvesting accounts for about 50% to 70% of the entire planting process. In order to reduce the labor input of fruit picking, agricultural auxiliary robots are used in the prior art to harvest fruits. However, fruit picking has high operating requirements for agricultural auxiliary robots, and high picking accuracy is required to ensure the quality of picking operations. Among them, the quality of picking operations directly affects the storage, processing and sales of fruits, which ultimately affects market prices and economic benefits. Due to the characteristics of the fruit stalks in the fruit planting environment, such as disorderly growth directions and different shapes, the complexity of fruit picking operations is very large. Therefore, the degree of automation for fruit picking is still very low. For example, patent application CN116034732A discloses a fuzzy fruit picking method, which obtains an image of the fruit to be picked, identifies and analyzes the image of the fruit to be picked, calculates the direction of the ripe fruit ear and the coordinates of the picking point of the fruit stalk, divides the direction of the fruit ear into forward growth, left growth and right growth, determines the picking posture and cutting position of the end effector according to the direction of the fruit ear and the coordinates of the picking point of the fruit stalk, and moves the end effector to the cutting position to complete the picking of the fruit. However, in the actual growing environment, the direction of the fruit ear is often chaotic, and simply summarizing the direction of the fruit ear as forward growth, left growth and right growth often leads to unsatisfactory picking results. For example, patent application CN114846998A discloses a fruit picking method and system using a binocular robot based on the YOLOv4 algorithm. The patent describes a method for dealing with fruits that are obscured by fruit leaves. However, when fruits are cultivated on cultivation racks in greenhouses, they are rarely obscured when they are ripe. Adding classification logic for obscured fruits will increase the cost of fruit picking.

[0003] In the existing technology, the characteristics of the fruit stems in the planting environment, such as disorderly growth direction and various shapes, are not taken into account. The collision and pulling problem of the robotic arm with the surrounding crops when performing the picking task is not considered. At the same time, there are problems such as long picking cycle and low efficiency. Summary of the invention

[0004] The purpose of the present invention is to provide a method for picking ripe fruits in order to overcome the defects of the above-mentioned prior art, taking into account the collision and pulling problem between the robotic arm and the surrounding crops when performing the picking task, thereby improving the fruit picking efficiency and shortening the picking cycle.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] A method for picking ripe fruits comprises the following steps:

[0007] According to the growth characteristics of the fruit, the pre-picking position of the robot arm and the pre-picking posture of the end effector are preset;

[0008] Acquire an image of the fruit to be picked, perform image analysis and detection on the image of the fruit to be picked, and obtain position information and posture information of the stem of the mature fruit in the camera coordinate system;

[0009] The position information of the ripe fruit stem in the depth camera coordinate system is transformed into the position information of the ripe fruit stem in the robot arm base coordinate system, and the path planning is performed according to the position information of the ripe fruit stem in the robot arm base coordinate system and the structural parameters of the end effector to determine the auxiliary picking middle point, the cutting position and the auxiliary retreat middle point;

[0010] The robot arm is moved from the pre-picking position to the auxiliary picking middle point along the planned path, and the end effector is adjusted to a suitable angle according to the posture information of the ripe fruit stem;

[0011] After the adjustment is completed, the robot arm is moved linearly from the auxiliary picking middle point to the shearing position, the ripe fruit is sheared and clamped by the end effector, and then retreated linearly along the original path to the auxiliary retreat middle point;

[0012] The robotic arm moves from the auxiliary retreat midpoint to a preset release position to release the picked ripe fruits, thereby completing the picking.

[0013] Furthermore, the setting principle of the pre-picking position of the robotic arm is that the number of fruits in the image of fruits to be picked acquired by the depth camera on the robotic arm at the pre-picking position is the largest.

[0014] Furthermore, the pre-picking posture of the end effector is specifically that the end effector is facing the fruit planting ridge and the angle between the shear plane of the end effector and the horizontal plane is 0°.

[0015] Furthermore, the step of acquiring the posture information of the ripe fruit stems includes: identifying the ripe fruits in the picture of the fruits to be picked by using the YOLO algorithm, obtaining the ripe fruit stems by linear fitting, and taking the angle between the ripe fruit stems and the y-coordinate axis of the camera coordinate system as the posture information of the ripe fruit stems;

[0016] The included angle matches the angle at which the end effector is adjusted at the intermediate point of the auxiliary picking.

[0017] Furthermore, the specific steps of transforming the position information of the ripe fruit stem in the depth camera coordinate system to the position information of the ripe fruit stem in the robot arm base coordinate system include:

[0018] The homogeneous transformation matrix between the depth camera coordinate system and the robot end coordinate system is obtained through the visual hand-eye calibration method;

[0019] Obtain the homogeneous transformation matrix between the robot end coordinate system and the robot base coordinate system through the robot kinematics method;

[0020] The homogeneous transformation matrix of the depth camera coordinate system and the robot base coordinate system is obtained from the above two homogeneous transformation matrices;

[0021] The position information of the ripe fruit stalk in the depth camera coordinate system is transformed into the position information of the ripe fruit stalk in the robotic arm base coordinate system according to the homogeneous transformation matrix between the depth camera coordinate system and the robotic arm base coordinate system.

[0022] Furthermore, the position information of the ripe fruit stem in the depth camera coordinate system is:

[0023] (P x ,P y ,P z )

[0024] Where P x is the horizontal position information of the ripe fruit stem in the depth camera coordinate system, P y is the vertical position information of the ripe fruit stem in the depth camera coordinate system, P z is the position information of the mature fruit stem in the depth direction in the depth camera coordinate system;

[0025] The position information of the ripe fruit stem in the robot arm base coordinate system is:

[0026] (P_t x ,P_t y ,P_t z )

[0027] In the formula, P_t x is the position information of the ripe fruit stem on the x-axis in the robot base coordinate system, P_t y is the position information of the ripe fruit stem on the y-axis in the robot base coordinate system, P_t z It is the position information of the ripe fruit stem on the z-axis in the robot arm base coordinate system.

[0028] Furthermore, the position coordinates of the auxiliary picking intermediate point are:

[0029] (P_m1x ,P_m1 y ,P_m1 z )

[0030] P_m1 x =P_t x -(L1+L2)*cos(α)

[0031] P_m1 y =P_t y +(L1+L2)*sin(α)

[0032] P_m1 z =P_t z +Z1

[0033] Where, P_m1 x P_m1 is the position information of the auxiliary picking center point on the x-axis. y P_m1 is the position information of the auxiliary picking center point on the y-axis. z is the position information of the auxiliary picking center point on the z-axis, L1 is the axial length of the end effector, L2 is the compensation value caused by the installation position of the end effector, α is the angle between the projection point of the position coordinate of the ripe fruit stem on the horizontal plane and the line connecting the coordinate origin in the depth camera coordinate system and the z-axis of the camera coordinate system, and Z1 is the compensation value in the z-axis direction in the robot arm base coordinate system.

[0034] Furthermore, the selection rule of the compensation value in the z-axis direction in the robot base coordinate system is:

[0035]

[0036] Where Z0 is the height threshold, L z To compensate for the height.

[0037] Furthermore, the position coordinates of the shearing position are:

[0038] (P_p x , P_p y , P_p z )

[0039] P_p x =P_m1 x +L3*cos(α)

[0040] P_p y =P_m1 y -L3*sin(α)

[0041] P_p z =P_m1 z -Z2

[0042]

[0043] In the formula, P_p x is the position information of the shearing position on the x-axis, P_p y is the position information of the shearing position on the y-axis, P_p z is the position information of the shearing position on the z-axis, L3 is the straight-line distance from the middle point of the auxiliary picking to the shearing position, Z2 is the compensation value provided when selecting the shearing position, and L z2 Compensation height for determining the cutting position.

[0044] Furthermore, the position coordinates of the auxiliary fallback intermediate point are:

[0045] (P_m2 x ,P_m2 y ,P_m2 z )

[0046] P_m2 x =P_p x -L4*cos(α)

[0047] P_m2 y =P_p y +L4*sin(α)

[0048] P_m2 z =P_p z +Z3

[0049]

[0050] Where P_m2 x To assist in the position information of the back-off center point on the x-axis, P_m2 y To assist in the position information of the back-off center point on the y-axis, P_m2 z is the position information of the auxiliary retraction center point on the z-axis, L4 is the straight-line distance of the end effector from the shearing position to the auxiliary retraction middle point, Z3 is the compensation value provided when selecting the auxiliary retraction middle point, L z3 To determine the compensation height when assisting in retracting the intermediate point.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] 1. The present invention obtains images of fruits to be picked, performs image analysis and detection on the images of fruits to be picked, and obtains position information and posture information of the mature fruit stalks in the camera coordinate system; the final picking posture of the end effector is determined according to the stem posture information, and the end effector of the robotic arm is guided to adjust to a suitable angle according to the final picking posture of the end effector, so that the end effector picks the fruits almost perpendicular to the fruit stalks, which greatly improves the success rate of fruit picking, shortens the picking time, and improves the harvesting efficiency.

[0053] 2. The present invention determines the auxiliary picking midpoint through the stem posture information of mature fruits, divides the fruit picking methods into horizontal picking and oblique picking based on the fruit height, and adopts different auxiliary picking midpoint selection strategies according to different fruit heights, which effectively improves the success rate of robot arm path planning and reduces the collision with surrounding fruit plants during the movement of the robot arm. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a schematic diagram of the process of the ripe fruit picking method proposed by the present invention;

[0055] Figure 2 This is a schematic diagram of the coordinate transformation process;

[0056] Figure 3 Schematic diagram of the preset release point for ripe fruits. DETAILED DESCRIPTION

[0057] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0058] Abbreviations involved:

[0059] Coordinate transformation: TransForm, TF

[0060] Example 1

[0061] This embodiment provides a method for picking ripe fruits. Figure 1 As shown, the following steps are included:

[0062] S1. The robotic arm moves to the designated position and waits for the fruit picking instruction. When the robotic arm receives the picking instruction, the pre-picking position and posture of the robotic arm end effector are pre-set according to the growth characteristics of the fruit; otherwise, the robotic arm continues to wait for the picking instruction at the current position.

[0063] An end effector and a depth camera are provided at the end of the robotic arm. The setting principle of the pre-picking position of the robotic arm is that the number of fruits in the image of the fruits to be picked obtained by the depth camera on the robotic arm at the pre-picking position is the largest. The pre-picking posture of the end effector is specifically that the end effector is facing the fruit planting ridge and the angle between the shear plane of the end effector and the horizontal plane is 0°.

[0064] S2. The fruit crops are photographed by a depth camera installed on the end effector to obtain images of the fruits to be picked in the planting environment at the current moment.

[0065] S3. The recognition model in the image recognition and detection system analyzes the image of the fruit to be picked. If ripe fruit is detected in the current image, the recognition model analyzes the growth position and growth posture of the stem of the ripe fruit in the image; otherwise, the robotic arm moves to the next working position and continues to wait for picking instructions.

[0066] In this embodiment, the YOLOV5 recognition model is used to recognize the ripe fruits in the image of the fruit to be picked, and the position information and posture information of the stems of the ripe fruits are obtained. The step of obtaining the posture information of the stems of the ripe fruits includes: recognizing the ripe fruits in the image of the fruit to be picked by the YOLO algorithm, obtaining the stems of the ripe fruits by linear fitting, and taking the angle between the stems of the ripe fruits and the y-coordinate axis of the camera coordinate system as the posture information of the stems of the ripe fruits.

[0067] S4. Transform the position information of the ripe fruit stalk in the camera coordinate system to the position information of the ripe fruit in the robot arm base coordinate system. According to the position information of the fruit root in the robot arm base coordinate system and the structural parameters of the end effector, perform robot arm path planning and determine the auxiliary picking middle point, shearing position and auxiliary retraction middle point. The end effector moves from the pre-picking posture to the auxiliary picking middle point.

[0068] The position information of the ripe fruit stem in the depth camera coordinate system is:

[0069] (P x ,P y ,P z )

[0070] Where P x is the horizontal position information of the ripe fruit stem in the depth camera coordinate system, P y is the vertical position information of the ripe fruit stem in the depth camera coordinate system, P z It is the position information of the ripe fruit stem in the depth direction in the depth camera coordinate system.

[0071] The position information of the ripe fruit stem in the coordinate system of the robot base is:

[0072] (P_tx ,P_t y ,P_t z )

[0073] In the formula, P_t x is the position information of the ripe fruit stem on the x-axis in the robot base coordinate system, P_t y is the position information of the ripe fruit stem on the y-axis in the robot base coordinate system, P_t z It is the position information of the ripe fruit stem on the z-axis in the robot arm base coordinate system.

[0074] The robot path planning is performed through the RTT path planning algorithm to obtain the planned path of the robot from the pre-picking position to the auxiliary picking middle point. The coordinates based on the depth camera coordinate system are converted to the coordinates based on the robot base coordinate system through the TF transformation, that is, the homogeneous transformation matrix from the robot base coordinate system to the depth camera coordinate system is obtained, and the robot path planning and the coordinate determination of the auxiliary middle in the picking path are completed in the base coordinate system. The TF coordinate transformation method can be divided into the acquisition of the homogeneous transformation matrix between the depth camera coordinate system and the robot end tool coordinate system and the acquisition of the homogeneous transformation matrix between the robot base coordinate system and the robot end coordinate system.

[0075] The specific steps of transforming the position information of the ripe fruit stem in the depth camera coordinate system to the position information of the ripe fruit stem in the robot arm base coordinate system are as follows: Figure 2 As shown, including:

[0076] S1. Obtain the homogeneous transformation matrix between the depth camera coordinate system and the robot end coordinate system through the visual hand-eye calibration method;

[0077] S2. Obtain the homogeneous transformation matrix between the robot end coordinate system and the robot base coordinate system through the robot kinematics method;

[0078] S3. Obtain the homogeneous transformation matrix of the depth camera coordinate system and the robot arm base coordinate system from the above two homogeneous transformation matrices;

[0079] S4. According to the homogeneous transformation matrix between the depth camera coordinate system and the robot arm base coordinate system, the position information of the ripe fruit stem in the depth camera coordinate system is transformed into the position information of the ripe fruit stem in the robot arm base coordinate system.

[0080] The auxiliary picking middle point is determined by the ripe fruit position information and the installation method and size of the end effector. The position coordinates of the auxiliary picking middle point are:

[0081] (P_m1 x ,P_m1 y ,P_m1 z )

[0082] P_m1 x =P_t x -(L1+L2)*cos(α)

[0083] P_m1 y =P_t y +(L1+L2)*sin(α)

[0084] P_m1 z =P_t z +Z1

[0085] Where, P_m1 x P_m1 is the position information of the auxiliary picking center point on the x-axis. y P_m1 is the position information of the auxiliary picking center point on the y-axis. z is the position information of the auxiliary picking center point on the z-axis, L1 is the axial length of the end effector, L2 is the compensation value caused by the installation position of the end effector, α is the angle between the projection point of the position coordinate of the ripe fruit stem on the horizontal plane and the line connecting the coordinate origin in the depth camera coordinate system and the z-axis of the camera coordinate system, and Z1 is the compensation value in the z-axis direction in the robot arm base coordinate system.

[0086] The selection rule of the compensation value in the z-axis direction in the robot base coordinate system is:

[0087]

[0088] Where Z0 is the height threshold, L z is the compensation height. In this embodiment, the height threshold Z0 is 0, and the compensation height L z The value is 0.15 meters.

[0089] In the robot arm base coordinate system, when the position information P_t of the ripe fruit stem on the z-axis z When the height threshold Z0 is greater than the compensation value Z1, the auxiliary intermediate point and the coordinates of the mature fruit stem are on the same horizontal plane. When the position information P_t on the z-axis of the mature fruit stem is z When the height is less than the threshold value Z0, the coordinates of the auxiliary picking middle point and the mature fruit stem are not on the same horizontal plane. Adding a compensation value can reasonably select the coordinates of the auxiliary picking middle point. Different auxiliary picking middle point selection strategies are adopted according to different fruit heights, which effectively improves the success rate of the robot arm path planning.

[0090] S5. At the middle point of the assisted picking, the end effector is adjusted to a suitable angle according to the posture information of the fruit stem.

[0091] At the midpoint of the auxiliary picking, the end effector is adjusted to a suitable posture for cutting the fruit stem. The adjusted angle is the posture information of the mature fruit stem, which is the angle between the fruit stem and the y-axis of the depth camera coordinate system after linear fitting by the image recognition and detection system.

[0092] S6, the end effector moves linearly for a distance from the auxiliary picking midpoint after the posture is adjusted and reaches the shearing position of the end effector. At this shearing position, the end effector completes the shearing and clamping of the ripe fruit.

[0093] The position coordinates of the clipping position are:

[0094] (P_p x , P_p y , P_p z )

[0095] P_p x =P_m1 x +L3*cos(α)

[0096] P_p y =P_m1 y -L3*sin(α)

[0097] P_p z =P_m1 z -Z2

[0098] In the formula, P_p x is the position information of the shearing position on the x-axis, P_p y is the position information of the shearing position on the y-axis, P_p z is the position information of the cutting position on the z-axis, and L3 is the straight-line distance that the robot arm moves from the middle point of auxiliary picking to the cutting position. Linear motion can effectively avoid collision with the planting environment around the fruit.

[0099] The selection rules of Z2 are as follows:

[0100]

[0101] Z2 is the compensation value provided when selecting the shear position, L z2 In order to determine the compensation height at the cutting position, adding the compensation value Z2 can reasonably select the cutting position coordinates. Different cutting position selection strategies are adopted according to different fruit heights, which effectively improves the success rate of the robot arm path planning.

[0102] In this embodiment, the straight line segment movement distance L3 is 0.1 meters, and the compensation height L z2 The value is 0.05 meters.

[0103] S7. After completing the shearing and clamping work, the end effector holds the fruit and retreats a certain distance along the original straight path to reach the auxiliary retreat midpoint.

[0104] The coordinates of the auxiliary retreat center point are:

[0105] (P_m2 x ,P_m2 y ,P_m2 z )

[0106] P_m2 x =P_p x -L4*cos(α)

[0107] P_m2 y =P_p y +L4*sin(α)

[0108] P_m2 z =P_p z +Z3

[0109] Where P_m2 x To assist in the position information of the back-off center point on the x-axis, P_m2 y To assist in the position information of the back-off center point on the y-axis, P_m2 z is the position information of the auxiliary retraction center point on the z-axis, and L4 is the straight-line distance from the end effector retracting from the shearing position to the auxiliary retraction midpoint.

[0110] The selection rules of Z3 are as follows:

[0111]

[0112] Z3 is the compensation value provided when selecting the auxiliary retreat intermediate point, L z3 In order to determine the compensation height of the auxiliary retraction midpoint, adding the compensation value Z3 can reasonably select the coordinates of the auxiliary retraction midpoint. Different auxiliary retraction midpoint selection strategies are adopted according to different fruit heights, which effectively improves the success rate of the robot arm path planning.

[0113] In this embodiment, the linear movement distance L4 from the shearing position to the auxiliary retreat midpoint is 0.12 meters, and the compensation height L set when determining the auxiliary retreat midpoint is z3 The value is 0.05 meters.

[0114] S8, the end effector moves from the auxiliary retraction middle point to the preset release position to release the ripe fruit that has been picked. After releasing the ripe fruit, the robotic arm returns to the working position and waits for the picking instruction.

[0115] In this embodiment, in order to prevent the ripe fruits from being piled up in a "mountain" shape in the fruit frame and causing the fruits to fall out, three release positions are set in this embodiment so that the ripe fruits can evenly fill the fruit frame. The top view of the fruit release position is as follows: Figure 3 shown.

[0116] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. A method for picking ripe fruits, characterized in that: The following steps are involved: According to the growth characteristics of the fruit, the pre-picking position of the robot arm and the pre-picking posture of the end effector are preset; Acquire an image of the fruit to be picked, perform image analysis and detection on the image of the fruit to be picked, and obtain position information and posture information of the stem of the mature fruit in the camera coordinate system; The position information of the ripe fruit stem in the depth camera coordinate system is transformed into the position information of the ripe fruit stem in the robot arm base coordinate system, and the path planning is performed according to the position information of the ripe fruit stem in the robot arm base coordinate system and the structural parameters of the end effector to determine the auxiliary picking middle point, the cutting position and the auxiliary retreat middle point; The robot arm is moved from the pre-picking position to the auxiliary picking middle point along the planned path, and the end effector is adjusted to a suitable angle according to the posture information of the ripe fruit stem; After the adjustment is completed, the robot arm is moved linearly from the auxiliary picking middle point to the shearing position, the ripe fruit is sheared and clamped by the end effector, and then retreated linearly along the original path to the auxiliary retreat middle point; The robotic arm moves from the auxiliary retreat midpoint to a preset release position to release the picked ripe fruits, thereby completing the picking.

2. The method for picking ripe fruits according to claim 1, characterized in that: The setting principle of the pre-picking position of the robotic arm is that the number of fruits in the image of fruits to be picked acquired by the depth camera on the robotic arm at the pre-picking position is the largest.

3. The method for picking ripe fruits according to claim 1, characterized in that: The pre-picking posture of the end effector is specifically that the end effector is facing the fruit planting ridge and the angle between the shear plane of the end effector and the horizontal plane is 0°.

4. The method for picking ripe fruits according to claim 1, characterized in that: The step of acquiring the posture information of the ripe fruit stem comprises: identifying the ripe fruit in the to-be-picked fruit image by using the YOLO algorithm, obtaining the ripe fruit stem by linear fitting, and taking the angle between the ripe fruit stem and the y-coordinate axis of the camera coordinate system as the posture information of the ripe fruit stem; The included angle matches the angle at which the end effector is adjusted at the intermediate point of the auxiliary picking.

5. The method for picking ripe fruits according to claim 1, characterized in that: The specific steps of transforming the position information of the ripe fruit stem in the depth camera coordinate system to the position information of the ripe fruit stem in the robot arm base coordinate system include: The homogeneous transformation matrix between the depth camera coordinate system and the robot end coordinate system is obtained through the visual hand-eye calibration method; Obtain the homogeneous transformation matrix between the robot end coordinate system and the robot base coordinate system through the robot kinematics method; The homogeneous transformation matrix of the depth camera coordinate system and the robot base coordinate system is obtained from the above two homogeneous transformation matrices; The position information of the ripe fruit stalk in the depth camera coordinate system is transformed into the position information of the ripe fruit stalk in the robotic arm base coordinate system according to the homogeneous transformation matrix between the depth camera coordinate system and the robotic arm base coordinate system.

6. The method for picking ripe fruits according to claim 1, characterized in that: The position information of the ripe fruit stem in the depth camera coordinate system is: (P x ,P y ,P z ) Where P x is the horizontal position information of the ripe fruit stem in the depth camera coordinate system, P y is the vertical position information of the ripe fruit stem in the depth camera coordinate system, P z is the position information of the mature fruit stem in the depth direction in the depth camera coordinate system; The position information of the ripe fruit stem in the robot arm base coordinate system is: (P_t x ,P_t y ,P_t z ) In the formula, P_t x is the position information of the ripe fruit stem on the x-axis in the robot base coordinate system, P_t y is the position information of the ripe fruit stem on the y-axis in the robot base coordinate system, P_t z It is the position information of the ripe fruit stem on the z-axis in the robot arm base coordinate system.

7. The method for picking ripe fruits according to claim 5, characterized in that: The position coordinates of the auxiliary picking middle point are: (P_m1 x ,P_m1 y ,P_m1 z ) P_m1 x =P_t x -(L1+L2)*cos(α) P_m1 y =P_t y +(L1+L2)*sin(α) P_m1 z =P_t z +Z1 Where, P_m1 x P_m1 is the position information of the auxiliary picking center point on the x-axis. y P_m1 is the position information of the auxiliary picking center point on the y-axis. z is the position information of the auxiliary picking center point on the z-axis, L1 is the axial length of the end effector, L2 is the compensation value caused by the installation position of the end effector, α is the angle between the projection point of the position coordinate of the ripe fruit stem on the horizontal plane and the line connecting the coordinate origin in the depth camera coordinate system and the z-axis of the camera coordinate system, and Z1 is the compensation value in the z-axis direction in the robot arm base coordinate system.

8. The method for picking ripe fruits according to claim 7, characterized in that: The selection rule of the compensation value in the z-axis direction in the robot base coordinate system is: Where Z0 is the height threshold, L z To compensate for the height.

9. The method for picking ripe fruits according to claim 7, characterized in that: The position coordinates of the shearing position are: (P_p x ,P_p y ,P_p z ) P_p x =P_m1 x +L3*cos(a) P_p y =P_m1 y -L3*sin(a) P_p z =P_m1 z -Z2 In the formula, P_p x is the position information of the shearing position on the x-axis, P_p y is the position information of the shearing position on the y-axis, P_p z is the position information of the shearing position on the z-axis, L3 is the straight-line distance from the middle point of the auxiliary picking to the shearing position, Z2 is the compensation value provided when selecting the shearing position, and L z2 Compensation height for determining the cutting position.

10. The method for picking ripe fruits according to claim 9, characterized in that: The position coordinates of the auxiliary retreat intermediate point are: (P_m2 x ,P_m2 y ,P_m2 z ) P_m2 x =P_p x -L4*cos(α) P_m2 y =P_p y +L4*sin(α) P_m2 z =P_p z +Z3 Where, P_m2 x To assist in the position information of the back-off center point on the x-axis, P_m2 y To assist in the position information of the back-off center point on the y-axis, P_m2 z is the position information of the auxiliary retraction center point on the z-axis, L4 is the straight-line distance of the end effector from the shearing position to the auxiliary retraction middle point, Z3 is the compensation value provided when selecting the auxiliary retraction middle point, L z3 To determine the compensation height when assisting in retracting the intermediate point.

Images