A potato picking and harvesting method based on PLP-net

Abstract

The present invention relates to the field of potato harvesting technology, and in particular to a potato picking and harvesting method based on PLP-net, which comprises S1. a picking and harvesting robot moves to an unpicked area; S2. potatoes to be picked are identified based on a PLP-net algorithm; S3. the plane position and gripping depth of the potatoes to be picked are located and calculated; S4. a potato gripping strategy is formulated and a command is sent to a gripping device; S5. after the gripping is completed, it is determined whether it is the last potato in the area; and S6. it is determined whether there is an unpicked area. The present invention proposes a complete set of potato recognition and harvesting solutions, which can effectively improve the degree of automation and harvesting quality of the potato harvesting process; the PLP-net algorithm is used to identify potatoes, on the one hand, providing a parallel manipulator with a gripping object and a gripping strategy to ensure gripping accuracy and gripping efficiency; on the other hand, it provides a basis for a grading and pushing device to grade potatoes, and directly performs fruit grading after the gripping is completed, thereby improving harvesting efficiency and quality.

Description

Technical Field

[0001] The present invention relates to the technical field of potato harvesting, in particular to a potato picking and harvesting method based on PLP-net. Background Art

[0002] Currently, the primary method of potato harvesting is segmented harvesting. First, a potato harvester is used to dig the potatoes out of the ground and initially separate any impurities. Then, a potato picker is used to collect the potatoes from the ground. Compared to potato combine harvesters, potato pickers offer greater adaptability and flexibility. However, these machines still suffer from a high rate of potato damage, so they are generally used to harvest starchy potatoes, while commercial potatoes are still picked manually. Manual harvesting is labor-intensive and inefficient; on the other hand, with the declining agricultural workforce, labor costs are rising year by year. These two factors severely constrain the potato industry's development, leading to the urgent need for a machine-replacement solution. Summary of the Invention

[0003] The present invention aims to solve the above problems and provides a potato picking and harvesting method based on PLP-net, the technical solution adopted by the present invention is as follows:

[0004] A potato picking and harvesting method based on PLP-net comprises the following steps:

[0005] S1. The harvesting robot moves from the starting point to the unharvested area;

[0006] S2. Identify potatoes to be picked up in the unpicked area based on the PLP-net algorithm;

[0007] S3. Positioning and calculating the plane position and grasping depth of the picked potatoes;

[0008] S4. Develop a potato grasping strategy and send commands to the grasping device;

[0009] S5. After the capture is completed, it is determined whether it is the last potato in the area. If not, steps S3 and S4 are repeated. If so, the harvesting robot is driven to move to the next unpicked area.

[0010] S6. Determine whether there is an unpicked area. If so, repeat steps S2 to S5. If not, complete the picking task.

[0011] The PLP-net algorithm described in step S2 includes a backbone extraction network and a detection head network. The backbone extraction network includes two branches, feature extraction and downsampling. The feature extraction branch uses the captured potato picture as an input signal, inputs the convolution layer, and then sequentially inputs the convolution layer and the residual block for feature extraction. The feature extraction branch includes a total of 5 convolution layers and 4 residual blocks. The result output from the first convolution layer is also used as the input of the downsampling branch for maximum pooling, and then sequentially performs feature fusion and maximum pooling with the results output from the second to fourth convolution layers. A residual block is set between the feature fusion after the fourth convolution layer and the maximum pooling. The last residual block output of the downsampling branch is input into the feature fusion branch for the last feature fusion. The calculated result is then subjected to the ECA residual block. The spatial pyramid pooling is performed and then input into the detection head network; in the detection head network, the first upsampling operation is performed first, and then the upsampling result is fused with the 6th layer of the feature extraction branch, and the fused features are input into the residual block. After the residual block is output, the second upsampling operation is performed and the features are fused with the 4th layer of the feature extraction branch, and the fused features are input into the convolution layer. The output of the convolution layer and the output of the residual block are fused again, and after the residual block is calculated again, the output features are obtained; the output features are divided into two branches, one of which is directly output by the medium target detection head, and the other branch is input into another convolution layer, whose output is fused with the output of the spatial pyramid pooling, and the fused features are output by the large target detection head.

[0012] Based on the above scheme, the picking and harvesting robot includes a body and a moving chassis. The moving chassis carries the body to move. The body is provided with a navigation depth camera for identifying unpicked areas and a satellite positioning module for positioning. The body is provided with an identification depth camera, a parallel manipulator and a conveying device. The identification depth camera is used to identify potatoes to be picked up in the area. The parallel manipulator is arranged in front of the conveying device and is used to clamp the potatoes identified by the identification depth camera and place them on the conveying device.

[0013] Based on the above scheme, the potato grasping strategy includes calculating the center point of the potato plane, the grasping depth, and the grasping angle. When identifying potatoes using the PLP-net algorithm, the center point of the selection box is used as the center point of the potato plane, and the center point is calculated as the coordinate of the potato center point. The distance between the highest point of the potato surface and the ground is identified and calculated by the recognition depth camera. The grasping depth coordinate value of the parallel manipulator is calculated by pre-determining the specific grasping depth value or depth ratio. The angle between the edge line of the potato selection box and the coordinate axis is calculated, and the grasping direction of the parallel manipulator is made parallel to the short side of the potato selection box to obtain the grasping angle of the parallel manipulator.

[0014] Preferably, after the parallel manipulator completes the grasping action, it provides feedback to the host computer of the picking and harvesting robot, and the feedback content includes the command acceptance status and the command execution status; the command acceptance status includes the target object grasping command and the manipulator behavior command, the target object grasping command indicates whether to start the action and grasp the target potato, the manipulator behavior command includes the grasping plane coordinates, the grasping depth coordinates and the manipulator grasping angle, the feedback results of the command acceptance status include receiving a completion signal, missing a partial signal and missing a complete signal; the command execution status indicates whether the target potato is successfully grasped.

[0015] Preferably, the conveying device includes a conveyor belt and baffles, and the number of the baffles is multiple and fixedly connected to the conveyor belt, and one potato is placed between adjacent baffles; the picking and harvesting robot also includes a grading pushing device, and the grading pushing device includes a pushing cylinder and a grading collection frame, and the pushing cylinder is arranged on one side of the conveyor belt, and pushes the potatoes on the conveyor belt into the grading collection frame; the number of the grading collection frames is multiple and arranged along the transmission direction of the conveyor belt, and each grading collection frame contains potatoes of different grades; after the appearance information of the potato to be grabbed is recognized by the depth camera, the upper computer calculates the weight of the potato and marks the grading information of the potato, and the potatoes of each grade are pushed into the grading collection frame by the pushing cylinder at the corresponding grading collection frame.

[0016] Based on the above scheme, the length, width and height information of the potatoes are extracted from the potato pictures taken by the recognition depth camera, and the weight of the potatoes is estimated and marked through a deep learning algorithm. Potatoes weighing more than 150g are defined as level one, potatoes weighing more than 100g and less than or equal to 150g are defined as level two, and potatoes weighing more than 50g and less than or equal to 100g are defined as level three.

[0017] Based on the above scheme, the deep learning algorithm uses a PW neural network to fit the potato weight training set. The input layer of the PW neural network includes three input data, namely length input l, width input b and height input c. The output layer includes one output signal, which is the potato weight d. Several hidden layers are set between the input layer and the output layer. The length, width, height and weight information of the potatoes in the training set are input into the PW neural network. Through multiple iterative training, the fitting relationship between the length, width and height of the potato and the weight is obtained.

[0018] Preferably, a lifting mechanism is provided in the vehicle body, the lifting mechanism includes a weight sensor and a limit switch, the grading and collecting frame is provided on the lifting mechanism, the lifting mechanism drives the grading and collecting frame to descend according to the weight of the potatoes therein, when the grading and collecting frame descends to the limit switch, the picking and harvesting robot suspends work, and the upper computer sends a box-changing command to the user.

[0019] Preferably, the picking and harvesting robot also includes a laser radar for identifying obstacles randomly encountered during the movement and driving the picking and harvesting robot to avoid them.

[0020] Preferably, the picking and harvesting robot uses the corners of the working area as the starting point of the work and moves continuously in an S shape.

[0021] The beneficial effects of the present invention are:

[0022] 1. The PLP-net algorithm is used to identify potatoes. This algorithm provides the parallel manipulator with object location information and grasping strategies, ensuring grasping accuracy and efficiency, effectively preventing potato damage or omission during the grasping process. It also provides a basis for the grading and pushing device to grade potatoes. After the grasping is completed, the fruit can be directly graded. This integration of multiple functions improves harvesting efficiency and quality.

[0023] 2. The PLP-net algorithm rationally reduces the number of detection heads, retaining only those for detecting large and medium-sized objects. This simplifies the model structure and reduces computational complexity, allowing the model to focus more on detecting potatoes with practical harvest value, thereby improving overall detection performance. The ECA attention mechanism is introduced to compensate for the potential loss in precision caused by the removal of detection heads, further enhancing the algorithm model's accuracy in potato offal identification in potato picking scenarios. By lightweighting the algorithm model, the computational speed is significantly increased while still meeting accuracy requirements. The simplified model structure also mitigates the computing power limitations of the host computer on small mobile devices.

[0024] 3. A harvesting robot was proposed that integrates the functions of movement, positioning, potato identification, grasping, potato grading, and obstacle avoidance. It can accurately grasp and grade potatoes without damage in a single operation, meeting the functional requirements of the potato harvesting process for mobile devices. The robot also achieves high integration, reduces equipment size and cost, and provides flexibility and controllability.

[0025] 4. Proposing a complete set of potato identification and harvesting solutions can effectively improve the automation level and harvesting quality of the potato harvesting process, significantly reduce the labor costs required, increase the harvesting speed, and contribute to the large-scale development of the potato industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 : Flowchart of the picking and harvesting method of the present invention;

[0027] Figure 2 : Schematic diagram of the structure of the picking and harvesting robot of the present invention;

[0028] Figure 3: The front view of the interior of the picking and harvesting robot of the present invention;

[0029] Figure 4 : Schematic diagram of the internal structure of the picking and harvesting robot of the present invention;

[0030] Figure 5 : Schematic diagram of the internal structure of the picking and harvesting robot of the present invention from another perspective;

[0031] Figure 6 : Schematic diagram of the lifting mechanism of the picking and harvesting robot of the present invention;

[0032] Figure 7 : Control principle diagram of the operating system of the present invention;

[0033] Figure 8 : Schematic diagram of the parallel manipulator working process of the present invention;

[0034] Figure 9 : Specific implementation diagram of the parallel manipulator workflow of the present invention;

[0035] Figure 10 : PLP-net algorithm network model diagram of the present invention;

[0036] Figure 11 : The residual block calculation structure model diagram in the PLP-net algorithm of the present invention;

[0037] Figure 12 : The convolutional layer calculation structure model diagram in the PLP-net algorithm of the present invention;

[0038] Figure 13 : The spatial pyramid pooling calculation structure model diagram in the PLP-net algorithm of the present invention;

[0039] Figure 14 : Calculation structure model diagram of the residual bottleneck module in the PLP-net algorithm of the present invention;

[0040] Figure 15 : ECA residual block structure model diagram in the PLP-net algorithm of the present invention;

[0041] Figure 16 : ECA residual bottleneck block structure model diagram in the PLP-net algorithm of the present invention;

[0042] Figure 17 : Diagram of the detection head calculation structure model in the PLP-net algorithm of the present invention;

[0043] Figure 18 :The present invention adopts Yolo v8n-obb algorithm test effect diagram;

[0044] Figure 19: The present invention adopts the PLP-net algorithm test effect diagram;

[0045] Figure 20 : PW neural network structure diagram of the present invention;

[0046] Figure 21 : Schematic diagram of the travel path of the picking and harvesting robot of the present invention.

[0047] Explanation of the accompanying symbols: 1-vehicle body, 2-motion chassis, 3-satellite positioning module, 41-navigation depth camera, 42-lidar, 43-recognition depth camera, 44-parallel manipulator, 51-conveyor belt, 52-baffle, 53-push cylinder, 54-grading and collecting frame, 55-lifting mechanism, 56-travel switch. DETAILED DESCRIPTION

[0048] The present invention will be further described below with reference to the accompanying drawings and examples:

[0049] In the present invention, unless otherwise expressly specified or limited, terms such as "mounted," "connected," "connect," and "fixed" should be understood broadly. For example, they may refer to fixed connection, detachable connection, or integration; they may refer to direct connection or indirect connection through an intermediate medium; they may refer to internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0050] In the description of the present invention, it should be understood that the terms "center", "length", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0051] In the present invention, unless otherwise expressly specified or limited, a first feature being "above" or "below" a second feature may include the first and second features being in direct contact, or may include the first and second features being in contact not directly but through another feature between them. Furthermore, a first feature being "above," "above," and "above" a second feature may include the first feature being directly above or obliquely above the second feature, or may simply mean that the first feature is higher in level than the second feature. A first feature being "below," "below," and "below" a second feature may include the first feature being directly below or obliquely below the second feature, or may simply mean that the first feature is lower in level than the second feature.

[0052] like Figure 1 As shown, a potato picking and harvesting method based on PLP-net includes the following steps:

[0053] S1. The harvesting robot moves from the starting point to the unharvested area;

[0054] S2. Identify potatoes to be picked up in the unpicked area based on the PLP-net algorithm;

[0055] S3. Positioning and calculating the plane position and grasping depth of the picked potatoes;

[0056] S4. Develop a potato grasping strategy and send commands to the grasping device;

[0057] S5. After the capture is completed, it is determined whether it is the last potato in the area. If not, steps S3 and S4 are repeated. If so, the harvesting robot is driven to move to the next unpicked area.

[0058] S6. Determine whether there is an unpicked area. If so, repeat steps S2 to S5. If not, complete the picking task.

[0059] like Figures 10 to 16As shown, the PLP-net algorithm described in step S2 is improved based on the Yolo v8-obb ​​algorithm model, including a backbone extraction network and a detection head network. The backbone extraction network includes two branches, feature extraction and downsampling. The feature extraction branch takes the captured potato picture as input, inputs the convolution layer, and then sequentially inputs the convolution layer and the residual block for feature extraction. The feature extraction branch includes a total of 5 convolution layers and 4 residual blocks. The result output from the first convolution layer is also used as the input of the downsampling branch for maximum pooling, and then sequentially performs feature fusion and maximum pooling with the results output from the second to fourth convolution layers. A residual block is set between the feature fusion after the fourth convolution layer and the maximum pooling. The last residual block output of the downsampling branch is input to the feature fusion branch for the last feature fusion. The calculated result is passed through the ECA residual block for space addition. The spatial pyramid pooling is then input into the detection head network; in the detection head network, the first upsampling operation is first performed, and then the upsampling result is fused with the 6th layer of the feature extraction branch, and the fused features are input into the residual block. After the residual block is output, the second upsampling operation is performed and the features are fused with the 4th layer of the feature extraction branch. The fused features are input into the convolution layer, and the output of the convolution layer is fused with the output of the residual block again. After the residual block is calculated again, the output features are obtained; the output features are divided into two branches, one of which is directly output by the medium target detection head, and the other branch is input into another convolution layer, and its output is fused with the output of the spatial pyramid pooling. The fused features are then output by the large target detection head. The detection feature map size corresponding to the large target detection head is 20*20, which is used to detect targets larger than 32*32, and the detection feature map size corresponding to the medium target detection head is 40*40, which is used to detect targets larger than 16*16.

[0060] Using the same equipment and the same configuration, the Yolo v8obb algorithm and the PLP-net algorithm were used to test the same batch of test sets. The experimental results are compared as follows: Figure 18 、 Figure 19 As shown in Table 1.

[0061] Table 1 Comparative test data of Yolo v8obb algorithm and PLP-net algorithm

[0062]

[0063] The above charts show that compared with Yolov8n-obb, the PLP-net model has slightly lower accuracy and average precision, but it is sufficient to meet the requirements for potato recognition. At the same time, the floating-point operations of the PLP-net model are reduced by 7.2 GFLOPs, the BN weight is reduced by 2.1 MB, and the frame rate is increased by 99.4 f / s. The data shows that the PLP-net model has less computation, better real-time performance, and faster running speed, making it more suitable for deployment on embedded devices with lower computing power.

[0064] like Figure 7 As shown in the figure, the harvesting robot can be divided into an upper-level decision-making component and a lower-level execution component. The upper-level decision-making component includes the potato harvesting robot operating system, which receives input signals from the navigation depth camera, recognition depth camera, lidar, and satellite positioning module. The lower-level execution component includes a parallel robotic arm, a conveying device, a graded pusher, and an intelligent motion chassis. The lower-level execution component receives commands from the upper-level decision-making component, executes corresponding actions, and provides information feedback. Wireless control is also included, allowing operators to use a 2.4G wireless remote control to drive the intelligent motion chassis.

[0065] like Figures 2 to 6 As shown, the picking and harvesting robot includes a body 1 and a moving chassis 2, the moving chassis 2 carries the body 1 to move, and a navigation depth camera 41 for identifying unpicked areas and a satellite positioning module 3 for positioning are provided on the body 1. An identification depth camera 43, a parallel manipulator 44 and a conveying device are provided in the body 1. The identification depth camera 43 is used to identify potatoes to be picked up in the area, and the parallel manipulator 44 is provided in front of the conveying device and is used to grab the potatoes identified by the identification depth camera 43 and place them on the conveying device.

[0066] like Figure 8 and Figure 9 As shown, the potato grasping strategy includes calculating the center point of the potato plane, the grasping depth, and the grasping angle. When the PLP-net algorithm is used to identify potatoes, the center point of the selection box is used as the center point (x, y) of the potato plane. The center point is calculated as the coordinate of the potato center point. The distance between the highest point of the potato surface and the ground is identified and calculated by the recognition depth camera 43. The grasping depth coordinate value z of the parallel manipulator 44 is calculated by pre-determining the specific grasping depth value or depth ratio. The angle between the edge line of the potato selection box and the coordinate axis in the plane is calculated, and the grasping direction of the parallel manipulator 44 is made parallel to the short side of the potato selection box to obtain the grasping angle of the parallel manipulator 44.

[0067] After the parallel manipulator 44 completes the grasping action, it provides feedback to the host computer of the picking and harvesting robot. The feedback content includes the command acceptance status and the command execution status. The command acceptance status includes the target object grasping command and the manipulator behavior command. The target object grasping command indicates whether to start the action and grasp the target potato. The manipulator behavior command includes the grasping plane coordinates, the grasping depth coordinates and the manipulator grasping angle. The feedback results of the command acceptance status include receiving a completion signal, missing a partial signal and missing a complete signal. The command execution status indicates whether the target potato is successfully grasped.

[0068] The conveying device includes a conveyor belt 51 and a baffle 52. There are multiple baffles 52 and they are fixedly connected to the conveyor belt 51. One potato is placed between adjacent baffles 52. The picking and harvesting robot also includes a grading pushing device. The grading pushing device includes a pushing cylinder 53 and a grading collection frame 54. The pushing cylinder 53 is arranged on one side of the conveyor belt 51 and pushes the potatoes on the conveyor belt 51 into the grading collection frame 54. There are multiple grading collection frames 54 and they are arranged along the transmission direction of the conveyor belt 51. Each grading collection frame 54 contains potatoes of different grades. After the appearance information of the potato to be grabbed is identified by the recognition depth camera 43, the upper computer calculates the weight of the potato and marks the grading information of the potato. Potatoes of each grade are pushed into the grading collection frame 54 by the pushing cylinder 53 at the corresponding grading collection frame 54.

[0069] Based on the potato image taken by the recognition depth camera 43, the length, width and height information of the potato are extracted, and the weight of the potato is estimated and marked using a deep learning algorithm. Potatoes weighing more than 150g are defined as level one, potatoes weighing more than 100g and less than or equal to 150g are defined as level two, and potatoes weighing more than 50g and less than or equal to 100g are defined as level three. Specifically, Figure 20 As shown, the deep learning algorithm uses a PW neural network to fit the potato weight training set. The input layer of the PW neural network includes three input data, namely, length input l, width input b and height input c. The output layer includes one output signal, which is the potato weight d. Several hidden layers are set between the input layer and the output layer. The length, width, height and weight information of the potatoes in the training set are input into the PW neural network. Through multiple iterative training, the fitting relationship between the length, width and height of the potato and the weight is obtained.

[0070] A lifting mechanism 55 is provided in the vehicle body 1, and the lifting mechanism 55 includes a weight sensor and a limit switch 56. The grading and collecting frame 54 is provided on the lifting mechanism 55. The lifting mechanism 55 drives the grading and collecting frame 54 to descend according to the weight of the potatoes therein. When the grading and collecting frame 54 descends to the limit switch 56, the picking and harvesting robot suspends work, and the upper computer sends a box-changing command to the user.

[0071] The picking and harvesting robot also includes a laser radar 42 for identifying obstacles randomly encountered during the movement and driving the picking and harvesting robot to avoid them.

[0072] The potatoes are placed in a loose distribution and are not in a straight line. Due to the low flexibility of satellite navigation, this solution uses a combination of camera vision navigation and satellite navigation. The main idea is to use visual navigation and satellite navigation in different scenarios based on their advantages and disadvantages. Optional travel methods include Figure 21 As shown, the picking and harvesting robot uses the corners of the working area as the starting point of the work and moves continuously in an S shape. When working in the field, it uses the navigation depth camera 41 for visual navigation, which has good flexibility. When turning and turning around in the field, it uses the satellite positioning module 3 for satellite navigation, which has high accuracy. The dotted part in the figure is the visual navigation area, and the implementation part is the satellite navigation area.

[0073] The present invention has been described above by way of examples, but the present invention is not limited to the above specific embodiments. Any changes or modifications based on the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A potato picking and harvesting method based on PLP-net, characterized in that: The following steps are included: S1. The harvesting robot moves from the starting point to the unharvested area; S2. Identify potatoes to be picked up in the unpicked area based on the PLP-net algorithm; S3. Positioning and calculating the plane position and grasping depth of the picked potatoes; S4. Develop a potato grasping strategy and send commands to the grasping device; S5. After the capture is completed, it is determined whether it is the last potato in the area. If not, steps S3 and S4 are repeated. If so, the harvesting robot is driven to move to the next unpicked area. S6. Determine whether there is an unpicked area. If so, repeat steps S2 to S5. If not, complete the picking task. The PLP-net algorithm described in step S2 includes a backbone extraction network and a detection head network. The backbone extraction network includes two branches: feature extraction and downsampling. The feature extraction branch takes the captured potato picture as input, inputs it into the convolution layer, and then sequentially inputs it into the convolution layer and the residual block for feature extraction. The feature extraction branch includes 5 convolution layers and 4 residual blocks. The output result from the first convolution layer is also used as the input of the downsampling branch for maximum pooling, and then sequentially performs feature fusion and maximum pooling with the output results of the second to fourth convolution layers. A residual block is set between the feature fusion and maximum pooling after the fourth convolution layer, and the last residual block of the downsampling branch is output and input into the feature fusion branch for the last feature fusion. The calculated result is subjected to spatial pyramid pooling after the ECA residual block and then input into the detection head network. In the detection head network, first, The first upsampling operation is performed, and then the upsampling result is fused with the 6th layer of the feature extraction branch. The fused features are input into the residual block. After the residual block is output, the second upsampling operation is performed and the features are fused with the 4th layer of the feature extraction branch. The fused features are input into the convolution layer. The output of the convolution layer and the output of the residual block are fused again. After the residual block is calculated again, the output features are obtained. The output features are divided into two branches, one of which is directly output by the medium target detection head, and the other branch is input into another convolution layer, whose output is fused with the output of the spatial pyramid pooling, and the fused features are output by the large target detection head.

2. A potato picking and harvesting method based on PLP-net according to claim 1, characterized in that: The picking and harvesting robot comprises a vehicle body (1) and a moving chassis (2), wherein the moving chassis (2) carries the vehicle body (1) for movement, and a navigation depth camera (41) for identifying an unpicked area and a satellite positioning module (3) for positioning are provided on the vehicle body (1). An identification depth camera (43), a parallel manipulator (44) and a conveying device are provided in the vehicle body (1), wherein the identification depth camera (43) is used to identify potatoes to be picked up in the area, and the parallel manipulator (44) is provided in front of the conveying device and is used to clamp the potatoes identified by the identification depth camera (43) and place them on the conveying device.

3. A potato picking and harvesting method based on PLP-net according to claim 2, characterized in that: The potato grasping strategy includes calculating the center point of the potato plane, the grasping depth and the grasping angle. When the potato is identified by the PLP-net algorithm, the center point of the selected box is used as the center point of the potato plane, and the center point is calculated as the coordinate of the potato center point. The distance between the highest point of the potato surface and the ground is identified and calculated by the recognition depth camera (43). The grasping depth coordinate value of the parallel manipulator (44) is calculated by pre-determining the specific grasping depth value or depth ratio. The angle between the edge line of the potato selection box and the coordinate axis is calculated, and the grasping direction of the parallel manipulator (44) is made parallel to the short side of the potato selection box to obtain the grasping angle of the parallel manipulator (44).

4. A potato picking and harvesting method based on PLP-net according to claim 2, characterized in that: After the parallel manipulator (44) completes the grasping action, it provides feedback to the host computer of the picking and harvesting robot, and the feedback content includes the command acceptance status and the command execution status; the command acceptance status includes the target object grasping command and the manipulator behavior command, the target object grasping command indicates whether to start the action and grasp the target potato, the manipulator behavior command includes the grasping plane coordinates, the grasping depth coordinates and the manipulator grasping angle, the feedback result of the command acceptance status includes receiving a completion signal, missing a partial signal and missing a complete signal; the command execution status indicates whether the target potato is successfully grasped.

5. The potato picking and harvesting method based on PLP-net according to claim 2, characterized in that: The conveying device includes a conveyor belt (51) and a baffle (52), the baffles (52) are multiple in number and fixedly connected to the conveyor belt (51), and one potato is placed between adjacent baffles (52); the picking and harvesting robot also includes a grading pushing device, the grading pushing device includes a pushing cylinder (53) and a grading collection frame (54), the pushing cylinder (53) is arranged on one side of the conveyor belt (51), and pushes the potatoes on the conveyor belt (51) into the grading collection frame (54); the grading collection frame (54) is multiple in number and arranged along the transmission direction of the conveyor belt (51), and each grading collection frame (54) contains potatoes of different grades; after the appearance information of the potato to be grabbed is recognized by the recognition depth camera (43), the upper computer calculates the weight of the potato and marks the grading information of the potato, and the potatoes of each grade are pushed into the grading collection frame (54) by the pushing cylinder (53) at the corresponding grading collection frame (54).

6. A potato picking and harvesting method based on PLP-net according to claim 5, characterized in that: Based on the potato pictures taken by the recognition depth camera (43), the length, width and height information of the potatoes are extracted, and the weight of the potatoes is estimated and marked using a deep learning algorithm. Potatoes weighing more than 150g are defined as level one, potatoes weighing more than 100g but less than or equal to 150g are defined as level two, and potatoes weighing more than 50g but less than or equal to 100g are defined as level three.

7. A potato picking and harvesting method based on PLP-net according to claim 6, characterized in that: The deep learning algorithm uses a PW neural network to fit a potato weight training set. The input layer of the PW neural network includes three input data, namely, length input l, width input b, and height input c. The output layer includes one output signal, which is the potato weight d. Several hidden layers are arranged between the input layer and the output layer. The length, width, height, and weight information of the potatoes in the training set are input into the PW neural network. Through multiple iterative training, a fitting relationship between the length, width, height, and weight of the potatoes is obtained.

8. The potato picking and harvesting method based on PLP-net according to claim 5, characterized in that: A lifting mechanism (55) is provided in the vehicle body (1), and the lifting mechanism (55) includes a weight sensor and a travel switch (56). A grading and collecting frame (54) is provided on the lifting mechanism (55). The lifting mechanism (55) drives the grading and collecting frame (54) to descend according to the weight of the potatoes therein. When the grading and collecting frame (54) descends to the travel switch (56), the picking and harvesting robot stops working, and the upper computer sends a box-changing command to the user.

9. The potato picking and harvesting method based on PLP-net according to claim 1, characterized in that: The picking and harvesting robot also includes a laser radar (42) for identifying obstacles randomly encountered during the movement and driving the picking and harvesting robot to avoid them.

10. The potato picking and harvesting method based on PLP-net according to claim 1, characterized in that: The picking and harvesting robot uses the corners of the working area as the starting point and moves continuously in an S-shape.

Images