Agricultural machinery, a system for generating cutting point data for fruit tree branches, and a method for generating cutting point data for fruit tree branches.

Abstract

The present invention provides a method for generating cutting point data, a system for generating cutting point data, and agricultural machinery, which can be used to promote the automation and unmanned operation of fruit tree pruning while maintaining fruit yield and quality, and which includes information indicating the three-dimensional position of the points on which fruit tree branches should be cut. [Solution] A method for generating cutting point data, which includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, using one or more computing devices, includes: obtaining information on a pruning mode selected by a user from a plurality of pruning modes, each of which has a different method for determining the point on which a fruit tree branch should be cut; determining one or more points on which a fruit tree branch should be cut based on sensor data of the fruit tree branch obtained by one or more sensors and the selected pruning mode; and generating cutting point data for each of the one or more points on which a fruit tree branch should be cut.

Description

[Technical Field]

[0001] This disclosure relates to agricultural machinery, a system for generating cutting point data for fruit tree branches, and a method for generating cutting point data for fruit tree branches. [Background technology]

[0002] As a next-generation agricultural initiative, research and development of smart agriculture utilizing ICT (Information and Communication Technology) and IoT (Internet of Things) is underway. Research and development is also progressing toward the automation and unmanned operation of agricultural vehicles such as tractors used in the fields. For example, agricultural vehicles that automatically steer using positioning systems such as GNSS (Global Navigation Satellite System), which are capable of precise positioning, have been put into practical use.

[0003] Patent Document 1 describes a work vehicle capable of autonomously moving between multiple rows of trees in an orchard such as a vineyard. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] U.S. Patent Application Publication No. 2023 / 288936 [Overview of the project] [Problems that the invention aims to solve]

[0005] There is a demand for automation and unmanned operation of pruning work on fruit trees in orchards such as vineyards. Pruning is the process of removing unnecessary branches from fruit trees in order to shape the tree. Pruning can be performed during both the growing season and the dormant season, but in this specification, it mainly refers to the work performed during the dormant season (e.g., winter), after the harvest of the year's fruit has finished and before the growth of the fruit trees for the following year begins. The amount and quality of the harvest in the next season are determined by which branches are cut and which are left, so pruning work performed during the dormant season is considered one of the important tasks in fruit tree cultivation. In pruning work, it is necessary to make a comprehensive judgment on the health of each fruit tree, the amount of sunlight it receives, the amount of airflow, etc., for each fruit tree which has a different shape, and to perform the optimal pruning for each fruit tree based on experience and intuition. Automating pruning work that involves such judgment is not easy.

[0006] This disclosure aims to provide a method for generating cutting point data, a system for generating cutting point data, and an agricultural machine having such a system, which can solve the aforementioned problems, and which include information indicating the three-dimensional position of the point on which a fruit tree branch should be cut. [Means for solving the problem]

[0007] Preferred embodiments of the present invention relate to a method for generating cutting point data including information indicating the three-dimensional position of a point to be cut on a fruit tree branch, a system for generating cutting point data for fruit tree branches, and an agricultural machine having such a system.

[0008] This disclosure provides solutions as described in the following items.

[0009] [Item a1] A method for generating cutting point data, which includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, using one or more computing devices, The method for determining the point on which the fruit tree branches should be cut involves obtaining information on the pruning mode selected by the user from a plurality of different pruning modes, Based on sensor data of the fruit tree branches acquired by one or more sensors, and the selected pruning mode, one or more points to be cut are determined for the fruit tree branches. To generate the cutting point data for each of the one or more points to be cut. Methods that include...

[0010] [Item a2] The method according to item a1, further comprising inputting the generated cutting point data into a control device that controls the three-dimensional position of a cutter for cutting the branches of the fruit tree.

[0011] [Item a3] Determining the one or more points to be cut means Based on the aforementioned sensor data, measurement values ​​for two or more attributes of one or more branches of the fruit tree are obtained, Based on the measured values ​​and the priority of the two or more attributes, it is determined whether each of the one or more branches should be removed or kept. For each of the branches designated as to be removed, determine the point at which to cut. Includes, The method according to item a1 or a2, wherein the setting of the priority is made different according to the pruning mode.

[0012] [Item a4] The method according to item a3, wherein the two or more attributes include at least one of the following: the color of the branch, the direction in which the branch grows, the thickness of the branch, the height of the base of the branch, the size of the buds on the branch, the direction in which the buds on the branch face, the length of the branch, and the length of the internodes of the branch.

[0013] [Item a5] The method according to item a3 or a4, wherein the user can change and save the priority settings of the plurality of pruning modes.

[0014] [Item a6] Determining the one or more points to be cut means Based on the sensor data, obtaining measurement values regarding one or more attributes of each of the one or more branches of the fruit tree; Based on the measurement values, determining for each of the one or more branches whether it is a branch to be removed or a branch to be left; For each of the branches determined to be branches to be removed, determining a point to be cut; including; The method according to item a1 or a2, wherein in determining the point to be cut, the setting of the validity / invalidity of the setting parameter regarding the measurement value, which can be switched between valid / invalid, is made different according to the pruning mode.

[0015] [Item a7] The one or more attributes include the color of the branch, The setting of the validity / invalidity of the setting parameter regarding the measurement value is The method according to item a6, including the setting of the validity / invalidity of determining the branch with a green color of the branch as the branch to be left.

[0016] [Item a8] When the setting is valid, determining for each of the one or more branches whether it is a branch to be removed or a branch to be left is Based on the measurement value regarding the color of the branch, including determining the branch with a green color of the branch as the branch to be left, the method according to item a7.

[0017] [Item a9] Determining the one or more points to be cut is Based on the measurement values, determining the number of buds to be left on the branches determined to be branches to be left; Based on the number of buds to be left, determining a point to be cut for the branches determined to be branches to be left; further including; The one or more attributes include attributes related to the vigor of the fruit tree, The setting of the validity / invalidity of the setting parameter regarding the measurement value is The method according to any one of items a6 to a8, including enabling / disabling the setting of enabling / disabling the number of buds to be left on the branches determined to be left based on the measured values ​​relating to the vigor of the fruit tree.

[0018] [Item a10] If the above setting is enabled, determining the number of buds to leave is: Based on the measured values ​​relating to the vigor of the fruit tree, if it is determined that the vigor of the branch to be kept is stronger than a predetermined range, the number of buds to be left on the branch to be kept will be increased. The method according to item a9, wherein, based on the measured values ​​relating to the vigor of the fruit tree, if it is determined that the vigor of the branch to be kept is weaker than the predetermined range, the number of buds to be left on the branch to be kept is reduced.

[0019] [Item a11] The method according to item a9 or a10, wherein the attributes relating to the vigor of the fruit tree include at least one of the thickness of the branch, the size of the buds on the branch, and the length of the internodes of the branch.

[0020] [Item a12] The attributes related to the vigor of the aforementioned fruit tree include the thickness of the branches, Determining whether each of the one or more branches to be removed or kept is: For each of the one or more branches mentioned above, a factor score is determined based on the thickness of that branch. Based on the factor score, it is determined whether each of the one or more branches will be designated as a branch to be removed or a branch to be kept. Includes, If the above setting is enabled, determining the number of buds to leave is: If the factor score for the thickness of the branch determined to be kept is greater than a predetermined range, the number of buds to be kept is increased beyond a predetermined value. The method according to any one of items a9 to a11, wherein if the factor score for the thickness of the branch determined to be kept is smaller than the predetermined range, the number of buds to be kept is reduced to a predetermined value.

[0021] [Item a13] The factor score for each of the one or more branches relating to the thickness of the branch is: If the thickness of the branch is greater than the predetermined range, the thickness of the branch will be lower than when the thickness of the branch is within the predetermined range. The method according to item a12, wherein if the thickness of the branch is smaller than the predetermined range, it is determined to be lower than if the thickness of the branch is larger than the predetermined range.

[0022] [Item a14] The attributes related to the vigor of the aforementioned fruit tree include the size of the buds on the branches. Determining whether each of the one or more branches to be removed or kept is: For each of the one or more branches mentioned above, a factor score is determined based on the size of the buds on that branch. Based on the factor score, it is determined whether each of the one or more branches will be designated as a branch to be removed or a branch to be kept. Includes, If the above setting is enabled, determining the number of buds to leave is: If the factor score relating to the size of the buds of the branches determined to be kept is greater than a predetermined range, the number of buds to be kept is increased beyond a predetermined value. The method according to any one of items a9 to a13, wherein if the factor score for the size of the buds of the branch determined to be retained is smaller than the predetermined range, the number of buds to be retained is reduced to a predetermined value.

[0023] [Item a15] The factor score for each of the one or more branches with respect to the size of the bud is, If the average size of the buds on the branch is greater than the predetermined range, then the average size of the buds on the branch will be lower than when the average size is within the predetermined range. The method according to item a14, wherein if the average value of the bud size on the branch is smaller than the predetermined range, it is determined to be lower than if the average value of the bud size on the branch is larger than the predetermined range.

[0024] [Item a16] The method according to any one of items a6 to a15, wherein the user can change and save the enable / disable setting of the setting parameter relating to the measured value for the plurality of pruning modes.

[0025] [Item a17] A system for generating cutting point data that includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, One or more sensors that acquire sensor data from the branches of the fruit tree, A data processing device that generates the cutting point data of the fruit tree branches based on the sensor data, Equipped with, The aforementioned data processing device is The method for determining the point to cut the fruit tree branches obtains information on the pruning mode selected by the user from a plurality of different pruning modes, Based on the sensor data and the selected pruning mode, one or more points to be cut are determined for the fruit tree branch. A system that generates cutting point data for each of the one or more cutting points.

[0026] [Item a18] A system for generating cutting point data that includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, One or more sensors that acquire sensor data from multiple branches of the fruit tree, Means for carrying out the steps of the method described in any one of items a1 to a15 A system that has

[0027] [Item a19] The system further comprises a cutter for cutting the branches of the fruit tree and a control device for controlling the three-dimensional position of the cutter. The data processing device inputs the generated cutting point data to the control device. The control device controls the three-dimensional position of the cutter based on the cutting point data, as described in item a17 or a18.

[0028] [Item a20] Agricultural machinery having a system described in any one of items a17 to a19.

[0029] [Item a21] The system further comprises an arm that supports the cutter, a support that supports the arm, and a drive device that moves the support. The control device controls the three-dimensional position of the cutter by controlling the movement of the arm, as described in item a20, reference to item a19.

[0030] [Item b1] A method for generating cutting point data, which includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, using one or more computing devices, The method for determining the point on which the fruit tree branches should be cut involves obtaining information on the pruning mode selected by the user from a plurality of different pruning modes, Based on sensor data of the fruit tree branches acquired by one or more sensors, and the selected pruning mode, one or more points to be cut are determined for the fruit tree branches. To generate the cutting point data for each of the one or more points to be cut. Includes, A method for determining the points to be cut, wherein the enabled / disabled settings of one or more switchable setting parameters differ depending on the pruning mode.

[0031] [Item b2] The setting to enable / disable the one or more setting parameters mentioned above is: The method according to item b1, including setting whether or not to determine the one or more points to be cut again after determining the one or more points to be cut.

[0032] [Item b3] If the above setting is enabled, After determining the one or more points to be cut, the system determines the one or more points to be cut again based on user instructions, sensor data, and pruning mode. To generate cutting point data for each of the one or more cutting points that have been determined again. The method described in item b2, further including the method described in item b2.

[0033] [Item b4] The setting to enable / disable the one or more setting parameters mentioned above is: The method according to item b1, including enabling / disabling the setting of presenting the generated cutting point data to the user and receiving user instructions.

[0034] [Item b5] The generated cutting point data is further input to a control device that controls the three-dimensional position of a cutter used to cut the fruit tree branches. If the above setting is enabled, The method according to item b4, further comprising displaying the generated cutting point data on a display device of a user's terminal device before inputting it to the control device, and receiving user instructions input from the terminal device.

[0035] [Item b6] The setting to enable / disable the one or more setting parameters mentioned above is: The method according to item b1, comprising setting whether to enable or disable the generation of the cutting point data such that the branch is cut by a plane perpendicular to the direction in which the branch grows.

[0036] [Item b7] If the above setting is enabled, the cutting point data is generated as follows: This includes generating the cutting point data such that the branch is cut by a plane perpendicular to the direction in which the branch is growing, If the above setting is invalid, the cutting point data will not be generated. The method of item b6, comprising generating the cutting point data such that the branch is cut in a plane horizontal to the ground.

[0037] [Item b8] The setting to enable / disable the one or more setting parameters mentioned above is: The method according to item b1, including setting whether or not to enable / disable determining which branches to keep from two or more branches of the fruit tree to be treated.

[0038] [Item b9] If the above setting is enabled, determining the one or more points to be cut is: Based on the sensor data, determine whether each of the two or more branches should be designated as a branch to be removed or a branch to be kept, such that at least two of the two or more branches are designated as branches to be kept. For each of the branches designated as to be removed, determine the point at which to cut. The method described in item b8, including the method described in item b8.

[0039] [Item b10] If the above setting is enabled, determining whether each of the two or more branches is to be removed or kept is: Based on the aforementioned sensor data, measurement values ​​are obtained for each of the two or more branches and two or more attributes. Based on the measured values ​​and the priority of the two or more attributes, it is determined whether each of the two or more branches should be removed or kept. The method described in item b9, including the method described in item b9.

[0040] [Item b11] If the above setting is enabled, determining whether each of the two or more branches is to be removed or kept is: For each of the two or more branches, a factor score is determined based on the measured values ​​for each of the two or more attributes. For each of the two or more branches, a total score is calculated based on the factor score for each of the two or more attributes and the priority of that attribute. Based on the total score, it is determined whether each of the two or more branches will be designated as a branch to be removed or a branch to be kept. The method described in item b10, including the method described in item b10.

[0041] [Item b12] The setting to enable / disable the one or more setting parameters mentioned above is: The method according to item b1, which includes setting whether or not to include the bud closest to the base of the branch in the determination of the number of buds to leave on the branch that has been determined to be left on the fruit tree.

[0042] [Item b13] Determining the one or more points to be cut means Based on the aforementioned sensor data, it is determined whether each of the one or more branches should be removed or kept. For each of the branches designated as to be removed, the point at which to cut should be determined, Based on the aforementioned measurement values, the number of buds to be left on the branch that has been determined to remain is determined, Based on the number of buds to be left, the point to be cut on the branch that has been decided to be left is determined. Includes, If the above setting is enabled, determining the number of buds to leave is: The method according to item b12, comprising determining the number of buds to be kept by counting the bud closest to the base of the branch in question into the number of buds to be kept.

[0043] [Item b14] The setting to enable / disable the one or more setting parameters mentioned above is: The method according to item b1, including setting whether or not to enable the removal of non-candidate branches that should not be selected as branches to be kept from one or more branches of the fruit tree to be treated, before determining which branches to keep.

[0044] [Item b15] Determining the one or more points to be cut means Based on the sensor data, it is determined whether each of the one or more branches will be a branch to be removed or a branch to be kept. For each of the branches designated as to be removed, determine the point at which to cut. Includes, If the above setting is enabled, determining whether each of the one or more branches is to be removed or kept is: Based on the sensor data, determine whether the one or more branches include any non-candidate branches that should not be selected as branches to be kept. If the aforementioned non-candidate branches are included, the branch selected from the branches remaining after removing the non-candidate branches from the one or more branches shall be determined as the branch to be kept. The method described in item b14, including the method described in item b14.

[0045] [Item b16] The setting to enable / disable the one or more setting parameters mentioned above is: The method according to item b1, comprising, after determining whether one or more branches of the fruit tree to be treated should be removed or left, setting an enable / disable setting for determining whether to maintain or change the decision on whether to remove or leave the branches, based on the distribution of buds on the branches determined to be left.

[0046] [Item b17] If the above setting is enabled, determining the one or more points to be cut is: Based on the aforementioned sensor data, it is determined whether each of the one or more branches grouped into one of several groups should be removed or kept. Based on the distribution of buds on the branches designated as branches to be kept for each of the aforementioned multiple groups, a decision is made to maintain or change the decision regarding whether each of the one or more branches grouped into other groups should be designated as a branch to be removed or a branch to be kept. For each of the branches designated as to be removed, determine the point at which to cut. The method described in item b16, including the method described in item b16.

[0047] [Item b18] The setting to enable / disable the one or more setting parameters mentioned above is: After determining the one or more points to be cut, the setting of whether or not to determine the one or more points to be cut again. The generated cutting point data is presented to the user, and the ability to enable / disable receiving user instructions is set. In generating the aforementioned cutting point data, the setting to enable / disable generating the cutting point data so that the branch is cut by a plane perpendicular to the direction in which the branch is growing, The setting to enable / disable the determination of which branches to keep from two or more branches of the fruit tree to be treated. In determining the number of buds to leave on the branches of the fruit tree that have been selected to remain, the setting of whether or not to include the bud closest to the base of the branch, The setting to enable / disable the removal of non-candidate branches that should not be selected as branches to be kept from one or more branches of the fruit tree to be processed, before deciding which branches to keep, and After deciding whether to remove or keep one or more branches of the fruit tree to be treated, the system enables / disables the setting to maintain or change the decision on whether to remove or keep a branch, based on the distribution of buds on the branches that have been decided to keep. The method described in item b1, which includes at least one of the following.

[0048] [Item b19] The method according to any one of items b1 to b18, wherein the user can change and save the enable / disable settings of one or more setting parameters of the multiple pruning modes.

[0049] [Item b20] A system for generating cutting point data that includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, One or more sensors that acquire sensor data from the branches of the fruit tree, A data processing device that generates the cutting point data of the fruit tree branches based on the sensor data, Equipped with, The aforementioned data processing device is The method for determining the point to cut the fruit tree branches obtains information on the pruning mode selected by the user from a plurality of different pruning modes, Based on the sensor data and the selected pruning mode, one or more points to be cut are determined for the fruit tree branch. For each of the one or more points to be cut, the cutting point data is generated. A system that determines the point to be cut by enabling or disabling one or more switchable setting parameters, and enables or disables them depending on the pruning mode.

[0050] [Item b21] A system for generating cutting point data that includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, One or more sensors that acquire sensor data from the branches of the fruit tree, Means for carrying out the steps of the method described in any one of items b1 to b19 A system that has

[0051] [Item b22] The system further comprises a cutter for cutting the branches of the fruit tree and a control device for controlling the three-dimensional position of the cutter. The data processing device inputs the generated cutting point data to the control device. The control device controls the three-dimensional position of the cutter based on the cutting point data, as described in item b20 or b21.

[0052] [Item b23] Agricultural machinery having a system described in any one of items b20 to b22.

[0053] [Item b24] The system further comprises an arm that supports the cutter, a support that supports the arm, and a drive device that moves the support. The control device controls the three-dimensional position of the cutter by controlling the movement of the arm, as described in item b23, reference to item b22.

[0054] [Item c1] A method for generating cutting point data, which includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, using one or more computing devices, The method for determining the point on which the fruit tree branches should be cut involves obtaining information on the pruning mode selected by the user from a plurality of different pruning modes, Based on sensor data of the fruit tree branches acquired by one or more sensors, and the selected pruning mode, one or more points to be cut are determined for the fruit tree branches. To generate the cutting point data for each of the one or more points to be cut. Includes, The aforementioned multiple pruning modes are, The first pruning mode, In the determination of the points to be cut, the setting of priority for two or more attributes of the fruit tree branch is the same as in the first pruning mode, and the setting of enable / disable one or more switchable setting parameters in the determination of the points to be cut is different from that of the first pruning mode, in the second pruning mode. Methods that include...

[0055] [Item c2] Determining the one or more points to be cut means Based on the sensor data, measurement values ​​for each of the two or more attributes of one or more branches of the fruit tree are obtained, Based on the measured values ​​and the priority of the two or more attributes, it is determined whether each of the one or more branches should be removed or kept. For each of the branches designated as to be removed, determine the point at which to cut. The method described in item c1, including the method described in item c1.

[0056] [Item c3] The method according to item c1 or c2, further comprising inputting the generated cutting point data into a control device that controls the three-dimensional position of a cutter for cutting the fruit tree branches.

[0057] [Item c4] The method according to any one of items c1 to c3, wherein the plurality of pruning modes further include a third pruning mode in which the priority setting differs from that of the first pruning mode and the enable / disable setting of the one or more setting parameters is the same as that of the first pruning mode.

[0058] [Item c5] The two or more attributes mentioned above include attributes related to the vigor of the fruit tree, The method according to item c4, wherein in the third pruning mode, the priority of attributes related to the vigor of the fruit tree is higher than in the first pruning mode.

[0059] [Item c6] The method according to item c5, wherein the attributes related to the vigor of the fruit tree include at least one of the thickness of the branches, the size of the buds on the branches, and the length of the internodes of the branches.

[0060] [Item c7] Determining the one or more points to be cut means Based on the aforementioned measurement values, the number of buds to be left on the branch that has been determined to remain is determined, Based on the number of buds to be left, the point to be cut on the branch that has been decided to be left is determined. It further includes, In the third pruning mode, the setting to enable / disable the adjustment of the number of buds to be left on the branches determined to be left based on the measured values ​​relating to the vigor of the fruit tree is enabled, as described in item c5 or c6.

[0061] [Item c8] The two or more attributes mentioned above include attributes related to the tree shape of the fruit tree, The method according to item c4, wherein in the third pruning mode, the priority of attributes related to the shape of the fruit tree is higher than in the first pruning mode.

[0062] [Item c9] The method according to item c8, wherein the attributes related to the shape of the fruit tree include at least one of the direction in which the branches grow, the height of the base of the branches, the direction in which the buds on the branches face, and the length of the branches.

[0063] [Item c10] The two or more attributes mentioned above include attributes related to the health status of the fruit tree, The method according to any one of items c4 to c9, wherein in the third pruning mode, the priority of the attribute related to the health of the fruit tree is lower than in the first pruning mode.

[0064] [Item c11] The attributes related to the health of the fruit tree are those described in item c10, including the color of the branches.

[0065] [Item c12] The setting to enable / disable the one or more setting parameters mentioned above is: After determining the one or more points to be cut, the setting of whether or not to determine the one or more points to be cut again. The generated cutting point data is presented to the user, and the ability to enable / disable receiving user instructions is set. In generating the aforementioned cutting point data, the setting to enable / disable generating the cutting point data so that the branch is cut by a plane perpendicular to the direction in which the branch is growing, The setting to enable / disable the determination of which branches to keep from two or more branches of the fruit tree to be treated. In determining the number of buds to leave on the branches of the fruit tree that have been selected to remain, the setting of whether or not to include the bud closest to the base of the branch, The setting to enable / disable the removal of non-candidate branches that should not be selected as branches to be kept from one or more branches of the fruit tree to be processed, before deciding which branches to keep, and After deciding whether to remove or keep one or more branches of the fruit tree to be treated, the system enables / disables the setting to maintain or change the decision on whether to remove or keep a branch, based on the distribution of buds on the branches that have been decided to keep. The method described in any one of items c1 to c11, including at least one of the following.

[0066] [Item c13] The method according to any one of items c1 to c12, wherein the user can change and save the settings for the priority of the multiple pruning modes and the settings for enabling / disabling one or more setting parameters.

[0067] [Item c14] A system for generating cutting point data that includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, One or more sensors that acquire sensor data from the branches of the fruit tree, A data processing device that generates the cutting point data of the fruit tree branches based on the sensor data, Equipped with, The aforementioned data processing device is The method for determining the point to cut the fruit tree branches obtains information on the pruning mode selected by the user from a plurality of different pruning modes, Based on the sensor data and the selected pruning mode, one or more points to be cut are determined for the fruit tree branch. For each of the one or more points to be cut, the cutting point data is generated. The aforementioned multiple pruning modes are, The first pruning mode, In the determination of the points to be cut, the setting of priority for two or more attributes of the fruit tree branch is the same as in the first pruning mode, and the setting of enable / disable one or more switchable setting parameters in the determination of the points to be cut is different from that of the first pruning mode, in the second pruning mode. A system that includes this.

[0068] [Item c15] A system for generating cutting point data that includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, One or more sensors that acquire sensor data from the branches of the fruit tree, Means for carrying out the steps of the method described in any one of items c1 to c13 A system that has

[0069] [Item c16] The system further comprises a cutter for cutting the branches of the fruit tree and a control device for controlling the three-dimensional position of the cutter. The data processing device inputs the generated cutting point data to the control device. The control device controls the three-dimensional position of the cutter based on the cutting point data, as described in item c14 or c15.

[0070] [Item c17] Agricultural machinery having a system described in any one of items c14 through c16.

[0071] [Item c18] The system further comprises an arm that supports the cutter, a support that supports the arm, and a drive device that moves the support. The control device controls the three-dimensional position of the cutter by controlling the movement of the arm, as described in item c17, reference to item c16.

[0072] [Item d1] A method for generating cutting point data, which includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, using one or more computing devices, The method for determining the point to be cut on the fruit tree branches is a plurality of pruning modes, each of which is associated with a method for cultivating the fruit tree. Information on the pruning mode selected by the user is obtained from these plurality of pruning modes. Based on sensor data of the fruit tree branches acquired by one or more sensors, and the selected pruning mode, one or more points to be cut are determined for the fruit tree branches. To generate the cutting point data for each of the one or more points to be cut. Includes, A method for determining the point to be cut, wherein the method for determining the point to be cut varies according to the cultivation method of the fruit tree.

[0073] [Item d2] The method for cultivating the fruit tree, as described in item d1, comprising at least one of the shape of the trellis system for the fruit tree, the pruning method for the fruit tree, and the training method for the fruit tree.

[0074] [Item d3] The method according to item d1 or d2, further comprising inputting the generated cutting point data into a control device that controls the three-dimensional position of a cutter for cutting the fruit tree branches.

[0075] [Item d4] Before obtaining the information on the aforementioned pruning mode, To obtain information on the aforementioned fruit trees, Based on the acquired information about the fruit trees, the system presents the user with candidates for the pruning mode. The method described in any one of items d1 to d3, further including the method described in any one of items d1 to d3.

[0076] [Item d5] The method according to item d4, wherein the information of the fruit tree includes at least one of the information on the cultivation method of the fruit tree, the variety of the fruit tree, the age of the fruit tree, and the field in which the fruit tree is located.

[0077] [Item d6] Obtaining information on the aforementioned fruit trees means A method according to item d4 or d5, which includes obtaining information about the fruit tree based on user input.

[0078] [Item d7] Obtaining information on the aforementioned fruit trees means The method according to item d4 or d5, comprising obtaining information about the fruit tree based on sensor data of the fruit tree or the field in which the fruit tree is located.

[0079] [Item d8] The method according to any one of items d1 to d7, wherein, depending on the cultivation method of the fruit tree, the setting of priority for two or more attributes of the fruit tree's branches in determining the point to be cut, and / or the setting of enabling or disabling one or more switchable setting parameters in determining the point to be cut.

[0080] [Item d9] The method according to item d8, wherein the setting of the priority differs depending on the cultivation method of the fruit tree.

[0081] [Item d10] The two or more attributes mentioned above include the length of the branch and / or the length of the internodes of the branch. The method according to item d9, wherein the priority of branch length and / or internode length of branches is varied depending on the pruning method of the fruit tree.

[0082] [Item d11] The two or more attributes mentioned above include the direction in which the buds on the branch face, and / or the size of the buds on the branch. The method according to item d9 or d10, wherein, depending on the pruning method of the fruit tree, the priority of the direction in which the buds on the branches face and / or the size of the buds on the branches is varied.

[0083] [Item d12] The method described in any one of items d8 to d11, wherein the two or more attributes include at least one of the following: the color of the branch, the direction in which the branch grows, the thickness of the branch, the height of the base of the branch, the size of the buds on the branch, the direction in which the buds on the branch face, the length of the branch, and the length of the internodes of the branch.

[0084] [Item d13] The setting to enable / disable the one or more setting parameters mentioned above is: After determining the one or more points to be cut, the setting of whether or not to determine the one or more points to be cut again. The generated cutting point data is presented to the user, and the ability to enable / disable receiving user instructions is set. In generating the aforementioned cutting point data, the setting to enable / disable generating the cutting point data so that the branch is cut by a plane perpendicular to the direction in which the branch is growing, The setting to enable / disable the determination of which branches to keep from two or more branches of the fruit tree to be treated. In determining the number of buds to leave on the branches of the fruit tree that have been selected to remain, the setting of whether or not to include the bud closest to the base of the branch, The setting to enable / disable the removal of non-candidate branches that should not be selected as branches to be kept from one or more branches of the fruit tree to be processed, before deciding which branches to keep, and After deciding whether to remove or keep one or more branches of the fruit tree to be treated, the system enables / disables the setting to maintain or change the decision on whether to remove or keep a branch, based on the distribution of buds on the branches that have been decided to keep. The method described in any one of items d8 through d12, including at least one of the following.

[0085] [Item d14] The method according to any one of items d8 to d13, wherein the user can change and save the settings for the priority of the multiple pruning modes and the settings for enabling / disabling one or more setting parameters.

[0086] [Item d15] A system for generating cutting point data that includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, One or more sensors that acquire sensor data from the branches of the fruit tree, A data processing device that generates the cutting point data of the fruit tree branches based on the sensor data, Equipped with, The aforementioned data processing device is From a plurality of pruning modes, each of which has a different method for determining the point to be cut on the fruit tree branches, and each of which is associated with a method for cultivating the fruit tree, information on the pruning mode selected by the user is obtained. Based on the sensor data and the selected pruning mode, one or more points to be cut are determined for the fruit tree branch. For each of the one or more points to be cut, the cutting point data is generated. A system that varies the method for determining the point to be cut according to the cultivation method of the fruit tree.

[0087] [Item d16] A system for generating cutting point data that includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, One or more sensors that acquire sensor data from the branches of the fruit tree, Means for carrying out the steps of the method described in any one of items d1 to d14 A system that has

[0088] [Item d17] The system further comprises a cutter for cutting the branches of the fruit tree and a control device for controlling the three-dimensional position of the cutter. The data processing device inputs the generated cutting point data to the control device. The control device controls the three-dimensional position of the cutter based on the cutting point data, as described in item d15 or d16.

[0089] [Item d18] Agricultural machinery having a system described in any one of items d15 to d17.

[0090] [Item d19] The system further comprises an arm that supports the cutter, a support that supports the arm, and a drive device that moves the support. The control device controls the three-dimensional position of the cutter by controlling the movement of the arm, as described in item d18, reference to item d17.

[0091] The comprehensive or specific embodiments of this disclosure may be implemented by apparatus, systems, methods, integrated circuits, computer programs, or computer-readable non-temporary storage media, or any combination thereof. Computer-readable storage media may include volatile storage media or non-volatile storage media. Apparatus may consist of multiple devices. If apparatus consists of two or more devices, these two or more devices may be located in a single device or in two or more separate devices. [Effects of the Invention]

[0092] Embodiments of this disclosure provide a method for generating cut point data, a system for generating cut point data, and agricultural machinery, which can be used to promote the automation and unmanned operation of fruit tree pruning while maintaining fruit yield and quality, and which include information indicating the three-dimensional position of the point on which a fruit tree branch should be cut. [Brief explanation of the drawing]

[0093] [Figure 1A]Figure 1A is a flowchart showing an example of the procedure for generating fruit tree branch cutting point data using a fruit tree branch cutting point data generation method or cutting point data generation system according to an embodiment of the present disclosure. [Figure 1B] Figure 1B is a flowchart showing another example of the procedure for generating fruit tree branch cutting point data using a fruit tree branch cutting point data generation method or cutting point data generation system according to embodiments of the present disclosure. [Figure 1C] Figure 1C is a flowchart illustrating an example procedure using a method or system according to an embodiment of the present disclosure. [Figure 1D] Figure 1D is a block diagram showing a schematic configuration example of a cutting point data generation system according to an embodiment of the present disclosure. [Figure 1E] Figure 1E is a block diagram showing an example configuration of a data processing device in a cutting point data generation system according to an embodiment of the present disclosure. [Figure 1F] Figure 1F is a schematic diagram showing an example of the configuration of a cutting point data generation system according to an embodiment of the present disclosure. [Figure 2] Figure 2 is a schematic diagram showing how an agricultural machine having a cutting point data generation system according to an embodiment of the present disclosure moves within an orchard. [Figure 3] Figure 3 is a front perspective view of the cutting point data generation system 1 according to an embodiment of the present disclosure. [Figure 4] Figure 4 is a schematic diagram showing an enlarged view of a part of the cutting point data generation system 1. [Figure 5A] Figure 5A is an example block diagram of a cloud system that includes a mobile platform and interacts with a cloud platform and a user platform. [Figure 5B] Figure 5B is an example block diagram of a cloud system that includes a mobile platform and interacts with a cloud platform and a user platform. [Figure 6A] Figure 6A is a schematic diagram illustrating short-sprout pruning. [Figure 6B]Figure 6B is a schematic diagram illustrating short-sprout pruning. [Figure 6C] Figure 6C is a schematic diagram illustrating short-sprout pruning. [Figure 7A] Figure 7A is a schematic diagram illustrating long-shoot pruning. [Figure 7B] Figure 7B is a schematic diagram illustrating long-shoot pruning. [Figure 7C] Figure 7C is a schematic diagram illustrating long-shoot pruning. [Figure 7D] Figure 7D is a schematic diagram illustrating long-shoot pruning. [Figure 8] Figure 8 shows examples of multiple pruning modes provided in the cutting point data generation system according to the embodiment of this disclosure. [Figure 9A] Figure 9A shows an example of the display screen of an operating terminal. [Figure 9B] Figure 9B shows an example of the display screen of the operating terminal. [Figure 9C] Figure 9C shows an example of the display screen of an operating terminal. [Figure 10] Figure 10 is a flowchart showing an example of a procedure for generating branch cutting point data for fruit trees according to an embodiment of the present disclosure. [Figure 11] Figure 11 is a flowchart showing a specific example of the process performed in step S242. [Figure 12A] Figure 12A is a diagram illustrating an example of the process performed in step S242. [Figure 12B] Figure 12B is a diagram illustrating an example of the process performed in step S242. [Figure 12C] Figure 12C is a diagram illustrating an example of the process performed in step S242. [Figure 12D] Figure 12D is a diagram illustrating an example of how to set the priority of each attribute. [Figure 12E] Figure 12E is a diagram illustrating an example of how to set the priority of each attribute. [Figure 13]Figure 13 is a flowchart showing an example of a procedure for generating branch cutting point data for fruit trees according to an embodiment of the present disclosure. [Figure 14] Figure 14 is a flowchart showing a specific example of the process performed in step S240. [Figure 15] Figure 15 is a flowchart showing an example of a procedure for generating branch cutting point data for fruit trees according to an embodiment of the present disclosure. [Figure 16] Figure 16 is a flowchart showing an example of a procedure for generating branch cutting point data of a fruit tree according to an embodiment of the present disclosure. [Figure 17A] Figure 17A is a flowchart showing an example of a procedure for generating branch cutting point data for fruit trees according to an embodiment of the present disclosure. [Figure 17B] Figure 17B is a schematic diagram illustrating the setting parameter "Cutting Orientation". [Figure 18] Figure 18 is a flowchart showing an example of a procedure for generating branch cutting point data of a fruit tree according to an embodiment of the present disclosure. [Figure 19] Figure 19 is a flowchart illustrating an example of the procedure for generating branch cutting point data for fruit trees according to an embodiment of the present disclosure. [Figure 20A] Figure 20A shows an example of an image used in the cutting point data generation method and cutting point data generation system according to the embodiments of this disclosure. [Figure 20B] Figure 20B is a flowchart showing an example of the process performed in step S241c. [Figure 20C] Figure 20C is a flowchart showing an example of the process performed in step S241c. [Figure 20D] Figure 20D is a flowchart showing an example of the process performed in step S241c. [Figure 21] Figure 21 is a flowchart showing an example of a procedure for generating branch cutting point data for fruit trees according to an embodiment of the present disclosure. [Figure 22]Figure 22 is a schematic diagram illustrating the process in the flowchart of Figure 21. [Figure 23] Figure 23 is a flowchart illustrating an example of the procedure for generating branch cutting point data of a fruit tree according to an embodiment of the present disclosure. [Figure 24] Figure 24 is a flowchart illustrating an example of the procedure for generating branch cutting point data for fruit trees according to an embodiment of the present disclosure. [Figure 25] Figure 25 is a flowchart illustrating an example of the procedure for generating branch cutting point data for fruit trees according to an embodiment of the present disclosure. [Figure 26A] Figure 26A shows the results of evaluating each pruning mode in Figure 8 using multiple evaluation criteria. [Figure 26B] Figure 26B shows the results of evaluating each pruning mode in Figure 8 using multiple evaluation criteria. [Figure 26C] Figure 26C shows the results of evaluating each pruning mode in Figure 8 using multiple evaluation criteria. [Figure 27] Figure 27 illustrates an example of the evaluation method for each evaluation item for each pruning mode. [Figure 28] Figure 28 shows examples of multiple pruning modes provided in the cutting point data generation system according to the embodiment of this disclosure. [Figure 29A] Figure 29A shows the results of evaluating each pruning mode in Figure 28 using multiple evaluation criteria. [Figure 29B] Figure 29B shows the results of evaluating each pruning mode in Figure 28 using multiple evaluation criteria. [Figure 29C] Figure 29C shows the results of evaluating each pruning mode in Figure 28 using multiple evaluation criteria. [Figure 30A] Figure 30A shows an example of the display screen of an operating terminal. [Figure 30B] Figure 30B shows an example of the display screen of an operating terminal. [Figure 31] Figure 31 is a flowchart showing an example of a procedure for generating branch cutting point data for fruit trees according to an embodiment of the present disclosure. [Figure 32A] Figure 32A is an image or schematic diagram illustrating the acquisition of measurement values ​​related to the direction in which branches are growing. [Figure 32B] Figure 32B is a diagram showing a table illustrating multiple classes related to the direction in which branches grow, evaluation criteria for each of these classes, and examples of scores corresponding to each of these classes. [Figure 32C] Figure 32C is an image used to obtain measurements related to branch thickness, or a schematic diagram illustrating the acquisition of these measurements. [Figure 32D] Figure 32D is a diagram showing multiple classes related to branch thickness, evaluation criteria for each of the classes, and a table illustrating examples of scores corresponding to each of the classes. [Figure 32E] Figure 32E is an image or schematic diagram used to explain the acquisition of measurement values ​​related to the height of the base of a branch. [Figure 32F] Figure 32F is a diagram showing a table illustrating multiple classes related to the height of the base of a branch, the evaluation criteria for each of the multiple classes, and examples of scores corresponding to each of the multiple classes. [Figure 32G] Figure 32G is an image or schematic diagram used to explain the acquisition of measurements regarding the size of buds on a branch. [Figure 32H] Figure 32H is a diagram showing a table illustrating multiple classes of bud size on a branch, evaluation criteria for each of these classes, and examples of scores corresponding to each of these classes. [Figure 32I] Figure 32I is an image or schematic diagram used to explain the acquisition of measurements regarding the direction in which buds on a branch face. [Figure 32J] Figure 32J is a diagram showing a table illustrating multiple classes related to the direction in which buds on a branch face, evaluation criteria for each of these classes, and examples of scores corresponding to each of these classes. [Figure 32K]Figure 32K is an image or schematic diagram illustrating the acquisition of measurements related to branch length. [Figure 32L] Figure 32L is a diagram showing multiple classes related to branch length, evaluation criteria for each of the multiple classes, and a table illustrating examples of scores corresponding to each of the multiple classes. [Figure 32M] Figure 32M is an image or schematic diagram used to explain the acquisition of measurements regarding the internode length of a branch. [Figure 32N] Figure 32N is a diagram showing multiple classes related to branch internode length, evaluation criteria for each of the classes, and a table illustrating examples of scores corresponding to each of the classes. [Figure 32O] Figure 32O is a flowchart showing an example of the process for determining the factor score related to branch color. [Figure 32P] Figure 32P is a flowchart showing an example of the process for calculating the inclination angle θp and azimuth angle θa of each branch. [Figure 32Q] Figure 32Q is a flowchart showing an example of a process for calculating the inclination angle of a bud with respect to a direction perpendicular to the horizontal plane. [Figure 32R] Figure 32R is a flowchart showing an example of a process for calculating the average distance between the coordinates of two adjacent buds. [Modes for carrying out the invention]

[0094] Hereinafter, with reference to the drawings, a method for generating cutting point data including information indicating the three-dimensional position of the point to be cut on a fruit tree branch, a system for generating cutting point data, and an agricultural machine according to embodiments of this disclosure will be described. Note that parts with the same reference numerals appearing in multiple drawings indicate the same or equivalent parts.

[0095] The following embodiments are illustrative examples for embodying the technical concept of the present invention and do not limit the present invention to these embodiments. Descriptions of the size, material, shape, and relative arrangement of components are intended as examples only, and are not intended to limit the scope of the present invention to those specific examples. The size and positional relationships of the components shown in each drawing may be exaggerated for ease of understanding.

[0096] In this disclosure, “parallel” includes cases where the angle between two lines, edges, planes, etc., is between 0° and 5°, unless otherwise specified. Also, in this disclosure, “perpendicular” or “orthogonal” includes cases where the angle between two lines, edges, planes, etc., is between 90° and ±5°, unless otherwise specified. Unless otherwise specified, the angle between two lines, edges, planes, etc., is positive and not negative.

[0097] <Method and system for generating cutting point data for fruit tree branches> A method for generating cutting point data for fruit tree branches (hereinafter sometimes referred to as the "cutting point data generation method") and a system for generating cutting point data for fruit tree branches (hereinafter sometimes referred to as the "cutting point data generation system" or "cutting system") according to embodiments of the present disclosure will be described with reference to Figures 1A, 1B, 1C, and 2. Cutting point data is data that includes information indicating the three-dimensional position of the point on the fruit tree branch to be cut. As described below, the method for generating cutting point data for fruit tree branches according to embodiments of the present disclosure may include determining the point on the fruit tree branch to be cut and generating cutting point data for the determined point to be cut.

[0098] Figures 1A, 1B, and 1C are flowcharts illustrating an example of the procedure for generating fruit tree branch cutting point data using a fruit tree branch cutting point data generation method or a fruit tree branch cutting point data generation system according to an embodiment of the present disclosure. That is, the cutting point data generation method according to an embodiment of the present disclosure includes the steps described below. Here, an example of generating fruit tree branch cutting point data using an agricultural machine 101 equipped with a cutting point data generation system will be described, as shown in the example in Figure 2.

[0099] Figure 2 schematically shows how an agricultural machine 101 equipped with a cutting point data generation system moves within an orchard. In the example shown in Figure 2, the cutting point data generation system is mounted on an agricultural machine 101 that has a mobile body, and the agricultural machine 101 generates cutting point data for the branches of fruit trees (e.g., grapevines) 200 as it moves between multiple rows of fruit trees 201 in an orchard (e.g., a vineyard). In this example, a user 9 located away from the agricultural machine 101 can change or control the method of cutting point data generation by the cutting point data generation system by operating an operation terminal 400. The user operating the operation terminal 400 may be on the agricultural machine 101. The agricultural machine 101 moves between multiple rows of fruit trees 201 in the orchard along a path indicated by the dashed arrows in Figure 2, for example. The agricultural machine 101 may move autonomously between the multiple rows of fruit trees 201. Agricultural machinery having a cutting point data generation system is not limited to work vehicles such as tractors, but may also include transport vehicles, mobile robots, mobile robots, and unmanned aerial vehicles (UAVs, so-called drones) such as multicopters. In this specification, grapevines are sometimes used as an example of fruit trees, but the embodiments of this disclosure are not limited to grapevines and can be applied to other types of trees.

[0100] First, refer to Figure 1A.

[0101] In step S050, information is obtained about the pruning mode selected by the user from among several pruning modes, each with a different method for determining the point to be cut on the fruit tree branches. For example, the cutting point data generation system provides several pruning modes, each with a different method for determining the point to be cut on the fruit tree branches, and the user selects one of these pruning modes. Examples of the methods for determining the point to be cut in each of the multiple pruning modes will be described later.

[0102] Multiple pruning modes are recorded in a storage device located inside or outside the agricultural machine 101, which is equipped with a cutting point data generation system. User 9 selects a pruning mode, for example, by operating an operation terminal 400. The operation terminal 400 operated by user 9 may be a portable or fixed operation terminal. A fixed operation terminal may be attached to the agricultural machine 101 or located away from the agricultural machine 101. The operation terminal 400 may be equipped with a display device such as a touchscreen. The operation terminal 400 may further be equipped with one or more buttons. The display device may be a display such as a liquid crystal or organic light-emitting diode (OLED). The operation terminal 400 may be equipped with a storage device. Multiple pruning modes may be recorded in the storage device of the operation terminal 400.

[0103] In step S100, sensor data acquired by one or more sensors is obtained, specifically sensor data of one or more branches of the fruit tree 200. The sensor data may include information indicating the three-dimensional structure of the multiple branches of the fruit tree 200. For example, a LiDAR sensor on the agricultural machine 101 repeatedly outputs sensor data indicating the distance and direction to each measurement point on the branches of the fruit tree 200, or the three-dimensional coordinate values ​​of each measurement point. Alternatively, an image of the branches of the fruit tree 200 acquired by a camera on the agricultural machine 101 may be obtained, and the estimated depth of the branches of the fruit tree may be obtained based on the acquired image. The sensor data does not necessarily have to include information indicating the three-dimensional structure of the multiple branches of the fruit tree 200; for example, an image of the branches of the fruit tree 200 acquired by camera 20 may be used as sensor data. The methods for acquiring and processing sensor data are fully incorporated herein by reference from U.S. Patent Application No. 18 / 379,630 (U.S. Patent Application Publication No. 2024 / 0282105). Each of the fruit trees 200 may be assigned an identifier. Sensor data acquired for each fruit tree 200 may be stored in memory, associated with the identifier of the corresponding fruit tree 200.

[0104] The order of steps S050 and S100 is irrelevant, and they may be performed simultaneously (in parallel). Alternatively, the method of acquiring sensor data in step S100 may be varied depending on the pruning mode information acquired in step S050. For example, based on the pruning mode information acquired in step S050, the sensor data necessary for determining the cutting points in that pruning mode may be acquired in step S100.

[0105] In step S200, based on the pruning mode information acquired in step S050 and the sensor data acquired in step S100, one or more points on the branches of the fruit tree 200 to be cut are determined. Some or all of the multiple branches of the fruit tree 200 are subject to step S200. As described above, the method for determining the points to be cut differs depending on the pruning mode selected by the user, and the points to be cut are determined in a manner appropriate to the selected pruning mode.

[0106] In step S300, cutting point data is generated for each of the cutting points determined in step S200, including information indicating its three-dimensional position.

[0107] As shown in the example in Figure 1B, the procedure for generating cutting point data for fruit tree branches may further include step S400. In step S400, the cutting point data generated in step S300 is input to a control device 600 (see Figure 1D) that controls the three-dimensional position of a cutter 620 (see Figure 1D) that cuts the branches of the fruit tree 200. In this way, the cutter 620 can be made to perform the cutting of the branches of the fruit tree 200.

[0108] The acquisition of sensor data in step S100 may be performed, for example, once or multiple times per second. After acquiring sensor data at a certain time, the processing in steps S200 and S300 may be performed by the data processing device within the period until the next sensor data is acquired. In such a case, the agricultural machine with the cutter can move along the row of fruit trees and sequentially cut the branches of each fruit tree with the cutter based on the generated cutting point data.

[0109] As shown in the example in Figure 1C, the methods and systems according to embodiments of the present disclosure may omit step S300. Such a system can output data indicating one or more points to be cut, determined in S200. Such data may be input into another system to generate cut point data. Alternatively, such data may be used, for example, to predict fruit yield.

[0110] In the example shown in Figure 1C, the method according to the embodiment of the present disclosure includes: obtaining information on a pruning mode selected by the user from a plurality of pruning modes, each having a different method for determining the point on which a fruit tree branch should be cut (step S050); obtaining sensor data from one or more sensors, specifically sensor data for one or more branches of the fruit tree (step S100); and determining one or more points on which a fruit tree branch should be cut based on the sensor data and the information on the selected pruning mode (step S200).

[0111] The processing steps described above are performed using one or more computing devices. These one or more computing devices may include not only the processor of an ECU (Electric Control Unit) mounted on an agricultural machine having a cutting point data generation system, but also the processors of one or more server computers and / or terminal devices (including portable and fixed types) connected to the cutting point data generation system via a communication network as shown in Figure 1F. Furthermore, the data processing device of the cutting point data generation system according to the embodiments of this disclosure performs the processing steps described above. Some or all of the functions of the data processing device of the cutting point data generation system according to the embodiments of this disclosure may be implemented by one or more server computers and / or terminal devices (including portable and fixed types) connected to the cutting point data generation system via a communication network.

[0112] Figure 1D is a block diagram illustrating a schematic configuration example of a cutting point data generation system according to an embodiment of the present disclosure. As shown in Figure 1D, the cutting point data generation system 1000 according to an embodiment of the present disclosure comprises one or more sensors (sensor group) 520 and a data processing device 530 that generates cutting point data for fruit tree branches based on sensor data acquired from the sensor group 520 and information on a selected pruning mode. The data processing device 530 acquires information on a pruning mode selected by the user from, for example, a terminal device 400 operated by the user. The data processing device 530 may be connected to, for example, a cutter control device (sometimes simply called a "control device") 600 that controls the three-dimensional position of a cutter (sometimes called a "cutting tool") 620 that cuts fruit tree branches. The cutting point data generation system 1000 may further include the cutter control device 600. The cutting point data generation system 1000 may further include the cutter control device 600 and a cutter 620.

[0113] The cutting point data generation system 1000 may be mounted on an agricultural machine that cuts fruit tree branches, or some or all of the processing performed by the cutting point data generation system 1000 may be performed by one or more computing devices located outside the agricultural machine that cuts fruit tree branches. For example, sensor data acquired by sensors on other agricultural machines different from the agricultural machine that cuts fruit tree branches may be used. Also, a server computer connected to a network may function as part or all of the data processing device 530. Various data necessary for generating cutting point data, including multiple pruning modes, may be recorded in a storage device on the agricultural machine that cuts fruit tree branches, or some or all of this data may be recorded in a storage device located outside the agricultural machine. For example, some or all of this data may be recorded on a server computer connected to a network. The data processing device 530 that performs the processing in steps S200 and S300 may be mounted on an agricultural machine that cuts fruit tree branches, or one or more computing devices located outside the agricultural machine that cuts fruit tree branches may function as part or all of the data processing device.

[0114] The sensor group 520 acquires sensor data of the fruit tree branches (for example, sensor data including information showing the three-dimensional structure of the fruit tree branches). The sensor group 520 may include, for example, imaging devices such as cameras (e.g., stereo cameras) that acquire images of the fruit tree branches, and LiDAR sensors that acquire point cloud data by sensing the fruit tree branches. The sensor group 520 may include one or more imaging devices and / or one or more LiDAR sensors.

[0115] The data processing device 530 is one or more computing devices that process sensor data acquired by the sensor group 520. For example, it may be implemented by an electronic control unit (ECU) for image recognition. The data processing device 530 may include one or more processors and one or more memories. Some of the processing performed by the data processing device 530 may be performed, for example, inside the sensor group 520 (e.g., an imaging device) (e.g., within a camera module). If both the sensor group 520 and the data processing device 530 are included in agricultural machinery, the sensor group 520 and the data processing device 530 are communicated together, for example, via a bus. If both the operating terminal 400 and the data processing device 530 are included in agricultural machinery, the operating terminal 400 and the data processing device 530 are communicated together, for example, via a bus.

[0116] The cutter control device 600 is one or more computing devices that control the three-dimensional position of the cutter 620 based on the cutting point data generated by the data processing device 530. It is implemented by a computing device such as one or more electronic control units (ECUs). If the cutter 620 is supported by an arm, the cutter control device 600 further controls the movement of the arm supporting the cutter 620.

[0117] As shown in the example in Figure 1, when a cutting point data generation system is mounted on an agricultural machine having a moving body, the cutting point data generation system includes a cutting tool 24, a robot arm 22 that supports the cutting tool 24, a base (support) 32 that supports the robot arm 22, and a drive device that moves the base 32. The drive device may include various devices necessary for driving the agricultural machine, such as a prime mover and a transmission. One or more ECUs in the agricultural machine control the movement (e.g., driving) of the agricultural machine by controlling the prime mover, transmission, running gear (multiple wheels 36), etc. included in the drive device.

[0118] Figure 1E is a block diagram showing an example configuration of a data processing device 530. In the example shown in Figure 1E, the data processing device 530 comprises a processor 531, a ROM (Read Only Memory) 533, a RAM (Random Access Memory) 535, a communication device 537, and a storage device 539. These components can be interconnected via a bus 532.

[0119] The processor 531 is a semiconductor integrated circuit, also referred to as a central processing unit (CPU) or microprocessor. The processor 531 may include an image processing unit (GPU). The processor 531 sequentially executes a computer program describing a predetermined set of instructions stored in the ROM 533 to realize the processing necessary for generating the cutoff point data of this disclosure. The data processing device 530 may comprise a plurality of processors 531. The processing necessary for generating the cutoff point data of this disclosure may be performed collaboratively by the plurality of processors 531. Part or all of the processor 531 may be an FPGA (Field Programmable Gate Array), ASIC (Application Specific Integrated Circuit), or ASSP (Application Specific Standard Product) equipped with a CPU.

[0120] The communication device 537 is an interface for data communication between the data processing device 530 and an external computing device. The communication device 537 can perform wired communication such as CAN (Controller Area Network), or wireless communication compliant with the Bluetooth® standard and / or Wi-Fi® standard.

[0121] The storage device 539 can store sensor data acquired from the sensor group 520, sensor data during processing, or data during the process of generating cutoff point data. The storage device 539 includes, for example, a hard disk drive or a non-volatile semiconductor memory.

[0122] The hardware configuration of the data processing unit 530 is not limited to the examples described above. It is not necessary for part or all of the data processing unit 530 to be mounted on the agricultural machine used for cutting fruit tree branches. By utilizing the communication device 537, one or more computing devices located outside the agricultural machine used for cutting fruit tree branches can function as part or all of the data processing unit 530. For example, one or more computing devices included in one or more server computers and / or terminal devices connected to a network can function as part or all of the data processing unit 530. Alternatively, one or more computing devices mounted on the agricultural machine used for cutting fruit tree branches may perform all the functions required of the data processing unit 530.

[0123] One example of a “control device” in this disclosure is a computing device comprising at least one processor and at least one memory for storing a computer program (code) that defines a control process performed by the processor. Another example of a “control device” is a computing device comprising a hardware accelerator such as an FPGA (Field-Programmable Gate Array), ASSP (Application Specific Standard Product), or ASIC (Application-Specific Integrated Circuit) configured to perform the control process.

[0124] Similarly, one example of a “data processing device” in this disclosure is a computing device comprising at least one processor and at least one memory for storing a computer program (code) that defines a processing process to be performed by the processor. Another example of a “data processing device” is a computing device comprising a hardware accelerator, such as an FPGA or ASIC, configured to perform a processing process.

[0125] In this disclosure, “processor” refers to hardware electronic circuits such as a CPU (Central Processing Unit), GPU (Graphics Processing Unit), DSP (Digital Signal Processor), ISP (Image Signal Processor), or NPU (Neural Network Processing Unit). “Memory” refers to hardware electronic circuits such as ROM (Read Only Memory) or RAM (Random Access Memory). Part of the memory may be a storage medium connected to the processor by wiring or a network. These hardware electronic circuits may be implemented by one or more integrated circuits (ICs) or large-scale integrated circuits (LSIs). Each functional unit or block and associated component within the electronic circuit may be manufactured individually as separate integrated circuit chips, or some or all of these functional units or blocks may be combined and manufactured as a single integrated circuit chip.

[0126] A program defining the operation of the processor is designed to cause the processor to perform one or more functions, operations, steps, or processes in embodiments of the present invention.

[0127] Figure 1F is a schematic diagram showing an example configuration of a cutting point data generation system. The data processing device 530 is not limited to the example where it is mounted on the agricultural machine 101. That is, some or all of the functions of the data processing device 530 may be realized by one or more servers (computers) 500 or terminal devices (including portable and fixed types) 600 connected to the communication device 537 of the data processing device 530 by a communication network 800. An operating terminal 400 may also be connected to the communication network 800. Other agricultural machines (e.g., tractors) 700 may be connected to such a communication network 800, and communication may take place between the agricultural machine 101 having the data processing device 530 and the other agricultural machines 700. Some of the data used for processing by the data processing device 530 may be provided to the data processing device 530 from the other agricultural machines 700 via the communication network 800.

[0128] <Example of a cutting point data generation system> Figure 3 shows a front perspective view of a cutting system 1 according to a preferred embodiment of the present invention. As shown in Figure 3, the cutting system 1 may have a moving body or the like. However, the cutting system 1 can be installed on a moving body or a cart that can be towed by a person, or on a self-propelled or self-propelled cart or moving body.

[0129] As shown in Figure 3, the cutting system 1 includes a base frame 10, side frames 12 and 14, a horizontal frame 16, and a vertical frame 18. The side frames 12 and 14 are mounted on the base frame 10, and the side frames 12 and 14 directly support the horizontal frame 16. The vertical frame 18 is mounted on the horizontal frame 16. One or more devices, such as a camera 20, a robotic arm 22, and / or a cutting tool 24, may be mounted and supported, for example, on the vertical frame 18 and / or on any other frame among frames 10, 12, 14, or 16.

[0130] The base frame 10 has a base frame motor 26 that can move the side frames 12 and 14 along the base frame 10 so that one or more devices can be moved in the depth direction (z-axis shown in Figure 3). The horizontal frame 16 has a horizontal frame motor 28 that can move the vertical frame 18 along the horizontal frame 16 so that one or more devices can be moved in the horizontal direction (x-axis shown in Figure 3). The vertical frame 18 has a vertical frame motor 30 that can move one or more devices vertically (y-axis shown in Figure 3) along the vertical frame 18. Each of the base frame motor 26, horizontal frame motor 28, and vertical frame motor 30 may be, for example, a screw motor. A screw motor can provide relatively high precision for precisely moving and positioning one or more devices. However, each of the base frame motor 26, horizontal frame motor 28, and vertical frame motor 30 may be any motor that provides a continuous torque of, for example, about 0.2 Nm or more, preferably about 0.3 Nm or more.

[0131] Each of the base frame motor 26, horizontal frame motor 28, and vertical frame motor 30 may be designed and / or sized according to the total weight of one or more devices. Furthermore, the couplers for each of the base frame motor 26, horizontal frame motor 28, and vertical frame motor 30 may be modified according to the diameter of the motor shaft and / or the corresponding mounting hole pattern.

[0132] The base frame 10 can be mounted on the base 32, and the base electronics system 34 can also be mounted on the base 32. Multiple wheels 36 can be mounted on the base 32. For example, as shown in Figures 5A and 5B, the multiple wheels 36 can be controlled by the base electronics system 34, which may have a power supply 35 for driving an electric motor 37 or the like. As an example, the multiple wheels 36 can be driven by an electric motor 37 having a target capacity of about 65 kW to about 75 kW, and the power supply 35 for the electric motor 37 may be a battery with a capacity of about 100 kWh.

[0133] The base electronics system 34 also includes a processor and memory elements programmed or configured to perform autonomous navigation of the cutting system 1. Furthermore, as shown in Figure 3, a LiDAR (light detection and ranging) system 38 and a Global Navigation Satellite System (GNSS) 40 are installed or supported, for example, on the base frame 10 or base 32 and / or other frames among frames 10, 12, 14, or 16, so that the position data of the cutting system 1 can be determined. The LiDAR system 38 and GNSS 40 may be used for obstacle avoidance and navigation when the cutting system 1 is moving autonomously. Preferably, for example, the cutting system 1 is implemented using a remote control interface and can communicate via one or more of Ethernet, USB, wireless communication, and GPS RTK (real-time kinematics). The remote control interface and communication device may be included in either or both of the base electronics system 34 and the imaging electronics system 42 (described later). As shown in Figure 3, the cutting system 1 may include a display device 43 that displays data and / or images obtained by one or more devices and information provided by the base electronic system 34 (e.g., location, speed, battery life of the cutting system 1), or may be communicably connected to such a display device 43. Alternatively, the data and / or images obtained by one or more devices and provided by the base electronic system 34 may be displayed to the user through a user platform.

[0134] Figure 4 is an enlarged view of a part of the cutting system 1 having one or more devices. As shown in Figure 4, one or more devices include, for example, a camera 20, a robotic arm 22, and a cutting tool 24, which may be mounted on the vertical frame 18 and / or other frames among frames 10, 12, 14, or 16. Further devices among the one or more devices may also be mounted, for example, on the vertical frame 18 and / or other frames among frames 10, 12, 14, or 16.

[0135] Camera 20 may include a stereo camera, an RGB camera, etc. As shown in Figure 4, camera 20 may have a body 20a that includes a first camera / lens 20b (e.g., left camera / lens) and a second camera / lens 20c (e.g., right camera / lens). Alternatively, body 20a may include two or more cameras / lenses. The resolution of camera 20 may be, for example, 1536 × 2048 pixels or 2448 × 2048 pixels, but camera 20 may have a different resolution. Camera 20 may have, for example, a PointGrey CM3-U3-31S4C-CS or PointGrey CM3-U3-50S5C sensor and a 3.5mm f / 2.4 or 5mm f / 1.7 lens, and a field of view of 74.2535 × 90.5344 or 70.4870 × 80.3662. Camera 20 may have other sensors and lenses, and may also have different fields of view.

[0136] One or more light sources 21 may be mounted on one or more sides of the camera body 20a. The light sources 21 may have LED light sources oriented in the same direction as one or more devices, such as the camera 20, along the z-axis as shown in Figure 3. The light sources 21 may provide illumination to one or more objects imaged by the camera 20. For example, the light sources 21 may act as a flash to compensate for ambient light when imaged by the camera 20 during daytime operation. During nighttime operation, the light sources 21 may act as a flash for the camera 20, or the light sources may provide steady illumination to the camera 20. In a preferred embodiment, one or more light sources 21 may have, for example, 100-watt LED modules, but LED modules with different wattages (e.g., 40 watts or 60 watts) may be used.

[0137] The robot arm 22 may include robot arms known to those skilled in the art, such as the Universal Robot 3 e-series robot arms and the Universal Robot 5 e-series robot arms. For example, the robot arm 22, also known as an articulated robot arm, may have multiple joints that act as axes enabling degrees of freedom of motion. Here, the more rotary joints the robot arm 22 has, the higher the degrees of freedom of motion it has. For example, the robot arm 22 may have 4 to 6 joints, and these will provide the same number of axes of rotation for motion.

[0138] In a preferred embodiment of the present invention, the controller may be configured or programmed to control the movement of the robot arm 22. For example, the controller may be configured or programmed to control the movement of the robot arm 22 to which a cutting tool 24 is attached, and to position the cutting tool 24, according to steps described later. For example, the controller may be configured or programmed to control the movement of the robot arm 22 based on the location of the cutting point located on the target crop.

[0139] In a preferred embodiment of the present invention, the cutting tool 24 has a body 24a and a blade portion 24b, as shown, for example, in Figure 4. The blade portion 24b may have a driven blade that moves relative to a fixed blade and is operated to perform a cutting operation together with the fixed blade. The cutting tool 24 may have, for example, a cutting device disclosed in U.S. Patent Application No. 17 / 961,666 (U.S. Patent Application Publication No. 2024 / 0116193), which is titled “End Effector Including cutting blade and pulley assembly” and is incorporated herein by reference in its entirety.

[0140] In a preferred embodiment of the present invention, the cutting tool 24 may be attached to the robot arm 22 using a robot arm mount assembly 23. The robot arm mount assembly 23 may be, for example, the robot arm mount assembly disclosed in U.S. Patent Application No. 17 / 961,668 (Publication No. 2024 / 0116173), which is titled “Robotic Arm Mount Assembly including Rack and Pinion” and is incorporated herein by reference.

[0141] The cutting system 1 may have an imaging electronic system 42, which can be installed on the side frame 12 or side frame 14, for example, as shown in Figure 3. The imaging electronic system 42 may supply power to and control each of the base frame motor 26, the horizontal frame motor 28, and the vertical frame motor 30. That is, the imaging electronic system 42 may have a power supply that provides power to each of the base frame motor 26, the horizontal frame motor 28, and the vertical frame motor 30. The imaging electronic system 42 may also have a processor and memory element programmed or configured to control each of the base frame motor 26, the horizontal frame motor 28, and the vertical frame motor 30. The processor and memory element of the imaging electronic system 42 may also be configured or programmed to control one or more devices having a camera 20, a robot arm 22, a robot arm mount assembly 23, and a cutting tool 24. The processor and memory element of the imaging electronic system 42 may also be configured or programmed to process image data obtained by the camera 20.

[0142] As described above, the imaging electronic system 42 and the base electronic system 34 can include a group of processors and memory elements. The group of processors can be a hardware processor, a multipurpose processor, a microprocessor, a dedicated processor, a digital signal processor (DSP), and / or other types of processing components configured or programmed to process data. The memory elements can include one or more of volatile, non-volatile, and / or replaceable data storage elements. For example, the memory elements can include magnetic, optical, and / or flash memory elements that can be integrally or partially integrated with the processor. The memory elements can store instructions and / or instruction sets or programs that can be read and / or executed by the processor.

[0143] In another preferred embodiment of the present invention, the imaging electronic system 42 can be implemented, partially or completely, by the base electronic system 34. For example, each of the base frame motor 26, the horizontal frame motor 28, and the vertical frame motor 30 may receive power from and / or be controlled by the base electronic system 34 instead of the imaging electronic system 42.

[0144] In a further preferred embodiment of the present invention, the imaging electronic system 42 may be connected to a power source (single or plural) different from the base electronic system 34. For example, a power source may be included in one or both of the imaging electronic system 42 and the base electronic system 34. Also, the base frame 10 may be detachably attached to the base 32 so that the base frame 10, the side frames 12 and 14, the horizontal frame 16, the vertical frame 18, and the components installed thereon can be installed on another moving body or the like.

[0145] The base frame motor 26, the horizontal frame motor 28, and the vertical frame motor 30 can move one or more devices along three separate directions or three separate axes. However, in another preferred embodiment of the present invention, only some of the one or more devices, such as the camera 20, the robotic arm 22, and the cutting tool 24, may be moved by the base frame motor 26, the horizontal frame motor 28, and the vertical frame motor 30. For example, the base frame motor 26, the horizontal frame motor 28, and the vertical frame motor 30 may move only the camera 20. Further, the cutting system 1 may be configured to linearly move the camera 20 along only a single axis while the camera takes a plurality of images, as described below. For example, the horizontal frame motor 28 may be configured to linearly move the camera 20 across a target crop, such as a grapevine, and the camera 20 may be able to take a plurality of images of the grapevine.

[0146] The imaging electronics 42 and the base electronics 32 of the cutting system 1 are each, for example, NVIDIA(R) JETSON TMThe mobile platform may be provided by being partially or fully implemented by edge computing, such as by an AGX computer. In a preferred embodiment of the present invention, edge computing provides all the computational and communication needs of the disconnected system 1. Figures 5A and 5B show an example block diagram of a cloud system that includes a mobile platform and interacts with a cloud platform and a user platform. As shown in Figures 5A and 5B, the edge computing of the mobile platform includes a cloud agent, which is a service-based component that facilitates communication between the mobile platform and the cloud platform. For example, the cloud agent can receive command and instruction data from the cloud platform (e.g., a web application on the cloud platform) and forward the command and instruction data to the corresponding component of the mobile platform. As another example, the cloud agent can send operational and production data to the cloud platform. Preferably, the cloud platform may include software components and data storage to maintain the overall operation of the cloud system. The cloud platform preferably provides enterprise-level services with on-demand capability, fault tolerance, and high availability (e.g., Amazon Web Services). TMThe cloud platform includes one or more application programming interfaces (APIs) for communicating with the mobile platform and the user platform. Preferably, the APIs are protected with a high level of security, and the capacity of each API can be automatically adjusted according to the computing load. The user platform controls the cloud system and provides a dashboard for receiving data acquired by the mobile platform and the cloud platform. The dashboard can be implemented by a web-based application (e.g., an internet browser), a mobile application, a desktop application, etc.

[0147] As an example, the edge computing of the mobile platform shown in Figures 5A and 5B can obtain data from hardware GPS (Global Positioning System) (e.g., GNSS 40) and LiDAR data (e.g., from LiDAR system 38). The mobile platform can also obtain data from camera 20. The edge computing of the mobile platform may have, for example, temporary storage for storing the raw data obtained by camera 20. The edge computing of the mobile platform may also have, for example, persistent storage for storing processed data. Specifically, camera data stored in temporary storage may be processed by an artificial intelligence (AI) model, the camera data may then be stored in persistent storage, and a cloud agent may retrieve the camera data from persistent storage and transmit it.

[0148] [Fruit tree pruning methods: Short-spur pruning and long-spur pruning] Referring to Figures 6A-6C and 7A-7D, we will explain examples of fruit tree pruning methods. As will be explained below, depending on the fruit tree pruning method, there are cases where cutting point data is generated for branches that have been decided to be kept, and cases where cutting point data is not generated for branches that have been decided to be kept.

[0149] First, spur pruning will be explained with reference to Figures 6A to 6C. Figures 6A to 6C are schematic diagrams illustrating spur pruning. Figure 6A schematically shows 200a of fruit trees before pruning, in a state where harvesting is complete and the leaves have fallen, with a magnified view of a portion of the 200a of fruit trees in the opening section. Figure 6B schematically shows 200a of fruit trees after pruning from the state shown in Figure 6A, and Figure 6C schematically shows 200a of fruit trees after that. For simplicity, in the diagrams, buds 59 and new shoots 61 are shown only on some branches 58, while the remaining branches 58 are not shown.

[0150] As shown in Figure 6A, the fruit tree 200a has multiple spurs 56, and multiple canes 58 grow from each spur 56. Each cane 58 has a bud 59. The basal bud 60 located closest to the base of each cane 58 (the side closer to the spur 56) is shown separately from the other buds 59. The distance between two adjacent buds 59 on each cane 58 is called the internode length Ln. In spur pruning, as shown in Figure 6B, typically only one cane 58 is left from each spur 56, and the others are removed. Furthermore, the remaining canes 58 are also pruned short so that they have only a few buds 59 (for example, two to three). The branch 58 that has been cut short and left intact is indicated with the reference numeral "58a," and this remaining branch 58a is sometimes called a fruiting cane. Growing from the state shown in Figure 6B, as shown in Figure 6C, a new shoot 61 sprouting from the bud 59 of the fruiting cane 58a grows into a branch and bears fruit. As the new shoot 61 grows, it transforms into a branch and becomes the target of pruning during the next dormancy period (for example, the next winter). In pruning during the next dormancy period, the fruiting cane 58a and the short shoot 56 together may be referred to as the short shoot.

[0151] In the illustrated example, multiple short shoots 56 are supported by thick branches 54 that extend roughly horizontally. The thick branches 54 are supported by a trunk 52 that extends roughly vertically from the ground. The thick branches 54 are sometimes called cordons. This type of vine training is sometimes called cordon training. As shown in the illustrated example, a vine training method in which two cordons 54 extend from the trunk 52 (for example, two cordons 54 extend from both the left and right sides of the trunk 52) is called double-cordon training or bilateral-cordon training. In contrast, a vine training method in which only one cordon 54 extends from the trunk 52 is called single-cordon training. Note that depending on the training method, a fruit tree may not have cordons 54 that extend roughly horizontally. For example, in head training, all of the multiple canes grow from the trunk located at the top of the trunk, and in this case there are no cordons between the trunk and the canes.

[0152] In the illustrated example, only one branch 58 is left as the fruiting cane from among the multiple branches 58 growing from each short shoot 56, but this is not the only example. For example, in addition to the fruiting cane, a reserve fruiting cane (renewal cane) may also be left. The reserve fruiting cane should also be pruned short so that it has only a few buds (for example, two to three).

[0153] Cane pruning will be explained with reference to Figures 7A to 7D. Figures 7A to 7D are schematic diagrams illustrating cane pruning. Figure 7A shows a fruit tree 200b before pruning, in a state where harvesting is complete and the leaves have fallen. Figure 7B shows a fruit tree 200b after pruning from the state in Figure 7A. Figure 7C shows a fruit tree 200b after training and tying work from the state in Figure 7B. Figure 7D shows a fruit tree 200b after that. For simplicity, the diagrams show buds 59 and new shoots 61 on only some branches 58, while the remaining branches 58 are not shown.

[0154] In long-shoot pruning, as shown in Figure 7A, of the multiple branches 58 growing from the head 53 of the main trunk 52, as shown in Figure 7B, a few branches 58 (for example, 2 to 4) are left, and the rest are removed. In the example shown in the figure, two branches 58_1 and 58_2 are left. In long-shoot pruning, the branches 58 to be left (58_1 and 58_2) are basically not cut. As shown in Figure 7C, after the pruning work, the remaining branches 58 are trained and tied. To determine the direction of new shoots growing from the buds 59 of the remaining branches 58, the remaining branches 58 are bent in the desired direction and fixed to a wire 71. For example, in this example, the remaining branches 58 are fixed to a wire 71 that extends approximately horizontally so that they grow approximately horizontally. The wire 71 may be supported, for example, by a support that extends approximately vertically. As the plant grows from the state shown in Figure 7C, new shoots 61 sprouting from buds 59 on the remaining branch 58 grow and bear fruit, as shown in Figure 7D. The remaining branch 58 is sometimes called the fruiting cane.

[0155] In long-shoot pruning, the number of branches 58 to leave can vary depending on the training method of the fruit tree, for example. As shown in the illustrated example, when fruiting branches 58 are to be extended on both the left and right sides of the main trunk 52, two branches 58 are selected to leave. The training method in which two fruiting branches 58 extend from the main trunk 52, as shown in the illustrated example, is called the Guyot double training method. In contrast, the training method in which only one fruiting branch extends from the main trunk 52 is called the Guyot single training method. Note that the training method shown in the illustration does not have thick branches that extend almost horizontally, and all of the multiple fruiting branches 58 grow from the base 53 located at the top of the main trunk 52, so it is sometimes classified as a head-trained method.

[0156] As illustrated in the example, the shape of a trellis system configured so that new shoots (or branches) grow vertically upward is called a VSP (vertical shoot position). A trellis system consists of supports, wires, nets, etc., to support the branches and vines of plants.

[0157] As shown in the example, in addition to the predetermined number (2 in the diagram) of fruiting branches 58, reserve fruiting branches 58b may also be left. The reserve fruiting branches 58b are left after being cut short so that they have a predetermined number (for example, several) of buds 59.

[0158] In this specification, the term "fruit tree cultivation method" may encompass the shape of the trellis system, the pruning method, and the training method for fruit trees. That is, the fruit tree cultivation method is determined by at least one of the following elements: the shape of the trellis system, the pruning method, and the training method. "Fruit tree cultivation method" is used to include field design. For example, if the fruit tree is a grapevine, the grapevine cultivation method includes vineyard design. That is, field design (e.g., vineyard design) is determined by at least one of the following elements: the shape of the trellis system, the pruning method, and the training method for the fruit tree (e.g., a grapevine).

[0159] <Examples of multiple pruning modes> Figure 8 shows examples of the multiple pruning modes available in the cutting point data generation system.

[0160] In the example in Figure 8, the multiple pruning modes are broadly categorized into three types: Quality mode, which prioritizes pruning quality; Shape mode, which prioritizes the shape of the fruit tree; and Yield mode, which prioritizes fruit yield. Each of these three types has a Normal Type and a Speed ​​Type, which prioritizes reducing the time required for pruning compared to the Normal Type. In other words, in the example in Figure 8, a total of six types of pruning modes are available. The six types of pruning modes differ in how they determine the points on the fruit tree branches to be cut. In the table in Figure 8, the settings for determining the points to be cut in each pruning mode are shown with numbers from "1" to "6" indicating the priority of the branch attributes used to determine the points to be cut, and the enabled / disabled settings of the switchable setting parameters are shown with "ON" or "OFF". A smaller number indicates a higher priority for the branch attributes. The switchable / enable setting parameters may include setting parameters for specific attributes (sometimes called "specific setting parameters") and setting parameters common to all attributes (sometimes called "common setting parameters"). Details on "setting attribute priority" and "setting setting parameters to be enabled / disabled" will be described later, but in the example in Figure 8, the six pruning modes differ in how they determine where to cut the fruit tree branches, due to differences in at least one of the attribute priority settings and the setting parameter enable / disable settings.

[0161] In the example in Figure 8, the six pruning modes use the same combination of branch attributes to determine the cutting point. In the table in Figure 8, the shaded attributes "branch length" and "branch internode length" indicate that they are not used to determine the cutting point in this example. However, embodiments of the present disclosure are not limited to this example. In embodiments of the present disclosure, the methods for determining the cutting point of a fruit tree branch may differ from one another, by using different types or combinations of one or more branch attributes to determine the cutting point.

[0162] In the example in Figure 8, the six pruning modes use the same combination of enable / disable setting parameters to determine the cutting points. In the table in Figure 8, the enabled / disabled setting of the shaded setting parameter "Count Basel Bud" indicates that in this example, it is not used to determine the cutting points. However, embodiments of this disclosure are not limited to this example. In embodiments of this disclosure, the methods for determining the cutting points of fruit tree branches may differ among the multiple pruning modes, by having different types or combinations of one or more enable / disable setting parameters used to determine the cutting points.

[0163] The example shown in Figure 8 illustrates several pruning modes available for a fruit tree cultivation method determined by a combination of trellis system (VSP), training method (cordon training), and pruning method (short-pruning). However, these modes are not limited to this cultivation method and can be applied to other methods as well.

[0164] When performing pruning work on fruit trees, users can select one pruning mode from several available modes according to their needs (for example, according to the variety and condition of the fruit tree, the intended use of the fruit, the condition of the field, the user's requests, etc.). Users can, for example, select a pruning mode from several modes that suits their priorities in the pruning work. The cutting point data generation method and cutting point data generation system according to this embodiment allow users to select a pruning mode that meets their needs without individually adjusting the settings for how to determine the points to be cut, making it easy for users to operate and user-friendly.

[0165] Furthermore, the plurality of pruning modes prepared in the cutting point data generation system are not limited to those preset in the cutting point data generation system. The pruning mode preset in the cutting point data generation system may be modified (edited) by the user, or may be newly created by the user. That is, the user can also change and save the setting regarding the method of determining the points to be cut in the plurality of pruning modes. Specific examples will be described later. The user can also adjust the setting regarding the method of determining the points to be cut according to needs as required.

[0166] <Example of the display screen of the operation terminal> FIGS. 9A, 9B, and 9C show examples of the display screen of the operation terminal 400 when having the plurality of pruning modes of FIG. 8. In the cutting point data generation system according to the embodiment of the present disclosure, a graphical user interface (GUI) that allows the user to select any one of the plurality of pruning modes is displayed on the display screen of the operation terminal 400 operated by the user. An example of such a GUI will be described while referring to FIGS. 9A to 9C.

[0167] As shown in Figure 9A, the display screen of the operating terminal 400 shows six buttons 410a corresponding to six different pruning modes. The user can select one of the pruning modes by selecting one of the six buttons 410a and then selecting the OK button 430a. In the example in Figure 9A, the speed type of the quality priority mode is selected, and a graph 420 showing the characteristics of the selected pruning mode is also displayed. Graph 420 is, for example, a graph showing the results of evaluating each pruning mode against multiple evaluation items, and could be a radar chart. In this example, the multiple evaluation items include five items: pruning quality ("Pruning Quality"), tree shape ("Vine Shape"), fruit yield ("Yield Boost"), tree health ("Vine Health"), and reduction in pruning time ("Pruning Speed"). When the user switches the button 410a selected on the display screen of Figure 9A, the display of the graph 420 showing the characteristics of the corresponding pruning mode switches accordingly. By switching the selection button 410a, the user can switch between graphs 420 that show the characteristics of each pruning mode, allowing them to check and compare the characteristics of each pruning mode. Examples of evaluation methods for multiple evaluation items of each pruning mode will be described later.

[0168] In the example shown in Figure 9A, in addition to the six pre-configured pruning modes, a button 410b is displayed representing pruning modes that have been added by the user by changing and saving the settings of any of the six pre-configured pruning modes. The user can also select an added pruning mode by selecting button 410b and then selecting the OK button 430a. Furthermore, a button 410c is displayed for the user to add a new pruning mode.

[0169] As shown in the example in Figure 9A, when any pruning mode (in this example, the speed type of the quality priority mode) is selected, selecting the "Next" button 430c on the display screen of Figure 9A transitions to the display screen of Figure 9B or Figure 9C. The display of Figure 9B or Figure 9C may also be displayed as a pop-up on the display screen of Figure 9A. The display screens of Figures 9B and 9C show the settings for how to determine the points to be cut in the selected pruning mode. Specifically, the display screens of Figures 9B and 9C show the settings for the priority of branch attributes and the settings for enabling / disabling switchable setting parameters, respectively. The user can check these settings for each pruning mode using the display screens of Figures 9B and 9C. Switching between the display screen of Figure 9B and the display screen of Figure 9C is done by selecting the "Next" button 430d on the display screen of Figure 9B, or the "Back" button 430e on the display screen of Figure 9C. By selecting the "Cancel" button 430f on the display screen in Figure 9B or Figure 9C, you will return to the display screen in Figure 9A.

[0170] Furthermore, the user can change the above settings on the display screens in Figures 9B and 9C. When the above settings are changed on the display screens in Figures 9B and 9C, the changes are reflected in Graph 420. The user can adjust the settings for determining the points to be cut according to their needs while checking Graph 420. The display screen in Figure 9B shows sortable buttons 440, each representing one of the six attributes of a branch, along with priority numbers "1" to "6". The user can change the attribute priority settings, for example, by rearranging the buttons 440. In the example in Figure 9B, the button 440 for the attribute "Cane Color" is selected, and a display 450 indicating the setting parameter "Retain Green Cane" related to the attribute "Cane Color," and a toggle switch 452 for enabling / disabling the setting parameter "Retain Green Cane" are also displayed. The user can enable / disable the setting parameter "Retain Green Cane" by operating the toggle switch 452. The screen shows the attribute "Cane Color" selected, and in this state, a display 450 indicating the setting parameter "Retain Green Cane" related to the attribute "Cane Color," and a toggle switch 452 for enabling / disabling the setting parameter "Retain Green Cane" are further displayed. The user can enable / disable the setting parameter "Retain Green Cane" by operating the toggle switch 452. The display screen in Figure 9C shows a display 460 indicating common setting parameters, and toggle switches 462 for enabling / disabling each setting parameter. The user can enable / disable each common setting parameter by operating the toggle switches 462.

[0171] <Setting attribute priority> In the cutting point data generation method and cutting point data generation system according to this embodiment, the priority settings for two or more attributes of a fruit tree branch in determining the point to be cut are made different depending on the pruning mode. In other words, the multiple pruning modes provided in the cutting point data generation method and cutting point data generation system according to this embodiment include two or more pruning modes in which the priority settings for two or more attributes of a fruit tree branch are different from each other. For example, in the example in Figure 8, the quality priority mode, the tree shape priority mode, and the yield priority mode have different priority settings for two or more attributes of a fruit tree branch.

[0172] Figure 10 is a flowchart showing an example of the procedure for generating cutting point data for fruit tree branches according to this embodiment. The flowchart in Figure 10 differs from the flowchart in Figure 1A mainly in that it includes steps S230, S242, and S250 as step S200 for determining the point to be cut. Step S200 in the example of Figure 10 will be mainly explained. Note that step S200 in Figure 10 can also be applied to the flowcharts in Figures 1B and 1C.

[0173] In step S230, based on the sensor data acquired in step S100, measurement values ​​for two or more attributes of one or more branches of the fruit tree are obtained. "One or more branches" refers to one or more branches of the fruit tree that are subject to processing in step S200, for example, one or more branches from which fruiting branches are selected. The one or more branches subject to processing may be, for example, one or more branches that are grouped into the same group when multiple branches of the fruit tree are grouped into multiple groups. The one or more branches subject to processing may be two or more branches.

[0174] The attributes of a branch include at least one of the following: branch color ("Cane Color"), branch direction ("Cane Direction"), branch thickness ("Cane Thickness"), branch base height ("Cane Location"), branch bud size ("Bud Size"), branch bud direction ("Bud Direction"), branch length ("Cane Length"), and branch internode length (i.e., the distance between adjacent buds) ("Internode Length"). In this disclosure, the "attributes" of a branch refer to attributes that appear in the branch's appearance and may also be rephrased as morphological features, appearance characteristics, or outward features. Details of each attribute are described below.

[0175] In step S242, based on the measured values ​​obtained in step S230 and the priority of two or more attributes, it is determined whether each of the one or more branches should be removed or kept. In this example, the priority of the attributes differs depending on the selected pruning mode. The priority of the attributes in each pruning mode may be set, for example, by the user operating the operation terminal 400 (for example, the display screen in Figure 9B). A specific example of the processing performed in step S242 will be described later with reference to Figure 11, etc.

[0176] In step S242, each of the one or more branches to be processed is classified as either a branch to be removed or a branch to be kept. A "branch to be removed" means a branch that is mostly or entirely removed so as not to contain any buds. A "branch to be kept" is a branch that is not to be removed, i.e., a branch that is not removed at all or a branch that is partially removed so as to contain at least one bud. Branches determined to be kept include, for example, fruiting canes, in both short-pruning and long-pruning. In addition to fruiting canes, branches determined to be kept may also include reserve fruiting canes, in both short-pruning and long-pruning. Whether or not to keep reserve fruiting canes can be set by setting parameters, as will be described later. As mentioned above, long-pruning differs from short-pruning in that cutting point data may not be generated for branches determined to be kept. Branches to be kept may also include branches for which the decision of whether to remove or keep has been postponed. The branches to be removed are all branches except those that have been selected to be kept.

[0177] In step S250, for each branch that was determined to be removed in step S242, the point at which it should be cut is determined.

[0178] By setting different priority levels for attributes according to the pruning mode, the method for determining which points to cut, specifically, the method for determining which branches to keep from those to be processed, can be varied according to the pruning mode. As explained with reference to Figure 11, etc., when determining which branches to keep, typically when selecting fruiting branches, the contribution of each attribute can be varied to determine which branches to keep in a way that meets the needs.

[0179] <Determination of points to cut based on measured values ​​for each attribute and attribute priority> The process performed in step S242 (a step in which, based on the measured values ​​for each attribute and the priority of the attributes, one or more branches are determined to be either removed or kept) will be explained with reference to Figure 11 and Figures 12A, 12B, 12C, 12D, and 12E. Figure 11 is a flowchart showing a specific example of the process performed in step S242.

[0180] In step S242a, for each of the one or more branches to be processed, a factor score is determined for each of the two or more attributes based on the measurement values ​​obtained in step S230. For example, Figure 12A shows an example of obtaining and evaluating measurement values ​​for six attributes A to F for six branches 58_1 to 58_6 that are grouped into the same group. Specifically, for each of the six branches 58_1 to 58_6, a factor score F for each of the six attributes A to F is determined. A ~F F Determine the factor score F in the blanks in the table in Figure 12A. A ~F F The number of branches and attributes to be processed is determined in step S242a, and the total score Ts is determined in step S242b, which will be described later. Note that the number of branches and attributes to be processed are merely examples and are not limited to these. The factor score for each attribute of each branch may be determined such that the higher the branch, the more favorable the branch is as a fruiting branch with respect to that attribute. A branch that is favorable as a fruiting branch is, for example, a branch that is expected to bear good quality fruit. Specific examples of methods (e.g., evaluation criteria) for determining the factor score for each attribute of each branch will be described later.

[0181] In step S242b, priority information for two or more attributes is obtained. Priority information is obtained, for example, based on input via the user's operating terminal. The order of step S242b and step S242a or step S230 does not matter. Step S242b may be performed simultaneously (in parallel) with step S242a or step S230.

[0182] In step S242c, for each of one or more branches to be processed, a total score Ts is calculated based on the factor scores for each of the two or more attributes determined in step S242a and the priority information obtained in step S242b.

[0183] FIG. 12B is a diagram for explaining an example of calculating a total score Ts based on the factor scores for respective attributes and the priorities of the respective attributes for each branch. For example, in the example of FIG. 12B, the priorities (the order of priority) are set in the order of attribute D, attribute A, attribute B, attribute C, attribute E, and attribute F from the highest priority. In the example of FIG. 12B, the total score Ts for each branch is obtained by adding up the values obtained by multiplying the factor scores for the respective attributes by a priority weight W P corresponding to the priority of that attribute. The example of the value of the priority weight W P is described in FIG. 12B, but it is not limited to this example. As long as the priority weight W P is set to increase as the priority is higher. Also, the method of calculating the total score Ts is not limited to this example. For example, the total score Ts can be calculated based on the values obtained by correcting the factor scores for the respective attributes according to the priorities of the attributes. That is, the higher the factor score of an attribute with a higher priority, the greater the contribution to the total score Ts.

[0184] The priorities of the respective attributes are not limited to the case where different ranks are assigned to all the attributes as in the example of FIG. 12B. Referring to FIGS. 12D and 12E, another example will be described. For example, as in the example of FIG. 12D, among the six attributes, the same rank may be assigned to two or more attributes. In such a case, the same value of the priority weight W PThe following applies. In the example in Figure 12D, for the sake of convenience in expressing the formula for calculating the total score Ts, attribute A is assigned a different number as the second and attribute B as the third, but both attribute A and attribute B have the second priority. Also, as in the example in Figure 12E, it is possible to set the priority so that the factor score for one or more of the six attributes is not included in the calculation of the total score Ts. In such a case, the attribute that is set not to be included in the calculation of the total score Ts (attribute A in the example in Figure 12E) has a priority weight W P Set the value of to zero. You may combine the examples in Figures 12D and 12E.

[0185] In step S242d, based on the total score Ts calculated for each of the one or more branches to be processed, it is determined whether each of the one or more branches to be removed or kept is determined. For example, among the one or more branches to be processed, the branch with the highest total score Ts is determined to be kept, and the branches other than the one determined to be kept are determined to be removed.

[0186] Referring to Figures 13 and 14, an example is given where priority settings are not set for two or more attributes. In embodiments of this disclosure, setting priority settings for two or more attributes is not mandatory. In that case, the method for determining the points on which fruit tree branches should be cut is varied according to the pruning mode in a manner other than by varying the setting of attribute priority settings. Figure 13 is a flowchart showing an example of the procedure for generating fruit tree branch cutting point data according to embodiments of this disclosure, and Figure 14 is a flowchart showing a specific example of the process performed in step S240 of Figure 13. The flowchart of Figure 13 differs from the flowchart of Figure 10 in that it has step S240 instead of step S242.

[0187] In step S240, based on the measurement values ​​obtained in step S230, it is determined whether each of the one or more branches will be removed or kept. In step S240, the following processes S240a, S240b, and S240c are performed.

[0188] In step S240a, for each of the one or more branches to be processed, a factor score is determined for each of the one or more attributes based on the measured values ​​obtained in step S230. The processing in step S240a is performed in the same manner as the processing in step S242a in Figure 11.

[0189] In step S240b, for each of the one or more branches to be processed, a total score Ts is calculated based on the factor scores for each of the one or more attributes determined in step S240a. The total score Ts can be, for example, the sum of the factor scores for each of the one or more attributes (if there is only one attribute, its factor score is used as the total score Ts).

[0190] In step S240c, based on the total score Ts calculated for each of the one or more branches to be processed, it is determined whether each of the one or more branches to be removed or kept is determined. For example, among the one or more branches to be processed, the branch with the highest total score Ts is determined to be kept, and the branches other than the one determined to be kept are determined to be removed.

[0191] <Enable / Disable setting parameters> In the cutting point data generation method and cutting point data generation system according to this embodiment, the enabled / disabled settings of one or more switchable setting parameters in determining the point to be cut on a fruit tree branch are made different depending on the pruning mode. In other words, the multiple pruning modes provided in the cutting point data generation method and cutting point data generation system according to this embodiment include two or more pruning modes in which the enabled / disabled settings of at least one of the one or more setting parameters differ from each other. For example, in the example in Figure 8, in each of the quality priority mode, tree shape priority mode, and yield priority mode, the enabled / disabled settings of the common setting parameters differ between the normal type and the speed type. Furthermore, the enabled / disabled settings of specific setting parameters differ between the quality priority mode and the tree shape priority mode, and the enabled / disabled settings of specific setting parameters differ between the tree shape priority mode and the yield priority mode.

[0192] Examples of setting parameters are described below. In the example in Figure 8, common setting parameters include "Retry Enabled," "Check Before Cut," "Cutting Orientation," "Leave Renewal Canes," "Count Basel Bud," "Filter Healthy Canes," and "Bud Density," while specific setting parameters include "Retain Green Cane" and "Bud Count Adjust." Although each setting parameter is described below using individual flowcharts, in embodiments of this disclosure, multiple setting parameters can be used in combination. In such cases, the processing of the corresponding flowcharts can be combined.

[0193] (Example 1 of common configuration parameters) • Setting parameter "Retry Enabled": This setting determines whether or not to allow the system to re-determine the point to disconnect after it has already been determined. The "Retry Enabled" setting determines whether or not the system can re-determine the cutting points after the initial determination, for example, based on user instructions. Enabling the "Retry Enabled" setting allows for more accurate determination of cutting points. On the other hand, enabling the "Retry Enabled" setting may increase the processing load and processing time of the cutting point generation system. Therefore, disabling the "Retry Enabled" setting can reduce the processing load and processing time.

[0194] The setting parameter "Retry Enabled" will be explained with reference to Figure 15. Figure 15 is a flowchart showing an example of the procedure for generating branch cutting point data for fruit trees according to this embodiment. The flowchart in Figure 15 differs from the example described above (for example, the example in Figure 1A) in that it further includes steps S202 and S204.

[0195] The processes in steps S050, S100, and S200 are carried out in the same manner as in the example described above (for example, the example in Figure 1A).

[0196] After step S200, if the setting parameter "Retry Enabled" is enabled (if it is "Yes" in step S202), in step S204, for example, based on user instructions, one or more points to be cut are determined again based on the pruning mode information acquired in step S050 and the sensor data acquired in step S100.

[0197] In step S300, for each of the points to be cut determined in step S204, cutting point data is generated that includes information indicating its three-dimensional position.

[0198] (Example 2 of common setting parameters) • Setting parameter "Check Before Cut": Enables / disables the display of generated cutting point data to the user and the reception of user instructions. The "Check Before Cut" setting parameter determines whether or not the generated cutting point data is presented to the user, for example, by displaying it on an operating terminal. Enabling the "Check Before Cut" setting parameter allows for more accurate determination of the points to be cut. On the other hand, enabling the "Check Before Cut" setting parameter may increase the processing load and processing time of the cutting point generation system. Therefore, disabling the "Check Before Cut" setting parameter can reduce the processing load and processing time.

[0199] The setting parameter "Check Before Cut" will be explained with reference to Figure 16. Figure 16 is a flowchart showing an example of the procedure for generating cutting point data for fruit tree branches according to this embodiment.

[0200] The processing in steps S050 and S100 is carried out in the same manner as in the example described above (for example, the example in Figure 1A).

[0201] If the setting parameter "Check Before Cut" is enabled (if "Yes" is selected in step S206), in step S200, based on the pruning mode information acquired in step S050 and the sensor data acquired in step S100, one or more points to be cut are determined for the branches of the fruit tree 200. At this time, the process in step S200 is performed for a predetermined number of fruit trees. The predetermined number of pieces of information is acquired, for example, based on user input. Except for the fact that the process in step S200 is performed for a predetermined number of fruit trees, the process in step S200 is performed in the same manner as in the example described above (for example, the example in Figure 1A).

[0202] After step S200, in step S300, cutting point data is generated for each of the points to be cut determined in step S200, including information indicating its three-dimensional position. The processing in step S300 is carried out in the same manner as in the example described above (for example, the example in Figure 1A).

[0203] After step S300, in step S322, the cutting point data generated in step S300 is displayed on the display device of the terminal device 400 operated by the user.

[0204] After step S322, in step S324, the system receives user instructions from the terminal device 400 operated by the user. The user instructions include whether or not to continue displaying the generated cut-point data on the terminal device 400. If the received user instructions include continuing to display the generated cut-point data on the terminal device 400 (if "Yes" is given in step S326), the processes of steps S200, S300, S322, and S324 described above are repeated. If the received user instructions include not continuing to display the generated cut-point data on the terminal device 400 (if "No" is given in step S326), the processes of steps S200 and S300 are performed in the same manner as in the example described above (for example, the example in Figure 1A).

[0205] If the setting parameter "Check Before Cut" is invalid (i.e., "No" in step S206), the processes in steps S200 and S300 are carried out in the same way as in the example described above (for example, the example in Figure 1A).

[0206] (Example 3 of common configuration parameters) • Setting parameter "Cutting Orientation": This setting enables or disables the generation of cutting point data so that the branch is cut by a plane perpendicular to the direction in which the branch is growing. The "Cutting Orientation" setting determines whether the cutting plane for branches is perpendicular to the direction of branch growth or horizontal to the ground when generating cutting point data. Disabling the "Cutting Orientation" setting and cutting with a plane horizontal to the ground reduces the processing load and time required for the cutting point generation system, as the cutting plane will be determined parallel to the ground for all branches. On the other hand, cutting with a plane horizontal to the ground can lead to moisture accumulation on the cut surface, which may be undesirable from a branch health perspective, such as making the branches more susceptible to disease. Enabling the "Cutting Orientation" setting and cutting with a plane perpendicular to the direction of branch growth may increase the processing load and time, but it can suppress the accumulation of moisture on the cut surface. Users can enable or disable the "Cutting Orientation" setting according to their needs and circumstances.

[0207] The setting parameter "Cutting Orientation" will be explained with reference to Figures 17A and 17B. Figure 17A is a flowchart of an example of the procedure for generating cutting point data for fruit tree branches according to this embodiment. The flowchart in Figure 17A differs from the example described above (for example, the example in Figure 1A) in the processing of step S300. Figure 17B is a schematic diagram for explaining the setting parameter "Cutting Orientation," and the cut surface of branch 58 is shown with dashed lines for both the case where the setting parameter "Cutting Orientation" is enabled ("ON") and the case where it is disabled ("OFF").

[0208] The processes in steps S050, S100, and S200 are carried out in the same manner as in the example described above (for example, the example in Figure 1A).

[0209] In step S300, the following process is performed as shown in Figure 17B. If the setting parameter "Cutting Orientation" is enabled (if it is "Yes" in step S310), in step S312, cutting point data is generated for each of the one or more points to be cut, such that the branch 58 is cut on a plane perpendicular to the direction in which the branch 58 is growing. If the setting parameter "Cutting Orientation" is disabled (if it is "No" in step S310), in step S314, cutting point data is generated for each of the one or more points to be cut, such that the branch 58 is cut on a plane horizontal to the ground GR. In the figure, the ground GR is horizontal to the xy plane.

[0210] (Example 4 of common setting parameters) • Setting parameter "Leave Renewal Cane": Enables / disables the setting that determines which branches to keep from one or more branches to be processed in a fruit tree. The setting parameter "Leave Renewal Cane" can be described as a setting to determine whether or not to leave additional reserve fruiting canes (sometimes called renewal canes) in addition to the main fruiting cane as branches to be kept. In this example, one or more branches to be processed could be two or more branches. If the setting parameter "Leave Renewal Canes" is enabled, reserve fruiting canes can be used if the main fruiting cane does not function properly, thereby improving fruit yield. On the other hand, enabling the setting parameter "Leave Renewal Canes" may increase the processing load and processing time of the cutting point generation system, so disabling the setting parameter "Leave Renewal Canes" can reduce the processing load and processing time.

[0211] The setting parameter "Leave Renewal Cane" will be explained with reference to Figure 18. Figure 18 is a flowchart illustrating an example of the procedure for generating branch cutting point data for fruit trees according to this embodiment, and is a flowchart of the procedure that may be performed in step S240c of Figure 14 (a step in which it is decided whether each of the one or more branches to be processed will be a branch to be removed or a branch to be kept, based on the total score Ts calculated for each of the one or more branches to be processed). The flowchart in Figure 18 can also be applied to step S242d of Figure 11.

[0212] In step S240c1, among the one or more branches to be processed, the branch with the highest total score Ts calculated in step S240b is selected as the branch to be kept. The branch with the highest total score Ts can be selected as the branch to be kept (for example, the fruiting branch).

[0213] If the factor score for each attribute of each branch is determined such that the higher the branch is in a favorable state as a fruiting branch with respect to that attribute, then branches with a higher total score Ts (the sum of these factors) are considered more favorable as fruiting branches. By selecting the branch with the highest total score Ts as the fruiting branch, it is possible to select the branch that is expected to bear the best quality fruit in the current or next season from among the one or more branches being treated, thereby promoting the automation of pruning work while maintaining fruit yield and quality.

[0214] If the setting parameter "Leave Renewal Cane" is enabled (i.e., "Yes" in step S240c2), in step S240c3, the branch with the second highest total score Ts among the one or more branches to be processed is also selected to be kept. In other words, when the setting parameter "Leave Renewal Cane" is enabled, at least two of the one or more branches to be processed are selected to be kept. The branch with the second highest total score Ts is considered to have a high probability of being the second most desirable branch as a fruiting cane. By selecting the branch with the second highest total score Ts as a reserve fruiting cane, the automation of pruning can be promoted while maintaining fruit yield and quality.

[0215] After step S240c3, proceed to step S240c4. If the answer in step S240c2 is No, proceed to step S240c4.

[0216] In step S240c4, all branches other than the one or more branches to be processed that have been decided to be kept are decided to be branches to be removed.

[0217] (Example 5 of common setting parameters) • Setting parameter "Count Basel Bud": When determining the number of buds to leave on a fruit tree branch that has been selected to be kept, this setting determines whether or not to include the bud closest to the base of that branch. The "Count Basel Bud" setting parameter determines whether or not to include the basal bud located closest to the base of each branch as a bud. When the "Count Basel Bud" setting parameter is enabled, the basal buds of each branch are included as buds; when the "Count Basel Bud" setting parameter is disabled, the basal buds of each branch are not included as buds. Users can switch the "Count Basel Bud" setting parameter on or off depending on their needs and circumstances.

[0218] The setting parameter "Count Basel Bud" may be configured to be enabled or disabled only when the setting parameter "Bud Count Adjust" (see Figure 25), which will be described later, is enabled.

[0219] (Example 6 of common setting parameters) • Setting parameter "Filter Healthy Cane": Enables / disables the ability to remove non-candidate branches that should not be selected as branches to be kept from one or more branches targeted for processing in fruit trees, before deciding which branches to keep. The "Filter Healthy Cane" setting determines whether or not to pre-detect branches that should not be selected as branches to be kept (sometimes called "non-candidate branches") from one or more branches being processed, and remove them from the list of candidates to be kept. By enabling the "Filter Healthy Cane" setting, for example, branches that may have health problems can be removed from the list of candidates to be kept. As mentioned above, branches to be kept include, for example, fruiting branches. By avoiding the selection of branches that are not in good health as fruiting branches, a decrease in fruit yield and quality can be suppressed. On the other hand, enabling the "Filter Healthy Cane" setting may increase the processing load and processing time of the cutting point generation system, so disabling the "Filter Healthy Cane" setting can reduce the processing load and processing time.

[0220] The setting parameter "Filter Healthy Cane" will be explained with reference to Figure 19. Figure 19 is a flowchart illustrating an example of the procedure for generating branch cutting point data for fruit trees according to this embodiment, and is a flowchart of the procedure that may be performed in step S240 of Figure 13 (a step in which, based on measured values, each of one or more branches is determined to be either a branch to be removed or a branch to be kept). The flowchart in Figure 19 can also be applied to step S242 of Figure 10.

[0221] As shown in Figure 19, if the setting parameter "Filter Healthy Cane" is enabled (if it is "Yes" in step S241a), proceed to step S241b. If the setting parameter "Filter Healthy Cane" is disabled (if it is "No" in step S241a), proceed to step S241h. Steps S241h and the subsequent step S241j may be performed in the same way as step S240 shown in Figure 14, for example.

[0222] In step S241c, based on the sensor data acquired in step S100, it is determined whether or not one or more branches to be processed (for example, one or more branches grouped into the same group among multiple groups) contain any non-candidate branches.

[0223] Figure 20A shows an example of an image used in the cutting point data generation method and cutting point data generation system according to this embodiment. In step S241c, based on the segmented image 51a, for example as shown in Figure 20A, it is determined whether or not the six branches 58_1 to 58_6 grouped into the same group contain any non-candidate branches. The image 51a shown in Figure 20A can be obtained by applying instance segmentation to an image of a fruit tree obtained by a camera. "Segmentation" is a general term for algorithms that classify objects or individuals (instances) contained in an image into classes or categories on a pixel-by-pixel basis, and is used in deep learning. Among segmentation algorithms, instance segmentation is an algorithm that classifies individuals contained in an image. By applying instance segmentation to an image containing fruit tree branches, individual parts of the fruit tree can be identified or extracted. The segmented image includes a mask that extracts each of the parts of the fruit tree (e.g., main trunk, main branches, fruiting branches, branches, short shoots, etc.) in the input image data. For example, the segmented image 51a includes short-sprout masks M56_1, M56_2, and M56_3, which extract the short-sprouts 56_1, 56_2, and 56_3 respectively; branch masks M58_1, M58_2, M58_3, M58_4, M58_5, and M58_6, which extract the branches 58_1, 58_2, 58_3, 58_4, 58_5, and 58_6 respectively; and a main branch mask M54, which extracts the main branch 54. In the figure, the regions extracted by each mask are shown with hatching (or color) and the reference code of the mask. Branch masks M58_1 to M58_6 are sometimes collectively referred to as branch mask M58, and short-sprout masks M56_1 to M56_3 are sometimes collectively referred to as short-sprout mask M56.

[0224] Based on the segmented image 51a shown in Figure 20A, information on one or more attributes (e.g., branch color, branch shape, branch thickness, branch length, fruit tree variety, fruit tree age, geographical location, etc.) is obtained for each of the six branches 58_1 to 58_6, and based on the obtained information, it is determined whether or not a branch is an outside candidate. Specifically, for example, healthy branches are usually brown, while branches in poor health may have at least partially black or white surfaces. For example, a branch determined to have a predetermined range (or predetermined percentage) of its surface area as black or white may be detected as an outside candidate branch (a diseased branch). If an outside candidate branch is included among the six branches 58_1 to 58_6 (if the answer is "Yes" in step S241c), the process proceeds to step S241d. If no outside candidate branches are included among the six branches 58_1 to 58_6 (if the answer is "No" in step S241c), the process proceeds to step S241h.

[0225] The determination of whether or not one or more branches to be processed (for example, one or more branches grouped into the same group) contain non-candidate branches can be performed by one or more of the following methods, for example:

[0226] (i) For example, by obtaining measurements regarding the color of the branch, it is possible to determine whether or not the branch is an outside candidate branch. The determination is made by the following steps, as shown in Figure 20B. Figure 20B is a flowchart showing an example of the process performed in step S241c.

[0227] Step S10-1: Use one or more sensors (e.g., cameras) to acquire sensor data of the branches (e.g., images including the branches).

[0228] Step S10-2: Use the acquired sensor data to extract the parts corresponding to the branches. For example, apply AI-based segmentation (e.g., instance segmentation) to the acquired image.

[0229] Step S10-3: Obtain information about the color of the part corresponding to the extracted branch (e.g., RGB values, HSL values, and their statistics).

[0230] Step S10-4: Determine whether an edge is an outside candidate based on the acquired color information. For example, the relationship between color information and evaluation criteria for whether an edge is an outside candidate (e.g., a table) is stored in a memory device, and the determination is made by referring to the stored information (table).

[0231] (ii) Whether or not a branch is an excluded branch can be determined by whether or not it has cane spots and / or galls on its surface. If a branch has cane spots and / or galls on its surface, it is highly likely that the branch is diseased. This can be combined with the determination method in (i) above. The determination is made by the following steps, for example, shown in Figure 20C. Figure 20C is a flowchart showing an example of the process performed in step S241c.

[0232] Step S12-1: Use one or more sensors (e.g., cameras) to acquire sensor data of the branches (e.g., images including the branches).

[0233] Steps S12-2 and S12-3: Using the acquired sensor data, extract the parts corresponding to branches (Step S12-2), and determine whether or not the branches have spots and / or bumps (Step S12-3). For example, in Step S12-2, segmentation (e.g., instance segmentation) is applied to the acquired image to extract the parts corresponding to branches. The detection of spots and bumps in Step S12-3 can be performed, for example, by object detection using artificial intelligence (AI).

[0234] (iii) A machine learning model can be used to determine whether the branch is an outside branch or not. This determination is made by the following steps, for example, as shown in Figure 20D. Figure 20D is a flowchart showing an example of the process performed in step S241c.

[0235] Step S14-1: Acquire images of the branches using one or more imaging devices (e.g., cameras).

[0236] Step S14-2: Prepare images of diseased branches and healthy branches as a training dataset, and prepare a trained model by training it using supervised learning. Note that the order of Step S14-1 and Step S14-2 does not matter and can be performed simultaneously (in parallel).

[0237] Step S14-3: The trained model prepared in Step S14-2 is input with the branch image acquired in Step S14-1 and is made to determine (output) whether or not the branch is likely to be diseased.

[0238] (iv) Based on input of other information, it can be determined whether or not the branch is an excluded branch. For example, if information is available (or can be obtained) that there is a suspected disease that may be obtained in work other than pruning performed on the fruit tree (e.g., quality measurement work), information on the past presence or absence of diseases of the fruit tree (history), disease prediction information, etc., then this information can be input into the system and stored. If this information is input into the system, it can be determined whether or not the branch is an excluded branch based on this information.

[0239] In step S241d, a decision is made, for example based on user input, whether to include non-candidate branches in the process of determining whether to remove them or keep them. For example, the user can pre-configure whether to automatically continue the process of determining whether to remove or keep branches other than non-candidate branches when non-candidate branches are detected. If the answer in step S241d is Yes (for example, if the setting is to automatically continue the process of determining whether to remove or keep branches for non-candidate branches), the process proceeds to step S241e.

[0240] In step S241e, from the one or more branches grouped in the same group, the branches that are not candidates are removed and the branches to be kept are selected and decided. Then, in step S241f, from the one or more branches to be processed, the branches other than the branches that were decided to be kept are decided to be removed. At this time, the branches that were not candidates are also decided to be removed.

[0241] If the answer to step S241d is No (for example, if the system is configured not to automatically continue the process of deciding whether to remove or keep non-candidate branches), proceed to step S241g. In step S241g, the user is notified that non-candidate branches have been detected. The user may also be notified of further information that identifies the non-candidate branches.

[0242] After step S241g, as described below for the processing in steps S241r and S241s, a decision is made on whether to include the non-candidate branch in the process of determining whether it should be removed, whether it should be included in the process of determining whether it should be removed or kept, or whether it should not be included in the process of determining whether it should be removed or kept (for example, by adding information that it is neither a branch to be removed nor a branch to be kept, and not generating cutting point data for the non-candidate branch). For example, the user can receive notification that a non-candidate branch has been detected, check data such as an image of the detected non-candidate branch, and then select and input which of the above processing to perform.

[0243] After step S241g, in step S241r, it is determined, for example based on user input, whether to include the non-candidate branch in the process of determining whether to remove it or keep it. If the answer in step S241r is Yes, then in step S241s, it is determined, for example based on user input, whether to decide to remove the non-candidate branch. If the answer in step S241s is Yes, then the process proceeds to step S241e and the subsequent step S241f. For example, if the detected non-candidate branch is likely to be a diseased branch, and the detected non-candidate branch is to be decided to remove it at that point, then the answer in step S241r should be Yes and in step S241s should also be Yes. In this case, in steps S241e and S241f, the branches to be kept are selected from the branches excluding the non-candidate branch and the detected branch. If the answer is No in step S241s, the process proceeds to step S241h and the subsequent step S241j, where it is determined whether to remove or keep each of the one or more branches grouped into the same group, including the non-candidate branches and the detected branches. For example, if there is little need to immediately remove the detected non-candidate branches, such as when the detected non-candidate branches are unlikely to be diseased, then the answer should be Yes in step S241r and No in step S241s. In this case, steps S241h and S241j are used to select which branches to keep from among the non-candidate branches and the detected branches.

[0244] If the answer in step S241r is No, that is, if the non-candidate branch is not to be included in the process of determining whether to remove it or keep it, the process proceeds to step S241t. In step S241t, for each of the branches remaining after removing the non-candidate branch from the one or more branches grouped in the same group, a decision is made as to whether to remove it or keep it. The decision of whether to remove it or keep it may be made using the examples described above. For example, if it is difficult to determine whether the detected non-candidate branch is a diseased branch or not, the answer in step S241r is No, and the process proceeds to step S241t. For the detected non-candidate branch, information is added indicating that it is neither a branch to remove nor a branch to keep, and the decision of whether to remove it or keep it is postponed.

[0245] (Example 7 of common setting parameters) • Setting parameter "Bud Density": This setting enables / disables the ability to maintain or change the decision on whether to remove or keep a branch after determining whether to remove or keep it for one or more branches of a fruit tree. This decision is based on the distribution of buds on the branches that have been selected to be kept. The "Bud Density" setting parameter determines whether to re-determine (adjust) which branches to remove or keep after a decision has been made for each group of branches (e.g., for each group) by considering the distribution of remaining buds over a wider area (e.g., the entire fruit tree). Enabling the "Bud Density" setting parameter makes it possible to make the distribution of remaining buds more uniform across the entire fruit tree, for example. Therefore, an improvement in fruit yield can be expected. On the other hand, enabling the "Bud Density" setting parameter may increase the processing load and processing time of the cutting point generation system, so disabling the "Bud Density" setting parameter can reduce the processing load and processing time.

[0246] The setting parameter "Bud Density" will be explained with reference to Figures 21 and 22. Figure 21 is a flowchart showing an example of the procedure for generating cutting point data for fruit tree branches according to this embodiment. The flowchart in Figure 21 differs from the example described above (for example, the example in Figure 1A) in that it has steps S220, S222, S290a, and S290b as step S200 for determining the point to be cut. Figure 22 is a schematic diagram to illustrate the process in the flowchart of Figure 21. Figure 22 shows the state of a hypothetical fruit tree if pruning is performed according to the decision in step S220. For simplicity, buds 59 are shown only on some of the branches 58. Note that Figures 21 and 22 can be applied mainly to short-pruning.

[0247] The processing in steps S050 and S100 is carried out in the same manner as in the example described above (for example, the example in Figure 1A).

[0248] In step S220, based on the pruning mode information acquired in step 050 and the sensor data acquired in step S100, the multiple branches 58 of the fruit tree are grouped into multiple groups. The grouping of the multiple branches 58 may be based on the position of the base of each of the multiple branches 58. For example, the multiple groups correspond to the multiple short shoots 56 of the main branch 54 that supports the multiple branches 58 of the fruit tree. Branches 58 growing from the same short shoot 56 may be grouped into the same group. Branches 58 growing from within a predetermined range may be grouped into the same group. Alternatively, the multiple groups may correspond to multiple regions R1, R2, ... arranged along the direction in which the main branch 54 grows (left-right direction in the figure) of the main branch 54 that supports the multiple branches 58 of the fruit tree. Of the multiple branches 58 that a fruit tree has, branches that grow from the same area may be grouped into the same group. Details of the grouping process will be described later.

[0249] Next, in step S222, based on the sensor data acquired in step S100, it is determined whether each of the one or more branches grouped into the same group in step S220 should be removed or kept. The process in step S222 is performed for each group. That is, in step S222, for each group, it is determined whether each of the one or more branches grouped into that group should be removed or kept.

[0250] If the setting parameter "Bud Density" is enabled (if "Yes" is selected in step S290a), in step S290b, for each of the multiple groups, a decision is made to change or maintain the decision on whether to remove or keep each of the one or more branches grouped into other groups, based on the bud distribution of the branches determined to be kept in step S222. The bud distribution is the distribution of buds throughout the entire fruit tree, for example, the density of bud placement in the direction along which the main branch 54 supporting branch 58 grows (left-right direction in Figure 22). Information on the bud distribution of the branches determined to be kept in step S222 can be obtained based on information on the branches determined to be kept in step S222 and information on the number of buds to be kept on each of the branches to be kept. Information on the number of buds to be kept on each of the branches to be kept can be obtained, for example, based on user input.

[0251] The branches to be kept in step S290b include the branches that were decided to be removed in step S222. In other words, in addition to the branches decided to be kept in step S222, additional branches can be decided to be kept in step S290b. By changing (re-determining) the branches that were decided to be removed in step S222 to the branches to be kept in step S290b, the density of buds on the remaining branches can be made more uniform throughout the fruit tree.

[0252] An example of the process in step S290b is described below. Specifically, in addition to the branches decided to be kept in step S222, additional branches to be kept are determined as follows. For example, if there is an area where the density of buds is partially low, additional branches to be kept are determined from among the multiple branches of the fruit tree that are grouped into a group located near that area. For example, if multiple groups include a first group of branches that are not grouped, additional branches to be kept are determined from among the one or more branches grouped into a group adjacent to the first group. Of the one or more branches grouped into a group adjacent to the first group, additional branches to be kept may be determined from among the branches that grow in the direction of the first group. The first group is, for example, a group corresponding to short shoots that do not have branches. Also, if multiple groups include a second group that does not have branches to be kept, additional branches to be kept are determined from among the one or more branches grouped into a group adjacent to the second group. Of the one or more branches grouped into a group adjacent to the second group, additional branches to be kept may be determined from among the branches that grow in the direction of the second group. The second group is, for example, a group in which one or more branches grouped together have all been determined to be branches to be removed.

[0253] Information regarding the cultivation method of the fruit tree may be obtained, and in step S290b, based on the information regarding the cultivation method of the fruit tree and the distribution of buds on the branches determined to be kept in step S222, a decision may be made again as to whether each of the multiple branches on the fruit tree should be removed or kept.

[0254] Based on the decision in step S290b, the process in step S300 is carried out.

[0255] If the setting parameter "Bud Density" is invalid (i.e., "No" in step S290a), the process proceeds to step S300 after step S222.

[0256] (Example 1 of specific setting parameters) Setting parameter "Retain Green Cane": • Attributes: Setting parameters related to branch color • Enable / disable setting to decide which branches to keep if they are green. The "Retain Green Cane" setting determines whether or not to retain a branch if its color is green. Enabling the "Retain Green Cane" setting prevents the pruning of branches that are not in a suitable condition for pruning (for example, too early in the season). Enabling the "Retain Green Cane" setting allows for more accurate determination of pruning points and helps maintain the health of the fruit tree. On the other hand, enabling the "Retain Green Cane" setting may increase the processing load and processing time of the pruning point generation system, so disabling the "Retain Green Cane" setting can reduce the processing load and processing time.

[0257] The setting parameter "Retain Green Cane" will be explained with reference to Figure 23. Figure 23 is a flowchart illustrating an example of the procedure for generating branch cutting point data for fruit trees according to this embodiment, and is a flowchart showing a specific example of the processing performed in step S240 of Figure 13 (a step in which it is determined whether each of the one or more branches should be removed or kept, based on the measured values ​​of one or more attributes). In this example, the one or more attributes include the color of the branch.

[0258] If the setting parameter "Retain Green Cane" is enabled (if "Yes" is selected in step S240i1), in step S240i2, the color of each of the one or more branches is determined based on the measured values ​​related to the branch color. If the branch is determined to be green (if "Yes" is selected in step S240i3), in step S240i4, that branch is decided to be kept. The determination of the branch color can be performed in the same way as, for example, when the setting parameter "Filter Healthy Cane" is enabled.

[0259] If the setting parameter "Retain Green Cane" is invalid (if it is "No" in step S240i1), proceed to steps S240a, S240b, and S240c. The processing in steps S240a, S240b, and S240c may be carried out in the same way as in the example in Figure 14. If the branch color is not determined to be green (if it is "No" in step S240i3), proceed to steps S240a, S240b, and S240c.

[0260] (Example 2 of specific setting parameters) Setting parameter "Bud Count Adjust": • Setting parameters related to attributes concerning the vigor of fruit trees • Enable / disable setting to adjust the number of buds left on branches determined to be kept, based on measured values ​​related to the vigor of fruit trees. The setting parameter "Bud Count Adjust" determines whether or not to adjust the number of buds left on branches that have been selected to be kept. When the setting parameter "Bud Count Adjust" is enabled, the number of buds left can be adjusted according to the vigor of the branches selected to be kept (e.g., fruiting canes). If the vigor of the fruiting cane is weaker than a predetermined range, the yield and quality of the fruit may decrease. By determining the point to cut so that the number of buds left is less than the set value (e.g., a value entered by the user), the decrease in fruit yield and quality can be suppressed. If the vigor of the fruiting cane is stronger than a predetermined range, by determining the point to cut so that the number of buds left is more than the set value, it is expected that a larger yield can be obtained without reducing quality. In this way, by adjusting the number of buds left according to the vigor of the fruit tree and determining the point to cut, the decrease in fruit yield and quality can be suppressed. On the other hand, enabling the "Bud Count Adjust" setting parameter may increase the processing load and processing time of the cut point generation system. Therefore, disabling the "Bud Count Adjust" setting parameter can reduce the processing load and processing time.

[0261] The setting parameter "Bud Count Adjust" will be explained with reference to Figures 24 and 25. Figure 24 is a flowchart illustrating an example of the procedure for generating branch cutting point data for fruit trees according to this embodiment, and is a flowchart showing a specific example of the process performed in step S200 (a step in which one or more cutting points are determined for the branches of the fruit tree based on pruning mode information and sensor data). Figure 25 is a flowchart illustrating an example of the procedure for generating branch cutting point data for fruit trees according to this embodiment, and is a flowchart showing a specific example of the process performed in step S260 of Figure 24 (a step in which the number of buds to be left on the branches determined to be left is determined based on measured values ​​for one or more attributes).

[0262] In the example shown in Figure 24, the processes of steps S230a, S240, S250, S260, and S270 are performed in step S200.

[0263] In step S230a, based on the sensor data acquired in step S100, measurement values ​​are obtained for one or more attributes of each of one or more branches of the fruit tree, including attributes related to the vigor of the fruit tree. Attributes related to the vigor of the fruit tree include, for example, at least one of the branch thickness, the size of the buds on the branch, and the length of the internodes of the branch. The processing in step S230a can be carried out, for example, similarly to the processing in step S230 in Figure 10.

[0264] In step S240, based on the measurement values ​​obtained in step S230, it is determined whether each of the one or more branches should be removed or kept. The process in step S240 can be carried out in the same way as the process in step S240 shown in Figure 13, for example.

[0265] In step S250, the point to be cut is determined for each of the branches that were determined to be removed in step S240. The point to be cut for each branch to be removed is determined such that each of the branches 58 determined to be removed will not have any buds after being cut (i.e., the number of buds after being cut will be zero). For example, in the case of short-pruning and cordon training, the point to be cut is determined so that the branch 58 is cut near the short pruning 56 at its base. For example, the point to be cut is determined so that the branch 58 is cut between the short pruning 56 at its base and the bud 59 that is closest to the short pruning 56 among the buds 59 that the branch 58 has. In the case of bush training (for example, in the case of long-pruning), the cutting point data is generated so that the branch 58 is cut near the base of the bush 53. For example, the point to be cut is determined so that the branch 58 is cut between the base of the bush 53 and the bud 59 that is closest to the bush 53 among the buds 59 that the branch 58 has.

[0266] In step S260, the number of buds to be left on the branch determined to be kept in step S240 is determined based on the measurement values ​​obtained in step S230a. Details of the process performed in step S260 will be explained with reference to Figure 25. In step S260, if the setting parameter "Count Basel Bud" is enabled, the bud closest to the base of the branch determined to be kept is counted to determine the number of buds to be left.

[0267] In step S270, based on the number of buds to be left determined in step S260, the point to be cut is determined for the branch that was determined to be left in step S240.

[0268] Referring to Figure 25, the process performed in step S260 will be explained.

[0269] In step S260a, information on the set value of the number of buds to be left on each branch to be kept is obtained. This information on the set value of the number of buds to be left is obtained, for example, based on user input. The user can input the set value of the number of buds to be left on each branch to be kept, depending on, for example, the fruit tree variety, pruning method, training method, cultivation plan based on yield plan, field design (for example, vineyard design if the fruit tree is a grapevine), etc. Field design and vineyard design can be determined by, for example, at least one element of the trellis system shape, pruning method, and training method.

[0270] If the setting parameter "Bud Count Adjust" is enabled (if "Yes" is selected in step S260b), in step S260c, the strength of the tree vigor of the branch decided to be kept in step S240 is determined based on the measurement values ​​obtained in step S230c. For example, if the branch thickness is thinner than a predetermined value or the bud size is smaller than a predetermined value, the tree vigor is determined to be weaker than the predetermined range. If the branch thickness is thicker than a predetermined value or the bud size is larger than a predetermined value, the tree vigor is determined to be stronger than the predetermined range. For example, if the branch thickness is within the predetermined range or the bud size is within the predetermined range, the tree vigor is determined to be within the predetermined range.

[0271] In step S260c, for example, the strength of the tree vigor of the branches decided to be kept may be determined based on factor scores determined in step S240 based on the thickness of the branches and / or the size of the buds. For example, if the factor score for branch thickness is smaller than a predetermined value, or if the factor score for bud size is smaller than a predetermined value, the tree vigor is determined to be weaker than a predetermined range. If the factor score for branch thickness is larger than a predetermined value, or if the factor score for bud size is larger than a predetermined value, the tree vigor is determined to be stronger than a predetermined range. Examples of methods for determining factor scores for each attribute will be described later.

[0272] If, in step S260d, the tree vigor is determined to be stronger than the predetermined range, the process proceeds to step S260e. In step S260e, the number of buds to be left is increased. Specifically, in step S260e, the number of buds to be left is determined to be greater than the set value obtained in step S260a.

[0273] If, in step S260d, the tree's vigor is determined to be weaker than a predetermined range, the process proceeds to step S260g. In step S260g, the number of buds to be left is reduced. Specifically, in step S260g, the number of buds to be left is determined to be smaller than the set value obtained in step S260a.

[0274] If it is determined in step S260d that the tree vigor is within a predetermined range, the process proceeds to step S260f. In step S260f, the number of buds to be left is determined to match the set value obtained in step S260a.

[0275] If the setting parameter "Bud Count Adjust" is disabled (i.e., "No" in step S260b), the process proceeds to step S260h. In step S260h, the number of buds to be kept is determined to the setting value obtained in step S260a.

[0276] <Relationship between each pruning mode> In the cutting point data generation method and cutting point data generation system according to this embodiment, the multiple pruning modes, each having a different method for determining the point to be cut on a fruit tree branch, include a first pruning mode and a second pruning mode in which the setting of priority for two or more attributes of the fruit tree branch in determining the point to be cut is the same as in the first pruning mode, and the setting of enable / disable one or more switchable setting parameters in determining the point to be cut is different from that of the first pruning mode. For example, in the example in Figure 8, in each of the quality priority mode, tree shape priority mode, and yield priority mode, the normal type and speed type have the same setting of priority for two or more attributes of the fruit tree branch, and the setting of enable / disable the setting parameters is different from that of the first pruning mode.

[0277] In the cutting point data generation method and cutting point data generation system according to this embodiment, the multiple pruning modes may further include a third pruning mode in which the attribute priority settings differ from those of the first pruning mode, and the enabled / disabled settings for the setting parameters are the same as those of the first pruning mode. In the example in Figure 8, for example, the normal type of the quality-priority mode and the normal type of the tree shape-priority mode have different attribute priority settings from each other, and the enabled / disabled settings for the setting parameters are the same. That is, if the normal type of the quality-priority mode is the first pruning mode, then the normal type of the tree shape-priority mode is an example of the third pruning mode. Also, if the speed type of the quality-priority mode is the first pruning mode, then the speed type of the tree shape-priority mode and the speed type of the yield-priority mode can be considered as the third pruning modes.

[0278] <Features of each pruning mode> Referring to Figures 26A, 26B, and 26C, the characteristics of each pruning mode shown in Figure 8 will be explained by comparing them. Figures 26A, 26B, and 26C show the results of evaluating each pruning mode shown in Figure 8 using multiple evaluation items. The multiple evaluation items include five items: (1) pruning quality, (2) tree shape of the fruit tree, (3) fruit yield, (4) health of the fruit tree, and (5) reduction in pruning time. In Figures 26A, 26B, and 26C, the evaluation results for each evaluation item are shown numerically and also as graphs. A higher numerical value for each evaluation item indicates a higher evaluation result for that item. Note that the numerical values ​​of the evaluation results in Figures 26A to 26C are for illustrative purposes only. Figure 27 is a diagram illustrating an example of the evaluation method for each evaluation item for each pruning mode.

[0279] (Harvest yield priority mode) We will compare the normal type in yield-prioritizing mode with the normal type in quality-prioritizing mode. The same can be said when comparing the speed type in yield-prioritizing mode with the speed type in quality-prioritizing mode. As mentioned above, these are related to the relationship between the third pruning mode and the first pruning mode described above.

[0280] The yield-prioritizing mode is a pruning mode in which the evaluation result for "fruit yield" among the five evaluation items is higher compared to the quality-prioritizing mode. In the example in Figure 8, in the yield-prioritizing mode, the priority of attributes related to the vigor of the fruit tree is set higher compared to the quality-prioritizing mode. Attributes related to the vigor of the fruit tree include at least one of the following: branch thickness, bud size on the branch, and internode length of the branch. Attributes related to the vigor of the fruit tree can also be said to be attributes related to fruit yield. In the yield-prioritizing mode, compared to the quality-prioritizing mode, fruit yield can be improved by increasing the contribution of attributes related to the vigor of the fruit tree in determining which branches to keep.

[0281] Figure 27 shows examples of evaluation methods (for example, methods for determining the score that shows the evaluation result) for each evaluation item for each pruning mode. In the table in Figure 27, "☆" indicates that the higher the priority of the attribute, the higher the score (i.e., the higher the evaluation); "○" indicates that when the setting parameter is enabled, a higher score (i.e., the higher the evaluation) is given than when it is disabled; and "●" indicates that when the setting parameter is disabled, a higher score (i.e., the higher the evaluation) is given than when it is enabled.

[0282] As shown in Figure 27, the evaluation results (e.g., scores indicating the evaluation results) for the pruning mode regarding fruit yield can be determined by a combination of one or more of the following: The priority of attributes related to the vigor of fruit trees is set higher when determining the result. • When the setting parameter "Bud Count Adjust" is enabled, the value is determined to be higher than when the setting parameter "Bud Count Adjust" is disabled. • When the setting parameter "Leave Renewal Canes" is enabled, the value is determined to be higher than when the setting parameter "Leave Renewal Canes" is disabled.

[0283] Regarding the priority of attributes related to the vigor of fruit trees, the relationship with fruit yield is as described above. By enabling the setting parameter "Bud Count Adjust," as described above, the number of buds to be left can be adjusted according to the vigor of the branches decided to be left (e.g., fruiting canes), thereby improving fruit yield. By enabling the setting parameter "Leave Renewal Canes," as described above, spare fruiting canes can be used if the fruiting canes fail, thus improving fruit yield.

[0284] (Tree shape priority mode) We will compare the normal type in the tree shape priority mode with the normal type in the quality priority mode. As mentioned above, these are related to the relationship between the third pruning mode and the first pruning mode. The same can be said when comparing the speed type in the tree shape priority mode with the speed type in the quality priority mode.

[0285] The tree shape priority mode is a pruning mode in which the evaluation result for "tree shape" among the five evaluation items is higher compared to the quality priority mode. In the example in Figure 8, in the tree shape priority mode, the priority of attributes related to the shape of the fruit tree is set higher compared to the quality priority mode. Attributes related to the shape of the fruit tree include at least one of the following: the direction in which the branches grow, the height of the base of the branches, the direction in which the buds on the branches face, and the length of the branches. In the tree shape priority mode, the shape of the fruit tree after pruning can be improved by giving a higher contribution to the attributes related to the shape of the fruit tree in determining which branches to keep, compared to the quality priority mode.

[0286] As shown in Figure 27, the evaluation results regarding the shape of the fruit tree for each pruning mode can be determined by combining one or more of the following: The priority of attributes related to the shape of fruit trees is set higher when determining the result. When the "Bud Density" setting parameter is enabled, it is determined to be higher than when the "Bud Density" setting parameter is disabled.

[0287] By enabling the "Bud Density" setting parameter, as mentioned above, the distribution of buds to be left on the remaining branches can be made more uniform throughout the fruit tree, resulting in a more aesthetically pleasing tree shape after pruning.

[0288] (Quality priority mode) We will compare the normal type in quality-priority mode with the normal type in yield-priority mode and the normal type in tree shape-priority mode. The same can be said when comparing the speed type in quality-priority mode with the speed type in yield-priority mode and the speed type in tree shape-priority mode. As mentioned above, these are related to the relationship between the first and third pruning modes described above.

[0289] The quality-priority mode is a pruning mode in which the evaluation results for "health of the fruit tree" and "quality of pruning" among the five evaluation items are higher compared to the yield-priority mode and the tree shape-priority mode. In the example in Figure 8, in the quality-priority mode, the priority of attributes related to the health of the fruit tree is set higher compared to the yield-priority mode and the tree shape-priority mode. Attributes related to the shape of the fruit tree include branch color. In the quality-priority mode, compared to the yield-priority mode and the tree shape-priority mode, the contribution of attributes related to the health of the fruit tree in determining which branches to leave is increased, thereby improving the health of the fruit tree after pruning and reducing the impact of pruning work on the health of the fruit tree.

[0290] As shown in Figure 27, the evaluation results regarding the health of the fruit tree in each pruning mode can be determined by a combination of one or more of the following: • The priority of attributes related to the health of the fruit tree is set higher, and the result will be determined accordingly. • When the setting parameter "Retain Green Cane" is enabled, the value is determined to be higher than when the setting parameter "Retain Green Cane" is disabled. When the setting parameter "Cutting Orientation" is enabled, it is determined to be higher than when the setting parameter "Cutting Orientation" is disabled. • When the setting parameter "Filter Healthy Canes" is enabled, the value is determined to be higher than when the setting parameter "Filter Healthy Canes" is disabled. When the "Bud Density" setting parameter is enabled, it is determined to be higher than when the "Bud Density" setting parameter is disabled.

[0291] Enabling the "Retain Green Cane" setting parameter prevents the pruning of branches that are not in a suitable condition for cutting (for example, too early in the season), thus helping to maintain the health of the fruit tree. Enabling the "Cutting Orientation" setting parameter prevents moisture from accumulating on the cut surface, as mentioned above, thus preventing the branch from becoming diseased. Enabling the "Filter Healthy Canes" setting parameter removes branches that may have health problems from the list of branches to keep (for example, fruiting canes), as mentioned above.

[0292] By enabling the "Bud Density" setting parameter, as mentioned above, the distribution of buds to be left on the remaining branches can be made more uniform throughout the fruit tree. This allows for more uniform sunlight exposure and ventilation, which is expected to improve the health of the fruit tree.

[0293] (Speed ​​type and normal type) We will compare the normal type and the speed type in each of the following modes: quality priority mode, tree shape priority mode, and yield priority mode. As mentioned above, these are related to the relationship between the first and second pruning modes described above. In each of the quality priority mode, tree shape priority mode, and yield priority mode, the speed type is the pruning mode that scores higher than the normal type in the evaluation item of "reduction in pruning time" among the five evaluation items.

[0294] As shown in Figure 27, the evaluation results regarding the reduction in pruning time for each pruning mode can be determined by combining one or more of the following: • When the setting parameter "Retry Enabled" is disabled, the value is determined to be higher than when the setting parameter "Retry Enabled" is enabled. • When the setting parameter "Check Before Cut" is disabled, the value is determined to be higher than when the setting parameter "Check Before Cut" is enabled. • When the setting parameter "Cutting Orientation" is disabled, it is determined to be higher than when the setting parameter "Cutting Orientation" is enabled. • When the "Bud Density" setting parameter is disabled, it is determined to be higher than when the "Bud Density" setting parameter is enabled.

[0295] Disabling these setting parameters significantly reduces the processing time required by the cutting point generation system compared to when they are enabled.

[0296] <Pruning modes associated with fruit tree cultivation methods> In the cutting point data generation method and cutting point data generation system according to this embodiment, a fruit tree cultivation method is associated with each of the multiple pruning modes, each of which has a different method for determining the point on which a fruit tree branch should be cut, and the method for determining the point on which a fruit tree branch should be cut is varied according to the fruit tree cultivation method. In other words, the multiple pruning modes provided in the cutting point data generation method and cutting point data generation system according to this embodiment include two or more pruning modes, each associated with a different cultivation method and having a different method for determining the point on which a fruit tree branch should be cut.

[0297] A method of cultivating fruit trees includes at least one of the following: the shape of the trellis system, the pruning method, and the training method. If at least one of the trellis system shape, pruning method, or training method differs, the method of cultivating fruit trees is considered different. A method of cultivating fruit trees encompasses field design. For example, if the fruit tree is a grapevine, the method of cultivating grapevines includes vineyard design. Field design and vineyard design can be determined by at least one of the following elements: the shape of the trellis system, the pruning method, and the training method.

[0298] Referring to Figures 8 and 28, examples of the multiple pruning modes provided in the cutting point data generation system according to this embodiment will be described. The cutting point data generation system according to this embodiment provides a total of 12 types of pruning modes, as shown in Figures 8 and 28.

[0299] As described above, the example shown in Figure 8 is an example of six pruning modes provided for a fruit tree cultivation method determined by a combination of trellis system: VSP, training method: cordon training, and pruning method: short-pruning (hereinafter sometimes referred to as "cultivation method 1"). In other words, in this embodiment, each of the six pruning modes in Figure 8 is associated with cultivation method 1. Figure 28 shows examples of multiple pruning modes provided for a fruit tree cultivation method determined by a combination of trellis system: VSP, training method: bush training, and pruning method: long-pruning (hereinafter sometimes referred to as "cultivation method 2"). In other words, each of the six pruning modes in Figure 28 is associated with cultivation method 2. As shown in Figure 28, six pruning modes are also provided for cultivation method 2, similar to the example in Figure 8 (cultivation method 1). The six pruning modes for cultivation method 2 are broadly divided into three types: a quality-prioritizing mode that prioritizes pruning quality, a tree shape-prioritizing mode that prioritizes the shape of the fruit tree, and a yield-prioritizing mode that prioritizes fruit yield. Each of these three types has a normal type and a speed type that prioritizes reducing the time required for pruning compared to the normal type.

[0300] As can be seen from Figures 8 and 28, for each of the six pruning modes, the method for determining the points to be cut differs between the pruning mode associated with cultivation method 1 and the pruning mode associated with cultivation method 2. For example, even for the normal type of the same quality-priority mode, the method for determining the points to be cut differs between the pruning mode associated with cultivation method 1 and the pruning mode associated with cultivation method 2. In other words, the method for determining the points to be cut differs depending on the cultivation method of the fruit tree.

[0301] For each of the six pruning modes shown in Figures 8 and 28, we compare the pruning mode associated with cultivation method 1 with the pruning mode associated with cultivation method 2. The pruning modes associated with cultivation method 1 and cultivation method 2 differ in how they determine the point to be cut, due to the different combinations of branch attributes used to determine the point to be cut. In the case of cultivation method 1 (short-pruning) in Figure 8, the attributes "branch length" and "internode length of the branch" are not included in the attributes used to determine the point to be cut. In contrast, in the case of cultivation method 2 (long-pruning) in Figure 28, the attributes "branch length" and "internode length of the branch" are included in the attributes used to determine the point to be cut, while the attributes "direction of the buds on the branch" and "size of the buds on the branch" are not included in the attributes used to determine the point to be cut.

[0302] It can also be said that the pruning mode associated with cultivation method 1 and the pruning mode associated with cultivation method 2 have different priority settings for the branch attributes used to determine the point to be cut. In other words, the priority settings for the branch attributes used to determine the point to be cut may be set differently depending on the cultivation method of the fruit tree. In the examples in Figures 8 and 28, for example, the priority of the attribute "branch length" and / or "internode length of the branch" is set differently depending on the pruning method of the fruit tree. In the examples in Figures 8 and 28, for example, the priority of the attribute "direction in which the buds on the branch face" and / or "size of the buds on the branch" is set differently depending on the pruning method of the fruit tree.

[0303] Furthermore, the pruning modes associated with cultivation method 1 and cultivation method 2 differ in their methods for determining where to cut, due to differences in the combination of switchable setting parameters used to determine where to cut. In the case of cultivation method 2 (long-cane pruning) in Figure 28, the setting parameter "Bud Density" is not included in the method for determining where to cut, which differs from the case of cultivation method 1 (short-cane pruning) in Figure 8. In long-cane pruning, by including the branch attribute "internode length of the branch" as an attribute used to determine where to cut, the distribution of buds to be left on the remaining branches can be made more uniform throughout the fruit tree, similar to when the setting parameter "Bud Density" is enabled, thus eliminating the need to select whether to enable or disable the setting parameter "Bud Density". Note that in the case of long-cane pruning, the setting parameter "Bud Density" may be disabled in all pruning modes. If set in this way, the pruning mode associated with cultivation method 1 and the pruning mode associated with cultivation method 2 will have different settings for enabling / disabling the setting parameters used to determine the points to be cut.

[0304] Figures 29A, 29B, and 29C show the results of evaluating each pruning mode shown in Figure 28 using multiple evaluation criteria. Figures 29A to 29C show the evaluation results for the example shown in Figure 8, similar to those shown in Figures 26A to 26C. As shown in Figures 29A to 29C, the pruning modes shown in Figure 28 can be said to have been basically explained by referring to Figures 26A to 26C, just as the pruning modes shown in Figure 8 were explained. The evaluation method shown in Figure 27 can be applied to the example in Figure 28, regardless of the fruit tree cultivation method.

[0305] <Example of display screen on the operating terminal> Figures 30A and 30B show examples of the display screen of the operation terminal 400 when there are multiple pruning modes as shown in Figures 8 and 28. In the cutting point data generation system according to the embodiment of this disclosure, a graphical user interface (GUI) is displayed on the display screen of the operation terminal 400 operated by the user, which allows the user to select one of the multiple pruning modes. An example of such a GUI will be explained with reference to Figures 30A and 30B. The differences from the example explained with reference to Figures 9A to 9C will be explained in particular.

[0306] The example in Figure 30A differs from the display screen in Figure 9A in that a button 470 for selecting the fruit tree cultivation method is also displayed on the display screen of the operating terminal 400. In the example in Figure 30A, cultivation method 1 (trellis system: VSP, training method: cordon training, pruning method: short-pruning) is selected, and the normal type of quality-priority mode is selected. In the example in Figure 30B, cultivation method 2 (trellis system: VSP, training method: bush training, pruning method: long-pruning) is selected, and the normal type of quality-priority mode is selected. As in the examples in Figures 30A and 30B, when the button 470 for selecting the cultivation method is switched, the display of the graph 420 showing the characteristics of the corresponding pruning mode is switched in conjunction with this. In this way, different pruning modes are displayed according to the fruit tree pruning method. It is possible to transition from the display screen in Figure 30A or Figure 30B to a display screen similar to Figure 9B or Figure 9C. The user can change and save the method for determining the cutting points in each pruning mode on a display screen similar to Figure 9B or Figure 9C.

[0307] <Suggestions for pruning modes> In the cutting point data generation method and cutting point data generation system according to this embodiment, candidate pruning modes may be presented to the user based on information about the fruit tree.

[0308] Figure 31 is a flowchart showing an example of the procedure for generating branch cutting point data for fruit trees according to this embodiment. The flowchart in Figure 31 differs from the example described above (for example, the example in Figure 1A) in that it further includes steps S042 and S044 before step S050 (the step of obtaining information on the pruning mode selected by the user).

[0309] In step S042, information about the fruit tree is acquired. The information about the fruit tree includes at least one of the following: information about the cultivation method of the fruit tree, information about the variety of the fruit tree, information about the age of the fruit tree, and information about the field where the fruit tree is located. The information about the fruit tree may be acquired based on sensor data of the fruit tree branches acquired by one or more sensors, based on user input, or in combination. Sensor data of the fruit tree branches can be acquired, for example, in the same manner as the acquisition of sensor data in step S100. The information about the fruit tree may also be acquired based on sensor data of the field where the fruit tree is located (for example, image data acquired by an imaging device).

[0310] In step S044, based on the fruit tree information obtained in step S042, the user is presented with candidate pruning modes. For example, candidate pruning modes are displayed on the user's operating terminal.

[0311] After step S044, in step S050, information about the pruning mode selected by the user is obtained. The user may select a pruning mode by approving the candidate pruning mode presented in step S044. If the user does not approve the candidate pruning mode presented in step S044, they may select a different pruning mode.

[0312] The processes in steps S100, S200, and S300 are carried out in the same manner as in the example described above (for example, the example in Figure 1A).

[0313] <Grouping process> In embodiments of this disclosure, multiple branches of a fruit tree may be grouped into multiple groups, as shown in the example in Figure 21. In this case, one or more branches grouped into the same group can be treated as one or more branches to be processed in the example described above, and other processing can be performed on them. For example, one or more branches grouped into the same group may be selected to be kept, and all branches other than the selected branches may be selected to be removed. Since it is possible to select branches to be kept (e.g., fruiting branches) from among the multiple branches of a fruit tree that are grouped into the same group, efficient pruning work can be performed while maintaining fruit yield and quality. If multiple groups correspond to multiple short shoots, a fruiting branch can be selected for each short shoot, so it is possible to generate cutting point data that is more adapted to the needs of pruning work.

[0314] Grouping of multiple branches can be done based on the location of the base of each branch. For example, in the case of short-pruning and cordon training, multiple groups correspond to multiple short prunes on the fruit tree. Branches growing from the same short prune may be grouped together. Branches growing from a predetermined area may also be grouped together.

[0315] In the case of long-shoot pruning and / or bush training, the multiple branches of a fruit tree are grouped into one or more groups, which may vary depending on the number of branches left as fruiting canes. For example, examples of combinations of the number of branches Nn left as fruiting canes and the number of groups Ng include (Nn,Ng)=(1,1), (2,2), (3,3 or 2), (4 or more,2), etc. For example, when using a training method in which two fruiting canes grow from the bush (Guyot double training), the multiple branches of the fruit tree can be grouped into two groups. If the multiple branches of a fruit tree include branches growing in one direction (e.g., either left or right) from the bush or main trunk, and branches growing in the opposite direction (e.g., the other left or right), then one or more branches growing in one direction are grouped into the first group, and one or more branches growing in the other direction are grouped into the second group. If a single fruit tree has multiple branches that grow in only one direction from the main trunk or stem (for example, in the Guyot single training system), all branches are treated as a single group, and the grouping treatment described above can be omitted.

[0316] In the grouping process, multiple branches 58 of a fruit tree can be grouped into multiple groups based on a segmented image 51a, for example, as shown in Figure 20A. Based on the segmented image 51a, each branch 58 can be associated with a corresponding short shoot 56. Branches 58 associated with the same identifier representing the same short shoot 56 are grouped into the same group. For example, each branch mask M58 can be associated with the nearest short shoot mask M56. For example, by identifying pixels included in both the branch mask M58 and the short shoot mask M56, the overlap between the branch mask M58 and the short shoot mask M56 is indicated, and the connection point between the branch mask M58 and the short shoot mask M56 is identified. By identifying the connection point between the branch mask M58 and the short shoot mask M56, each branch mask M58 can be associated with the short shoot mask M56 that it touches at the connection point. For example, in the example in Figure 20A, the branch masks M58_1 to M58_6 are associated with the short-shoot mask M56_1. This allows the six branches 58_1 to 58_6, represented by the branch masks M58_1 to M58_6, to be recognized as growing from the short-shoot 56_1 represented by the short-shoot mask M56_1. As a result, the six branches 58_1 to 58_6 growing from the short-shoot 56_1 are grouped into a group that corresponds to the short-shoot 56_1.

[0317] Figure 20A shows an example image that includes only the area around short shoot 56_1 of the fruit tree, but in practice, a wider area may be used in the grouping process. An image including the entire fruit tree may also be used.

[0318] Buds on branches may be identified or extracted by applying instance segmentation to an image containing fruit tree branches, as in the example in Figure 20A, or they may be identified or detected using object detection. Each bud identified by instance segmentation or object detection is associated with an identifier (e.g., branch mask M58) that indicates the corresponding branch. If a bud is identified by instance segmentation, the connection point between the bud mask and the branch mask M58 is identified by identifying the pixels included in both the bud mask and the branch mask M58 from which the bud is extracted. Each bud mask may be associated with the branch mask M58 that it touches at the connection point. An object detection model trained using a deep learning-based algorithm can be used for the object detection process. Object detection algorithms such as YoloV5 and Yolov4 may also be used. The image to which object detection processing has been applied may include a rectangular bounding box for detecting each bud. Either the center point of the bounding box or one of the four vertices of the rectangle may be used as reference coordinates indicating the position of the bud. Based on the positional relationship between each bud's location (reference coordinate) and the branch mask M58, each bud can be associated with the nearest branch mask M58.

[0319] It is also possible that all 58 branches grouped together in the same group may be selected for removal. For example, if it is not possible to select which branches to keep from among the 58 branches grouped together in the same group, or if there are no suitable branches to keep, all 58 branches may be selected for removal. Conversely, it is also possible that all 58 branches grouped together in the same group may be selected to keep. For example, if it is determined that all 58 branches grouped together in the same group are not in a suitable condition for pruning (cutting) (for example, it is too early in the season), all 58 branches may be selected to keep. In this case, the generation of cutting point data is not required.

[0320] [Evaluation criteria for each attribute] Referring to Figures 32A to 32N, specific examples of the evaluation criteria for each attribute exemplified above will be explained. Figures 32A, 32C, 32E, 32G, 32I, 32K, and 32M show images or schematic diagrams illustrating the acquisition of measurement values ​​for each attribute. Figures 32B, 32D, 32F, 32H, 32J, 32L, and 32N show tables illustrating multiple classes for each attribute, the evaluation criteria for each of the multiple classes, and examples of scores corresponding to each of the multiple classes. The factor score for each attribute for each branch can be determined based on these tables. For example, the factor score for each attribute for each branch can be calculated based on these tables.

[0321] (1) Color of the branches For each of the one or more branches to be processed, measurements regarding the branch color are obtained using a segmented image, for example, as shown in Figure 20A. Based on these measurements, a factor score for the branch color may be determined. The factor score for the branch color is determined such that, for example, the closer the branch's color is to brown, the higher the score. If the outer color of a branch is brown, it indicates that the branch is dry and suitable for pruning, whereas, for example, a green branch is often not yet ready for pruning and is not suitable for pruning. For example, if the factor score for the branch color is lower than a predetermined value, it may be detected as an unsuitable branch that should not be selected as one to keep. If the factor score for the branch color is lower than a predetermined value, the user may be notified that there is an unsuitable branch.

[0322] The factor score for the color of each of the one or more branches being processed is determined by the following steps, for example, as shown in Figure 32O. Figure 32O is a flowchart showing an example of the process for determining the factor score for branch color.

[0323] Step S1-1: Use one or more sensors (e.g., cameras) to acquire sensor data of the branches (e.g., images containing the branches).

[0324] Step S1-2: Use the acquired sensor data to extract the parts corresponding to the branches. For example, apply AI-based segmentation (e.g., instance segmentation) to the acquired image.

[0325] Step S1-3: Obtain information about the color of the part corresponding to the extracted branch (e.g., RGB values, HSL values, and their statistics).

[0326] Step S1-4: Obtain a factor score based on the acquired color information. For example, store a table in memory that shows the relationship between color information and factor scores, and obtain the factor score by referring to the table.

[0327] (2) Direction in which the branches are growing For each of the one or more branches being processed, the measurement values ​​regarding the direction of branch growth are obtained using a segmented image, such as the one shown in Figure 20A. Figure 32A is a segmented image including a part (branch) of a fruit tree. For each branch, the inclination angle θp of the branch with respect to the direction opposite to gravity (the +z direction in the figure) and the azimuth angle θa of the branch in the horizontal plane perpendicular to the direction of gravity (the xy plane in the figure) are calculated. When calculating the inclination angle θp and azimuth angle θa, it is preferable to use the part of the branch closest to the base (i.e., the part of the branch closest to the short shoot). Based on the inclination angle θp and azimuth angle θa, a factor score regarding the direction of branch growth can be determined. If the shape of the fruit tree trellis system is VSP (vertical shoot position), it is preferable that the inclination angle θp is small. Also, for the azimuth angle θa, it may be preferable that the inclination is more in the left-right direction (±x direction in the figure) than in the front-back direction (±y direction in the figure). For example, the branch to be cut may be located in the forward direction (+y direction in the diagram) of the cutter used to cut the fruit tree branch. If we consider the azimuth angle θa as a clock face, with the +x direction being 3 o'clock and the +y direction being 12 o'clock, and defining 3 o'clock as 0° and counterclockwise as positive, then it is preferable for the azimuth angle θa to be within a first range Ra (e.g., 0°~45°, 135°~225°, and 315°~360°) which includes 0° and 180°, rather than within a second range Rb (e.g., 45°~135°, and 2255°~315°) which includes 90° and 270°.

[0328] The inclination angle θp and azimuth angle θa of each branch are calculated by the following steps, for example, as shown in Figure 32P. Figure 32P is a flowchart showing an example of the process for calculating the inclination angle θp and azimuth angle θa of each branch.

[0329] Step S2-1: Sensor data containing information indicating the three-dimensional structure of the branches is acquired by one or more sensors, and segmentation is applied to the sensor data to acquire segmentation information that identifies the branches. Sensor data may be acquired, for example, by acquiring point cloud data of the branches using a LiDAR sensor, or by acquiring images of the branches using an imaging device (camera). Segmentation information may be acquired by acquiring segmented information using two-dimensional image data, or by acquiring segmented information from point cloud data. If two-dimensional images are used in addition to point cloud data, a further step is performed to align the coordinate system of the two-dimensional images with the coordinate system of the point cloud data.

[0330] Step S2-2: Identify the point cloud data belonging to the regions extracted as edges by segmentation.

[0331] Step S2-3: Set up a three-dimensional Cartesian coordinate system with the origin at the base of the branch. The +z axis direction is opposite to the direction of gravity (i.e., vertically upward). For example, in the case of short-spur pruning, segmentation information is used to identify the boundary (connection point) between the branch and the short-spur or main branch, and the connection point between the branch and the short-spur or main branch is defined as the base of the branch. In the case of long-spur pruning, segmentation information is used to identify the boundary (connection point) between the branch and the plant, and the connection point between the branch and the plant is defined as the base of the branch.

[0332] Step S2-4: In the coordinate system defined in Step S2-3, calculate a vector from the point cloud data using a portion of the branch, for example, within a range of about 50cm to 60cm from the base of the branch. The vector can also be calculated using the entire branch, but it is preferable to use the range close to the base of the branch. For example, by using Singular Value Decomposition (SVD), the structure of a local part of the branch (the range close to the base) can be extracted from the point cloud data, and the vector can be calculated using that part.

[0333] Step S2-5: From the obtained vectors, determine the inclination angle θp and the azimuth angle θa.

[0334] Figure 32B shows Tables Tb1 and Tb2 as examples of multiple classes related to the direction of branch growth, the scores corresponding to each class, and the evaluation criteria for each class. The factor score related to the direction of branch growth is determined such that, for example, if the shape of the trellis system for fruit trees is VSP, the smaller the inclination angle θp, the higher the factor score. For example, if the shape of the trellis system for fruit trees is VSP, the factor scores may be determined in the following order from highest to lowest: when the inclination angle θp is smaller than a predetermined range, when the inclination angle θp is within a predetermined range, and when the inclination angle θp is larger than a predetermined range. Alternatively, if the shape of the fruit tree trellis system is VSP, the factors can be determined in descending order of highest factor score, such that the inclination angle θp is smaller than a predetermined range and the azimuth angle θa is within a first range Ra including 0° and 180°; the inclination angle θp is smaller than a predetermined range and the azimuth angle θa is within a second range Rb including 45° and 135°; the inclination angle θp is within a predetermined range and the azimuth angle θa is within a first range Ra including 0° and 180°; the inclination angle θp is within a predetermined range and the azimuth angle θa is within a second range Rb including 45° and 135°; and the inclination angle θp is larger than a predetermined range.

[0335] For example, the main trunk of a fruit tree may be inclined in the direction opposite to the direction of gravity (the +z direction in the diagram), and even in such cases, the factor score for the direction in which the branch is growing may be determined based on the inclination angle θp of the branch in the direction opposite to the direction of gravity and the azimuth angle θa of the branch in a horizontal plane perpendicular to the direction of gravity.

[0336] If the trellis system for fruit trees is not VSP (Vertical Spread Spectrum), the factor score for the direction of branch growth may be determined by evaluation criteria different from those exemplified.

[0337] (3) Thickness of the branch The measurement values ​​for the thickness of each of the one or more branches to be processed are obtained using a segmented image, for example, as shown in Figure 20A. Figure 32C is an enlarged view of a portion of the segmented image and includes the branch mask M58_a. For example, the measurement values ​​for the thickness of each branch are obtained using the branch mask included in such a segmented image. The measurement values ​​for the thickness of a branch are obtained, for example, by calculating the length in a direction perpendicular to the direction in which the branch grows at predetermined distances from the base of the branch and calculating the average value. The calculation of the length in a direction perpendicular to the direction in which the branch grows may be performed using parts of the branch other than those with buds, that is, using parts of the branch that do not have buds.

[0338] A factor score for branch thickness can be determined based on measurements of branch thickness. Figure 32D shows examples of multiple classes for branch thickness, the scores corresponding to each class, and the evaluation criteria for each class. The factor score for branch thickness is determined, for example, in descending order of factor score, such that the branch thickness (e.g., the average value above) is within a predetermined range, the branch thickness (e.g., the average value above) is greater than the predetermined range, and the branch thickness (e.g., the average value above) is smaller than the predetermined range.

[0339] (4) Height of the base of the branch For each of the one or more branches to be processed, the measured height of the branch base is obtained using a segmented image, for example, as shown in Figure 20A. Figure 32E is an enlarged view of a portion of the segmented image, and includes a branch mask M58_a, a short-sprout mask M56_a which extracts the short-sprouts on which the branches corresponding to branch mask M58_a grow, and a main branch mask M54_a. When the pruning method for fruit trees is short-sprout pruning, for example, such a segmented image is used to obtain the measured height of the branch base from the main branch. For example, the distance Dt between the position P1 of the base of branch mask M58_a (where it touches short-sprout mask M56_a) and the center line Lt of main branch mask M54_a is calculated. At this time, as explained with reference to Figure 20A, similar to the grouping process, each branch 58 may be associated with the corresponding short-sprout 56 based on the segmented image. If the pruning method for fruit trees is long-cane pruning, for example, segmented images can be used to obtain measurements of the height from the base of the branches to the main plant.

[0340] A factor score for branch base height can be determined based on measurements of the height at the base of the branch. Figure 32F shows multiple classes for branch base height, the scores corresponding to each class, and examples of evaluation criteria for each class. For example, if the shape of the fruit tree trellis system is VSP (vertical shoot position) and the pruning method of the fruit tree is short-pruning or long-pruning, the factor score for branch base height is determined in the following order from highest to lowest: when the height at the base of the branch is within a predetermined range, when the height at the base of the branch is below the predetermined range, and when the height at the base of the branch is above the predetermined range. This is because, when the shape of the fruit tree trellis system is VSP, it is preferable to have the fruit grow within a predetermined range from the main branch or the base of the plant (for example, an area of ​​about 10 cm from the main branch). As mentioned above, in the case of short-pruning, the height at the base of the branch is evaluated by the height of the branch base from the main branch, and in the case of long-pruning, it is evaluated by the height of the branch base from the base of the plant. If the trellis system for fruit trees is not VSP, the factor score for the height of the branch base may be determined by evaluation criteria different from those exemplified.

[0341] (5) The size of the buds on the branch The size of the buds on each of the one or more branches to be processed is measured using a segmented image, for example, as shown in Figure 20A. The size of the buds on a branch is obtained, for example, by calculating the average size of a predetermined number of buds on that branch. The predetermined number can be, for example, the set value for the number of buds to be left on the branch to be kept. Before obtaining the size of the buds on a branch, information on the set value for the number of buds to be left on the branch to be kept is obtained, for example, based on user input. Figure 32G shows an image of a part of a fruit tree (a branch). The size of a predetermined number (for example, 2) of buds is determined from the bud closest to the base of the branch (the bud closest to the short shoot or main branch), and the average value is calculated. The size of the buds is obtained, for example, by calculating the area of ​​the bud mask region from which the buds are extracted in the segmented image.

[0342] A factor score for the size of buds on a branch can be determined based on measurements of the bud size on the branch. Figure 32H shows multiple classes for the size of buds on a branch, the scores corresponding to each class, and examples of evaluation criteria for each class. The factor score for the size of buds on a branch is determined, for example, in descending order of factor score, such that the bud size (e.g., the average value above) is within a predetermined range, the bud size (e.g., the average value above) is greater than the predetermined range, and the bud size (e.g., the average value above) is smaller than the predetermined range.

[0343] (6) The direction in which the buds on the branch are pointing For each of the one or more branches to be processed, the measured values ​​regarding the direction in which the buds on the branch are pointing are obtained using a segmented image, for example, as shown in Figure 20A. The measured values ​​regarding the direction in which the buds on a branch are pointing are obtained, for example, by calculating the average value of the direction in which a predetermined number of buds on that branch are pointing. The predetermined number can be, for example, the set value for the number of buds to be left on the branch to be kept. Before obtaining the measured values ​​regarding the size of the buds on the branch, information on the set value for the number of buds to be left on the branch to be kept is obtained, for example, based on user input. Figure 32I shows an image of a part (branch) of a fruit tree. Starting from the bud closest to the base of the branch, the direction in which a predetermined number (for example, 2) of buds are pointing is determined and the average value is calculated. As the measured value of the direction in which the buds are pointing, for example, the inclination angle of the bud with respect to the direction perpendicular to the horizontal plane (xy plane in the figure) (±z direction in the figure) is obtained. As a variation, the measurement value may be the proportion of all buds on a branch whose tilt angle in the z-direction is oriented in a direction equal to or greater than a predetermined value.

[0344] A factor score for the direction of bud orientation can be determined based on measurements of the direction of bud orientation on a branch. Figure 32J shows multiple classes for the direction of bud orientation on a branch, the score corresponding to each class, and examples of evaluation criteria for each class. The factor score for the direction of bud orientation on a branch is determined, for example, when the shape of the fruit tree trellis system is VSP (vertical shoot position), with the highest factor scores being for branches where the direction of bud orientation (e.g., the average value above) is upward above the horizontal plane, and for branches where the direction of bud orientation (e.g., the average value above) is downward above the horizontal plane. The pruning method for fruit trees may be either short-pruning or long-pruning. This is because VSP is configured so that new shoots (or branches) grow vertically upward from the buds. If the shape of the fruit tree trellis system is not VSP, the factor score for the direction of bud orientation on a branch may be determined by evaluation criteria different from those exemplified.

[0345] The angle of inclination of a bud with respect to the direction perpendicular to the horizontal plane (the xy-plane in the figure) (the ±z direction in the figure) can be calculated, for example, by the following steps shown in Figure 32Q. Figure 32Q is a flowchart showing an example of the process for calculating the angle of inclination of a bud with respect to the direction perpendicular to the horizontal plane.

[0346] Step S6-1: Using one or more sensors, sensor data containing information indicating the three-dimensional structure of the branch is acquired, and segmentation or object detection is applied to the sensor data to acquire data identifying buds as segmentation information. Sensor data acquisition may involve, for example, acquiring point cloud data of the branch using a LiDAR sensor. Images of the branch may be further acquired using an imaging device (camera). Segmentation information may be acquired by acquiring segmented information using two-dimensional image data, or by acquiring segmented information from point cloud data. If two-dimensional images are used in addition to point cloud data, a further step is performed to align the coordinate system of the two-dimensional images with the coordinate system of the point cloud data.

[0347] Step S6-2: Identify point cloud data belonging to regions classified as buds by segmentation or object detection.

[0348] Step S6-3: Set up a 3D Cartesian coordinate system with the origin at the base of the bud. The +z axis direction is opposite to the direction of gravity (i.e., vertically upward). By using segmentation information to identify the boundary (connection point) between the bud and the branch, the connection point between the bud and the branch is defined as the base of the bud.

[0349] Step S6-4: In the coordinate system defined in Step S6-3, calculate vectors from the point cloud data representing buds.

[0350] Step S6-5: From the obtained vector, determine the inclination angle of the bud with respect to the direction perpendicular to the horizontal plane.

[0351] (7) Length of the branches The length measurements for each of the one or more branches being processed are obtained using a segmented image, such as the one shown in Figure 20A. Figure 32K shows an image of a part of a fruit tree (a branch). The length of the branch is defined as the length from the base of the branch (for example, in the case of short-pruning, the boundary (connection point) between the branch and the short pruning or main branch; in the case of long-pruning, the boundary (connection point) between the branch and the plant) to the end of the branch (the end furthest from the base). If the end of the branch is not included in the image (outside the field of view), the end of the branch is defined as the point furthest from the base of the branch within the image. The length of the branch is not limited to the straight-line distance between two points; the curved length along the length direction of the branch can also be used.

[0352] A factor score for branch length can be determined based on measurements of branch length. Figure 32L shows multiple classes for branch length, the scores corresponding to each class, and examples of evaluation criteria for each class. The factor score for branch length is determined, for example, in the case of long-shoot pruning, with the highest factor score being for branch lengths within a predetermined range, branch lengths longer than a predetermined range, and branch lengths shorter than a predetermined range, in descending order of importance. As a threshold, for example, half the distance between the main trunks of fruit trees may be used. The "predetermined range" in the evaluation criteria of Figure 32L includes half the distance between the main trunks of adjacent fruit trees. Information on the distance between the main trunks of adjacent fruit trees may be obtained based on sensor data from two or more adjacent fruit trees (e.g., sensor data including information showing the three-dimensional structure of the fruit trees) or based on user input.

[0353] In the case of long-shoot pruning, cutting point data is generally not generated for the branches to be kept. However, if the length of the branches decided to be kept is longer than a predetermined range (for example, if classified as class "2" in the example in Figure 32L), cutting point data may be generated for the branches to be kept so that the length is less than or equal to the predetermined range.

[0354] In the case of short-sprout pruning, the factor score for branch length may be determined by evaluation criteria different from those exemplified.

[0355] (8) Length of internodes of branches The measured internode length of each of the one or more branches being processed is obtained using a segmented image, for example, as shown in Figure 20A. Figure 32M shows an image of a part (branch) of a fruit tree. As shown in Figure 32M, this is obtained by calculating the average distance between adjacent buds among the buds on the branch. As described above, buds on a branch may be extracted by instance segmentation, similar to the example in Figure 20A, or buds may be detected by object detection. For example, the distance between adjacent buds can be determined by using the center point of the extracted or detected bud as the reference coordinate of the bud.

[0356] A factor score for the internode length of a branch can be determined based on measurements of the distance between adjacent buds. Figure 32N shows several classes for the internode length of a branch, the scores corresponding to each class, and examples of evaluation criteria for each class. The factor score for the internode length of a branch is determined, for example, in the case of long-shoot pruning, with the highest factor score being for branches where the distance between adjacent buds (e.g., the average value above) is within a predetermined range, where the distance between adjacent buds (e.g., the average value above) is longer than the predetermined range, and where the distance between adjacent buds (e.g., the average value above) is shorter than the predetermined range. In the case of short-shoot pruning, the factor score for the internode length of a branch may be determined by evaluation criteria different from those exemplified.

[0357] The factor score for the internode length of each of the one or more branches being processed is determined by the following steps, for example, as shown in Figure 32R. Figure 32R is a flowchart showing an example of a process for calculating the average distance between the coordinates of two adjacent buds.

[0358] Step S8-1: Using one or more sensors, sensor data containing information indicating the three-dimensional structure of the branch is acquired, and segmentation or object detection is applied to the sensor data to acquire data identifying buds as segmentation information. Sensor data acquisition may involve, for example, acquiring point cloud data of the branch using a LiDAR sensor. Images of the branch may be further acquired using an imaging device (camera). Segmentation information may be acquired by acquiring segmented information using two-dimensional image data, or by acquiring segmented information from point cloud data. If two-dimensional images are used in addition to point cloud data, a further step is performed to align the coordinate system of the two-dimensional images with the coordinate system of the point cloud data.

[0359] Step S8-2: Define the center coordinates of the point cloud data belonging to the region classified as a bud by segmentation or object detection as the bud coordinates.

[0360] Step S8-3: Find the straight-line distance between the coordinates of two adjacent buds associated with the same branch. As a variation, instead of the straight-line distance between the coordinates of two adjacent buds associated with the same branch, you may find and use the curvilinear distance (the distance along the direction in which the branch is growing).

[0361] Step S8-4: Calculate the average value of a predetermined number of distances between the coordinates of two adjacent buds, which were determined in Step S8-3. [Industrial applicability]

[0362] The technology disclosed herein may be applied to agricultural machinery used in smart agriculture. [Explanation of symbols]

[0363] 101... Agricultural machinery, 200, 200a, 200b... Fruit trees, 201... Fruit tree rows, 530... Data processing equipment, 1000... Cutting point data generation system

Claims

1. A method for generating cutting point data, which includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, using one or more computing devices, The method for determining the point on which the fruit tree branches should be cut involves obtaining information on the pruning mode selected by the user from a plurality of different pruning modes, Based on sensor data of the fruit tree branches acquired by one or more sensors, and the selected pruning mode, one or more points to be cut are determined for the fruit tree branches. To generate the cutting point data for each of the one or more points to be cut. Methods that include...

2. The method according to claim 1, further comprising inputting the generated cutting point data into a control device that controls the three-dimensional position of a cutter for cutting the branches of the fruit tree.

3. Determining the one or more points to be cut means Based on the sensor data, measurement values ​​for two or more attributes of one or more branches of the fruit tree are obtained. Based on the measured values ​​and the priority of the two or more attributes, it is determined whether each of the one or more branches will be a branch to be removed or a branch to be kept. For each of the branches designated as to be removed, determine the point at which to cut. Includes, The method according to claim 1 or 2, wherein the setting of the priority is made different according to the pruning mode.

4. The method according to claim 3, wherein the two or more attributes include at least one of the following: the color of the branch, the direction in which the branch is growing, the thickness of the branch, the height of the base of the branch, the size of the buds on the branch, the direction in which the buds on the branch are facing, the length of the branch, and the length of the internodes of the branch.

5. The method according to claim 3, wherein the user can change and save the priority settings of the plurality of pruning modes.

6. Determining the one or more points to be cut means Based on the sensor data, measurement values ​​are obtained for one or more attributes of one or more branches of the fruit tree. Based on the measured values, it is determined whether each of the one or more branches will be removed or kept. For each of the branches designated as to be removed, determine the point at which to cut. Includes, The method according to claim 1 or 2, wherein the setting of the setting parameter for the measured value, which can be switched between enabled and disabled in determining the point to be cut, is set to enable or disable depending on the pruning mode.

7. The aforementioned one or more attributes include the color of the branch, The setting of enabling / disabling the aforementioned setting parameter for the measured value is as follows: The method according to claim 6, including setting whether or not to enable / disable determining that a branch should be kept if the branch is green in color.

8. If the above setting is enabled, determining whether each of the one or more branches is to be removed or kept is: The method according to claim 7, comprising determining that the branch to be kept if the color of the branch is green, based on the measured value relating to the color of the branch.

9. Determining the one or more points to be cut means Based on the aforementioned measurement values, the number of buds to be left on the branch that has been determined to remain is determined, Based on the number of buds to be left, the point to be cut on the branch that has been decided to be left is determined. It further includes, The one or more attributes mentioned above include attributes related to the vigor of the fruit tree, The setting of enabling / disabling the aforementioned setting parameter for the measured value is as follows: The method according to claim 6, further comprising setting whether or not to enable / disable adjusting the number of buds to be left on the branches determined to be left based on the measured values ​​relating to the vigor of the fruit tree.

10. If the above setting is enabled, determining the number of buds to leave is: Based on the measured values ​​relating to the vigor of the fruit tree, if it is determined that the vigor of the branch to be kept is stronger than a predetermined range, the number of buds to be left on the branch to be kept will be increased. The method according to claim 9, wherein, based on the measured values ​​relating to the vigor of the fruit tree, if it is determined that the vigor of the branch to be kept is weaker than the predetermined range, the number of buds to be left on the branch to be kept is reduced.

11. The method according to claim 9, wherein the attributes related to the vigor of the fruit tree include at least one of the thickness of the branches, the size of the buds on the branches, and the length of the internodes of the branches.

12. The attributes related to the vigor of the aforementioned fruit tree include the thickness of the branches, Determining whether each of the one or more branches to be removed or kept is: For each of the one or more branches mentioned above, a factor score is determined based on the thickness of that branch. Based on the factor score, it is determined whether each of the one or more branches will be designated as a branch to be removed or a branch to be kept. Includes, If the above setting is enabled, determining the number of buds to leave is: If the factor score for the thickness of the branch determined to be kept is greater than a predetermined range, the number of buds to be kept is increased beyond a predetermined value. The method according to claim 9, further comprising reducing the number of buds to be left below a predetermined value if the factor score relating to the thickness of the branch determined to be left is smaller than the predetermined range.

13. The factor score for each of the one or more branches relating to the thickness of the branch is, If the thickness of the branch is greater than the predetermined range, the thickness of the branch will be lower than when the thickness of the branch is within the predetermined range. The method according to claim 12, wherein if the thickness of the branch is smaller than the predetermined range, it is determined to be lower than if the thickness of the branch is larger than the predetermined range.

14. The attributes related to the vigor of the aforementioned fruit tree include the size of the buds on the branches. Determining whether each of the one or more branches to be removed or kept is: For each of the one or more branches mentioned above, a factor score is determined based on the size of the buds on that branch. Based on the factor score, it is determined whether each of the one or more branches will be designated as a branch to be removed or a branch to be kept. Includes, If the above setting is enabled, determining the number of buds to leave is: If the factor score relating to the size of the buds of the branches determined to be kept is greater than a predetermined range, the number of buds to be kept is increased beyond a predetermined value. The method according to claim 9, further comprising reducing the number of buds to be retained to a predetermined value if the factor score relating to the size of the buds of the branches determined to be retained is smaller than the predetermined range.

15. The factor score for each of the one or more branches with respect to the size of the bud is, If the average size of the buds on the branch is greater than the predetermined range, the average size of the buds on the branch will be lower than when the average size of the buds on the branch is within the predetermined range. The method according to claim 14, wherein if the average value of the bud size of the branch is smaller than the predetermined range, it is determined to be lower than if the average value of the bud size of the branch is larger than the predetermined range.

16. The method according to claim 6, wherein the user can change and save the enable / disable setting of the setting parameter relating to the measured value for the plurality of pruning modes.

17. A system for generating cutting point data that includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, One or more sensors that acquire sensor data from the branches of the fruit tree, A data processing device that generates the cutting point data of the fruit tree branches based on the sensor data, Equipped with, The aforementioned data processing device is The method for determining the point to cut the fruit tree branches obtains information on the pruning mode selected by the user from a plurality of different pruning modes, Based on the sensor data and the selected pruning mode, one or more points to be cut are determined for the fruit tree branch. A system that generates cutting point data for each of the one or more cutting points.

18. A system for generating cutting point data that includes information indicating the three-dimensional position of the point on which a fruit tree branch should be cut, One or more sensors that acquire sensor data from multiple branches of the fruit tree, Means for carrying out the steps of the method according to claim 1 or 2 A system that has

19. The system further comprises a cutter for cutting the branches of the fruit tree and a control device for controlling the three-dimensional position of the cutter. The data processing device inputs the generated cutting point data to the control device. The system according to claim 17, wherein the control device controls the three-dimensional position of the cutter based on the cutting point data.

20. An agricultural machine having the system described in claim 19.

21. The system further comprises an arm that supports the cutter, a support that supports the arm, and a drive device that moves the support. The agricultural machine according to claim 20, wherein the control device controls the three-dimensional position of the cutter by controlling the movement of the arm.

Images