JP2017127292A - Agricultural working vehicle - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an agricultural working vehicle capable of more flexibly performing autonomous travel based on an operator's actual operation.SOLUTION: An agricultural working vehicle includes a travelling machine body, a working machine, a teacher data storage part 82, and a control part 4. The working machine is mounted on the travelling machine body. The working machine is used for agricultural work. The teacher data storage part 82 can store farm field information including information indicating the shape of a farm field, and past travelling information and past work information in at least a partial area of the farm field or another farm field. The control part 4 can generate a work route in the farm field based on the farm field information, the past travelling information, and the past work information.SELECTED DRAWING: Figure 3

Description

  The present invention mainly relates to an agricultural work vehicle configured to be able to travel autonomously.

  2. Description of the Related Art Conventionally, agricultural work vehicles that can autonomously travel using a satellite positioning system are known. Patent document 1 discloses this kind of work vehicle. The work vehicle of Patent Document 1 is recognized as a recognition area point every time the vehicle body reaches the field edge by an operator's operation, and the inside of a polygon connecting the recognition area points with a straight line is set as a recognition area. After setting the area, the tillage path when the farm is run for the first time by the operator's operation is displayed on the monitor, and when the operator determines that the field is appropriate, the set field area and the generation path are stored. When it is determined to be appropriate, correction is made, autonomous traveling means that autonomously travels within the recognized recognition area is provided, and the autonomous traveling along the generation route is performed during the second and subsequent tillage operations. ing. Patent Document 1 assumes that, with this configuration, only one process is operated by man-made operation, and thereafter good work can be performed while maintaining the same operation conditions.

Japanese Patent No. 4801252

  However, in the configuration of Patent Document 1, the second and subsequent autonomous traveling is possible for a field that has been manually operated once, but the autonomous traveling could not be performed flexibly depending on the situation such as work contents. .

  This invention is made in view of the above situation, The objective is to provide the agricultural work vehicle which can perform autonomous driving | running | working more flexibly based on the actual driving | operation of an operator.

Means and effects for solving the problems

  The problems to be solved by the present invention are as described above. Next, means for solving the problems and the effects thereof will be described.

  According to an aspect of the present invention, an agricultural work vehicle having the following configuration is provided. That is, this agricultural work vehicle includes a vehicle body part, a work machine, a storage part, and a control part. The working machine is attached to the vehicle body and used for farm work. The storage unit can store field information including information indicating the shape of the field, and past travel information and past work information in at least a part of the field or at least a part of another field. is there. The control unit can generate a work route in the field based on the field information, the past traveling information, and the past work information.

  Thereby, based on the driving | operation which the operator actually performed, the operation | work by an automatic driving | operation can be performed more flexibly.

  The agricultural work vehicle preferably has the following configuration. That is, this agricultural work vehicle includes a communication unit that can communicate with other agricultural work vehicles. The control unit acquires at least one of the farm field information, the past traveling information, and past work information from the other agricultural work vehicle via the communication unit, and the communication unit. It is possible to provide at least one of the above to the other agricultural work vehicle.

  Thereby, the information for implement | achieving favorable automatic driving | operation can be easily shared with other agricultural work vehicles.

1 is a side view showing an overall configuration of a robot tractor according to an embodiment of the present invention. The top view of a robot tractor. The block diagram which shows the main structures of the control system of a robot tractor. The figure which shows a mode that the working machine was lowered | hung to the working position. The conceptual diagram which shows the teacher data given for learning of a motion prediction model. The figure which showed the remote control apparatus. The side view which showed a mode that the manned robot tractor accompanies the unmanned robot tractor. The top view which showed a mode that the robot tractor of manual operation mode drive | works a farm field by operation of an operator. The top view which showed a mode that the robot tractor of automatic operation mode was work | operating, drive | working unattended based on the learning result in the manual operation mode in FIG. The top view which showed a mode that the robot tractor of manual operation mode learned operation of an operator about a part of agricultural field. The top view which showed a mode that the robot tractor of automatic operation mode worked while driving | running | working the remaining area | region of an agricultural field unattended based on the learning result in the manual operation mode in FIG. The block diagram which shows the example which transmits / receives the data regarding learning between several robot tractors.

  Next, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a side view showing an overall configuration of a robot tractor 1 according to an embodiment of the present invention. FIG. 2 is a plan view of the robot tractor 1. FIG. 3 is a block diagram showing the main configuration of the control system of the robot tractor 1.

  First, a robot tractor (hereinafter may be simply referred to as “tractor”) 1 as an embodiment of an agricultural work vehicle according to the present invention will be described. As shown in FIG.1 and FIG.2, the tractor 1 is provided with the traveling body (vehicle body part) 2 which self-propels in the agricultural field. The traveling machine body 2 is provided with a work machine 3 detachably. The work machine 3 is used for farm work. Examples of the work machine 3 include various work machines such as a tillage machine, a mowing machine, a plow, a fertilizer machine, a seeding machine, and the like. 2 can be attached. In the present embodiment, a rotary tiller is used as the work machine 3. The traveling machine body 2 is configured to be able to change the height and posture of the attached work machine 3.

  The configuration of the tractor 1 will be described in detail with reference to FIGS. 1 and 2. As shown in FIG. 1, the traveling machine body 2 of the tractor 1 is supported at its front part by a pair of left and right front wheels 7 and 7 and at its rear part by a pair of left and right rear wheels 8 and 8.

  A bonnet 9 is disposed at the front of the traveling machine body 2. An engine 10 that is a drive source of the tractor 1 is accommodated in the bonnet 9. The engine 10 can be configured by, for example, a diesel engine, but is not limited thereto, and may be configured by, for example, a gasoline engine.

  A cabin 11 for an operator to board is arranged behind the bonnet 9. Inside the cabin 11, there are mainly provided a handle 12 for a steering operation by an operator, a seat 13 for the operator to sit on, and various operation devices for performing various operations. However, the agricultural work vehicle is not limited to the one with the cabin 11 and may be one without the cabin 11.

  Examples of the operation device include the monitor device 14, the throttle lever 15, the shift lever, the PTO switch 17, the PTO speed change lever 18, and the plurality of hydraulic speed change levers 16 shown in FIG. These operating devices are arranged in the vicinity of the seat 13 or in the vicinity of the handle 12. The monitor device 14 is configured to display various information of the tractor 1. The throttle lever 15 is for setting the rotational speed of the engine 10. The shift lever is for changing the speed ratio of the transmission 22. The PTO switch 17 is for switching the transmission / cutoff of power to a PTO shaft (power take-off shaft) (not shown) protruding from the rear end of the transmission 22. That is, when the PTO switch is in the ON state, power is transmitted to the PTO shaft and the PTO shaft rotates to drive the work machine 3, while when the PTO switch is in the OFF state, the power to the PTO shaft is cut off. The working machine 3 is stopped without rotating the PTO shaft. The PTO speed change lever 18 is used to change the power input to the work machine 3, and specifically, is a speed change operation for the rotational speed of the PTO shaft. The hydraulic speed change lever 16 can switch and operate a hydraulic external take-off valve (not shown).

  In addition, operating devices such as a main transmission lever 27 and a work implement lifting switch 28 are provided at the front portion of the armrest 19 disposed on the right side of the seat 13.

  The main transmission lever 27 is for changing the traveling speed of the tractor 1 and is configured such that when the main transmission lever 27 is tilted forward, the traveling speed is increased, and when the main transmission lever 27 is tilted backward, the traveling speed is decreased. The main transmission lever 27 is configured to be capable of stepless operation, and the traveling speed of the tractor 1 is steplessly changed according to the amount of lever operation.

  The work implement raising / lowering switch 28 is configured as an electric switch that is provided on the main transmission lever 27 and can be operated up and down, and is used when raising and lowering the work implement 3. Thereby, the working machine 3 can be lowered to start the tilling work by the tilling claws 25, or can be raised to end the tilling work.

  As shown in FIG. 1, a chassis 20 of the tractor 1 is provided at the lower part of the traveling machine body 2. The chassis 20 includes a body frame 21, a transmission 22, a front axle 23, a rear axle 24, and the like.

  The body frame 21 is a support member at the front portion of the tractor 1 and supports the engine 10 directly or via a vibration isolation member. The transmission 22 changes the power from the engine 10 and transmits it to the front axle 23 and the rear axle 24. The front axle 23 is configured to transmit the power input from the transmission 22 to the front wheels 7. The rear axle 24 is configured to transmit the power input from the transmission 22 to the rear wheel 8.

  As shown in FIG. 3, the tractor 1 includes a control unit 4 for controlling the operation of the traveling machine body 2 (forward, reverse, stop, turn, etc.) and the operation of the work machine 3 (elevation, drive, stop, etc.). Prepare. The control unit 4 is electrically connected with a governor device 41, a transmission device 42, a lifting actuator 44, and the like.

  The governor device 41 adjusts the rotational speed of the engine 10. By controlling the governor device 41 by the control unit 4 and appropriately adjusting the rack position, the rotational speed of the engine 10 can be set to a desired rotational speed.

  Specifically, the transmission 42 is, for example, a movable swash plate type hydraulic continuously variable transmission, and is provided in the transmission 22. By controlling the transmission 42 by the control unit 4 and appropriately adjusting the angle of the swash plate (not shown), the transmission 22 can have a desired transmission ratio.

  The lifting / lowering actuator 44 operates the three-point link mechanism that connects the work machine 3 to the traveling machine body 2, for example, thereby moving the work machine 3 to the retracted position (the position where the farm work is not performed, for example, the position shown in FIG. 1) or the work position. The position is raised or lowered to any one of (a position where farm work is performed, for example, the position shown in FIG. 4). In addition, since the working machine 3 is comprised as a rotary tillage apparatus in this embodiment, the farm work by the working machine 3 means a tilling work. Agricultural work can be performed with the work machine 3 at a desired height by controlling the elevating actuator 44 by the control unit 4 and appropriately moving the work machine 3 up and down.

  The tractor 1 including the control unit 4 as described above controls various parts of the tractor 1 (the traveling machine body 2, the work implement 3, and the like) by the control unit 4 when the operator gets into the cabin 11 and performs various operations. Thus, the farm work can be performed while traveling in the field. In addition, the tractor 1 of this embodiment travels by instructing forward, reverse, turning, etc. by the remote control device (remote control device) 46 shown in FIGS. 1 and 3 even when the operator does not board the tractor 1. It is also possible to make the tractor 1 autonomously travel.

  Specifically, as shown in FIG. 3, the tractor 1 includes various configurations in the control unit 4 for enabling autonomous traveling. Further, the tractor 1 is provided with various configurations such as a positioning antenna 6 necessary for acquiring its own position information based on the positioning system. With such a configuration, the tractor 1 can acquire its own position information based on the positioning system and can autonomously travel on the field.

  Next, the configuration of the tractor 1 for enabling autonomous traveling will be described in detail. Specifically, as shown in FIGS. 1 and 3, the tractor 1 includes a steering actuator 43, a positioning antenna 6, a wireless communication antenna 48, and the like in addition to the control unit 4.

  The steering actuator 43 is provided, for example, in the middle of the rotation shaft (steering shaft) of the handle 12 and adjusts the rotation angle (steering angle) of the handle 12. By controlling the steering actuator 43 by the control unit 4 and appropriately operating it, the steering angle of the handle 12 is set to a desired value, the front wheel 7 which is a steering wheel is turned, and the tractor 1 is turned at a desired turning radius. Can be operated.

  The positioning antenna 6 receives a signal from a positioning satellite constituting a positioning system such as a satellite positioning system (GNSS). As shown in FIG. 1, the positioning antenna 6 is disposed on the upper surface of the roof 92 of the cabin 11 of the tractor 1. The positioning signal received by the positioning antenna 6 is input to the position information calculation unit 49 shown in FIG. 3, and the position information calculation unit 49 stores the position information of the tractor 1 (strictly, the positioning antenna 6). For example, it is calculated as latitude / longitude information. The position information calculated by the position information calculation unit 49 is input to the control unit 4 and used for autonomous traveling.

  Here, as a specific example of the positioning system, there is a satellite positioning system using GPS technology (GPS satellite), but instead, a system using other satellites such as a quasi-zenith satellite and a Glonus satellite is used. It is also possible to do. Moreover, as a positioning system using GPS technology, single positioning, relative positioning, DGPS positioning, RTK-GPS positioning, or the like can be employed.

  The wireless communication antenna 48 receives a signal from the remote operation device 46 or transmits a signal to the remote operation device 46. As shown in FIG. 1, the radio communication antenna 48 is disposed on the upper surface of the roof 92 of the cabin 11 of the tractor 1. A signal from the remote control device 46 received by the radio communication antenna 48 is signal-processed by the radio communication unit (communication unit) 40 shown in FIG. A signal transmitted from the control unit 4 to the remote operation device 46 is subjected to signal processing by the wireless communication unit 40, then transmitted from the wireless communication antenna 48, and received by the remote operation device 46.

  As shown in FIG. 6, the remote operation device 46 is configured as a tablet personal computer including a touch panel 39. The operator can confirm the information by referring to information displayed on the display 37 of the remote control device 46 (for example, information on a field necessary for autonomous traveling). In addition, the operator operates the hardware key 38 or the like arranged near the touch panel 39 or the display 37 to transmit a control signal for controlling the tractor 1 to the control unit 4 of the tractor 1. be able to. Note that the remote operation device 46 is not limited to a tablet-type personal computer, but can be configured by, for example, a notebook-type personal computer. Alternatively, when the manned tractor 1x travels along with the unmanned tractor 1 as shown in FIG. 7, the monitor device 46x mounted on the manned tractor 1x may be a remote control device.

  The tractor 1 configured as described above can perform work by the work implement 3 while autonomously traveling along the work path on the field based on an instruction of an operator using the remote operation device 46.

  Next, raising and lowering of the working machine will be described with reference to FIGS. FIG. 4 is a side view showing a state where the work implement 3 is lowered to the work position from the state of FIG.

  As shown in FIG. 1, a work machine 3 is attached to the rear part of the traveling machine body 2 of the tractor 1. As described above, a part of the driving force of the engine 10 is transmitted to the work machine 3 through the PTO shaft, and the work machine 3 can be driven to perform the tilling work. At the lower portion of the work machine 3, a tilling claw 25 that is driven to rotate about a horizontally disposed shaft 26 is provided. By lowering the working machine 3 to the working position shown in FIG. 4, the rotating tillage claw 25 comes into contact with the soil, and the farming work in the field can be performed. Moreover, by raising the working machine 3 to the retreat position shown in FIG. 1, the tilling claw 25 can be detached from the soil and the tilling work can be stopped. The work machine 3 can be lifted and lowered by an operator operating the work machine lift switch 28, and can also be automatically controlled by the control unit 4.

  Next, the learning function of the control unit 4 will be described with reference to FIG. 3, FIG. 5, FIG. 8, FIG. FIG. 8 is a plan view showing a state where the robot tractor 1 in the manual operation mode travels on the field 61 by the operation of the operator. FIG. 9 is a plan view showing a state in which the robot tractor 1 in the automatic operation mode performs an operation while traveling unattended based on the learning result in the manual operation mode in FIG.

  The control part 4 of this embodiment is comprised so that the operation | movement of the tractor 1 performed by the operator's operation may be learned, and the tractor 1 can be made to drive automatically based on the learned operation | movement. The configuration will be described below.

  As shown in FIG. 3, the control unit 4 includes an operation mode switching unit 70, a learning unit 80, and an automatic operation control unit 71.

  The operation mode switching unit 70 is for switching between the automatic operation mode and the manual operation mode in the tractor 1. For example, the control unit 4 has a RAM (not shown), and an automatic operation mode and a manual operation mode are switched by switching an operation mode flag stored in the RAM. A specific switching operation of the operation mode can be realized by the operator appropriately operating the remote operation device 46. For example, when the operator touches the mode switching button displayed on the display 37 of the remote operation device 46 with a finger or the like, the remote operation device 46 transmits a mode switching signal, and this mode switching signal is transmitted via the wireless communication unit 40. The received operation mode switching unit 70 changes the operation mode flag to switch between the automatic operation mode and the manual operation mode.

  The learning unit 80 is configured to be able to learn the operation of the tractor 1 operated by the operator in the manual operation mode. A specific configuration of the learning unit 80 will be described later.

  The automatic operation control unit 71 is configured to allow the tractor 1 to perform automatic operation based on the operation of the tractor 1 learned by the learning unit 80.

  The learning unit 80 includes a motion prediction model 81 and a teacher data storage unit (storage unit) 82. The learning unit 80 operates based on teacher data stored in the teacher data storage unit 82 (data relating to the field 61 and data relating to an operation of the farm 61 when the operator operates the tractor 1 in the manual operation mode). The prediction model 81 can be trained.

  The teacher data storage unit 82 includes an input case data storage unit 85 and an output case data storage unit 86.

  The input case data storage unit 85 can store input case data input by an operator. The input example data is data related to the farm field 61 and includes information related to the shape of the farm field 61.

  Note that the information on the shape of the field 61 can be expressed, for example, as a set of position information of each vertex of a polygon that approximates the shape of the field 61a shown in FIG. The position information indicating the shape of the field 61 can be obtained, for example, by sequentially acquiring the position information by the position information calculation unit 49 while running the tractor 1 along the contour of the field 61. It can also be obtained by operating the device 46 and sequentially inputting position information.

  The input case data includes information on the work content (work information). Examples of the work information include the type (model) and size of the work machine. The work information can include various types of information for each work machine.

  The output case data storage unit 86 can store output case data that is data related to the operation of the tractor 1 operated by the operator in the manual operation mode. The output example data includes information related to the work route of the tractor 1 (information related to the route (travel route 65) on which the tractor 1 traveled the field 61, and information related to the lifting operation of the lifting actuator 44).

  The information on the travel route 65 can be expressed, for example, as a change in the position of the tractor 1 that actually travels in the manual operation mode (a set of position information calculated by the position information calculation unit 49). In addition, the travel route 65 may be simplified as a straight line and an arc, and may be expressed as position information on the start point and end point of the straight line, position information on the start point, end point, and arc center of the arc.

  Further, the information related to the lifting / lowering operation of the lifting / lowering actuator 44 (timing of lifting / lowering of the work implement 3) is obtained by detecting the position of the tractor 1 in the travel route 65 and the height of the work implement 3 at the corresponding position by an appropriate sensor. Information that associates the detected values with each other can be used.

  After the operator inputs the shape and the like of the field 61, when the operator operates in the manual operation mode in the field 61, information such as the shape of the field 61 is stored in the input case data storage unit 85, and the tractor 1 operated by the operator is stored. Is detected by the position information calculation unit 49 and various sensors (not shown) and stored in the output case data storage unit 86.

  As shown in FIG. 5, the motion prediction model 81 learns based on teacher data including a set of input case data and output case data stored in the teacher data storage unit 82. More specifically, the above input case data is expressed as a multidimensional vector, but if used as it is for learning, the amount of information is so large that learning cannot be completed in a realistic time. A vector (multidimensional feature vector) with a reduced number of dimensions is obtained by performing processing (feature extraction processing) for extracting only essential features on the input case data. Then, learning can be performed by giving the motion prediction model 81 a large number of sets of the feature vectors and multidimensional vectors representing the output case data.

  The learned motion prediction model 81 can output a multidimensional vector corresponding to the feature vector input thereto. The control unit 4 controls the traveling of the tractor 1 and the lifting / lowering operation of the lifting / lowering actuator 44 based on the information output from the motion prediction model 81.

  With the above configuration, when the work is performed again in the field 61 once learned by the learning unit 80, the tractor 1 can be automatically operated along the same route as the traveling route 65 that the operator has operated in the manned traveling.

  In addition, even when an unknown feature vector is given, the learned motion prediction model 81 can estimate and output a corresponding multidimensional vector (generalization ability). Therefore, even when the shape of the unknown field 61b as shown in FIG. 9 is given to the tractor 1 in the automatic operation mode, another field 61 (for example, a shape similar to the above-described field 61b as shown in FIG. 8). Based on the result of learning the operator's operation (operation of the tractor 1) in the past in the farm field 61a), flexible automatic operation of the tractor 1 can be realized.

  As described above, the control unit 4 of the present embodiment can learn the operation of the tractor 1 operated by the operator, and can automatically operate the tractor 1 based on the learned operation. As a result, the tractor 1 can automatically run the tractor 1 and the lift actuator 44 can be moved up and down along the travel path 65 that is closer to when the operator actually operates. As a result, it is possible to realize an automatic operation that finely responds to the individual demands of the users that differ for each actual field 61 and operation.

  The output case data stored in the output case data storage unit 86 includes not only the traveling path 65 of the tractor 1 and the lifting / lowering operation of the lifting / lowering actuator 44 operated by the operator, but also the braking operation of the tractor 1 (the left and right wheels). Information on so-called single brake that only brakes), information on the vehicle speed set in the tractor 1, information on the engine speed set in the tractor 1, and PTO shaft (working power of the engine 10 not shown) Information on the driving state of the mechanism that transmits to the machine 3 is included. Note that these pieces of information can be acquired from detection values of various sensors attached to the tractor 1 or setting values input to the control unit 4. Thereby, the control part 4 can learn an operator's operation including specific operation | movements, such as a brake operation | movement, and can make the tractor 1 autonomously travel. These pieces of information can be associated with the position of the tractor 1 in the travel route 65 in the same manner as the information related to the lifting operation of the lifting actuator 44.

  In addition to the above information, the output case data stored in the output case data storage unit 86 corresponds to the vehicle speed information of the tractor 1 adjusted according to the inclination of the field 61 and the slip rate of the tractor 1. Information on the vehicle speed of the tractor 1 adjusted in this way, information on the engine speed adjusted in response to changes in the engine load factor, information on vehicle speed adjusted in response to changes in the engine load factor, and engine load Information related to the lifting / lowering operation of the lifting / lowering actuator 44 corresponding to the change in rate is included. These pieces of information can be acquired from detection values of various sensors attached to the tractor 1. That is, in the past, the operator has come to the slope portion of the field 61 during traveling, the front wheel 7 or the rear wheel 8 slips, the load factor of the engine 10 increases, or the like depending on the specific situation. Based on this experience, adjustment of the vehicle speed, adjustment of the engine speed, raising / lowering of the lifting / lowering actuator 44, and the like were performed, and the operation required a high degree of skill. In this respect, the control unit 4 according to the present embodiment can accurately control the vehicle speed, the engine speed, and the like during autonomous traveling of the tractor 1 by learning, for example, an operation actually performed by an experienced operator.

  The input case data stored in the input case data storage unit 85 includes not only the shape of the field 61 but also the inclination of the field 61, the shape of the headland 63 in the field 61, trees and swamps in the field 61, and the like. Information on the obstacle, the quality of the soil in the field 61, and the like is included. Note that these pieces of information can be acquired from, for example, information input by the operator operating the remote operation device 46. As a result, the control unit 4 allows the tractor 1 to follow the traveling of the tractor 1 and the lifting / lowering operation of the lifting / lowering actuator 44 along the traveling path 65 that is closer to the case where the operator actually performs the tractor while appropriately responding to the detailed situation of the field 61. 1 can be performed automatically.

  Next, it will be described with reference to FIGS. 10 and 11 that the control unit 4 learns the operation of the tractor 1 in a part of the agricultural field 61 and applies it to the operation of the tractor 1 in the entire agricultural field 61. FIG. 10 is a plan view showing how the robot tractor 1 in the manual operation mode learns the operation of the operator for a part of the field 61. FIG. 11 is a plan view showing a state in which the robot tractor 1 in the automatic operation mode performs work while unmanned traveling in the remaining area of the farm field 61 based on the learning result in the manual operation mode in FIG. 10.

  In FIG. 10, the example of the agricultural field 61c which is a somewhat complicated shape is shown. In the field 61c, the shapes of the upper right part where the manned traveling is performed and the lower left part where the work is not yet performed are relatively similar. Moreover, the intermediate part which connects the upper right part and the lower left part of the agricultural field 61c is a simple rectangle.

  In such an agricultural field 61c, the operator sets the tractor 1 in the manual operation mode, inputs the shape of the agricultural field 61 only for the upper right part in FIG. 10, and operates the tractor 1 manually for only that part. Thereafter, the operator switches to the automatic operation mode, inputs information such as the shape of the middle part and the lower left part of the field 61 to the input case data storage unit 85, and enters the tractor 1 according to the output of the motion prediction model 81 corresponding to the input. Work can be done automatically. In this way, by causing a part of the field 61c to travel on a manned basis and causing the motion prediction model 81 to learn, the remaining areas are also similar to those performed by the operator during learning, as shown in FIG. It can be expected that running and work will be performed.

  That is, since only a part of the field 61 can be learned and applied to the entire field 61, it is possible to reduce the time and man-hours required for performing the manned traveling and causing the tractor 1 to learn.

  Next, FIG. 12 illustrates an example in which the control unit 4 included in the tractor 1 acquires data stored in the control unit 4 included in the other tractor 1a by wireless communication and uses the motion prediction model 81 as data for learning. It explains using. FIG. 12 is a block diagram illustrating a main configuration of the control system of the tractor 1 when the control unit 4 acquires data learned by the control unit 4 included in the other tractor 1a through wireless communication.

  In the example shown in FIG. 12, the control unit 4 a is provided in a tractor 1 a different from the tractor 1. The data obtained by the operator maneuvering in the manual operation mode in each of the tractor 1 and the tractor 1a is wirelessly transmitted and received between the two tractors 1 and 1a via the wireless communication antenna 48. be able to. Although not shown, the control unit 4a included in the tractor 1a also includes a learning unit 80 (an operation prediction model 81, an input case data storage unit 85, and an output case data storage unit 86).

  The data exchanged between the control units 4 and 4a may be teacher data stored in the input case data storage unit 85 and the output case data storage unit 86, or represents the motion prediction model 81 in which learning based on the teacher data has been completed. The data to be used may be used. In general, in order to construct an accurate motion prediction model 81 in the learning unit 80 of the tractor 1, it is necessary to give a large number of teacher data to the motion prediction model 81 for learning, but externally (other tractors 1 a). By using the obtained teacher data, the time and man-hours required for data acquisition can be reduced. In addition, when configured to exchange the data of the learned motion prediction model 81, it is possible to acquire an excellent motion prediction model constructed externally, and to reduce labor and time required for learning. It is preferable in that it can be performed.

  In addition, when exchanging the data regarding learning between the plurality of tractors 1 and 1a, information for specifying the model of the tractor 1, information for specifying the model of the work implement 3, and the attachment of the positioning antenna 6 to the tractor 1 It is preferable that information on the position and the like is included in the teacher data (input case data) given to the motion prediction model 81. That is, the lifting / lowering operation of the work machine 3 in the tractor 1 varies depending on the performance of the lifting / lowering actuator 44 provided in the tractor 1, the weight of the work machine 3, and the like, and the axis of the tilling claw 25 of the work machine 3 from the positioning antenna 6. The distance up to 26 (distance L shown in FIG. 1) varies depending on the model of the work implement 3, the mounting position of the positioning antenna 6, and the like. Therefore, by performing learning including the above information, it is possible to construct a general motion prediction model 81 that can be applied to various tractors, and to share learning results among a plurality of tractors. Becomes easier.

  As described above, the tractor 1 of this embodiment includes the traveling machine body 2, the work machine 3, the teacher data storage unit 82, and the control unit 4. The work machine 3 is attached to the traveling machine body 2. The work machine 3 is used for farm work. The teacher data storage unit 82 includes farm field information including information indicating the shape of the farm field 61, past travel information and past work in at least a partial area of the farm field 61 or at least a partial area of the other farm field 61. Information can be stored. The control unit 4 can generate a work route in the farm field 61 based on the farm field information, past travel information, and past work information.

  Thereby, based on the driving | operation which the operator actually performed, the operation | work by an automatic driving | operation can be performed more flexibly.

  Moreover, the tractor 1 of this embodiment is provided with the radio | wireless communication part 40 which can communicate with the other tractor 1a. The control unit 4 obtains at least one of the field information, the past travel information, and the past work information from the other tractor 1a via the wireless communication unit 40, or the other information via the wireless communication unit 40. It can also be provided to the tractor 1a.

  Thereby, the information for implement | achieving favorable automatic driving | operation can be easily shared with the other tractor 1a.

  The preferred embodiment of the present invention has been described above, but the above configuration can be modified as follows, for example.

  The remote operation device 46 of the above embodiment is configured to be able to remotely monitor and operate the work of the single tractor 1 autonomously with respect to one remote operation device 46, but is not limited to this. The tractor 1 may be configured to be remotely monitored and operated.

  In the above embodiment, an example in which data related to learning is transmitted and received between the two tractors 1 and 1a is shown, but the number of tractors 1 is not limited to two, and may be any number. For example, the control unit 4 may be wirelessly connected to a WAN such as the Internet and exchange learning data with the learning unit 80 provided in the control unit 4 of a distant tractor. In addition, a database capable of storing data related to learning may be constructed in a server connected to the Internet, and the data may be acquired from the database. As described above, as the number of tractors sharing data increases, it becomes easier to realize a good automatic operation in the tractor 1 more easily and in a short time.

  A work route may be created without using machine learning by the learning unit 80. For example, when the shape of the field is almost the same between the past and the present, the work route may be created by simply copying all past travel routes. Alternatively, the work route may be created by repeatedly arranging a predetermined repeating unit route (for example, a straight-line route and a turning route for one round trip) among the past traveling routes. In this case, when a plurality of repetitive unit travel routes appear in the past travel route, the average travel route obtained by calculating the average of the turning radius etc. is used as a repeat unit when creating a new work route. It may be used.

  When a special shape appears in a part of the shape of the field (for example, a turning circuit), or when an obstacle is arranged in the field, such a part that requires such a special operation (for example, reverse of the tractor 1) Only for a turn without a turn or a turn with a reverse movement of the tractor 1), a work route may be created based on past travel information and past work information.

  Instead of using machine learning, past travel information in other tractors, past work information, and field information at that time may be received, and a work route may be created based on the information. Specifically, the type and size of the work implement 3 are the same as when other tractors have worked in the past, and the difference in the shape of the field is also within a preset threshold range (the shape of the field is For example, it is conceivable to create a work route by simply copying a travel route when working with another tractor. In addition, in order to be able to use other tractors, past travel information, past work information, and farm field information at that time can be provided to other tractors by transmitting them as necessary. Is preferred.

  In traveling the field 61a based on the learning data acquired from the tractor 1a, the tractor 1 not only travels based on the learning data in the entire field 61a acquired from the tractor 1a, but also the field acquired from the tractor 1a. Based on any of the data relating to learning in a part of 61a, data relating to learning in the whole other field 61b acquired from the tractor 1a, and data relating to learning in a part of another field 61b obtained from the tractor 1a. Can also be run. That is, the tractor 1 acquires the input case data and the output case data when the other tractor 1a travels only a part of the field 61a, and the motion prediction model 81 learns, and the learning result is obtained for the entire field 61a. It can be applied when the tractor 1 travels. In addition, for example, the tractor 1 acquires input case data and output case data when another tractor 1a travels only a part of the field 61b, and the motion prediction model 81 learns, and the learning result is included in the above part. The present invention can be applied when the tractor 1 travels the whole of another field 61a including a portion having a similar shape.

  The output example data is data relating to the operation of the tractor 1 operated by the operator in the manual operation mode. However, the output example data is data relating to the operation of the tractor 1 in the automatic operation mode and data relating to the operation of other tractors 1a in the automatic operation mode. There may be.

  The present invention is not limited to being applied to a tractor as in the above embodiment, and can be applied to, for example, a rice transplanter. In that case, a planting part (planting apparatus) will correspond to a working machine. Furthermore, the present invention can also be applied to various other agricultural work vehicles.

1,1a Robot tractor (agricultural work vehicle)
2 Traveling body (body part)
3 Work machines 4, 4a Control unit 40 Wireless communication unit (communication unit)
61 (61a, 61b, 61c) Agricultural field 82 Teacher data storage unit (storage unit)

Claims (2)

The body part,
A working machine mounted on the vehicle body and used for farm work;
A storage unit capable of storing past field information including information indicating the shape of the field, and past travel information and past work information in at least a part of the field or at least a part of another field;
A control unit capable of generating a work route in the field based on the field information, the past travel information, and the past work information;
Agricultural work vehicle comprising: The agricultural work vehicle according to claim 1,
It has a communication unit that can communicate with other agricultural work vehicles,
The control unit acquires at least one of the farm field information, the past traveling information, and past work information from the other agricultural work vehicle via the communication unit, and the communication unit. An agricultural work vehicle characterized in that at least one of the above can be provided to the other agricultural work vehicle.

Images