Autonomous control device, autonomous control method, and autonomous control program

Abstract

To provide an autonomous control device, an autonomous control method, and an autonomous control program capable of making a deviation between a planned traveling path and an actual traveling path smaller than the conventional deviation.SOLUTION: An autonomous control device 32 for controlling an autonomously movable mobile device 1 comprises: positioning means for positioning a current position by using positioning radio waves from a navigation satellite 202A, and the like; direction change measuring means for measuring a change in a nose direction of the mobile device at a time interval shorter than an output interval of a positioning result by the positioning means; first correction means for correcting the nose direction of the mobile device so as to mitigate the change in the nose direction measured by the direction change measuring means; and return means for adjusting the mobile device to move in a planned direction on the planned path based on the positioning result of the positioning means.SELECTED DRAWING: Figure 14

Description

[Technical field]

[0001] The present invention relates to an autonomous control device, an autonomous control method, and an autonomous control program for controlling a mobile device. [Background technology]

[0002] Conventionally, in the case of automatic travel of a work machine such as a vehicle, a technique has been proposed for controlling the steering angle by eliminating the deviation between an actual travel position and a planned travel position (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-41593 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the case where the work machine travels automatically, for example, as shown in FIG. 32, the planned route A1 is a straight route. The actual travel route of the work machine is affected by the unevenness of the ground, etc., and if the travel direction is not corrected, it will deviate from the planned route A1. Therefore, the work machine corrects the travel direction so as to return to the planned route A1 at a predetermined timing. For this reason, for example, the actual route of the work machine becomes a bent route such as route A1a. In the case where positioning is performed by receiving positioning radio waves from navigation satellites that constitute the GNSS (Global Navigation Satellite System) as in the above-mentioned technology, the output of the positioning result is performed at a predetermined time interval such as times t0, t1, t2, etc. In this case, the travel direction cannot be corrected while the positioning result is being output. As a result, the actual travel route deviates from the planned route A1 by a predetermined width W1, for example.

[0005] In addition, positioning radio waves from navigation satellites have the property of being difficult to penetrate metal and water, so for example, it has been difficult for a work machine to operate while automatically traveling under the branches and leaves of trees in an orchard or inside a greenhouse, based on the position calculated by receiving positioning radio waves.

[0006] The present invention attempts to solve such problems, and aims to provide an autonomous control device, an autonomous control method, and an autonomous control program that can reduce the deviation between a planned travel path and an actual travel path more than ever before. [Means for solving the problem]

[0007] A first invention is an autonomous control device for controlling a mobile device capable of autonomous movement, comprising: a positioning means for positioning a current position using positioning radio waves from navigation satellites that constitute a GNSS (Global Navigation Satellite System); a direction change measuring means for measuring a change in the heading direction of the mobile device at a time interval shorter than the output interval of the positioning results by the positioning means; a first correction means for correcting the heading direction of the mobile device so as to offset the change in the heading direction measured by the direction change measuring means; and a return means for adjusting the mobile device so as to move in a planned direction on a planned route based on the positioning results by the positioning means, wherein the positioning means is configured to perform RTK (Real Time Kinematic) positioning and receive GNSS correction data from a communication base station of a mobile terminal.

[0008] According to the configuration of the first invention, the first correction means can correct the nose direction of the mobile device so as to reduce the change in the nose direction while the positioning result is output. Even if the mobile device is not moving in the planned direction on the planned route despite the correction of the nose direction by the first correction means, the adjustment by the return means adjusts the mobile device so that it moves in the planned direction on the planned route. Since the nose direction is corrected by the first correction means prior to the adjustment by the return means, the deviation between the planned traveling path of the mobile device and the actual traveling path can be made smaller than before. Here, the inventor of the present invention confirmed through experiments that the probability of obtaining a positioning result is higher even under trees or in a greenhouse by receiving GNSS correction data from the communication base station of the mobile terminal and performing RTK positioning compared to single positioning. As a result, the deviation between the planned traveling path of the mobile device and the actual traveling path can be made smaller than before even under the branches and leaves of a tree or in a greenhouse.

[0009] A second invention is an autonomous control device having the configuration of the first invention, which has a speed change measuring means for measuring changes in the movement speed of the mobile device in a direction perpendicular to the traveling direction of the mobile device at a time interval shorter than the output interval of the positioning result by the positioning means, and the first correction means is configured to correct the heading direction of the mobile device so as to offset changes in the heading direction measured by the direction change measuring means and changes in the movement position due to changes in the moving speed measured by the speed change measuring means.

[0010] According to the configuration of the second invention, since the speed change measuring means measures the change in the moving speed in a direction perpendicular to the nose direction, it is possible to measure the speed change even when the nose direction does not change, for example, when the mobile device skids sideways and moves parallel while maintaining the nose direction. The first correction means can correct the nose direction of the mobile device so as to reduce the change in the moving position caused by the change in the moving speed measured by the speed change measuring means, in addition to correcting the nose direction so as to reduce the change in the nose direction. In other words, whether the nose direction changes or does not change during the output of the positioning result, it is possible to correct the deviation from the scheduled traveling route.

[0011] A third invention is an autonomous control device having, in the configuration of the first or second invention, a relative direction measuring means for measuring the heading direction of a forward moving device in a relative relationship with the direction of the geomagnetic field at a time interval shorter than the output interval of the positioning results by the positioning means, and a second correction means for correcting the heading direction of the forward moving device so as to reduce the difference between the planned direction defined in the relative relationship with the direction of the geomagnetic field and the heading direction measured by the relative direction measuring means.

[0012] For example, even if the traveling direction of the mobile device deviates from the planned direction, if the deviation continues for a predetermined time, it cannot be detected as a change in the nose direction. In this regard, according to the configuration of the third invention, even if there is no change in the nose direction during the predetermined time between the output of the positioning result, the second correction means can reduce the deviation between the nose direction measured by the relative direction measurement means and the planned direction. This makes it possible to reduce the deviation between the moving speed of the mobile device and the planned speed more than before.

[0013] A fourth invention is an autonomous control device in the configuration of the third invention, which has a heading direction calculation means for calculating a heading direction of the mobile device based on Doppler information indicating the Doppler effect of the positioning radio waves generated by the relative movement between the navigation satellite and the mobile device, a direction deviation calculation means for calculating a deviation between the heading direction calculated by the heading direction calculation means and the planned direction, and a third correction means for correcting the heading direction of the mobile device so as to reduce the deviation calculated by the direction deviation calculation means.

[0014] The autonomous control device can calculate the moving direction, i.e., the nose direction, based on the Doppler information of the positioning radio waves from multiple navigation satellites. In a simple example, when Doppler information indicating that the mobile device is approaching one navigation satellite A and Doppler information indicating that the mobile device is moving away from another navigation satellite B are acquired, the mobile device is approaching the navigation satellite A. When the reliability of the nose direction calculated by the Doppler information is higher than that of the nose direction calculated based on the geomagnetism, the control of the nose direction using the Doppler information is effective. In addition, since the Doppler information can be acquired earlier than the positioning result, the nose direction can be corrected during the control of the nose direction based on the reliable current position based on the positioning result. In this regard, according to the configuration of the fourth invention, the third correction means can correct the nose direction based on the Doppler information, so that there are cases where it is possible to implement more accurate control of the nose direction. This makes it possible to reduce the deviation between the moving speed of the mobile device and the scheduled speed more than ever before.

[0015] A fifth invention is an autonomous control device in the configuration of the second invention, wherein the speed change measuring means is further configured to measure changes in speed in the planned direction at a time interval shorter than the acquisition interval of Doppler information, and further comprising a speed correction means for correcting the speed of the mobile device so as to offset the changes in speed measured by the speed change measuring means, and a speed return means for calculating the moving speed of the mobile device based on the Doppler information and adjusting the moving speed of the mobile device so that it matches the planned speed.

[0016] According to the configuration of the fifth invention, the speed correction means can correct the moving speed of the moving device so as to offset the change in speed measured by the speed change measurement means. Furthermore, even if the moving device is not moving at the planned speed despite the result of the correction of the moving speed by the speed correction means, the speed return means adjusts the moving device so that it moves at the planned speed. And, since the speed change measurement means measures the change in speed at a time interval shorter than the acquisition interval of the Doppler information, the moving speed of the moving device can be controlled even while the Doppler information is being acquired. That is, the moving speed can be corrected during reliable control of the moving speed based on the Doppler information. This makes it possible to reduce the deviation between the moving speed of the moving device and the planned speed more than ever before.

[0017] A sixth invention is an autonomous control device having, in the configuration of any of the first to fifth inventions, a priority means for prioritizing a signal from a work control means that controls the work performed by the mobile device when a signal regarding the movement of the mobile device is received from the work control means.

[0018] When the mobile device performs work such as tilling, for example, the heading direction and moving speed may be controlled by work control software according to the condition of the field, etc., in order to perform the work effectively. In this regard, according to the configuration of the sixth invention, since the mobile device has a priority means that prioritizes the signal from the work control means when a signal related to the movement of the mobile device is received from the work control means, it is possible to realize a moving route and moving speed for performing the work effectively, rather than simply proceeding along a planned route at a planned speed.

[0019] A seventh invention is an autonomous control device, in the configuration of the third invention, having a correction means for correcting the magnitude of the nose direction correction by the first correction means and / or the second correction means based on the magnitude of adjustment by the return means.

[0020] The larger the magnitude of the adjustment by the return means, the greater the degree to which the correction of the nose direction by the first correction means or the second correction means is insufficient. In this regard, according to the configuration of the seventh invention, the correction means can correct the magnitude of the correction of the nose direction by the first correction means and / or the second correction means based on the magnitude of the adjustment by the return means. This makes it possible to reduce the deviation between the moving speed of the mobile device and the scheduled speed compared to conventional methods while the positioning result is being output.

[0021] An eighth invention is an autonomous control device having, in the configuration of the first invention, a route recording means for recording an actual route, which is the actual route traveled by the mobile device, a difference calculation means for calculating the difference between the planned route and the actual route, and a difference reduction means for controlling the mobile device when moving along the planned route next time, based on the difference calculated by the difference calculation means, to reduce the difference between the planned route and the actual route.

[0022] According to the eighth aspect of the invention, when moving along the planned route for the second time, the difference between the planned route and the actual route can be reduced more than when moving along the planned route once. Here, the autonomous control device records the actual route based on the positioning position obtained by RTK positioning, and the coordinates of the actual route are close to the true coordinates. Therefore, the difference between the planned route and the actual route calculated by the eighth aspect of the invention is highly reliable.

[0023] A ninth invention is a control method by an autonomous control device for controlling a mobile device capable of autonomous movement, having a positioning means for positioning a current position using positioning radio waves from a navigation satellite, the autonomous control method carrying out the following steps: a direction change measurement step for measuring a change in the heading direction of the mobile device at a time interval shorter than the output interval of the positioning results by the positioning means; a first correction step for correcting the heading direction of the mobile device so as to offset the change in the heading direction measured by the direction change measurement means; and a return step for adjusting the mobile device so as to move in a planned direction on a planned route based on the positioning results by the positioning means, wherein the positioning means is configured to perform RTK (Real Time Kinematic) positioning and receive GNSS correction data from a communication base station of a mobile terminal.

[0024] A tenth invention is an autonomous control program that causes a computer controlling an autonomous control device for controlling a mobile device capable of autonomous movement to function as a positioning means that uses positioning radio waves received from a navigation satellite and GNSS correction data received from a communication base station of a mobile terminal to position a current position by RTK (Real Time Kinematic) positioning, a direction change measuring means that measures a change in the heading direction of the mobile device at a time interval shorter than the output interval of the positioning results by the positioning means, a first correction means that corrects the heading direction of the mobile device so as to reduce the change in the heading direction measured by the direction change measuring means, and a return means that adjusts the mobile device to move in a planned direction on a planned route based on the positioning results by the positioning means. Effect of the Invention

[0025] According to the present invention, the deviation between the planned travel route and the actual travel route can be made smaller than in the past. [Brief description of the drawings]

[0026] [Figure 1] 3 is a schematic diagram showing the operation of the autonomous control device according to the first embodiment of the present invention; FIG. [Diagram 2]FIG. 4 is a schematic diagram showing the operation of an autonomous control device. [Diagram 3] FIG. 2 is a schematic diagram showing the external configuration of a moving device. [Figure 4] FIG. 2 is a schematic diagram showing an internal configuration of a moving device. [Diagram 5] FIG. 2 is a schematic diagram showing a functional configuration of a mobile device. [Figure 6] 3 is a schematic diagram showing main information referred to by an autonomous control unit; FIG. [Figure 7] FIG. 4 is a conceptual diagram showing control of nose direction in the first embodiment. [Figure 8] FIG. 1 is a conceptual diagram showing a neural network. [Figure 9] 1 is a schematic flow chart illustrating a machine learning method. [Figure 10] FIG. 1 is a conceptual diagram showing a planned route and an actual route of travel. [Figure 11] FIG. 1 is a conceptual diagram showing a traveling mode of a mobile device. [Figure 12] 4 is a schematic flowchart showing an overall picture of control performed by an autonomous control device. [Figure 13] 4 is a schematic flowchart showing a control for correcting the nose direction. [Figure 14] 5 is a schematic flowchart showing control near a turning position and at the turning position. [Figure 15] FIG. 11 is a conceptual diagram showing control of nose direction in a second embodiment of the present invention. [Figure 16] FIG. 1 is a conceptual diagram showing a planned route and an actual route of travel. [Figure 17] 4 is a schematic flowchart showing a control for correcting the nose direction. [Figure 18] FIG. 13 is a conceptual diagram showing control of nose direction in a third embodiment of the present invention. [Figure 19] FIG. 1 is a conceptual diagram showing a planned route and an actual route of travel. [Figure 20] 4 is a schematic flow chart showing nose direction control. [Figure 21] FIG. 13 is a conceptual diagram showing control according to a fourth embodiment of the present invention. [Figure 22] FIG. 1 is a conceptual diagram showing a planned speed and an actual moving speed. [Diagram 23] 11 is a schematic flow chart showing speed control. [Figure 24] 13 is a schematic flowchart showing nose direction control in a fifth embodiment of the present invention. [Diagram 25] FIG. 13 is a conceptual diagram showing correction of nose direction control in the sixth embodiment of the present invention. [Figure 26] FIG. 1 is a conceptual diagram showing a traveling mode of a mobile device. [Figure 27] 10 is a conceptual diagram showing the relationship between the correction of a reference amount A, a reference amount B, and a second reference amount and an adjustment amount. [Figure 28] 10 is a conceptual diagram showing the relationship between the correction of a reference amount A, a reference amount B, and a second reference amount and an adjustment amount. [Figure 29] 4 is a schematic flow chart illustrating correction of heading control. [Diagram 30] FIG. 1 is a conceptual diagram showing a planned route. [Diagram 31] FIG. 1 is a conceptual diagram showing a difference between a planned route and an actual route. [Diagram 32] FIG. 1 is a conceptual diagram showing a conventional example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0027] Hereinafter, a detailed description will be given of a mode for carrying out the present invention (hereinafter, an embodiment). In the following description, the same components are given the same reference numerals, and the description thereof will be omitted or simplified. Descriptions of components that can be appropriately carried out by a person skilled in the art will be omitted, and only the basic configuration of the present invention will be described. The gist of the present invention is that while obtaining positioning results and Doppler information using positioning radio waves, the direction of travel is controlled based on changes in the traveling state, and ultimately the direction of travel is reliably controlled based on the positioning results and Doppler information.

[0028] First Embodiment The vehicle 1 (hereinafter referred to as "drone 1") shown in Figures 1, 2, and 3 is an example of a moving device, and is capable of autonomous movement. The drone 1 is configured to move autonomously on the ground, in addition to performing operations according to instructions by wireless signals from a control device 70 (see Figure 5, also called a "promo") that controls the drone 1. In this specification, autonomous movement means automatically progressing along a moving path by software without receiving a wireless signal from the control device 70. Autonomous movement is synonymous with automatic movement. Unlike this embodiment, the moving device is not limited to unmanned moving bodies such as unmanned vehicles and unmanned aerial vehicles (drones), but may be, for example, vehicles such as manned heavy machinery operated by a human being on board.

[0029] 1, the drone 1 is a vehicle that autonomously moves under the branches and leaves of trees in an orchard 220 and inside a greenhouse 230. The drone 1 performs tasks such as plowing a field 100 in the greenhouse 230, spraying fertilizer, and spraying insecticide.

[0030] The drone 1 plows the field 100 by passing through planned routes R1 to R6. In the planned routes R1 to R6, planned positions where the nose direction changes are called turning positions. For example, the turning position between the planned routes R1 and R2 is position P. The position where the turning position starts is position P1. The planned routes R1 to R6 are defined by coordinates.

[0031] The drone 1 is configured to measure its current position using positioning radio waves from navigation satellites that constitute the Global Navigation Satellite System (GNSS). The navigation satellites are, for example, navigation satellites 202A to 202D, as shown in FIG. 1. The drone 1 is configured to perform Real Time Kinematic (RTK) positioning and receive GNSS correction data by radio waves E1 from a communication base station 210 of a mobile terminal such as a mobile phone. The drone 1 can measure its position even under the branches and leaves of trees in an orchard 220 or inside a greenhouse 230. The drone 1 is configured to measure its current position and proceed along the planned routes R1 to R6 shown in FIG. 2. In this embodiment, the direction of travel is finely corrected between the output of the positioning result of the positioning performed by receiving the positioning radio waves. This makes it possible to reduce the difference between the actual travel route and the planned routes R1 to R6 more than ever before. This embodiment relates to control of the drone 1 to travel along a planned route in a planned direction when the planned route R1 of the drone 1 is a straight route.

[0032] As shown in Fig. 3, the drone 1 has a vehicle body 10. The vehicle body 10 stores a computer that controls each part of the drone 1, an autonomous control device 32, a wireless communication device, and the like. The autonomous control device 32 includes an inertial sensor and a positioning device. The autonomous control device 32 is an example of an autonomous control device. The inertial sensor includes a gyro sensor, an acceleration sensor, and an electronic compass.

[0033] A gyro sensor, also called an angular velocity sensor, is a sensor that measures the amount of change in angle per unit time (angular velocity). The gyro sensor in this embodiment is a vibration type gyro sensor that uses IC type MEMS (Micro Electro Mechanical System) technology and can measure angular velocity in three axes (up / down, left / right, and front / back). The gyro sensor is an example of a direction change measuring means.

[0034] The acceleration sensor is an IC type sensor that measures acceleration. The acceleration sensor in this embodiment is a capacitance type sensor that can measure acceleration in three axes (up / down, left / right, and front / back). The acceleration sensor is an example of a speed change measuring means.

[0035] An electronic compass is a device that can measure a direction by observing the geomagnetism of the earth. The electronic compass in this embodiment is an IC type compass, and is a three-axis electronic compass that uses Hall element technology. The electronic compass is an example of a relative direction measuring means.

[0036] The positioning device is a device for locating a current position using positioning radio waves from navigation satellites. Navigation satellites include, for example, satellites used in Michibiki (quasi-zenith satellite system) and satellites used in GPS (Global Positioning System). The positioning device basically receives positioning radio waves from four or more navigation satellites to measure the position of the drone 1. The positioning device is configured to perform the above-mentioned RTK positioning and receive GNSS correction data from the communication base station 210 of the mobile terminal. The positioning method using positioning radio waves and RTK positioning are well known, so a description thereof will be omitted. The positioning device is an example of a positioning means.

[0037] In addition, the vehicle body 10 is provided with an antenna 12 for wireless communication and an antenna 14 for receiving positioning radio waves from a navigation satellite.

[0038] In addition, a camera 16 is disposed on the vehicle body 10 for capturing images of the area ahead.

[0039] The vehicle body 10 has front wheels 18L and 18R and rear wheels 22L and 22R (see FIG. 4) arranged thereon.

[0040] The direction in which the camera 16 is disposed is called the nose direction in the drone 1. The nose direction is the traveling direction of the drone 1, and is the direction indicated by the arrow M1 in FIG.

[0041] As shown in Fig. 4, the front wheels 18L and 18R are connected to a steering system 20 and can rotate left and right (in the direction of the arrow X in Fig. 4). By controlling the steering system 20, the heading direction of the drone 1 can be controlled.

[0042] An engine 26 is disposed inside the vehicle body 10 near the front wheels 18L and 18R. The engine 26 is, for example, a diesel engine. The engine 26 is connected to the shafts 24 of the rear wheels 22L and 22R via a transmission 28, and rotates the rear wheels 22L and 22R. Note that the engine 26 is not limited to a diesel engine, and may be, for example, a gasoline engine or an electric motor.

[0043] The autonomous control device 32 is electrically connected to the steering system 20 and the engine 26, and controls the steering system 20 and the engine 26. The autonomous control device 32 is configured to adjust the traveling direction and traveling speed of the unmanned vehicle 1.

[0044] Fig. 5 is a schematic diagram showing an example of the functional configuration of the drone 1. As shown in Fig. 5, the drone 1 has an autonomous control unit 40, a wireless communication unit 58, an image processing unit 60, and an operation control unit 62. The autonomous control unit 40 has a CPU (Central Processing Unit) 50, a memory unit 52, a drive control unit 54, and a satellite positioning unit 56. The autonomous control unit 40 corresponds to the autonomous control device 32, and shows the functional configuration of the autonomous control device 32.

[0045] The drone 1 is capable of communicating with the outside world via a wireless communication unit 58. The drone 1 receives instructions such as for starting from a control device (radio transmitter) 70 operated by a user via the wireless communication unit 58.

[0046] The drone 1 operates the camera 16 (see FIG. 3) to acquire external images and processes the acquired photographic data using the image processing unit 60. The external images are mainly images of the direction in which the drone 1 is traveling.

[0047] The drone 1 controls the direction and speed of travel required for work using the work control unit 62. The work control unit 62 controls the work performed by the drone 1, and transmits signals related to the movement of the drone 1 to the CPU 50.

[0048] The drone 1 can measure the position of the drone 1 itself by the satellite positioning unit 56. The satellite positioning unit 56 corresponds to a positioning device, and basically receives positioning radio waves from four or more navigation satellites to measure the position of the drone 1 by RTK positioning. The GNSS correction data is received from the communication base station 210. The GNSS correction data is data including coordinate information of the communication base station 210 and phase information of radio waves (carrier waves) from the navigation satellites received by the communication base station 210. Communication with the communication base station 210 to receive the GNSS correction data is performed using a high-speed communication standard. The high-speed communication standard is, for example, LTE (Long Term Evolution). The satellite positioning unit 56 outputs the positioning result at a predetermined time interval. The predetermined time interval is, for example, 1 second (s).

[0049] Here, even under the branches and leaves of trees in the orchard 220 or inside the greenhouse 230, the RTK positioning according to this embodiment has a higher probability of obtaining positioning results than standalone positioning, and also has higher positioning accuracy.

[0050] The drone 1 controls the steering system 20 and the engine 26 by a drive control unit 54 that constitutes the autonomous control unit 40. The drive control unit 54 uses outputs from a gyro sensor, an acceleration sensor, and an electronic compass.

[0051] The gyro sensor measures the change in the nose direction of the drone 1 at a time interval shorter than the output interval of the positioning results by the satellite positioning unit 56. The time interval at which the gyro sensor measures the change in the nose direction is, for example, one-quarter of a second (0.25 seconds).

[0052] The acceleration sensor measures the change in speed (acceleration) of the drone 1 at a time interval shorter than the output interval of the positioning results by the satellite positioning unit 56. Acceleration is a change in speed, and therefore a change in the movement of the drone 1. As described above, the acceleration sensor is a three-axis acceleration sensor and can measure the three-dimensional movement of the drone 1. Therefore, it is possible to measure a change in speed having a component perpendicular to the traveling direction of the drone 1. For example, when the drone 1 moves parallel in the horizontal direction while maintaining the nose direction, the parallel movement can be measured. The time interval at which the acceleration sensor measures the change in movement is, for example, one-quarter of a second (0.25 seconds).

[0053] The time interval at which the gyro sensor measures the change in nose direction and the time interval at which the acceleration sensor measures the change in movement are adjusted according to the specifications and use of the drone 1. For example, if the drone 1 is a vehicle, it is relatively heavy and moves slower than a drone or the like, so the time interval is set relatively long. In contrast, in the case of a vehicle or drone that moves fast, the time interval is set relatively short. For example, the time interval can be adjusted in units of 1 / 1000th of a second (0.0001 seconds), but in this embodiment, for convenience of explanation, it is set to 1 / 4 second (0.25 seconds).

[0054] 6 shows main data used for control by the autonomous control unit 40. The autonomous control unit 40 uses the gyro sensor output, which is the measurement result by the gyro sensor, the acceleration sensor output, which is the measurement result by the acceleration sensor, and the electronic compass output, which is the measurement result by the electronic compass. The satellite positioning unit 56 uses satellite information such as orbit information of navigation satellites, GNSS correction data, and received positioning radio waves (not shown), and outputs Doppler information indicating the Doppler effect that can be obtained during positioning calculation, and positioning position information indicating the positioning position as a positioning result. The Doppler effect is a change in the frequency of the carrier wave of the positioning radio waves.

[0055] As shown in Fig. 7, in this embodiment, the autonomous control unit 40 performs fine correction of the nose direction by referring to the gyro sensor output and the acceleration sensor output (hereinafter referred to as "first correction process"), and corrects the position and direction using the positioning position information (hereinafter referred to as "return process"). The fine correction of the nose direction performed by referring to the gyro sensor output is called "first correction process A", and the fine correction of the nose direction performed by referring to the acceleration sensor output is called "first correction process B", and "first correction process A" and "first correction process B" are collectively called "first correction processes".

[0056] The drive control unit 54 controls the rotation of the engine 26 connected to the rear wheels 22L and 22R and the rotation of the front wheels 18L and 18R by the steering system 20, thereby controlling the running speed and running direction.

[0057] The storage unit 52 stores various data and programs necessary for autonomous movement, such as data indicating a movement plan for autonomously moving along a planned route, as well as the following programs.

[0058] The memory unit 52 stores a first correction program, a return program, an image recognition program, and an avoidance program. The CPU 50 and the first correction program are an example of a first correction means. The CPU 50 and the return program are an example of a return means. The CPU 50 and the image recognition program are an example of a recognition means. The CPU 50 and the avoidance program are an example of an avoidance means.

[0059] The drone 1 corrects the nose direction of the drone 1 by the first correction program so as to reduce the change in the nose angle measured by the gyro sensor and the change in the speed measured by the acceleration sensor. This correction of the nose direction is the above-mentioned "first correction process". The first correction process is a process of reducing the measured change in the nose angle and the acceleration. For example, when the gyro sensor measures that the nose direction has changed in a certain direction, the nose direction is changed to the opposite direction to that direction. Also, for example, when the acceleration sensor measures a speed change in a direction perpendicular to the traveling direction of the drone 1, the nose direction is changed so that the drone 1 faces in the opposite direction to that direction. This makes it possible to reduce the influence of the measured change in the nose angle and the acceleration. As a result of the first correction process, it does not matter whether the nose direction matches the direction of the planned route. The drone 1 corrects the nose direction by a predetermined reference amount by the first correction program. The reference amount is specified by an angle and a time, and for example, a 1 degree angle change continues for 0.05 seconds. The reference amount of the first correction process A is referred to as the "reference amount A," the reference amount of the first correction process B is referred to as the "reference amount B," and reference amounts A and B are collectively referred to as the "reference amounts."

[0060] The drone 1 adjusts the drone 1 by the return program so that the drone 1 moves in the planned direction on the planned route based on the positioning results by the satellite positioning unit 56. This adjustment to match the nose direction with the planned route is the above-mentioned "return process." Therefore, even if the drone 1 is not proceeding in the planned direction on the planned route due to the above-mentioned first correction process, the drone 1 can move in the planned direction on the planned route by the return program.

[0061] The drone 1 uses an image recognition program to recognize targets to be avoided in images captured by the camera 16. The drone 1 stores, for example, a neural network in the memory unit 52, and recognizes targets to be avoided using the neural network.

[0062] The learning method (machine learning process) will be outlined with reference to Figures 8 and 9. When a large number of image data are input as learning data to a neural network model of a computer (see Figure 8) (step S1 in Figure 9), learning is performed by the neural network algorithm (step S2). The learning data is data showing people in various states.

[0063] An example of the neural network model is a neural network conceptually shown in FIG. 8. Note that neural networks and deep learning are well known, and therefore only an overview will be given in this specification. A neural network is composed of an input layer, one or more hidden layers, and an output layer. Although FIG. 8 shows only one hidden layer, in reality, there are multiple hidden layers. That is, the learning in this embodiment is machine learning (deep learning) using a multi-layer neural network (deep neural network).

[0064] In machine learning, the weights w1a, etc. of the input values ​​input to the hidden layer and the output layer, and the biases (threshold values ​​in each layer) B1, etc. in the input layer, hidden layer, and output layer are adjusted so that the output from the output layer approaches the correct answer. As a result of the learning, a neural network with adjusted weights and biases is generated as learning result data (step S3 in FIG. 9). This learning generates, for example, a neural network for accurately recognizing that an object in an image is a human. The memory unit 52 stores the neural network generated in this manner.

[0065] The drone 1 uses an image recognition program to recognize objects in the captured images.

[0066] The drone 1 performs an avoidance operation based on the recognition result by the image recognition program according to the avoidance program. The drone 1 is configured to perform an avoidance operation when the avoidance target recognized by the recognition program satisfies a predetermined condition.

[0067] For example, the drone 1 performs an avoidance operation when a predetermined condition is satisfied that the distance between the drone 1 and the object to be avoided is within a predetermined distance range. The predetermined distance range is, for example, 5 meters (m). The distance can be measured by any suitable method. For example, the drone 1 may be equipped with a laser range finder, and the distance may be determined based on the output of the laser range finder.

[0068] Hereinafter, the control of the direction of travel of the drone 1 will be described with reference to FIG. 10 and FIG. 11. The planned route of the drone 1 is assumed to be a straight route A1 shown in FIG. 10(a). The autonomous control device 32 outputs the positioning result at a predetermined time interval, such as times t0, t1, t2, and t3, by the satellite positioning unit 56. The predetermined time interval is, for example, 1 second. The drone 1 also measures the change in the nose direction and the change in speed (acceleration) at a predetermined time interval shorter than the output interval of the positioning result, such as times t0, t0.25, t0.5, and t0.75. The predetermined time interval for measuring the change in the nose direction and the change in speed (acceleration) is, for example, four times per second. At time t1, etc., when the positioning result is acquired, the drone 1 performs a return process by a return program. Then, while the positioning result is acquired, a first correction process is performed, for example, at times t0.25, t0.5, and t0.75. When there are changes in both the heading direction and the speed, the inconsistency in the control is resolved by, for example, processing that prioritizes the change in the heading direction or that prioritizes the change in the speed. In this embodiment, when there are changes in both the heading direction and the speed, the change in the heading direction is prioritized, and the first correction processing A is performed.

[0069] As described above, the autonomous control device 32 performs the first correction process while acquiring the positioning result, and performs the return process after acquiring the positioning result. That is, since the first correction process is performed during the return process, the deviation between the planned route A1 and the actual route A1b is relatively small, and becomes a width W2. The width W2 is smaller than the width W1 of the conventional example (see FIG. 32).

[0070] As shown in FIG. 11(a), for example, when the autonomous control device 32 measures a change in the nose direction indicated by the arrow B1 at time t0.25, the autonomous control device 32 performs a first correction process to change the direction indicated by the arrow B2, which is the opposite direction to the change, so as to offset the change. In the example of FIG. 11(a), the autonomous control device 32 performs a return process based on the positioning result at time t1 so that the current position is on the planned route A1 and the traveling direction is the same as the direction of the planned route A1. As the return process, the autonomous control device 32 corrects the nose direction, for example, as indicated by the arrow D1, and controls so that the current position is on the planned route A1 and the traveling direction is the same as the direction of the planned route A1. FIG. 11(a) shows an example in which the positioning result is output at time t1, the return process is started in an extremely short time, and the return process is completed at time t1.05.

[0071] As shown in FIG. 11(b), for example, when the autonomous control device 32 does not measure (detect) a change in the nose direction at time t0.25, but measures acceleration in a direction deviating from the planned route A1, the autonomous control device 32 performs a first correction process as a change in the direction indicated by the arrow C2, which is the opposite direction to the change in position, so as to offset the change in position due to the change in acceleration. In the example of FIG. 11(b), the autonomous control device 32 performs a return process based on the positioning result at time t1 so that the current position is on the planned route and the traveling direction coincides with the direction of the planned route A1. The return process is started, for example, by changing the nose direction by a predetermined angle, and when the current position coincides with the planned route A1, the traveling direction is completed by matching it with the direction of the planned route A1. In this embodiment, the magnitude of the return process is defined as an "adjustment amount". The magnitude of the return process is specified by an angle and a time.

[0072] The control performed by the autonomous control device 32 will be outlined below with reference to the flowcharts of FIGS.

[0073] When the autonomous control device 32 launches the drone 1 (step ST1 in FIG. 12), it acquires an image of the outside (step ST2), performs image recognition on the entire image using a neural network (step ST4), recognizes an object to be avoided in the image (step ST5), and stops proceeding if it determines that the object is within the avoidance distance (step ST6). If there is no object to be avoided in the image or the object is not within the avoidance distance, it determines that the mission is complete (step ST7) and ends control. In parallel with the above steps ST2 to ST6, the drone 1 measures its current position while proceeding along a predetermined route and performing the task (step ST3).

[0074] Next, step ST3 will be described with reference to Fig. 13. When the autonomous control device 32 determines that it is near the turning position (step ST31 in Fig. 13), it performs control near the turning position (step ST40). The turning position is a position where the unmanned vehicle 1 should change its traveling direction, for example, position P in Fig. 2. Position P is a position where the unmanned vehicle 1 should change its traveling direction to transition from route R1 to route R2. Step ST40 will be described later.

[0075] When the autonomous control device 32 determines that it is not near a turning position (step ST31) and measures a change in direction or speed (step ST32), it performs a first correction process (step ST33). Furthermore, when the autonomous control device 32 acquires a positioning result (step ST34) and determines that the current traveling route is not on the planned route or in the planned direction (step ST35), it performs a return process (step ST36). Steps ST32 and ST33 and steps ST34 to ST36 are performed in parallel, and when the timing of the first correction process and the return process coincide, the return process is prioritized. Note that, unlike this embodiment, it may be configured to prioritize the first correction process when the timing of the first correction process and the return process coincide.

[0076] Next, step ST40 will be described with reference to Fig. 14. When the autonomous control device 32 judges that it is near a turning position, it reduces the speed (step ST41 in Fig. 14), when it judges that it is a turning start position (step ST42), it starts turning (step ST43), when it judges that it is in the planned direction (step ST44), it judges whether it is on the planned route (step ST45), and when it is not on the planned route, it adjusts the traveling direction so as to correct the position (step ST46). The vicinity of the turning position is, for example, a position 10 meters before the position where the route should be corrected. The turning start position is position P1 in Fig. 2.

[0077] Second Embodiment Next, a second embodiment will be described with reference to Figures 15 to 17. Note that a description of matters common to the first embodiment will be omitted, and the following description will focus on the differences from the first embodiment.

[0078] As shown in FIG. 15, in the second embodiment, in addition to the first correction process and the return process, the autonomous control unit 40 performs fine correction of the direction using the electronic compass output (hereinafter referred to as the "second correction process").

[0079] The electronic compass measures the heading direction of the drone 1 at a time interval shorter than the output interval of the positioning results by the satellite positioning unit 56. The time interval at which the electronic compass measures the change in the heading direction is, for example, half a second (0.5 seconds). The electronic compass measures the heading direction in a relative relationship with the direction of the earth's magnetic field. The planned direction, which is the planned direction in which the drone 1 will proceed along the planned route A1, is also defined in a relative relationship with the earth's magnetic field. For this reason, the electronic compass can measure the difference between the planned direction and the actual traveling direction.

[0080] The drone 1 stores a second correction program in the memory unit 52 (see FIG. 5). The CPU 50 and the second correction program are an example of a second correction means. The autonomous control device 32 corrects the nose direction of the drone 1 so as to reduce the difference between the planned nose direction and the nose direction measured by the electronic compass (hereinafter referred to as the "deviation of the nose direction"). (This is the above-mentioned "second correction process"). In addition, in case the timing of the first correction process and the second correction process coincide, a priority is defined so that one of the processes is prioritized. In this embodiment, the second correction process is prioritized over the first correction process. In case the timing of the second correction process and the return process coincide, a priority is defined so that one of the processes is prioritized. In this embodiment, the return process is prioritized over the second correction process.

[0081] As shown in FIG. 16(a), for example, when the autonomous control device 32 measures a change in the nose direction indicated by the arrow B1 at time t0.25, the autonomous control device 32 performs a first correction process to change the direction indicated by the arrow B2, which is the opposite direction to the change, so as to offset the change. In the example of FIG. 16(a), the autonomous control device 32 moves along the path indicated by the arrow A2, without returning to a path parallel to the planned path A1, by the first correction process. The autonomous control device 32 measures the deviation of the nose direction by the electronic compass at time t0.5. At time t0.5, the nose direction is the direction indicated by the arrow A2, and measures the deviation of the nose direction. In this case, the autonomous control device 32 corrects the nose direction by a second predetermined reference amount (hereinafter referred to as the "second reference amount"). For example, the second reference amount is an angle change of 1.5 degrees that continues for 0.05 seconds. 16(a), as a result of the second correction process, the traveling direction of the drone 1 coincides with the direction of the planned route A1, but does not coincide with the planned route A1 and is shifted parallel to it. At time t1.0, the autonomous control device 32 acquires the positioning result and corrects the heading direction as shown by the arrow D1, thereby performing a return process so that the current position is on the planned route and the traveling direction coincides with the planned direction.

[0082] FIG. 16(b) shows a state in which the deviation of the nose direction is not eliminated by the second correction process. At time t0.5, the nose direction is the direction shown by the arrow A2, and the autonomous control device 32 measures the deviation of the nose direction. In this case, the autonomous control device 32 corrects the nose direction by a second predetermined reference amount. In the example of FIG. 16(b), as a result of the second correction process, the traveling direction of the unmanned vehicle 1 does not match the direction of the planned route A1, but is the arrow A3. At time t1.0, the autonomous control device 32 acquires the positioning result and corrects the nose direction as shown by the arrow D2, thereby performing a return process so that the current position is on the planned route and the traveling direction matches the planned direction.

[0083] Next, the first correction process, the second correction process, and the return process will be described with reference to FIG. 17. When the autonomous control device 32 judges that it is not near a turning position (step ST31 in FIG. 17) and measures a change in direction or speed (step ST32), it performs the first correction process (step ST33). When the autonomous control device 32 measures the deviation (deviation of the nose direction) between the nose direction and the planned route direction (step ST101), it performs the second correction process (step ST102). When the autonomous control device 32 acquires the positioning result (step ST34) and judges that the current traveling route is not on the planned route or in the planned direction (step ST35), it performs the return process (step ST36). Steps ST32 and ST33, steps ST101 and ST102, and steps ST34 to ST36 are performed in parallel, and when the timings of the first correction process, the second correction process, and the return process coincide, the return process is given the highest priority, followed by the second correction process.

[0084] <Third embodiment> Next, a third embodiment will be described with reference to Figures 18 to 20. Note that a description of matters common to the first and second embodiments will be omitted, and the following description will focus on differences from the first and second embodiments.

[0085] As shown in FIG. 18, in this embodiment, in addition to the first correction process, the second correction process, and the return process, the autonomous control unit 40 also performs fine correction of the direction using Doppler information (hereinafter referred to as the “third correction process”).

[0086] In the third embodiment, in addition to the configuration in the second embodiment, a head direction calculation program, a direction deviation calculation program, and a third correction program are further stored in the memory unit 52 (see FIG. 5). The CPU 50 and the head direction calculation program are an example of a head direction calculation means. The CPU 50 and the direction deviation calculation program are an example of a direction deviation calculation means. The CPU 50 and the third correction program are an example of a third correction means.

[0087] The drone 1 calculates Doppler information indicating the Doppler effect for each positioning satellite 202A, etc., by the nose direction calculation program, and calculates the nose direction based on the Doppler information. For example, if the Doppler information of the positioning satellites 202A and 202B in FIG. 2 indicates that the drone 1 and the positioning satellites 202A and 202B are approaching each other and the approaching speed is different between the positioning satellites 202A and 202B, and the Doppler information of the positioning satellites 202C and 202D indicates that the drone 1 and the positioning satellites 202C and 202D are moving away from each other and the degree of the moving away is different between the positioning satellites 202C and 202D, the direction of travel of the drone 1 can be calculated based on the information. Measurement of the direction using the Doppler information of the positioning radio waves of multiple positioning satellites is well known, so a detailed description will be omitted.

[0088] The drone 1 calculates the deviation between the above-mentioned traveling direction and the direction of the planned route by the direction deviation calculation program. Since the planned route is stored in the memory unit 52, the drone 1 can calculate the deviation between the above-mentioned traveling direction and the direction of the planned route.

[0089] The drone 1 corrects the nose direction of the drone 1 by the third correction program so as to reduce the above deviation. This correction of the nose direction is the above-mentioned "third correction process." The autonomous control device 32 corrects the nose direction by a third predetermined reference amount (hereinafter referred to as the "third reference amount"). For example, the third reference amount is an angle change of 1.5 degrees that continues for 0.05 seconds.

[0090] Since the Doppler information can be acquired before the calculation for acquiring the positioning result converges, the drone 1 can perform the third correction process during the return process that uses the positioning result. A priority order is defined for the case where the timing of the first correction process or the second correction process coincides with the timing of the third correction process. In this embodiment, when the timing of the first correction process or the second correction process coincides with the timing of the third correction process, the third correction process is prioritized.

[0091] Hereinafter, the control of the traveling direction of the drone 1 will be described with reference to FIG. 19. The planned route of the drone 1 is assumed to be a straight route A1 shown in FIG. 19(a). The drone 1 outputs the positioning result by the satellite positioning unit 56 at a predetermined time interval (e.g., once per second), such as times t0, t1, t2, and t3. The drone 1 also measures the change in the nose direction and the change in the speed at a predetermined time interval (e.g., four times per second), such as times t0, t0.25, t0.5, and t0.75. At the time t1 at which the positioning result is acquired, the drone 1 performs a return process by a return program. Then, while acquiring the positioning result, for example, a first correction process is performed at time t0.25, a second correction process is performed at t0.5, and a third correction process is performed at t0.75.

[0092] As described above, the drone 1 performs fine corrections by the first correction process, the second correction process, and the third correction process while acquiring the positioning result, so the deviation between the planned route A1 and the actual route A1c is relatively small, and becomes a width W3. The width W3 is smaller than the width W2 (see FIG. 10) in the first embodiment.

[0093] Next, the first correction process to the third correction process and the return process will be described with reference to FIG. 20. When the autonomous control device 32 judges that it is not near a turning position (step ST31 in FIG. 20) and measures a change in direction or speed (step ST32), it performs the first correction process (step ST33). When the autonomous control device 32 measures the deviation between the nose direction and the planned route direction (step ST101), it performs the second correction process (step ST102). When the autonomous control device 32 acquires Doppler information (step ST201) and judges that the current traveling route is not in the direction of the planned route (step ST202), it performs the third correction process (step ST203). When the autonomous control device 32 acquires the positioning result (step ST34), it performs the return process by the above-mentioned control. When the timing of the above-mentioned first correction process to the third correction process and the return process coincides, the return process is given the highest priority, followed by the third correction process, the second correction process, and the first correction process in that order.

[0094] <Fourth embodiment> Next, a fourth embodiment will be described with reference to Fig. 21 to Fig. 23. Note that the description of the matters common to the first to third embodiments will be omitted, and the description will focus on the points different from the first to third embodiments. In the fourth embodiment, the moving speed is controlled.

[0095] As shown in FIG. 21, in this embodiment, the autonomous control device 32 performs a speed correction process to correct the speed by referring to the acceleration sensor output, and performs a speed return process to return the speed to the planned speed by using Doppler information.

[0096] In the fourth embodiment, in addition to the configuration of any one of the first to third embodiments, a speed correction program and a speed return program are further stored in the memory unit 52 (see FIG. 5). The CPU 50 and the speed correction program are an example of a speed correction means. The CPU 50 and the speed return program are an example of a speed return means. The acceleration sensor constituting the autonomous control device 32 also measures the change in speed in the nose direction. The acceleration sensor measures the change in speed at a time interval shorter than the acquisition interval of Doppler information.

[0097] The drone 1 corrects its speed by using a speed correction program to offset the above-mentioned speed changes. This speed correction is the above-mentioned "speed correction process."

[0098] The drone 1 uses a speed return program to calculate the movement speed of the drone 1 based on the Doppler information, and adjusts the speed so that the movement speed matches the planned speed. This speed adjustment is the "speed return process" described above. Since the orbits of the navigation satellites 202A and the like are known, the traveling speed of the drone 1 can be calculated using the Doppler information. A priority order is defined for cases where the timing of the speed correction process and the speed return process coincide. In this embodiment, when the timing of the speed correction process and the speed return process coincide, the speed return process is given priority.

[0099] Hereinafter, the control of the traveling speed of the drone 1 will be described with reference to FIG. 22. The planned speed of the drone 1 is assumed to be speed V1. The drone 1 outputs the positioning results by the satellite positioning unit 56 at predetermined time intervals (e.g., once per second), such as times t0, t1, t2, and t3. The drone 1 also measures the change in the nose direction and the change in speed at predetermined time intervals (e.g., four times per second), such as times t0, t0.25, t0.5, and t0.75. The drone 1 measures the change in the nose direction speed, and if there is a deviation from the planned speed, performs a speed correction process. The speed correction process is performed only for a predetermined reference speed. The reference speed is, for example, an increase or decrease of 1 meter per second (meter / second).

[0100] Then, the drone 1 performs a speed recovery process based on the Doppler information at predetermined time intervals (e.g., every 0.75 seconds) such as times t0.75, t1.5, and t2.25. If there is a discrepancy between the planned speed and the actual speed even after the speed correction process is performed, the discrepancy is eliminated by the speed recovery process.

[0101] Next, the speed adjustment of the drone 1 will be described with reference to the schematic flow chart of FIG. 23. The speed adjustment is performed in parallel with the adjustment of the traveling direction. When the drone 1 measures a speed change (step ST301 in FIG. 23), it performs a speed correction process (step ST302). When the drone 1 acquires Doppler information (step ST303) and determines that the speed deviates from the planned speed (step ST304), it performs a speed return process (step ST305). If the timing of the speed correction process and the speed return process coincide, the speed return process is given priority. Furthermore, if the timing of the speed correction process or the speed return process coincides with the adjustment of the traveling direction, the adjustment of the traveling direction is given priority.

[0102] <Fifth embodiment> Next, the fifth embodiment will be described with reference to Fig. 24. Note that the description of the matters common to the first to fourth embodiments will be omitted, and the description will focus on the differences from the first to fourth embodiments. In the fifth embodiment, the work such as plowing a field is prioritized in terms of the traveling direction and speed.

[0103] In the fifth embodiment, in addition to the configuration of any one of the first to fourth embodiments, a priority program is further stored in the storage unit 52 (see FIG. 5). The CPU 50 and the priority program are an example of a priority means.

[0104] When the drone 1 receives a signal related to the movement of the drone 1 from a task control unit 62 that controls tasks performed by the drone 1, the drone 1 is configured to prioritize the signal from the task control unit 62 over control for reducing the deviation between the planned route and the actual travel route according to a priority program. The task control unit 62 is an example of a task control means. The task control unit 62 is also called a task module. In other words, even if a change in direction or movement is measured, if it is due to a signal from the task module, the drone 1 does not adjust the travel direction by a first correction process or the like.

[0105] Next, the control of the drone 1 will be described with reference to the schematic flowchart of Fig. 24. The flowchart of Fig. 24 is an example in which a priority program is applied to the second embodiment. If the autonomous control device 32 has acquired a signal from the work module (step ST401), it prioritizes the signal from the work module (step ST402). On the other hand, if the autonomous control device 32 has not acquired a signal from the work module (step ST401), it performs the processing from step ST31 onwards.

[0106] Unlike this embodiment, the first modification process, the second modification process, or the third modification process may not be performed, and the return process and the priority process may be combined.

[0107] Sixth embodiment Next, a sixth embodiment will be described with reference to Figures 25 to 27. Note that a description of matters common to the first to fifth embodiments will be omitted, and the following description will focus on differences from the first to fifth embodiments.

[0108] As shown in FIG. 25, in this embodiment, the autonomous control device 32 corrects the magnitude of the correction by the first correction process A, the first correction process B, and the second correction process based on the magnitude of the adjustment by the return process. The reference amount A, the reference amount B, and the second reference amount are increased or decreased so that the magnitude (adjustment amount) of the adjustment by the return process is minimized. The initial settings of the reference amount A, the reference amount B, and the second reference amount are specified as amounts that are assumed not to recover the deviation from the planned route. The initial settings are, for example, amounts smaller than the adjustment amount when only the return process is performed for correcting the traveling direction of the unmanned vehicle 1. Therefore, basically, the adjustment amount is reduced by increasing the reference amount A, the reference amount B, and the second reference amount. The smaller the adjustment amount, the greater the degree to which the actual traveling route of the unmanned vehicle 1 matches the planned route A1.

[0109] In the sixth embodiment, in addition to the configuration in any one of the first to fifth embodiments, a correction program is stored in a storage unit 52 (see FIG. 5). The CPU 50 and the correction program are an example of a correction means.

[0110] The drone 1 corrects the magnitude of the correction of the nose direction by the first correction means and the second correction means based on the magnitude of the adjustment (adjustment amount) in the return process by a correction program. As described above, the first correction process corrects the nose direction by a predetermined reference amount. The second correction process corrects the nose direction by a predetermined second reference amount. Here, the first reference amount etc. is not necessarily appropriate. In this regard, the drone 1 performs a correction to increase or decrease the first reference amount and the second reference amount by a correction program, thereby minimizing the adjustment amount by the return process. For the first correction process, the drone 1 corrects the reference amount separately for the first correction process A and the second correction process B.

[0111] The correction of the first correction process A will be described with reference to Fig. 26. For example, as shown in Fig. 26, assume that at time t0.25, a change in the nose direction indicated by arrow B1 is measured by the gyro sensor. If the reference amount A of the first correction process A is too small, the nose direction will be too small, as indicated by arrow B2A. As a result, the amount of adjustment by the return process will be large. The same applies to the first correction process B and the second correction process.

[0112] In this regard, the autonomous control device 32 increases or decreases each of the reference amount A, the reference amount B, and the second reference amount, and corrects the adjustment amount so that it is minimized. In correcting the reference amount A, the reference amount B, and the second reference amount, the reference amount A, the reference amount B, and the second reference amount when the adjustment amount is minimized are called "optimum values." The optimum values ​​are the reference amount A, the reference amount B, and the second reference amount when the adjustment amount shows a minimum value when the reference amount A, the reference amount B, and the second reference amount are graphed in correspondence with the adjustment amount.

[0113] 27, for example, the reference amount A is corrected from time t2 to time t5. The times t1 to t5 are timings when the return process is performed. Since the adjustment amount is determined by the return process, the corrected reference amount A is applied in the next return process.

[0114] In the example of FIG. 27, the adjustment amount at time t1 is 0.3 seconds. At time t2, the adjustment amount is decreased by increasing the reference amount A. If the reference amount A is such that an angle change of 1 degree continues for 0.05 seconds, the reference amount A is increased and corrected to, for example, an angle change of 1 degree continues for 0.06 seconds. Assume that the adjustment amount is decreased as a result of increasing the reference amount A at the same rate at times t3 and t4. However, at time t5, the adjustment amount is increased as a result of increasing the reference amount A. This means that the reference amount A at time t4 was the optimal value. Therefore, the autonomous control device 32 sets the reference amount A to the condition at time t4.

[0115] Next, if the reference amount B is such that an angle change of 1 degree continues for 0.05 seconds, the reference amount B is increased at time t6, and corrected to, for example, an angle change of 1 degree continues for 0.06 seconds. Assume that the reference amount B is also increased at the same rate from time t7 to time t9, resulting in a decrease in the adjustment amount. However, at time t10, the adjustment amount has instead increased as a result of increasing the reference amount B. This means that the reference amount B at time t9 was the optimal value. Therefore, the autonomous control device 32 sets the reference amount B to the condition at time t9.

[0116] Next, if the second reference amount is a 1.5 degree angle change that continues for 0.05 seconds, the second reference amount is increased at time t11, and corrected to, for example, a 1.5 degree angle change that continues for 0.06 seconds. Assume that the second reference amount is also increased at the same rate at times t12 to t14, resulting in a decrease in the adjustment amount. However, at time t15, the second reference amount is increased, resulting in an increase in the adjustment amount. This means that the second reference amount at time t14 was the optimal value. Therefore, the autonomous control device 32 sets the second reference amount to the condition at time t14.

[0117] As described above, the amount of adjustment can be minimized by setting the multiple reference quantities, namely, reference quantity A, reference quantity B, and second reference quantity, to optimal values, respectively. This is because the first correction process A, first correction process B, and second correction process are correction processes based on outputs from different sensors, namely, the gyro sensor, the acceleration sensor, and the electronic compass, respectively.

[0118] In this embodiment, the correction of the reference amount A, the reference amount B, and the second reference amount is performed by increasing the time, but differently, the correction may be performed by increasing the angle, or both the time and the angle may be increased.

[0119] As described above, basically, the adjustment amount becomes smaller by increasing the reference amount A, the reference amount B, and the second reference amount, but depending on the actual situation of the place where the unmanned vehicle 1 travels, the adjustment amount may increase by increasing the reference amount A, etc. In this regard, the autonomous control device 32 judges whether an increase or decrease of the reference amount is appropriate. For example, as shown in FIG. 28, it is assumed that the adjustment amount increases by increasing the reference amount A at time t2. This means that the increase of the reference amount A is inappropriate as a correction of the reference amount A. In this case, the autonomous control device 32 decreases the reference amount A at time t3, correcting it to, for example, a 1 degree angle change lasting for 0.04 seconds. It is assumed that the adjustment amount also decreases at t4 as a result of decreasing the reference amount A at the same rate. However, at time t5, the adjustment amount increases as a result of decreasing the reference amount A. This means that the reference amount A at time t4 was the optimal value. Therefore, the autonomous control device 32 sets the reference amount A to the condition at time t4. In addition, in both cases where the adjustment amount increases, whether the reference amount A is increased or decreased, the current reference amount A is the optimal value, so the autonomous control device 32 maintains the current reference amount A. The same applies to the reference amount A and the second reference amount.

[0120] Hereinafter, the correction process of the reference amount will be described with reference to the flowchart of FIG. 29. The correction process of the reference amount is performed at an appropriate timing in parallel with the correction process of the nose direction of the drone 1. The autonomous control device 32 increases or decreases the reference amount A of the first correction process A (step ST501 of FIG. 29), and when it is determined that the reference amount A is an optimal value (step ST502), it maintains the reference amount A. Next, the autonomous control device 32 increases or decreases the reference amount B of the first correction process B (step ST503), and when it is determined that the reference amount B is an optimal value (step ST504), it maintains the reference amount B. Next, the autonomous control device 32 increases or decreases the second reference amount of the second correction process (step ST505), and when it is determined that the second reference amount is an optimal value (step ST506), it maintains the second reference amount. When it is determined that the termination condition is satisfied (step ST507), the autonomous control device 32 terminates. If the autonomous control device 32 determines that the end condition is not satisfied (step ST507), it repeats the processing from step ST501 to step ST506.

[0121] <Seventh embodiment> Next, a seventh embodiment will be described with reference to Fig. 30 and Fig. 31. Note that a description of matters common to the first to sixth embodiments will be omitted, and the description will focus on the differences from the first to sixth embodiments.

[0122] In the seventh embodiment, in addition to the configuration of any one of the first to sixth embodiments, a route recording program, a difference calculation program, and a difference reduction program are stored in the memory unit 52 (see FIG. 5). The CPU 50 and the route recording program are an example of a route recording means for recording an actual route, which is the actual route traveled by the unmanned vehicle 1. The CPU 50 and the difference calculation program are an example of a difference calculation means for calculating the difference between the planned route and the actual route. The CPU 50 and the difference reduction program are an example of a difference reduction means for reducing the difference between the planned route and the actual route by controlling the unmanned vehicle 1 when moving along the next planned route based on the difference calculated by the difference calculation program.

[0123] For example, as shown in FIG. 30, the planned route is assumed to be a route Ra in the greenhouse 230. The drone 1 moves while measuring the current position of the drone 1 by RTK positioning, but the route Rb along which the drone 1 actually moves does not completely match the route Ra. This is particularly noticeable at a turning position. Therefore, the drone 1 records the route Rb by a route recording program. Then, the drone 1 calculates the difference between the route Ra and the route Rb by a difference calculation program. Then, the drone 1 is configured to reduce the movement of the drone 1 by a difference reduction program so as to reduce the difference between the route Ra and the actual route Rb the next time the drone 1 travels along the route Ra. The movement of the drone 1 is, for example, the speed of the drone 1, the angle of turning, and the speed. As a result, when the drone 1 travels along the route Ra multiple times, the difference between the route Ra and the actual route Rb is reduced each time the drone 1 travels, thereby improving the efficiency of travel.

[0124] The present invention is not limited to the above-described embodiments, and modifications and improvements within the scope of the present invention that can achieve the object of the present invention are included in the present invention. [Explanation of symbols]

[0125] 1. Vehicle (drone) 10 Vehicle body 12 Antenna 14 Antenna 16 Cameras 18L,18R front wheel 20 Steering system 22L,22R rear wheel 24 Shaft 26 Engine 28 Transmission 32 Autonomous Control Device 202A, 202B, 202C, 202D Navigation satellites

Claims

1. An autonomous control device for controlling a mobile device capable of autonomous movement, comprising: A positioning means for measuring a current position using positioning radio waves from navigation satellites constituting a Global Navigation Satellite System (GNSS); a direction change measuring means for measuring a change in a heading direction of the mobile device at a time interval shorter than an output interval of the positioning result by the positioning means; a first correcting means for correcting the heading of the mobile device so as to counteract the change in heading measured by the heading change measuring means; a return means for adjusting the movement of the mobile device so as to move in a predetermined direction on a predetermined route based on a positioning result by the positioning means; having The positioning means is configured to perform RTK (Real Time Kinematic) positioning and receive GNSS correction data from a communication base station for a mobile terminal, and further the correction by the first correcting means and the adjustment by the returning means are performed in parallel, the correction by the first correcting means is performed during the adjustment by the returning means, and when the timing of the correction by the first correcting means and the timing of the adjustment by the returning means coincide, either the correction by the first correcting means or the adjustment by the returning means is given priority. Autonomous control device.

2. a speed change measuring means for measuring a change in a moving speed of the mobile device in a direction perpendicular to a traveling direction of the mobile device at a time interval shorter than an output interval of the positioning result by the positioning means, the first correction means is configured to correct the heading direction of the mobile device so as to offset a change in a moving position caused by a change in the heading direction measured by the direction change measuring means and a change in the moving speed measured by the speed change measuring means; The autonomous control device according to claim 1 .

3. a relative direction measuring means for measuring the heading direction of the mobile device in a relative relationship with the direction of geomagnetic field at a time interval shorter than an output interval of the positioning result by the positioning means; a second correcting means for correcting the heading direction of the mobile device so as to reduce a difference between the planned direction defined in a relative relationship with the direction of the geomagnetic field and the heading direction measured by the relative direction measuring means; The autonomous control device according to claim 1 , further comprising:

4. a heading direction calculation means for calculating a heading direction of the mobile device based on Doppler information indicating a Doppler effect of the positioning radio wave generated by a relative movement between the navigation satellite and the mobile device; a direction deviation calculation means for calculating a deviation between the nose direction calculated by the nose direction calculation means and the planned direction; a third correction means for correcting a heading direction of the mobile device so as to reduce the deviation calculated by the direction deviation calculation means; The autonomous control device according to claim 3 , further comprising:

5. The speed change measuring means is further configured to measure a change in speed in the expected direction at a time interval shorter than an acquisition interval of Doppler information indicating a Doppler effect of the positioning radio wave generated by a relative movement between the navigation satellite and the mobile device, and further a speed correction means for correcting the speed of the mobile device so as to offset the change in the speed measured by the speed change measuring means; a speed recovery means for calculating a moving speed of the mobile device based on the Doppler information and adjusting the moving speed of the mobile device so that the moving speed coincides with a scheduled speed; The autonomous control device according to claim 2 , further comprising:

6. a priority means for prioritizing a signal from a work control means for controlling a work performed by the mobile device when the mobile device receives a signal related to the movement of the mobile device from the work control means; The autonomous control device according to any one of claims 1 to 5.

7. a correction means for correcting a magnitude of the correction of the nose direction by the first correction means and / or the second correction means based on a magnitude of the adjustment by the return means, The autonomous control device according to claim 3 .

8. a route recording means for recording an actual route which is an actual route traveled by the mobile device; a difference calculation means for calculating a difference between the planned route and the actual route; a difference reduction means for controlling the moving device to reduce the difference between the planned route and the actual route when the moving device moves along the planned route next time, based on the difference calculated by the difference calculation means; The autonomous control device according to claim 1 .

9. A positioning means for measuring a current position by using positioning radio waves from a navigation satellite, A control method for controlling a mobile device capable of autonomous movement by an autonomous control device, comprising: a direction change measuring step of measuring a change in a heading direction of the mobile device at a time interval shorter than an output interval of the positioning result by the positioning means; a first correcting step of correcting the heading direction of the mobile device so as to counteract the change in the heading direction measured in the direction change measuring step; a return step of adjusting the mobile device so that the mobile device moves in a planned direction on a planned route based on a positioning result by the positioning means; Implemented the following: The positioning means is configured to perform RTK (Real Time Kinematic) positioning and receive GNSS correction data from a communication base station for a mobile terminal; The first correction step and the return step are performed in parallel, the correction in the first correction step is performed during the adjustment in the return step, and when the timing of the correction in the first correction step and the timing of the adjustment in the return step coincide, either the correction in the first correction step or the adjustment in the return step is prioritized. Autonomous control method.

10. A computer that controls an autonomous control device for controlling a mobile device capable of autonomous movement, a positioning means for measuring a current position by RTK (Real Time Kinematic) positioning using positioning radio waves received from navigation satellites and GNSS correction data received from a communication base station for a mobile terminal; a direction change measuring means for measuring a change in a heading direction of the mobile device at a time interval shorter than an output interval of the positioning result by the positioning means; a first correcting means for correcting the heading of the mobile device so as to counteract the change in heading measured by the heading change measuring means; and an autonomous control program for causing the mobile device to function as a return means for adjusting the mobile device so that the mobile device moves in a predetermined direction along a predetermined route based on a positioning result by the positioning means, an autonomous control program configured to perform the correction by the first correction means and the adjustment by the return means in parallel, to perform the correction by the first correction means during the adjustment by the return means, and to prioritize either the correction by the first correction means or the adjustment by the return means when the timing of the correction by the first correction means and the adjustment by the return means coincide.

Images