Classifications

• • G—PHYSICS
  • G05—CONTROLLING; REGULATING
  • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
  • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
  • G05D1/60—Intended control result
  • G05D1/646—Following a predefined trajectory, e.g. a line marked on the floor or a flight path
• • A—HUMAN NECESSITIES
  • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
  • A01B—SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL
  • A01B69/00—Steering of agricultural machines or implements; Guiding agricultural machines or implements on a desired track
• • A—HUMAN NECESSITIES
  • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
  • A01B—SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL
  • A01B69/00—Steering of agricultural machines or implements; Guiding agricultural machines or implements on a desired track
  • A01B69/001—Steering by means of optical assistance, e.g. television cameras
• • A—HUMAN NECESSITIES
  • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
  • A01B—SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL
  • A01B69/00—Steering of agricultural machines or implements; Guiding agricultural machines or implements on a desired track
  • A01B69/007—Steering or guiding of agricultural vehicles, e.g. steering of the tractor to keep the plough in the furrow
  • A01B69/008—Steering or guiding of agricultural vehicles, e.g. steering of the tractor to keep the plough in the furrow automatic
• • G—PHYSICS
  • G01—MEASURING; TESTING
  • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
  • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
  • G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
• • G—PHYSICS
  • G05—CONTROLLING; REGULATING
  • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
  • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
  • G05D1/20—Control system inputs
  • G05D1/24—Arrangements for determining position or orientation
  • G05D1/242—Means based on the reflection of waves generated by the vehicle
• • G—PHYSICS
  • G05—CONTROLLING; REGULATING
  • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
  • G05D2107/00—Specific environments of the controlled vehicles
  • G05D2107/20—Land use
  • G05D2107/21—Farming, e.g. fields, pastures or barns
• • G—PHYSICS
  • G05—CONTROLLING; REGULATING
  • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
  • G05D2109/00—Types of controlled vehicles
  • G05D2109/10—Land vehicles
• • G—PHYSICS
  • G05—CONTROLLING; REGULATING
  • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
  • G05D2111/00—Details of signals used for control of position, course, altitude or attitude of land, water, air or space vehicles
  • G05D2111/10—Optical signals
  • G05D2111/17—Coherent light, e.g. laser signals

Definitions

• the present disclosure relates to a work vehicle and a method of controlling the work vehicle.
• ICT Information and Communication Technology
• IoT Internet of Things
• work vehicles have been put into practical use that use positioning systems such as GNSS (Global Navigation Satellite System) that can perform precise positioning to automatically steer the vehicle.
• GNSS Global Navigation Satellite System
• Patent Document 1 discloses an example of a work vehicle that uses LiDAR to automatically travel between rows of crops in a field.
• SLAM Simultaneous Localization and Mapping
• a work vehicle autonomously navigates between multiple crop rows.
• the work vehicle includes an external sensor that outputs sensor data indicating a distribution of features around the work vehicle, and a control device that controls automatic travel of the work vehicle.
• the control device detects two rows of crops existing on both sides of the work vehicle based on the sensor data, and causes the work vehicle to travel along a route between the two rows of crops.
• the control device detects an end of at least a side of the crop row corresponding to the turning direction among the two crop rows based on the sensor data while traveling, the control device is configured to detect an end of the crop row on the side corresponding to the turning direction based on the sensor data.
• a fixed coordinate system and a target point for the turning movement are set. The control device controls the turning movement toward the target point based on the coordinate system.
• Computer-readable storage media may include volatile storage media or non-volatile storage media.
• the device may be composed of multiple devices. When a device is composed of two or more devices, the two or more devices may be arranged within one device, or may be arranged separately within two or more separate devices. .
• FIG. 1 is a side view schematically showing an example of a work vehicle and an implement connected to the work vehicle.
• FIG. 2 is a block diagram showing an example of the configuration of a work vehicle and an implement. It is a schematic diagram when a LiDAR sensor is seen from the side direction of a work vehicle. It is a schematic diagram when a LiDAR sensor is viewed from vertically above.
• FIG. 2 is a block diagram showing a configuration example of a LiDAR sensor.
• FIG. 1 is a diagram schematically showing an example of an environment in which a work vehicle travels.
• FIG. 2 is a perspective view schematically showing an example of the environment around the work vehicle.
• FIG. 2 is a diagram schematically showing an example of a travel route of a work vehicle.
• FIG. 1 is a side view schematically showing an example of a work vehicle and an implement connected to the work vehicle.
• FIG. 2 is a block diagram showing an example of the configuration of a work vehicle and an implement. It is a schematic
• FIG. 7 is a diagram schematically showing another example of a travel route of a work vehicle.
• FIG. 3 is a diagram for explaining a method of controlling the travel of a work vehicle in inter-row travel mode. It is a figure showing an example of an obstacle map.
• FIG. 7 is a diagram showing another example of an obstacle map.
• FIG. 3 is a diagram for explaining a process of detecting two tree rows based on an obstacle map.
• FIG. 3 is a diagram for explaining an example of a method for setting a turning coordinate system and a target point.
• FIG. 7 is another diagram for explaining an example of a method for setting a turning coordinate system and a target point.
• FIG. 3 is a diagram for explaining the operation of the work vehicle in the turning mode. 2 is a flowchart showing a specific example of a travel control method by the control device.
• FIG. 3 is a diagram illustrating an example of a situation where a work vehicle passes through a row of trees. It is a figure which shows an example of the operation
• FIG. 7 is a diagram for explaining an example of an operation of correcting a target point using an enlarged obstacle map.
• FIG. 7 is a diagram for explaining another example of an operation for correcting a target point.
• It is a flow chart which shows an example of operation of a control device when performing correction processing of a target point.
• FIG. 7 is a diagram illustrating an example in which a turning route is corrected while maintaining a target point. It is a flowchart which shows an example of the method of setting a target point based on an environmental map.
• work vehicle means a vehicle used to perform work at a work site.
• a "work site” is any place where work can be performed, such as a field, a forest, or a construction site.
• a "field” is any place where agricultural operations can be performed, such as an orchard, a field, a rice field, a grain farm, or a pasture.
• the work vehicle may be an agricultural machine such as a tractor, a rice transplanter, a combine harvester, a riding management machine, or a riding mower, or a vehicle used for purposes other than agriculture, such as a construction work vehicle or a snowplow.
• the work vehicle may be configured to be able to mount an implement (also referred to as a "work machine” or “work device”) depending on the content of the work on at least one of the front and rear parts of the work vehicle.
• an implement also referred to as a "work machine” or “work device”
• work travel The movement of a work vehicle while performing work using an implement is sometimes referred to as "work travel.”
• Automatic driving means controlling the running of a vehicle by the function of a control device, without manual operation by the driver.
• automatic driving not only the movement of the vehicle but also the operation of the work (for example, the operation of the implement) may be automatically controlled.
• the control device can control at least one of steering necessary for running the vehicle, adjustment of running speed, starting and stopping of running.
• the control device may control operations such as raising and lowering the implement, starting and stopping the operation of the implement, and the like.
• Driving by automatic driving may include not only driving a vehicle along a predetermined route toward a destination, but also driving the vehicle to follow a tracking target.
• a vehicle that performs automatic driving may run partially based on instructions from a user. Furthermore, in addition to the automatic driving mode, a vehicle that performs automatic driving may operate in a manual driving mode in which the vehicle travels by manual operation by the driver.
• ⁇ Automatic steering'' refers to steering a vehicle not manually but by the action of a control device. Part or all of the control device may be external to the vehicle. Communication such as control signals, commands, or data may occur between a control device external to the vehicle and the vehicle.
• a self-driving vehicle may run autonomously while sensing the surrounding environment without any human involvement in controlling the vehicle's driving. Vehicles that are capable of autonomous driving can run unmanned. Obstacle detection and obstacle avoidance operations may be performed during autonomous driving.
• the “external world sensor” is a sensor that senses the external state of the work vehicle.
• external sensors include LiDAR sensors, cameras (or image sensors), laser range finders (also referred to as “range sensors”), ultrasonic sensors, millimeter wave radars, and magnetic sensors.
• a “crop row” is a row of crops, trees, and other plants that grow in rows in a field such as an orchard or field, or in a forest.
• "crop row” is a concept that includes “tree row”.
• the "obstacle map” is local map data that expresses the positions or areas of objects around the work vehicle in a predetermined coordinate system.
• the coordinate system defining the obstacle map may be, for example, a vehicle coordinate system fixed to the work vehicle or a world coordinate system (eg, a geographic coordinate system) fixed to the earth.
• the obstacle map may include information other than position (for example, attribute information) regarding objects existing around the work vehicle.
• Obstacle maps can be represented in various formats, such as grid maps or point cloud maps.
• the work vehicle is a tractor used for agricultural work in a field such as an orchard.
• the technology of the present disclosure can be applied not only to tractors but also to other types of agricultural machines, such as rice transplanters, combines, riding management machines, and riding lawn mowers.
• the technology of the present disclosure can also be applied to work vehicles used for purposes other than agriculture, such as construction work vehicles or snowplows.
• FIG. 1 is a side view schematically showing an example of a work vehicle 100 and an implement 300 connected to the work vehicle 100.
• Work vehicle 100 in this embodiment can operate in both manual driving mode and automatic driving mode. In the automatic driving mode, the work vehicle 100 can run unmanned.
• the work vehicle 100 automatically travels in an environment where a plurality of rows of crops (for example, rows of trees) are planted, such as an orchard such as a vineyard or a field.
• the work vehicle 100 includes a vehicle body 101, a prime mover (engine) 102, and a transmission 103.
• the vehicle body 101 is provided with a traveling device including wheels with tires 104 and a cabin 105.
• the traveling device includes four wheels 104, axles for rotating the four wheels, and a braking device (brake) for braking each axle.
• the wheels 104 include a pair of front wheels 104F and a pair of rear wheels 104R.
• a driver's seat 107, a steering device 106, an operation terminal 200, and a group of switches for operation are provided inside the cabin 105.
• One or both of the front wheel 104F and the rear wheel 104R may be replaced with a plurality of wheels (crawlers) equipped with tracks instead of wheels with tires.
• the work vehicle 100 includes a plurality of external sensors that sense the surroundings of the work vehicle 100.
• the external sensors include multiple LiDAR sensors 140, multiple cameras 120, and multiple obstacle sensors 130.
• the cameras 120 may be provided, for example, on the front, rear, left and right sides of the work vehicle 100. Camera 120 photographs the environment around work vehicle 100 and generates image data. Images acquired by camera 120 may be transmitted to a terminal device for remote monitoring, for example. The image may be used to monitor work vehicle 100 during unmanned operation.
• the cameras 120 are provided as necessary, and the number thereof is arbitrary.
• the LiDAR sensor 140 is an example of an external sensor that outputs sensor data indicating the distribution of features around the work vehicle 100.
• two LiDAR sensors 140 are located on the cabin 105 at the front and rear.
• the LiDAR sensor 140 may be provided at another location (eg, at the lower front of the vehicle body 101). While the work vehicle 100 is traveling, each LiDAR sensor 140 collects sensor data indicating the distance and direction to each measurement point of an object in the surrounding environment, or the two-dimensional or three-dimensional coordinate value of each measurement point. is output repeatedly.
• the number of LiDAR sensors 140 is not limited to two, but may be one or three or more.
• the LiDAR sensor 140 may be configured to output two-dimensional or three-dimensional point cloud data as sensor data.
• point cloud data broadly means data indicating the distribution of a plurality of reflection points observed by the LiDAR sensor 140.
• the point cloud data may include, for example, information indicating the coordinate values of each reflection point in a two-dimensional space or three-dimensional space, or the distance and direction of each reflection point.
• the point cloud data may include information on the brightness of each reflection point.
• the LiDAR sensor 140 may be configured to repeatedly output point cloud data, for example, at a preset period.
• the external sensor may include one or more LiDAR sensors 140 that output point cloud data as sensor data.
• the sensor data output from the LiDAR sensor 140 is processed by a control device that controls automatic travel of the work vehicle 100.
• the control device can sequentially generate an obstacle map indicating the distribution of objects existing around the work vehicle 100 based on sensor data output from the LiDAR sensor 140 while the work vehicle 100 is traveling.
• the control device can also use an algorithm such as SLAM to connect obstacle maps during automatic driving to generate an environmental map.
• the control device can also estimate the position and orientation of work vehicle 100 (ie, self-position estimation) by matching the sensor data and the environmental map.
• the plurality of obstacle sensors 130 shown in FIG. 1 are provided at the front and rear of the cabin 105. Obstacle sensor 130 may also be placed at other locations. For example, one or more obstacle sensors 130 may be provided at arbitrary positions on the side, front, and rear of the vehicle body 101. Obstacle sensor 130 may include, for example, a laser scanner or an ultrasonic sonar. Obstacle sensor 130 is used to detect surrounding obstacles during automatic driving and to stop work vehicle 100 or take a detour.
• the work vehicle 100 further includes a GNSS unit 110.
• GNSS is a general term for satellite positioning systems such as GPS (Global Positioning System), QZSS (Quasi-Zenith Satellite System, such as Michibiki), GLONASS, Galileo, and BeiDou.
• the GNSS unit 110 receives satellite signals (also referred to as GNSS signals) transmitted from a plurality of GNSS satellites, and performs positioning based on the satellite signals. Although the GNSS unit 110 in this embodiment is provided in the upper part of the cabin 105, it may be provided in another position.
• GNSS unit 110 includes an antenna for receiving signals from GNSS satellites and processing circuitry.
• the work vehicle 100 in this embodiment is used in an environment where a plurality of trees grow, such as a vineyard, where it is difficult to use GNSS.
• positioning is mainly performed using the LiDAR sensor 140.
• positioning may be performed using the GNSS unit 110.
• the GNSS unit 110 may include an inertial measurement unit (IMU). Signals from the IMU can be used to supplement the position data.
• the IMU can measure the tilt and minute movements of the work vehicle 100. By using data acquired by the IMU to supplement position data based on satellite signals, positioning performance can be improved.
• the prime mover 102 may be, for example, a diesel engine.
• An electric motor may be used instead of a diesel engine.
• Transmission device 103 can change the propulsive force and moving speed of work vehicle 100 by shifting. The transmission 103 can also switch the work vehicle 100 between forward movement and reverse movement.
• the steering device 106 includes a steering wheel, a steering shaft connected to the steering wheel, and a power steering device that assists steering with the steering wheel.
• the front wheel 104F is a steered wheel, and by changing its turning angle (also referred to as a "steering angle"), the traveling direction of the work vehicle 100 can be changed.
• the steering angle of the front wheels 104F can be changed by operating the steering wheel.
• the power steering device includes a hydraulic device or an electric motor that supplies an auxiliary force to change the steering angle of the front wheels 104F. When automatic steering is performed, the steering angle is automatically adjusted by the power of a hydraulic system or an electric motor under control from a control device disposed within work vehicle 100.
• a coupling device 108 is provided at the rear of the vehicle body 101.
• the coupling device 108 includes, for example, a three-point support device (also referred to as a "three-point link” or “three-point hitch"), a PTO (Power Take Off) shaft, a universal joint, and a communication cable.
• the implement 300 can be attached to and detached from the work vehicle 100 by the coupling device 108.
• the coupling device 108 can change the position or posture of the implement 300 by raising and lowering the three-point link using, for example, a hydraulic device. Further, power can be sent from the work vehicle 100 to the implement 300 via the universal joint.
• the work vehicle 100 can cause the implement 300 to perform a predetermined work while pulling the implement 300.
• the coupling device may be provided at the front of the vehicle body 101. In that case, an implement can be connected to the front of the work vehicle 100.
• the implement 300 shown in FIG. 1 is a sprayer that sprays chemicals on crops, the implement 300 is not limited to a sprayer. Work with any implement, such as a mower, seeder, spreader, rake, baler, harvester, plow, harrow, or rotary. It can be used by connecting to the vehicle 100.
• the work vehicle 100 shown in FIG. 1 is capable of manned operation, it may also support only unmanned operation. In that case, components necessary only for manned operation, such as the cabin 105, the steering device 106, and the driver's seat 107, may not be provided in the work vehicle 100.
• the unmanned work vehicle 100 can run autonomously or by remote control by a user.
• FIG. 2 is a block diagram showing a configuration example of the work vehicle 100 and the implement 300.
• Work vehicle 100 and implement 300 can communicate with each other via a communication cable included in coupling device 108 .
• Work vehicle 100 can also communicate with terminal device 400 for remote monitoring via network 80 .
• the terminal device 400 is any computer such as a personal computer (PC), a laptop computer, a tablet computer, or a smartphone.
• the work vehicle 100 in the example of FIG. 2 includes a GNSS unit 110, a camera 120, an obstacle sensor 130, a LiDAR sensor 140, and an operation terminal 200, as well as a sensor group 150 that detects the operating state of the work vehicle 100, and a travel control system 160. , a communication device 190, an operation switch group 210, and a drive device 240. These components are communicatively connected to each other via a bus.
• the GNSS unit 110 includes a GNSS receiver 111, an RTK receiver 112, an inertial measurement unit (IMU) 115, and a processing circuit 116.
• Sensor group 150 includes a steering wheel sensor 152, a turning angle sensor 154, and an axle sensor 156.
• Travel control system 160 includes a storage device 170 and a control device 180.
• the control device 180 includes a plurality of electronic control units (ECUs) 181 to 184.
• the implement 300 includes a drive device 340, a control device 380, and a communication device 390. Note that FIG. 2 shows components that are relatively highly relevant to the automatic driving operation of the work vehicle 100, and illustration of other components is omitted.
• the GNSS receiver 111 in the GNSS unit 110 receives satellite signals transmitted from multiple GNSS satellites, and generates GNSS data based on the satellite signals.
• GNSS data is generated in a predetermined format, such as NMEA-0183 format.
• GNSS data may include, for example, values indicating the identification number, elevation, azimuth, and reception strength of each satellite from which the satellite signal was received.
• the GNSS unit 110 may position the work vehicle 100 using RTK (Real Time Kinematic)-GNSS.
• RTK Real Time Kinematic
• a correction signal transmitted from a reference station is used in addition to satellite signals transmitted from multiple GNSS satellites.
• the reference station may be installed near a work site where work vehicle 100 travels for work (for example, within 10 km from work vehicle 100).
• the reference station generates, for example, a correction signal in RTCM format based on satellite signals received from a plurality of GNSS satellites, and transmits it to the GNSS unit 110.
• RTK receiver 112 includes an antenna and a modem, and receives the correction signal transmitted from the reference station.
• the processing circuit 116 of the GNSS unit 110 corrects the positioning result by the GNSS receiver 111 based on the correction signal.
• RTK-GNSS By using RTK-GNSS, it is possible to perform positioning with an accuracy of a few centimeters, for example.
• Location information including latitude, longitude, and altitude information is obtained through highly accurate positioning using RTK-GNSS.
• GNSS unit 110 calculates the position of work vehicle 100 at a frequency of about 1 to 10 times per second, for example.
• the positioning method is not limited to RTK-GNSS, and any positioning method (interferometric positioning method, relative positioning method, etc.) that can obtain position information with the necessary accuracy can be used.
• positioning may be performed using VRS (Virtual Reference Station) or DGPS (Differential Global Positioning System).
• the GNSS unit 110 in this embodiment further includes an IMU 115.
• IMU 115 may include a 3-axis acceleration sensor and a 3-axis gyroscope.
• the IMU 115 may include an orientation sensor such as a 3-axis geomagnetic sensor.
• IMU 115 functions as a motion sensor and can output signals indicating various quantities such as acceleration, speed, displacement, and posture of work vehicle 100.
• Processing circuit 116 can estimate the position and orientation of work vehicle 100 with higher accuracy based on the signal output from IMU 115 in addition to the satellite signal and correction signal.
• the signal output from IMU 115 may be used to correct or supplement the position calculated based on the satellite signal and the correction signal.
• IMU 115 outputs signals more frequently than GNSS receiver 111.
• the IMU 115 outputs signals at a frequency of about tens to thousands of times per second. Using the high-frequency signal, the processing circuit 116 can measure the position and orientation of the work vehicle 100 at a higher frequency (eg, 10 Hz or more). Instead of the IMU 115, a 3-axis acceleration sensor and a 3-axis gyroscope may be provided separately. IMU 115 may be provided as a separate device from GNSS unit 110.
• the camera 120 is an imaging device that photographs the environment around the work vehicle 100.
• the camera 120 includes an image sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor).
• Camera 120 may also include an optical system including one or more lenses, and signal processing circuitry.
• Camera 120 photographs the environment around work vehicle 100 while work vehicle 100 is traveling, and generates image (for example, video) data.
• the camera 120 can shoot moving images at a frame rate of 3 frames per second (fps) or more, for example.
• the image generated by camera 120 can be used, for example, when a remote monitor uses terminal device 400 to check the environment around work vehicle 100. Images generated by camera 120 may be used for positioning or obstacle detection. As shown in FIG.
• a plurality of cameras 120 may be provided at different positions on the work vehicle 100, or a single camera may be provided.
• a visible camera that generates visible light images and an infrared camera that generates infrared images may be provided separately. Both a visible camera and an infrared camera may be provided as cameras that generate images for surveillance. Infrared cameras can also be used to detect obstacles at night.
• the obstacle sensor 130 detects objects existing around the work vehicle 100.
• Obstacle sensor 130 may include, for example, a laser scanner or an ultrasonic sonar. Obstacle sensor 130 outputs a signal indicating that an obstacle exists when an object exists closer than a predetermined distance from obstacle sensor 130 .
• a plurality of obstacle sensors 130 may be provided at different positions of work vehicle 100. For example, multiple laser scanners and multiple ultrasonic sonars may be placed at different positions on work vehicle 100. By providing such a large number of obstacle sensors 130, blind spots in monitoring obstacles around the work vehicle 100 can be reduced.
• the steering wheel sensor 152 measures the rotation angle of the steering wheel of the work vehicle 100.
• the turning angle sensor 154 measures the turning angle of the front wheel 104F, which is a steered wheel. Measured values by the steering wheel sensor 152 and the turning angle sensor 154 can be used for steering control by the control device 180.
• the axle sensor 156 measures the rotational speed of the axle connected to the wheel 104, that is, the number of rotations per unit time.
• the axle sensor 156 may be a sensor using a magnetoresistive element (MR), a Hall element, or an electromagnetic pickup, for example.
• the axle sensor 156 outputs, for example, a numerical value indicating the number of revolutions per minute (unit: rpm) of the axle.
• Axle sensor 156 is used to measure the speed of work vehicle 100. The measured value by the axle sensor 156 can be used for speed control by the control device 180.
• the drive device 240 includes various devices necessary for running the work vehicle 100 and driving the implement 300, such as the above-mentioned prime mover 102, transmission device 103, steering device 106, and coupling device 108.
• Prime mover 102 may include, for example, an internal combustion engine such as a diesel engine.
• the drive device 240 may include an electric motor for traction instead of or in addition to the internal combustion engine.
• Storage device 170 includes one or more storage media such as flash memory or magnetic disks.
• the storage device 170 stores various data generated by the GNSS unit 110, camera 120, obstacle sensor 130, LiDAR sensor 140, sensor group 150, and control device 180.
• the data stored in the storage device 170 may include an environmental map of the environment in which the work vehicle 100 travels, an obstacle map sequentially generated during travel, and route data for automatic driving.
• the storage device 170 also stores computer programs that cause each ECU in the control device 180 to execute various operations described below.
• Such a computer program may be provided to work vehicle 100 via a storage medium (eg, semiconductor memory or optical disk, etc.) or a telecommunications line (eg, the Internet).
• Such computer programs may be sold as commercial software.
• the control device 180 includes multiple ECUs.
• the plurality of ECUs include, for example, an ECU 181 for speed control, an ECU 182 for steering control, an ECU 183 for instrument control, and an ECU 184 for automatic driving control.
• ECU 181 controls the speed of work vehicle 100 by controlling prime mover 102, transmission 103, and brakes included in drive device 240.
• the ECU 182 controls the steering of the work vehicle 100 by controlling the hydraulic system or electric motor included in the steering device 106 based on the measured value of the steering wheel sensor 152.
• the ECU 183 controls the operations of the three-point link, PTO axis, etc. included in the coupling device 108 in order to cause the implement 300 to perform a desired operation. ECU 183 also generates a signal to control the operation of implement 300 and transmits the signal from communication device 190 to implement 300.
• the ECU 184 performs calculations and controls to realize automatic driving based on data output from the GNSS unit 110, camera 120, obstacle sensor 130, LiDAR sensor 140, and sensor group 150. For example, ECU 184 estimates the position of work vehicle 100 based on data output from at least one of GNSS unit 110, camera 120, and LiDAR sensor 140. In a situation where the reception strength of satellite signals from GNSS satellites is sufficiently high, ECU 184 may determine the position of work vehicle 100 based only on the data output from GNSS unit 110. On the other hand, in an environment such as an orchard where there are obstacles such as trees around the work vehicle 100 that prevent reception of satellite signals, the ECU 184 performs work using data output from the LiDAR sensor 140 or the camera 120.
• the position of vehicle 100 is estimated.
• the ECU 184 performs calculations necessary for the work vehicle 100 to travel along the target route based on the estimated position of the work vehicle 100.
• the ECU 184 sends a speed change command to the ECU 181 and a steering angle change command to the ECU 182.
• ECU 181 changes the speed of work vehicle 100 by controlling prime mover 102, transmission 103, or brake in response to a speed change command.
• the ECU 182 changes the steering angle by controlling the steering device 106 in response to a command to change the steering angle.
• control device 180 realizes automatic driving.
• control device 180 controls drive device 240 based on the measured or estimated position of work vehicle 100 and the sequentially generated target route. Thereby, the control device 180 can cause the work vehicle 100 to travel along the target route.
• a plurality of ECUs included in the control device 180 can communicate with each other, for example, according to a vehicle bus standard such as CAN (Controller Area Network). Instead of CAN, a faster communication method such as in-vehicle Ethernet (registered trademark) may be used.
• CAN Controller Area Network
• FIG. 2 each of the ECUs 181 to 184 is shown as an individual block, but the functions of each of these may be realized by a plurality of ECUs.
• An on-vehicle computer that integrates at least some of the functions of the ECUs 181 to 184 may be provided.
• the control device 180 may include ECUs other than the ECUs 181 to 184, and any number of ECUs may be provided depending on the function.
• Each ECU includes processing circuitry including one or more processors.
• the communication device 190 is a device that includes a circuit that communicates with the implement 300 and the terminal device 400.
• the communication device 190 includes a circuit that transmits and receives signals compliant with the ISOBUS standard, such as ISOBUS-TIM, to and from the communication device 390 of the implement 300. Thereby, it is possible to cause the implement 300 to perform a desired operation or to obtain information from the implement 300.
• Communication device 190 may further include an antenna and a communication circuit for transmitting and receiving signals to and from terminal device 400 via network 80.
• Network 80 may include, for example, a cellular mobile communications network such as 3G, 4G or 5G and the Internet.
• the communication device 190 may have a function of communicating with a mobile terminal used by a supervisor near the work vehicle 100. Communication with such mobile terminals may be conducted in accordance with any wireless communication standard, such as Wi-Fi (registered trademark), cellular mobile communications such as 3G, 4G or 5G, or Bluetooth (registered trademark). I can.
• the operation terminal 200 is a terminal for a user to perform operations related to the traveling of the work vehicle 100 and the operation of the implement 300, and is also referred to as a virtual terminal (VT).
• Operating terminal 200 may include a display device such as a touch screen and/or one or more buttons.
• the display device may be a display such as a liquid crystal or an organic light emitting diode (OLED), for example.
• OLED organic light emitting diode
• the operating terminal 200 may be configured to be detachable from the work vehicle 100. A user located away from work vehicle 100 may operate detached operation terminal 200 to control the operation of work vehicle 100.
• the drive device 340 in the implement 300 shown in FIG. 2 performs operations necessary for the implement 300 to perform a predetermined work.
• Drive device 340 includes a device depending on the use of implement 300, such as a hydraulic device, an electric motor, or a pump.
• Control device 380 controls the operation of drive device 340.
• Control device 380 causes drive device 340 to perform various operations in response to signals transmitted from work vehicle 100 via communication device 390. Further, a signal depending on the state of the implement 300 can be transmitted from the communication device 390 to the work vehicle 100.
• FIG. 3A is a schematic diagram of LiDAR sensor 140 viewed from the side of work vehicle 100.
• FIG. 3B is a schematic diagram of the LiDAR sensor 140 viewed from vertically above.
• 3A and 3B show three mutually orthogonal axes u, v, and w in a sensor coordinate system fixed to the LiDAR sensor 140.
• 3A and 3B schematically represent the central axis (or traveling direction) of the laser beam emitted from the LiDAR sensor 140.
• Each laser beam is collimated into parallel light but has a divergence angle of several milliradians (eg, 0.1-0.2 degrees). Therefore, the cross-sectional size (spot diameter) of each laser beam increases in proportion to the distance from the LiDAR sensor 140. For example, a light spot several centimeters in diameter may be formed 20 meters away from the LiDAR sensor 140. In the figure, for simplicity, the spread of the laser beam is ignored and only the central axis of the laser beam is shown.
• the LiDAR sensor 140 in the example shown in FIG. 3A can emit laser beams at different elevation angles from a plurality of laser light sources arranged in the vertical direction. Elevation angle is defined by the angle with respect to the uv plane. In this example, the uv plane is approximately parallel to the horizontal plane. Note that if the ground (ground surface) is inclined with respect to the horizontal plane, the uv plane and the horizontal plane intersect.
• FIG. 3A shows how N laser beams L 1 , . . . , L N are emitted.
• N is an integer of 1 or more, for example, 10 or more, and may be 64 or 100 or more in a high-performance model.
• the elevation angle of the k-th laser beam from the bottom among the plurality of laser beams is ⁇ k .
• FIG. 3A shows, as an example, the elevation angle ⁇ N-1 of the N-1th laser beam.
• the elevation angle of the laser beam directed above the UV plane is defined as a "positive elevation angle”
• the elevation angle of the laser beam directed below the UV plane is defined as a "negative elevation angle.”
• a LiDAR sensor in which N is 1 is sometimes referred to as a "two-dimensional LiDAR," and a LiDAR sensor in which N is two or more is sometimes referred to as a “three-dimensional LiDAR.”
• N is 2 or more
• the angle formed by the first laser beam and the Nth laser beam is referred to as a "vertical viewing angle.”
• the vertical viewing angle may be set within a range of about 20° to 60°, for example.
• the LiDAR sensor 140 can change the emission direction (for example, azimuth angle) of the laser beam, as shown in FIG. 3B.
• FIG. 3B shows how the emission directions of the plurality of laser beams shown in FIG. 3A are rotated around a rotation axis parallel to the w-axis.
• the range of the laser beam emission direction (azimuth angle) may be 360°, or may be an angular range smaller than 360° (for example, 210° or 270°).
• the range of the azimuth angle of the laser beam emission direction is referred to as the "horizontal viewing angle.”
• the horizontal viewing angle can be set within a range of about 90° to 360°, for example.
• the LiDAR sensor 140 sequentially emits pulsed laser light (laser pulses) in different azimuth directions while rotating the laser beam emission direction around a rotation axis parallel to the w axis. In this way, it becomes possible to measure the distance to each reflection point using pulsed laser light emitted at different elevation angles and different azimuth angles. Each reflection point corresponds to an individual point included in the point cloud data.
• the operation of measuring the distance to the reflection point while the azimuth of the laser beam rotates once around the rotation axis is called one scan.
• Sensor data obtained by one scan includes data measured for each layer associated with a specific elevation angle shown in FIG. 3A. Therefore, as the number of layers increases, the number of points in the point cloud obtained by one scan of the same environment increases.
• the LiDAR sensor 140 repeats the scanning operation at a frequency of about 1 to 20 times per second, for example. For example, more than 100,000 pulses of laser light can be emitted in different directions during one scan operation.
• FIG. 4 is a block diagram showing a configuration example of the LiDAR sensor 140.
• the LiDAR sensor 140 shown in FIG. 4 includes a plurality of laser units 141, an electric motor 144, a control circuit 145, a signal processing circuit 146, and a memory 147.
• Each laser unit 141 includes a laser light source 142 and a photodetector 143.
• Each laser unit 141 may include an optical system such as a lens and a mirror, but illustration thereof is omitted.
• the motor 144 changes the direction of the laser beam emitted from each laser light source 142, for example, by rotating a mirror placed on the optical path of the laser beam emitted from each laser light source 142.
• the laser light source 142 includes a laser diode, and emits a pulsed laser beam of a predetermined wavelength in response to a command from the control circuit 145.
• the wavelength of the laser beam may be, for example, a wavelength included in the near-infrared wavelength range (approximately 700 nm to 2.5 ⁇ m).
• the wavelength used depends on the material of the photoelectric conversion element used in the photodetector 143. For example, when silicon (Si) is used as a material for a photoelectric conversion element, a wavelength of around 900 nm can be mainly used.
• InGaAs indium gallium arsenide
• a wavelength of, for example, 1000 nm or more and 1650 nm or less may be used.
• the wavelength of the laser beam is not limited to the near-infrared wavelength range.
• wavelengths within the visible range approximately 400 nm to 700 nm
• the photodetector 143 is a device that detects laser pulses emitted from the laser light source 142 and reflected or scattered by an object.
• the photodetector 143 includes, for example, a photoelectric conversion element such as an avalanche photodiode (APD).
• APD avalanche photodiode
• the motor 144 rotates a mirror placed on the optical path of the laser beam emitted from each laser light source 142 in response to a command from the control circuit 145. Thereby, a scanning operation that changes the emission direction of the laser beam is realized.
• the control circuit 145 controls the emission of laser pulses by the laser light source 142, the detection of reflected pulses by the photodetector 143, and the rotational operation of the motor 144.
• Control circuit 145 may be realized by a circuit comprising a processor, such as a microcontroller unit (MCU).
• MCU microcontroller unit
• the signal processing circuit 146 is a circuit that performs calculations based on the signal output from the photodetector 143.
• the signal processing circuit 146 calculates the distance to the object that reflected the laser pulse emitted from each laser light source 142, for example, by the ToF (Time of Flight) method.
• the ToF method includes a direct ToF method and an indirect ToF method. In the direct ToF method, the distance to the reflection point is calculated by directly measuring the time from when a laser pulse is emitted from the laser light source 142 until the reflected light is received by the photodetector 143.
• the distance to each reflection point is calculated based on the ratio of the amount of light detected in each exposure period.
• Either the direct ToF method or the indirect ToF method can be used.
• the signal processing circuit 146 generates and outputs sensor data indicating, for example, the distance to each reflection point and the direction of the reflection point.
• the signal processing circuit 146 further calculates the coordinates (u, v) or (u, v, w) in the sensor coordinate system based on the distance to each reflection point and the direction of the reflection point, and calculates the sensor data. It may also be included in the output.
• control circuit 145 and the signal processing circuit 146 are divided into two circuits in the example of FIG. 4, they may be realized by one circuit.
• the memory 147 is a storage medium that stores data generated by the control circuit 145 and the signal processing circuit 146.
• the memory 147 stores, for example, the emission timing of the laser pulse emitted from each laser unit 141, the emission direction, the reflected light intensity, the distance to the reflection point, and the coordinates (u, v) or (u) in the sensor coordinate system. , v, w) are stored.
• Such data is generated and recorded in memory 147 each time a laser pulse is emitted.
• the control circuit 145 outputs the data at a predetermined period (for example, the time required to emit a predetermined number of pulses, a half scan period, one scan period, etc.).
• the output data is recorded in the storage device 170 of the work vehicle 100.
• the LiDAR sensor 140 outputs sensor data at a frequency of, for example, about 1 to 20 times per second.
• This sensor data may include coordinates of a plurality of points expressed in a sensor coordinate system and time stamp information. Note that the sensor data may include information on the distance and direction to each reflection point, but may not include coordinate information. In that case, the control device 180 converts the distance and direction information into coordinate information.
• the distance measurement method is not limited to the ToF method, and other methods such as the FMCW (Frequency Modulated Continuous Wave) method may be used.
• FMCW Frequency Modulated Continuous Wave
• the FMCW method light whose frequency is linearly changed is emitted, and the distance is calculated based on the frequency of a beat generated by interference between the emitted light and the reflected light.
• the LiDAR sensor 140 in this embodiment is a scan type sensor that acquires information on the distance distribution of objects in space by scanning with a laser beam.
• the LiDAR sensor 140 is not limited to a scan type sensor.
• the LiDAR sensor 140 may be a flash-type sensor that uses light diffused over a wide range to obtain information on the distance distribution of objects in space.
• a scan-type LiDAR sensor uses higher intensity light than a flash-type LiDAR sensor, so it can obtain distance information from a longer distance.
• flash-type LiDAR sensors have a simple structure and can be manufactured at low cost, so they are suitable for applications that do not require strong light.
• FIG. 5 is a diagram schematically showing an example of the environment in which the work vehicle 100 travels.
• FIG. 6 is a perspective view schematically showing an example of the environment around work vehicle 100.
• the work vehicle 100 uses the implement 300 to carry out predetermined work (for example, chemical spraying, grass cutting, pest control, etc.).
• predetermined work for example, chemical spraying, grass cutting, pest control, etc.
• the sky is blocked by branches and leaves, making it difficult to drive automatically using GNSS.
• GNSS In an environment where GNSS cannot be used, it is conceivable to travel while estimating the self-position by matching sensor data with an environmental map created in advance.
• the external shapes of leaves, fences, etc. of trees and other crops can change significantly depending on the season, making it difficult to continuously use environmental maps created in advance.
• the control device 180 in this embodiment detects the two rows of crops existing on both sides of the work vehicle 100 based on the sensor data output from the LiDAR sensor 140, and detects the route between the two rows of crops.
• the work vehicle 100 is made to travel along the line.
• the control device 180 sets a coordinate system for turning and a target point for turning, and moves the work vehicle 100 to the target point based on the coordinate system. Turn towards the spot.
• FIG. 7A is a diagram schematically showing an example of the travel route 30 of the work vehicle 100.
• the work vehicle 100 travels between the rows of trees 20 on a route 30 as shown.
• line segments included in route 30 are depicted as straight lines, but the route that work vehicle 100 actually travels may include meandering portions.
• the plurality of tree rows 20 are ordered from the end as a first tree row 20A, a second tree row 20B, a third tree row 20C, a fourth tree row 20D, and so on.
• FIG. 7A is a diagram schematically showing an example of the travel route 30 of the work vehicle 100.
• the work vehicle 100 travels between the rows of trees 20 on a route 30 as shown.
• line segments included in route 30 are depicted as straight lines, but the route that work vehicle 100 actually travels may include meandering portions.
• the plurality of tree rows 20 are ordered from the end as a first tree row 20A, a second tree row 20B, a third tree row 20C, a fourth tree
• the work vehicle 100 first travels between the first row of trees 20A and the second row of trees 20B, and when the travel is completed, it turns to the right and moves between the first row of trees 20A and the second row of trees 20B. It runs in the opposite direction between the third row of trees 20C. When the vehicle completes traveling between the second tree row 20B and the third tree row 20C, it further turns to the left and travels between the third tree row 20C and the fourth tree row 20D. Thereafter, by repeating the same operation, the vehicle travels to the end of the route 30 between the last two rows of trees. Note that if the distance between two adjacent tree rows is short, the vehicle may travel every other row as shown in FIG. 7B. In this case, after the last two rows of trees have been completed, an operation may be performed to travel between every other row of trees that has not yet been traveled. Such traveling is automatically performed by the work vehicle 100 based on sensor data output from the LiDAR sensor 140.
• positioning may be performed based on the GNSS signal at a timing when the GNSS unit 110 can receive the GNSS signal. For example, at the timing of turning on the route 30 shown in FIGS. 7A and 7B, there are no leaves blocking the GNSS signal, so positioning based on the GNSS signal is possible.
• the control device 180 of the work vehicle 100 in this embodiment operates in an inter-row driving mode in which the work vehicle 100 travels along a route between two adjacent tree rows, and in an inter-row driving mode in which the work vehicle 100 turns in a headland. Operates in turning driving mode.
• the headland is the area between the end of each row of trees and the orchard boundary.
• the control device 180 detects two rows of trees existing on both sides of the work vehicle 100 based on sensor data sequentially output from the LiDAR sensor 140, and creates a route between the two rows of trees.
• the work vehicle 100 is caused to travel along the route while setting.
• the control device 180 When the control device 180 detects at least the end of the tree row on the side corresponding to the turning direction (right or left) among the two adjacent tree rows, it sets a coordinate system for turning and a turning target point. .
• the coordinate system for turning travel may be referred to as a "turning coordinate system.”
• the turning coordinate system is a coordinate system fixed to the ground, and is used in controlling turning travel.
• the target point is the entrance point for the next inter-row run. After setting the turning coordinate system and the turning target point, when the work vehicle 100 reaches the end of the tree row, it shifts to the turning mode. In the turning travel mode, the control device 180 causes the work vehicle 100 to travel along a turning path set on the turning coordinate system.
• the control device 180 runs the work vehicle 100 along the turning route while estimating the self-position of the work vehicle 100 on the turning coordinate system based on sensor data sequentially output from the LiDAR sensor 140. let In the turning travel mode, the control device 180 may perform positioning using a signal output from the GNSS receiver 111 and/or a signal output from the IMU 115 in addition to sensor data. When the work vehicle 100 reaches the turning target point, it shifts to the inter-row driving mode again. Thereafter, similar operations are repeated until the last inter-row run is completed. Through the above operations, automatic travel between the plurality of tree rows 20 is realized. The above control is executed by the ECU 184 in the control device 180.
• FIG. 8 is a diagram for explaining a travel control method for the work vehicle 100 in the inter-row travel mode.
• the work vehicle 100 scans the surrounding environment with a laser beam using the LiDAR sensor 140 while traveling between two adjacent tree rows 20R and 20L. As a result, data indicating the distance distribution of objects existing in the environment is obtained. The data indicating the distance distribution is converted into, for example, two-dimensional or three-dimensional point group data and output as sensor data.
• the control device 180 sequentially generates the obstacle map 40 based on the sensor data output from the LiDAR sensor 140.
• Obstacle map 40 shows the distribution of objects in a vehicle coordinate system fixed to work vehicle 100. Obstacle map 40 has a predetermined length Lh and width Lw. Length Lh is a size in the vertical direction corresponding to the traveling direction of work vehicle 100. The width Lw is a size in the lateral direction perpendicular to both the traveling direction and the vertical direction of the work vehicle 100.
• the control device 180 detects two tree rows 20R and 20L existing on both sides of the work vehicle 100 based on the obstacle map 40. Specifically, the control device 180 performs processing such as Hough transform on the obstacle map 40 to obtain approximate straight lines (line segments) 41R and 41L of the tree rows 20R and 20L. The control device 180 sets the target route 45 between the approximate straight lines 41R and 41L (for example, at the center). Note that when the plurality of trees in the tree rows 20R and 20L are distributed in a curved line, the control device 180 may obtain an approximate curve instead of an approximate straight line and set the target route 45 between these approximate curves. good.
• the target route 45 may be set within a relatively short range (for example, a range of several meters) starting from the position of the work vehicle 100.
• Target route 45 may be defined by multiple waypoints. Each waypoint may include information on the position and direction (or speed) of a point through which work vehicle 100 should pass. The interval between waypoints can be set to, for example, a value on the order of several tens of centimeters (cm) to several meters (m).
• Control device 180 causes work vehicle 100 to travel along set target route 45. For example, the control device 180 performs steering control of the work vehicle 100 so as to minimize deviations in the position and direction of the work vehicle 100 with respect to the target route 45. Thereby, the work vehicle 100 can be driven along the target route 45.
• the obstacle map 40 is not limited to the illustrated example, but may be a map (for example, a voxel map) showing a three-dimensional distribution of features existing around the work vehicle 100, for example.
• the obstacle map 40 may be map data in another format such as a point cloud map.
• the control device 180 may generate the obstacle map 40 by removing data of points estimated to correspond to unnecessary objects such as the ground and weeds from the sensor data output from the LiDAR sensor 140.
• the control device 180 selects data whose height from the ground is within a predetermined range (for example, within a range of 0.1 m to 1.5 m) from among the point cloud data. ) may be extracted, and an obstacle map may be generated from the data of the extracted points.
• a predetermined range for example, within a range of 0.1 m to 1.5 m
• Such a method makes it possible to generate an obstacle map showing the distribution of trees (mainly trunks).
• FIG. 9A is a diagram showing an example of an obstacle map 40 generated based on sensor data.
• the obstacle map 40 shown in FIG. 9A grids in which objects exist are shown in black, and grids in which objects do not exist are shown in white.
• a black grid represents the presence of objects such as tree trunks or leaves.
• the obstacle map 40 may be expressed, for example, by data in which a numerical value "1" is assigned to a grid in which an object exists, and a numerical value "0" is assigned to a grid in which an object does not exist.
• the control device 180 may be configured to sequentially generate an obstacle map 40 as shown in FIG. 9A based on sensor data acquired by the LiDAR sensor 140 in one period of scanning.
• the obstacle map 40 may be updated every scan period.
• the obstacle map 40 may include not only two-dimensional position information as illustrated, but also height information from the ground or horizontal plane.
• the control device 180 may generate the obstacle map 40 showing the distribution of tree rows by extracting only points whose heights are within a predetermined range.
• the control device 180 may generate one obstacle map 40 by combining sensor data output from the plurality of LiDAR sensors 140.
• one obstacle map 40 may be generated by combining sensor data output from two LiDAR sensors 140 (see FIG. 1) placed before and after the work vehicle 100.
• one obstacle map may be generated by combining sensor data for multiple periods.
• the length Lh and width Lw of the obstacle map 40 are equal, but the length Lh and width Lw may be different.
• the length Lh of the obstacle map 40 may be longer than the width Lw.
• the control device 180 Based on the obstacle map 40, the control device 180 detects two tree rows 20R and 20L existing on both sides of the work vehicle 100. For example, as shown in FIG. 9C, the control device 180 calculates two approximate straight lines 41R and 41L (or an approximate curve) from a row of a plurality of points distributed along the traveling direction of the work vehicle 100. Two tree rows 20R and 20L can be detected.
• the control device 180 While traveling in the inter-row driving mode, if the control device 180 detects at least the end of the tree row on the side corresponding to the turning direction among the two tree rows 20R and 20L based on sensor data, the control device 180 switches to the turning driving mode. Execute the process for migration. For example, when the turning direction is to the right, the control device 180 detects the end of the right tree row 20R, and then executes processing for transitioning to the turning mode. Specifically, when the control device 180 detects the end of the tree row 20R on the side corresponding to the turning direction, it sets a coordinate system for turning (turning coordinate system) and a target point for turning.
• a coordinate system for turning turning coordinate system
• the target point of the turning run is the end point of the turning run, and is, for example, the start point of the next inter-row run.
• the control device 180 determines the position coordinates of the target point in the turning coordinate system based on the interval between the tree rows 20R and 20L and the position of the end of the tree row 20R on the turning direction side. After setting the turning coordinate system and the target point, control device 180 turns work vehicle 100 toward the target point based on the turning coordinate system.
• FIGS. 10A and 10B are diagrams for explaining an example of a method for setting a turning coordinate system and a target point.
• the control device 180 estimates the length Lr within the obstacle map 40 of at least the tree row 20R on the side corresponding to the turning direction among the two tree rows 20R and 20L, based on the obstacle map 40. do.
• the control device 180 can estimate the lengths of the approximate straight lines 41R and 41L of the tree rows 20R and 20L as the lengths Lr and Ll of the tree rows 20R and 20L in the obstacle map 40.
• the control device 180 detects the end of the tree row 20R based on the difference Le between the length Lh of the obstacle map 40 and the length Lr of the tree row 20R on the turning direction side within the obstacle map 40. For example, the control device 180 detects the end of the tree row 20R when the difference Le between the length Lh of the obstacle map 40 and the length Lr of the tree row 20R in the obstacle map 40 exceeds a threshold value. It can be determined that In other words, in the successively generated obstacle map 40, it can be determined that the end of the tree row 20R has been detected when the length Le of the area where no object exists beyond the tree row 20R exceeds a threshold value. .
• the threshold value may be set to a value larger than the interval ⁇ L between two adjacent trees in each tree row 20, for example. The interval ⁇ L is set in advance, and the information is recorded in the storage device 170.
• control device 180 After detecting the end of the tree row 20R on the turning direction side, the control device 180 sets a turning coordinate system. Control device 180 first determines the origin of the turning coordinate system based on the position of work vehicle 100 when the end of tree row 20R on the turning direction side is detected. For example, the control device 180 may set the position of the work vehicle 100 when the end of the tree row 20R is detected as the origin of the turning coordinate system. Alternatively, a position shifted by a predetermined distance in a predetermined direction from the position of the work vehicle 100 when the end of the tree row 20R is detected may be set as the origin of the turning coordinate system.
• FIG. 10B illustrates a turning coordinate system ⁇ t whose origin is the position of the work vehicle 100 when the end of the tree row 20R is detected.
• the turning coordinate system ⁇ t in this example is defined by the y-axis extending from the origin in the traveling direction of the work vehicle 100, and the x-axis extending in a direction parallel to the horizontal plane and perpendicular to the y-axis.
• the control device 180 estimates the interval Lg between the two tree rows 20R and 20L (that is, the interval between the two approximate straight lines 41R and 41L) based on the obstacle map 40, and determines the interval Lg.
• An integer multiple (excluding 0) is set as the x-coordinate value px of the target point P.
• the interval Lg between the tree rows may be a fixed value set in advance.
• the integer n can be set based on, for example, the minimum turning radius of the work vehicle 100 and the interval Lg between the rows of trees.
• n may be set to an integer of 1 or more.
• n may be set to an integer of 2 or more.
• k is an integer greater than or equal to 1 and twice the minimum turning radius is greater than Lg ⁇ (k ⁇ 1) and less than or equal to Lg ⁇ k
• n may be set to an integer greater than or equal to k.
• n may be set to an integer of 3 or more. Note that when the work vehicle 100 turns to the left, n is set to a negative integer.
• the coefficient n can be set in advance by the user, for example.
• the control device 180 sets the y-coordinate value of the target point P based on the y-coordinate value of the end of the tree row 20R in the turning coordinate system ⁇ t.
• the control device 180 may set the y-coordinate value of the end of the tree row 20R in the turning coordinate system ⁇ t as the y-coordinate value py of the target point P.
• a value obtained by adding or subtracting a predetermined amount to the y-coordinate value of the end of the tree row 20R may be set as the y-coordinate value py of the target point P.
• control device 180 sets the turning coordinate system ⁇ t based on the obstacle map 40, calculates the lengths Lr and Ll of the tree rows 20R and 20L, and the interval Lg between the tree rows, and adjusts these values to Based on this, the target point, which is the entrance of the passage between the rows of trees to be traveled next, is determined.
• FIG. 11 is a flowchart showing an example of a process for determining the turning coordinate system and the y-coordinate value py of the target point P.
• FIG. 12 is a flowchart illustrating an example of a process for determining the x-coordinate value px of the target point P.
• FIG. 13 is a diagram showing an example of parameters used in the process of determining the target point P.
• the control device 180 first generates the obstacle map 40 based on sensor data in step S101. As described above, the control device 180 generates the obstacle map 40 by extracting a portion in a predetermined spatial range from the sensor data. In the subsequent step S102, the control device 180 performs processing such as Hough transform on the obstacle map 40 to obtain line segments fr(u, v) corresponding to the tree rows on the left and right of the work vehicle 100, as shown in FIG. ) and fl(u,v). Here, (u, v) represents coordinates in the vehicle coordinate system. In subsequent step S103, the control device 180 acquires information regarding the turning direction (right or left). The turning direction (right or left) is set in advance, and the information is stored in the storage device 170.
• the turning direction (right or left) is set in advance, and the information is stored in the storage device 170.
• step S104 the control device 180 calculates the difference Le between the length Lh of the obstacle map 40 and the length Lr or Ll of the line segment corresponding to the tree row on the turning direction side (see FIG. 10A).
• step S105 the control device 180 determines whether the difference Le is larger than a threshold value. If the difference Le is less than or equal to the threshold, the process returns to step S101. If the difference Le is larger than the threshold value, the process advances to step S106.
• step S106 the control device 180 sets a turning coordinate system ⁇ t whose origin is the position of the work vehicle 100 at that time.
• step S107 the control device 180 sets the length Lr or Ll of the line segment corresponding to the row of trees on the turning direction side as the y-coordinate value py of the target point P.
• py is set in consideration of the deviation. In either case, a value greater than or equal to the y-coordinate value of the end of the tree row on the turning direction side can be set as the y-coordinate value of the target point P.
• the turning coordinate system and the y-coordinate value py of the target point P are determined.
• FIG. 12 may be performed at any timing before or after the operation shown in FIG. 11.
• control device 180 first obtains information regarding the turning direction (right or left) and the number of rows ahead (the above-mentioned coefficient n) in step S201.
• the turning direction (right or left) and the number of rows ahead to turn are set in advance, and the information is stored in the storage device 170.
• step S202 the control device 180 determines whether the interval Lg between the tree rows has been set. If the interval Lg between the tree rows has been set in advance, the process advances to step S206. If the interval Lg between the tree rows has not been set, the process advances to step S203.
• step S203 the control device 180 determines line segments fr(u,v) and fl(u,v) corresponding to the left and right tree rows from the obstacle map 40. Note that if the line segments fr(u,v) and fl(u,v) have already been determined in step S102 shown in FIG. 11, step S203 may be omitted.
• the control device 180 determines the calculation area length Lc and the calculation resolution.
• the calculation area length Lc is a numerical value indicating how long a range from the current position of the work vehicle 100 in the traveling direction is to be subjected to calculation.
• the resolution is a numerical value indicating the degree of spatial resolution in which calculation is performed in terms of the calculation area length.
• the calculation area length Lc and resolution may be fixed values set in advance, or may be set by the user.
• step S205 the control device 180 calculates the distances (referred to as "lateral distances") between each of the line segments fr (u, v) and fl (u, v) and the reference position of the work vehicle 100 in the calculation area. Average values Lwr and Lwl are calculated by averaging over the length Lc. Further, the control device 180 calculates the sum Lg of Lwr and Lwl, and sets it as the tree row interval.
• step S207 the control device 180 determines whether the turning direction is right or left. If the turning direction is to the right, the px calculated in step S206 is set as the x-coordinate value of the target point P. If the turning direction is to the left, the process advances to step S208, and the value obtained by multiplying px by -1 is set as the x-coordinate value of the target point P.
• the x-coordinate value px of the target point P can be determined.
• the control device 180 After setting the turning coordinate system ⁇ t and the turning target point P in the inter-row driving mode, the control device 180 switches to the turning driving mode. After setting the coordinate system ⁇ t and the target point P, the control device 180 determines whether turning is possible based on the sensor data output from the LiDAR sensor 140. If the control device 180 determines that turning is possible, it switches to the turning mode. For example, after setting the coordinate system ⁇ t and the target point P in the inter-row driving mode, the control device 180 determines, based on sensor data, that there is a space necessary for turning and that the work vehicle 100 (implement 300 is installed) is available. If it is determined that the vehicle (including the implement 300) has passed the end of the tree row 20R on the turning direction side, the mode is switched to the turning mode.
• FIG. 14 is a diagram for explaining the operation of work vehicle 100 in the turning travel mode.
• the control device 180 sets the turning route 46 on the turning coordinate system ⁇ t, and estimates the turning route 46 on the coordinate system ⁇ t based on the sensor data sequentially output from the LiDAR sensor 140.
• the work vehicle 100 is made to travel along.
• the control device 180 sets, as the turning route 46, an arcuate path connecting a point P0 where the work vehicle 100 passes the end of the row of trees 20R on the turning direction side and a turning target point P.
• the turning path 46 is defined by a plurality of waypoints. Each waypoint may include location and orientation information.
• control device 180 causes work vehicle 100 to travel along turning route 46 while estimating the self-position of work vehicle 100 based on the sensor data.
• an algorithm such as SLAM may be used for self-position estimation.
• the control device 180 connects the sequentially generated obstacle maps 40 to create an environmental map covering a relatively wide range, and performs matching between the environmental map and sensor data to estimate the self-position of the work vehicle 100 (i.e., position and direction estimation). Matching may be performed using any matching algorithm, such as NDT (Normal Distribution Transform) or ICP (Iterative Closest Point).
• Control device 180 performs control to reduce the deviation between the position and orientation of work vehicle 100 and the position and orientation of each waypoint on turning path 46. Thereby, the work vehicle 100 turns toward the target point P along the turning path 46. On the other hand, if there is not enough space for turning on the headland 50, the control device 180 may stop the work vehicle 100 or send a warning to the monitoring terminal device 400.
• FIG. 15 is a flowchart showing a specific example of a travel control method by the control device 180.
• the control device 180 can cause the work vehicle 100 to automatically travel between a plurality of tree rows by executing the operations from steps S301 to S321 shown in FIG. 15. The operation of each step will be explained below.
• the work vehicle 100 In the initial state, the work vehicle 100 is assumed to be located at the entrance of the passage between the first rows of trees, as shown in FIG. 7A or FIG. 7B.
• the control device 180 Upon receiving the command to start automatic travel, the control device 180 starts the operation in step S301.
• step S301 the control device 180 causes the work vehicle 100 to travel in inter-row travel mode.
• the control device 180 performs the following operations.
• the control device 180 generates the obstacle map 40 based on sensor data output from the LiDAR sensor 140.
• the obstacle map 40 approximate straight lines of two adjacent tree rows located on both sides of the work vehicle 100 are calculated.
• the approximate straight line can be calculated by, for example, performing a Hough transform on the obstacle map 40 and extracting two line segments that extend in a direction close to the traveling direction in the vicinity of the work vehicle 100.
• the control device 180 sets a target route by setting a plurality of waypoints at positions equidistant from the two approximate straight lines.
• control device 180 performs steering control to reduce the deviation. Thereby, the work vehicle 100 can be driven along the target route between the tree rows.
• the control device 180 may stop the work vehicle 100 or change the target route midway to avoid the obstacle. Good too. At this time, the control device 180 may send a warning to the monitoring terminal device 400.
• step S302 the control device 180 executes a process of detecting the end of the tree row based on the obstacle map 40.
• the control device 180 first performs a Hough transform on the obstacle map 40 and obtains the lengths Lr and Ll (see FIG. 10A) of the two extracted approximate straight lines.
• the control device 180 determines that the difference Le between the length Lh of the obstacle map 40 and the length Lr or Ll of the approximate straight line corresponding to the turning direction among the two approximate straight lines exceeds a preset threshold value. Determine whether it exceeds the limit. If the difference Le exceeds the threshold value, it is determined that the end of the tree row has been detected.
• the operations of steps S301 and S302 are repeated until the end of the tree row is detected. When the end of the tree row is detected, the process advances to step S303.
• step S303 the control device 180 determines whether the tree row whose end has been detected is the last tree row. Whether or not a tree row is the last tree row can be determined based on information about the distribution or number of tree rows stored in the storage device 170 in advance. If the tree row whose end has been detected is the last tree row, the control device 180 ends the work travel by the work vehicle 100. If the tree row whose end has been detected is not the last tree row, the process advances to step S304.
• step S304 the control device 180 sets the turning coordinate system ⁇ t.
• the position of the work vehicle 100 at the time when the end of the tree row on the turning direction side is detected is the origin, and the x-axis perpendicular to the traveling direction of the work vehicle 100;
• a coordinate system defined by the y-axis parallel to the traveling direction is set as a turning coordinate system ⁇ t.
• step S305 the control device 180 sets the coordinates (px, py) of the turning target point P in the turning coordinate system ⁇ t.
• the x-coordinate value px of the target point P can be set to a value obtained by multiplying the interval Lg between the tree rows by an integer n.
• the y-coordinate value py of the target point P may be set to the y-coordinate value of the end of the tree row on the turning direction side or a value higher than that.
• step S306 the control device 180 determines whether the work vehicle 100 has passed through the row of trees on the turning direction side. An example of this determination process will be described with reference to FIG. 16.
• FIG. 16 shows an example of a situation where the work vehicle 100 passes through a row of trees.
• the control device 180 moves the vehicle from the rear end of the work vehicle 100 (the rear end of the implement 300 if the implement 300 is installed) to the turning direction side (in the figure). In the example above, the distance Lsr to the object that is located directly next to the right) is calculated.
• the control device 180 causes the work vehicle 100 to move the tree line on the turning direction side. It can be determined that it has come off.
• the control device 180 controls the It may be determined that the vehicle 100 has passed through the row of trees on the turning direction side.
• the work vehicle 100 continues traveling between the tree rows until it passes through the tree row on the turning direction side, and repeats the determination in step S306. If it is determined that the work vehicle 100 has passed through the row of trees on the turning direction side, the process advances to step S307.
• step S307 the control device 180 determines whether there is a space necessary for turning. This determination may be made based on the obstacle map 40. As shown in FIG. 14, if the headland 50 between the field boundary 48 and the tree row is wide enough to allow turning, and there are no obstacles that impede turning, there is a space large enough for turning. It is determined that The position (for example, latitude and longitude) of the field boundary 48 may be set by the user in advance and recorded in the storage device 170, for example. Control device 180 determines the area required for turning based on, for example, the position of target point P, the position of turning start point P0, and the sizes of work vehicle 100 and implement 300.
• the controller 180 can determine that there is a space large enough for the turn. If there is not enough space for turning, the process proceeds to step S321, and the control device 180 stops the work vehicle 100. At this time, a warning signal may be transmitted to an external device such as the monitoring terminal device 400. If there is a space necessary for turning, the process advances to step S308.
• step S308 the control device 180 sets the turning route 46 and shifts from the inter-row driving mode to the turning driving mode.
• the turning path 46 may be an arcuate path connecting points P0 and P as shown in FIG. 14, or a path having another trajectory.
• Control device 180 performs steering control of work vehicle 100 so that work vehicle 100 travels along turning path 46 .
• control device 180 may perform turning control while estimating the position and orientation of work vehicle 100 in turning coordinate system ⁇ t based on sensor data and an already created obstacle map.
• a signal output from the GNSS receiver 111 and/or a signal output from the IMU 115 may be used to estimate the position and orientation of the work vehicle 100.
• control device 180 Since there is a possibility that people or other vehicles may pass through the headland 50, in order to avoid contact, the control device 180 sets the traveling speed of the working vehicle 100 during turning to be lower than the traveling speed when traveling between rows. You can keep it low. If an obstacle is detected during turning, control device 180 may stop work vehicle 100 or change turning route 46 midway to avoid the obstacle.
• step S309 the control device 180 determines whether the work vehicle 100 has reached the target point P. If the work vehicle 100 has not reached the target point, it continues turning. When the work vehicle 100 reaches the target point, the process advances to step S310, and the control device 180 shifts to the inter-row driving mode. Thereafter, the process returns to step S301 and the same operation is repeated.
• the work vehicle 100 can automatically travel between rows of trees and turn.
• a turning coordinate system and a target point are set, and travel control along a turning route is performed based on the turning coordinate system. This makes it possible to smoothly turn to change the traveling train.
• the target point for turning is set in step S305.
• the target point is maintained until the turning is completed.
• Such an operation is effective when the ends of all tree rows are aligned in the y direction, as shown in FIG. 14.
• the target point may need to be corrected after setting. For example, if there is another tree row on or near the turning route toward the target point P, the work vehicle 100 or the implement 300 will come into contact with the other tree row if the target point P is not changed. There are cases. Assuming such a case, after setting the target point P, the control device 180 may perform a process of correcting the target point P based on sensor data as necessary.
• FIG. 17A is a diagram showing an example of an operation for correcting the target point P.
• the fan shape in the figure schematically shows an example of the sensing range of the LiDAR sensor 140.
• the control device 180 modifies the y-coordinate value of the target point P to a value greater than or equal to the y-coordinate value of the end of the other tree row 20C. Accordingly, the control device 180 corrects the turning route from the route indicated by the black circle in the figure to the route indicated by the white circle. Thereby, contact between the work vehicle 100 or the implement 300 and the other tree row 20C can be avoided.
• FIG. 17B is a diagram showing another example of the operation of correcting the target point P.
• the control device 180 corrects the y-coordinate value of the target point P to a value greater than or equal to the y-coordinate value of the end of the other tree row 20C during the turn. Accordingly, the control device 180 corrects the turning route 46 from the route indicated by the black circle in the figure to the route indicated by the white circle. Thereby, contact between the work vehicle 100 or the implement 300 and the other tree row 20C can be avoided.
• the control device 180 may enlarge the size of the obstacle map 40 after setting the turning coordinate system ⁇ t. By enlarging the size of the obstacle map 40, it becomes easier to detect obstacles such as other tree rows 20C.
• FIG. 18A is a diagram for explaining an example of an operation for correcting the target point P using the enlarged obstacle map 40.
• the horizontal size of the obstacle map 40 is expanded to 1.5 times the size in the previous example.
• the size may be expanded not only in the horizontal direction but also in the vertical direction.
• the magnification rate is not limited to 1.5 times, but may be, for example, 2 times or more.
• the control device 180 detects objects existing within the range of the obstacle map 40 as obstacles. By enlarging the size of the obstacle map 40, the spatial range of objects detected as obstacles is enlarged.
• the work vehicle 100 before passing through the end of the nearest tree row 20R on the turning direction side (right side), the work vehicle 100 detects another tree row 20C located to the right based on the obstacle map 40. .
• the control device 180 extracts line segments corresponding to the tree row 20C by performing processing such as Hough transform on the obstacle map 40. Let the length of this line segment be Lc.
• the control device 180 is located at a position further away from the position of the work vehicle 100 in the turning direction than the distance Lwr from the tree row 20R closest to the work vehicle 100, and has a length that is approximately parallel to the y-axis and exceeds a predetermined length. If a line segment is detected, the y-coordinate value py of the target point P is updated.
• control device 180 sets the value obtained by adding the length Lc of the detected line segment to the travel distance Lt of the work vehicle 100 from the origin in the turning coordinate system ⁇ t as the y-coordinate value of the target point P. do. Thereby, the target point P is appropriately corrected.
• FIG. 18B is a diagram for explaining another example of the operation of correcting the target point.
• the work vehicle 100 corrects the target point P when detecting another tree row 20C while turning.
• the control device 180 creates a line segment with a length exceeding a predetermined length in the obstacle map 40 at a position where the x-coordinate value in the turning coordinate system ⁇ t is smaller than the x-coordinate value px of the target point P. If detected, the y-coordinate value py of the target point P is updated.
• the control device 180 converts the position coordinates (u1, v1) of the end of the line segment in the obstacle map 40 expressed in the vehicle coordinate system into the position coordinates (x1, y1) in the turning coordinate system ⁇ t. Convert.
• the control device 180 corrects the y-coordinate value py of the target point P to a value greater than or equal to the y-coordinate value y1 of the end of the tree row 20C. Thereby, the target point P is appropriately corrected.
• FIG. 19 is a flowchart illustrating an example of the operation of the control device 180 when performing the correction process for the target point P described above.
• the flowchart shown in FIG. 19 is the same as the flowchart shown in FIG. 15 except that steps S331, S332, S341, and S342 are added.
• step S331 the control device 180 determines whether there is another row of trees that impedes turning based on the obstacle map. If there are no other tree rows that impede turning, the process returns to step S306. If there are other tree rows that impede turning, the process advances to step S332.
• step S332 control device 180 modifies the target point.
• the determination method in step S331 and the target point correction method in step S332 are as described with reference to FIGS. 17A and 18A. By adding the processes of steps S331 and S332, the y-coordinate value of the target point can be corrected as necessary before turning.
• step S341 the control device 180 determines whether there is another row of trees that impedes turning based on the obstacle map. If there are no other tree rows that impede turning, the process advances to step S309. If there are other tree rows that impede turning, the process advances to step S342.
• step S342 control device 180 corrects the target point.
• the determination method in step S341 and the target point correction method in step S342 are as described with reference to FIG. 17B and FIG. 18B.
• the control device 180 also corrects the turning route as the position of the target point is corrected. By adding the processes of steps S341 and S342, the y-coordinate value of the target point can be corrected as necessary during turning, and the work vehicle 100 or the implement 300 can be prevented from coming into contact with other tree rows. can.
• the position of the target point P may be corrected according to the positional relationship between the ends of other tree rows and the target point P.
• the control device 180 detects the end of another row of trees based on sensor data during turning, and in the turning coordinate system ⁇ t, the x-coordinate value of the end of the other row of trees is the x-coordinate of the target point.
• the y-coordinate value of the end of another tree row is larger than the y-coordinate value of the target point, update the y-coordinate value of the target point with a value that is greater than or equal to the y-coordinate value of the end of the other tree row. You may.
• the target point P is modified, but contact with other tree rows may be avoided by modifying the turning route 46 without modifying the target point P.
• the control device 180 may detect a tree row other than two adjacent tree rows based on the sensor data, and then control the , the turning path may be modified.
• FIG. 20 is a diagram showing an example in which the turning route 46 is corrected while maintaining the target point P.
• the controller 180 corrects the turning route 46 without correcting the target point P.
• contact between the work vehicle 100 and the other tree rows 20C can be avoided by simply modifying the turning route 46 without modifying the target point P. . In that case, it is effective to apply the operation shown in FIG. 20.
• the method of setting the target point for turning travel is not limited to the above method, and other methods may be adopted. For example, if the height of the crop row is low and the surrounding environment of the turning destination road can be sensed using the LiDAR sensor 140, an environmental map is generated based on the sensor data, and the target point is determined based on the environmental map. May be set. An example of such an operation will be described below.
• FIG. 21 is a flowchart illustrating an example of a method for setting a target point based on an environmental map.
• steps S106 and S107 in the flowchart shown in FIG. 11 are replaced with steps S406, S407, and S408.
• the operations in steps S101 to S105 are the same as the operations in the corresponding steps in FIG.
• control device 180 sets a turning coordinate system having the position of work vehicle 100 as its origin, and starts generating an environmental map.
• the environment map may be a point cloud map or an occupancy grid map expressed in a rotating coordinate system.
• the environmental map can be generated by processing sequentially generated sensor data (or obstacle maps) that undergoes coordinate transformation and then is stitched together. For example, an algorithm such as SLAM may be used to generate the environmental map.
• step S407 the control device 180 determines whether the work vehicle 100 has passed the end of the row of trees on the turning direction side. This determination process is the same as the process shown in step S306 shown in FIG. 15. Until it is determined that the work vehicle 100 has passed the end of the tree row on the turning direction side, the work vehicle 100 continues to generate an environmental map based on sensor data while traveling between the tree rows. If it is determined that the work vehicle 100 has passed the end of the row of trees on the turning direction side, the process advances to step S408.
• step S408 the control device 180 sets the position (px, py) of the target point based on the environmental map expressed in the rotation coordinate system. For example, the control device 180 determines the x-coordinate value px of the target point based on information regarding a preset turning direction and how many rows ahead (n) to turn, and the spacing between tree rows estimated from the environmental map. can be set. The control device 180 can further set the y-coordinate value py of the target point based on the distribution of tree rows shown on the environmental map.
• the y-coordinate value py of the target point is set to a value greater than or equal to the y-coordinate value of the tip of the row of trees that is located on the side of the work vehicle 100 and closest to the travel route when viewed from the travel route for the next inter-row run. can be done.
• control device 180 sets a turning route from the current position of the work vehicle 100 to the target point position (px, py), and causes the work vehicle 100 to travel along the turning route.
• control device 180 performs steering control to minimize the deviation between the position and orientation of work vehicle 100 and the turning route while estimating its own position by matching sensor data with an environmental map. Thereby, the work vehicle 100 can be turned toward the target point.
• the one or more external sensors provided in the work vehicle are LiDAR sensors that output two-dimensional or three-dimensional point cloud data as sensor data by scanning with a laser beam.
• external sensors are not limited to such LiDAR sensors.
• other types of sensors such as flash-type LiDAR sensors or image sensors may be utilized.
• Such other types of sensors may also be utilized in combination with scanning LiDAR sensors.
• the work vehicle automatically travels between a plurality of rows of trees in an orchard, but the work vehicle may also be used to automatically travel between rows of crops other than rows of trees.
• the technology of the present disclosure may be applied to a work vehicle such as a tractor that automatically moves between multiple rows of crops in a field.
• the device that executes the processes necessary for automatic travel of the work vehicle in the above embodiments can also be later attached to a work vehicle that does not have these functions.
• a control unit that controls the operation of a work vehicle that travels between a plurality of crop rows can be used by being attached to the work vehicle.
• the present disclosure includes the work vehicle and the method of controlling the work vehicle described in the following items.
• a work vehicle that automatically travels between multiple rows of crops, an external sensor that outputs sensor data indicating a distribution of features around the work vehicle; a control device that controls automatic travel of the work vehicle; Equipped with The control device includes: detecting two rows of crops existing on both sides of the work vehicle based on the sensor data; driving the work vehicle along a path between the two crop rows; When the end of at least one of the two crop rows corresponding to the turning direction is detected based on the sensor data while traveling, a coordinate system fixed to the ground for turning travel; , and setting a target point for the turning run; controlling the turning movement toward the target point based on the coordinate system; work vehicle.
• the control device includes: While the work vehicle is traveling between the two crop rows, sequentially generating an obstacle map having a predetermined length and width based on the sensor data, Based on the obstacle map, estimating the length of the crop row on the side corresponding to the turning direction among the two crop rows within the obstacle map; detecting an end of the crop row based on a difference between a length of the obstacle map and a length of the crop row within the obstacle map; Work vehicle described in item 1.
• control device determines that an end of the crop row has been detected when a difference between the length of the obstacle map and the length of the crop row in the obstacle map exceeds a threshold. Work vehicle mentioned.
• the coordinate system is defined by a y-axis extending from the origin in the direction of travel of the work vehicle traveling between the two crop rows, and an x-axis extending in a direction parallel to a horizontal plane and perpendicular to the y-axis.
• the control device estimates an interval between the two crop rows based on the sensor data, setting an integer multiple of the interval as the x-coordinate value of the target point; Work vehicle described in item 4.
• the coordinate system is defined by a y-axis extending from the origin in the direction of travel of the work vehicle traveling between the two crop rows, and an x-axis extending in a direction parallel to a horizontal plane and perpendicular to the y-axis.
• the work vehicle according to item 4 wherein the control device sets the y-coordinate value of the end of the crop row in the coordinate system as the y-coordinate value of the target point.
• the control device After setting the target point, the control device detects an end of another crop row based on the sensor data, and in the coordinate system, the x-coordinate value of the end of the other crop row is set to the target point. If the x-coordinate value of the point is smaller than the y-coordinate value of the end of the other crop row and the y-coordinate value of the end of the other crop row is larger than the y-coordinate value of the target point, the y-coordinate value of the target point is The work vehicle according to item 8, which is updated with a y-coordinate value.
• the control device includes: operating in an inter-row driving mode in which the working vehicle travels along a route between the two crop rows, and a turning driving mode in which the working vehicle turns around a headland;
• the inter-row traveling mode the two rows of crops are detected based on the sensor data sequentially output from the external sensor, and the work vehicle is moved between the two rows of crops while setting the route between the two rows of crops. run along the route
• the turning mode a turning route is set on the coordinate system, and the vehicle moves along the turning route while estimating its own position on the coordinate system based on the sensor data sequentially output from the external sensor.
• drive a work vehicle The work vehicle described in any of items 1 to 9.
• the control device After setting the coordinate system and the target point in the inter-row driving mode, the control device determines whether or not a turn is possible based on the sensor data, and determines that a turn is possible. In this case, the work vehicle according to item 11 switches to the turning mode.
• the control device After setting the coordinate system and the target point in the inter-row driving mode, the control device determines, based on the sensor data, that there is a space necessary for the turning and that the work vehicle crosses the edge of the crop row.
• a method for controlling a work vehicle that automatically travels between multiple rows of crops comprising: Detecting two rows of crops existing on both sides of the work vehicle based on sensor data output from an external sensor mounted on the work vehicle; traveling the work vehicle along a path between the two crop rows; When the end of at least one of the two crop rows corresponding to the turning direction is detected based on the sensor data while traveling, a coordinate system fixed to the ground for turning travel; , and setting a target point for the turning trip, and controlling the turning trip toward the target point based on the coordinate system.
• control methods including.
• the technology of the present disclosure can be applied to a work vehicle such as a tractor that moves in an environment where multiple rows of crops (for example, rows of trees) exist, such as an orchard, a field, or a mountain forest.
• a work vehicle such as a tractor that moves in an environment where multiple rows of crops (for example, rows of trees) exist, such as an orchard, a field, or a mountain forest.
• Signal processing circuit 147... Memory, 150... Sensor group, 152... Steering wheel sensor, 154... Turning angle sensor, 156... Axle sensor, 160... Control system, 170... Storage device, 180... Control device, 181-184... ECU, 190... Communication device, 200... Operation terminal, 210... Operation switch group, 240... - Drive device, 300... Implement, 340... Drive device, 380... Control device, 390... Communication device, 400... Terminal device

Landscapes

• Engineering & Computer Science (AREA)
• Life Sciences & Earth Sciences (AREA)
• Mechanical Engineering (AREA)
• Soil Sciences (AREA)
• Environmental Sciences (AREA)
• Radar, Positioning & Navigation (AREA)
• Remote Sensing (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Aviation & Aerospace Engineering (AREA)
• Automation & Control Theory (AREA)
• Computer Networks & Wireless Communication (AREA)
• Electromagnetism (AREA)
• Guiding Agricultural Machines (AREA)
• Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Priority Applications (3)

Applications Claiming Priority (2)

Related Child Applications (1)

Publications (1)

Family

ID=89191081

Family Applications (1)

Country Status (4)

Citations (1)

Family Cites Families (3)

• 2023
  • 2023-06-07 WO PCT/JP2023/021173 patent/WO2023243514A1/ja not_active Ceased
  • 2023-06-07 EP EP23823806.7A patent/EP4541161A1/en active Pending
  • 2023-06-07 JP JP2024528765A patent/JPWO2023243514A1/ja active Pending
• 2024
  • 2024-12-11 US US18/976,400 patent/US20250098563A1/en active Pending

Patent Citations (1)

Non-Patent Citations (5)

Also Published As

Similar Documents

Legal Events