Method and apparatus for correcting steering value of autonomous work vehicle

The method and apparatus for autonomous vehicles correct steering values by setting waypoints and adjusting based on curvature deviations, ensuring accurate navigation along curved paths.

WO2026142040A1PCT designated stage Publication Date: 2026-07-02GINT CO LTD

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
GINT CO LTD
Filing Date
2025-12-04
Publication Date
2026-07-02

AI Technical Summary

Technical Problem

Autonomous work vehicles face challenges in accurately correcting steering values during curved path navigation, leading to potential deviations and collisions.

Method used

A method and apparatus that set waypoints at equal intervals, calculate curvature values, and adjust steering values based on deviations to ensure accurate path following.

Benefits of technology

Enables precise steering corrections for autonomous vehicles, preventing deviations and collisions during curved path navigation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2025020703_02072026_PF_FP_ABST
    Figure KR2025020703_02072026_PF_FP_ABST
Patent Text Reader

Abstract

One embodiment of the present invention discloses a method for correcting a steering value of a work vehicle which enables the work vehicle to travel along a curved path without deviating therefrom.
Need to check novelty before this filing date? Find Prior Art

Description

Method and apparatus for correcting steering values ​​of an autonomous work vehicle

[0001] The present invention relates to a method for correcting data output from a vehicle, and more specifically, to a method for stably operating a work vehicle by correcting the steering value of an autonomous work vehicle, and to an apparatus for implementing the method.

[0002] The precision agriculture sector is experiencing continuous growth driven by the introduction of new technologies. The global precision agriculture market, valued at 12.3649 trillion KRW as of 2022, is projected to achieve exponential growth by 2033, reaching 45.6891 trillion KRW with an impressive CAGR of 12.7%. Precision agriculture utilizes advanced technologies such as agricultural robots, autonomous work vehicles, sensors, drones, and GPS-based soil sampling to provide farmers with real-time data for decision-making and productivity improvement. Key technologies for implementing precision agriculture include GPS, IoT, and remote sensing applications, which assist in crop monitoring, weather forecasting, and soil management. The United States leads the market, driven by economic prosperity alongside the adoption of advanced technologies, while Japan and India demonstrate their own unique growth drivers. Although challenges such as farmer awareness and implementation costs persist, various collaborative projects undertaken by the industry are serving as initiatives to overcome these challenges. Precision agriculture promises to redefine global agriculture by promoting sustainable and efficient agricultural practices, beyond mere technological evolution.

[0003] In precision agriculture, autonomous driving technology refers to a technology that enables agricultural machinery and equipment to perform tasks automatically without human supervision. By utilizing GPS, sensors, machine learning, and artificial intelligence, this technology can enhance the efficiency of agricultural operations and improve productivity. Through precise route planning and task execution, autonomous driving technology increases the efficiency of farming operations, prevents unnecessary duplication, and enables the efficient utilization of resources. Furthermore, because autonomous driving technology in precision agriculture performs tasks along automatically set routes without human intervention, it improves work consistency and allows for consistent management of crops.

[0004] Autonomous driving technology in precision agriculture contributes to minimizing human input and increasing agricultural productivity. It enables robots or autonomous equipment to perform repetitive and tiring tasks that require human labor. Furthermore, autonomous driving technology in precision agriculture collects accurate data through sensors and GPS to provide insights into agricultural production, allowing for better decision-making and more precise management of crop growth. Autonomous driving technology is recognized as one of the core technologies bringing digital innovation to modern agriculture and improving efficiency and productivity.

[0005] The technical problem that the present invention aims to solve is to provide a method for correcting steering values ​​of an autonomous work vehicle and a device for implementing the method.

[0006] A method according to an embodiment of the present invention for solving the above technical problem comprises: a step of setting a plurality of waypoints at equal intervals from a starting point where the turning motion of a work vehicle in autonomous driving begins when turning motion of the work vehicle is detected; a step of selecting some of the plurality of waypoints and calculating a curvature value for each of the selected parts; a step of calculating a first steering value corresponding to each of the selected parts based on the calculated curvature value; and a step of calculating a deviation value by comparing a second steering value when the work vehicle passes the selected parts with the first steering value for each selected waypoint, and if the deviation value exceeds a threshold, correcting the second steering value of the work vehicle based on the deviation value.

[0007] An apparatus according to another embodiment of the present invention for solving the above technical problem comprises: a memory in which at least one program is stored; and a processor that performs calculations by executing the at least one program. When turning driving of a work vehicle in autonomous driving is detected, the processor sets a plurality of waypoints at equal intervals from a starting point where the turning driving begins, selects some of the plurality of waypoints, calculates a curvature value for each of the selected parts, calculates a first steering value corresponding to each of the selected parts based on the calculated curvature value, calculates a deviation value by comparing the first steering value with the second steering value when the work vehicle passes the selected parts for each selected waypoint, and if the deviation value exceeds a threshold, corrects the second steering value of the work vehicle based on the deviation value.

[0008] One embodiment of the present invention may provide a computer-readable recording medium storing a program for executing the above method.

[0009] According to the present invention, when an autonomous driving-based work vehicle travels along a curved path, it can perform accurate driving based on the curvature of the curved path.

[0010] FIG. 1 is a diagram exemplarily showing the result of observing a work vehicle according to the present invention from the side.

[0011] FIG. 2 is a schematic diagram showing the entire system for implementing the method according to the present invention.

[0012] FIG. 3 is a set of drawings illustrating an example of controlling a work vehicle according to one embodiment.

[0013] FIG. 4 is a diagram illustrating examples of data obtained from a work vehicle according to one embodiment.

[0014] FIG. 5 is a drawing for explaining another example of controlling a work vehicle according to one embodiment.

[0015] Figure 6 is a diagram illustrating the curved path driving of a work vehicle as an example.

[0016] FIG. 7 is a flowchart exemplarily illustrating the process of calculating a correction value to correct a steering value in the present invention.

[0017] FIGS. 8 and 9 are drawings illustrating an example in which a work vehicle predicts the curvature of a curved path.

[0018] FIG. 10 is a flowchart illustrating an example of a method according to the present invention.

[0019] A method according to an embodiment of the present invention for solving the above technical problem comprises: a step of setting a plurality of waypoints at equal intervals from a starting point where the turning motion of a work vehicle in autonomous driving begins when turning motion of the work vehicle is detected; a step of selecting some of the plurality of waypoints and calculating a curvature value for each of the selected parts; a step of calculating a first steering value corresponding to each of the selected parts based on the calculated curvature value; and a step of calculating a deviation value by comparing a second steering value when the work vehicle passes the selected parts with the first steering value for each selected waypoint, and if the deviation value exceeds a threshold, correcting the second steering value of the work vehicle based on the deviation value.

[0020] In the above method, the step of setting the plurality of waypoints at equal intervals may involve setting five waypoints at intervals of 1 meter and obtaining the coordinates of the set waypoints.

[0021] In the above method, the step of calculating the curvature value for the selected portion may select the remaining wayspoints among the plurality of waypoints, excluding the first and last waypoints based on the work vehicle.

[0022] In the above method, the first steering value can be calculated using a Pure Pursuit algorithm based on the calculated curvature value.

[0023] In the above method, the step of calculating each of the first steering values ​​is to determine whether the curvature value of the first waypoint located furthest from the starting point among the curvature values ​​for the selected portion is positive or negative, and to calculate each of the first steering values ​​only if there is a curvature value among the remaining waypoints excluding the first waypoint that is the same direction as the curvature value of the first waypoint.

[0024] In the above method, the first steering value and the second steering value may depend on the wheelbase length of the work vehicle.

[0025] In the above method, the work vehicle may be an autonomous driving-based tractor.

[0026] An apparatus according to another embodiment of the present invention for solving the above technical problem comprises: a memory in which at least one program is stored; and a processor that performs calculations by executing the at least one program. When turning driving of a work vehicle in autonomous driving is detected, the processor sets a plurality of waypoints at equal intervals from a starting point where the turning driving begins, selects some of the plurality of waypoints, calculates a curvature value for each of the selected parts, calculates a first steering value corresponding to each of the selected parts based on the calculated curvature value, calculates a deviation value by comparing the first steering value with the second steering value when the work vehicle passes the selected parts for each selected waypoint, and if the deviation value exceeds a threshold, corrects the second steering value of the work vehicle based on the deviation value.

[0027] In the above device, the processor can set five waypoints at intervals of 1 meter and obtain the coordinates of the set waypoints.

[0028] In the above device, the processor can select the remaining waypoints among the plurality of waypoints, excluding the first and last waypoints based on the work vehicle.

[0029] In the above device, the first steering value can be calculated using a Pure Pursuit algorithm based on the calculated curvature value.

[0030] In the above device, the processor determines whether the curvature value of the first waypoint located furthest from the starting point among the curvature values ​​for the selected portion is positive or negative, and calculates the first steering value each only if there is a curvature value among the remaining waypoints excluding the first waypoint that is the same direction as the curvature value of the first waypoint.

[0031] In the above device, the first steering value and the second steering value may depend on the wheelbase length of the work vehicle.

[0032] In the above device, the work vehicle may be an autonomous driving-based tractor.

[0033] One embodiment of the present invention may provide a computer-readable recording medium storing a program for executing the above method.

[0034] The present invention is capable of various modifications and may have various embodiments; specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention, and the methods for achieving them, will become clear by referring to the embodiments described below in detail together with the drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various forms.

[0035] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. When describing with reference to the drawings, identical or corresponding components are given the same reference numerals, and redundant descriptions thereof will be omitted.

[0036] In the following embodiments, terms such as first, second, etc. are used not in a limiting sense, but for the purpose of distinguishing one component from another component.

[0037] In the following embodiments, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0038] In the following embodiments, terms such as "include" or "have" mean that the features or components described in the specification are present, and do not preclude the possibility that one or more other features or components may be added.

[0039] Where an embodiment can be implemented differently, a specific process sequence may be performed differently from the order described. For example, two processes described consecutively may be performed substantially simultaneously or proceed in the reverse order of the description.

[0040] FIG. 1 is a diagram exemplarily showing the result of observing a work vehicle according to the present invention from the side.

[0041] The work vehicle illustrated in FIG. 1 includes front and rear wheels, and the front and rear wheels are enclosed by a single caterpillar. Since FIG. 1 illustrates an embodiment of a work vehicle, the work vehicle in the present invention may be a tracked vehicle as well as a general four-wheel drive vehicle. The work vehicle according to the present invention may be a work vehicle such as a tractor, harvester, excavator, bulldozer, sprinkler, rice transplanter, weeder, etc.

[0042] A work implement is connected to the rear of the work vehicle shown in FIG. 1, and the work implement can be powered by the PTO of the work vehicle's engine (or motor) and can be raised or lowered according to the hitch whenever the rear hitch of the work vehicle is raised or lowered. The rear hitch of the work vehicle is additionally equipped with a position sensor and an angle sensor so that the work implement, whose position changes due to the raising or lowering of the hitch, can be accurately detected. Although FIG. 1 schematically illustrates the rear PTO connected to the work implement at the rear of the work vehicle, depending on the embodiment, a work implement may also be placed at the front of the work vehicle, and the work implement placed at the front can also be powered by the front PTO of the work vehicle and perform various agricultural tasks as the work vehicle moves.

[0043] As illustrated in Fig. 1, there are virtually no limits to the range of tasks that can be performed by a work vehicle, such as a work vehicle. Consequently, the types of implements connected to and operated by the work vehicle are diverse, and their sizes are also bound to vary. Therefore, the user needs to accurately determine not only the overall specifications of the work vehicle that supplies power to the implement to operate it, but also the specifications (distance, size, etc.) of the parts (hitches) where the work vehicle and the implement are connected, or parts (distance, size, etc.) that must be selectively defined for physical balance or power efficiency on the work vehicle.

[0044] FIG. 2 is a schematic diagram showing the entire system for implementing the method according to the present invention.

[0045] Referring to FIG. 2, it can be seen that a system (1) according to one embodiment of the present invention includes a work vehicle (10) equipped with a steering value correction device (11), a server (20), a user terminal (50), and a GPS satellite (70). Here, the steering value correction device (11), the server (20), and the user terminal (50) can be electrically connected through a communication network (3).

[0046] The user may operate the work vehicle (10) by directly boarding it, or control the operation of the work vehicle (10) through an external device without boarding it. That is, in the present invention, the user is a person associated with the work vehicle (10), and depending on the embodiment, may be referred to as an operator or a driver. In particular, in the present invention, the user may be an owner who has purchased and owns the work vehicle (10), or, depending on the embodiment, a shared user who has been granted sharing rights to the work vehicle (10) by the owner of the work vehicle (10) and can use the work vehicle (10) for a predetermined period of time.

[0047] In the present invention, the work vehicle (10) may be agricultural machinery such as a trackor, harvester, sprayer, and weeder, or a construction vehicle such as an excavator or bulldozer. The work vehicle (10) may drive unmanned (i.e., without a driver) or drive based on the control of a driver. In one embodiment, the work vehicle (10) may be an electric tractor in which the drive unit is a motor, in which case the work vehicle (10) may omit a fuel tank for storing fuel and include a large battery or battery pack for supplying power to the motor.

[0048] The steering value correction device (11) is a type of telematics terminal and can be mounted or installed on a work vehicle (10). The steering value correction device (11) may include a processor (13) that performs various data processing or calculations, a memory (14) that stores various data used by the processor (13), etc., and a communication module (12) for communication with an external device such as a server (20).

[0049] The communication module (12) may include one or more components that enable wired / wireless communication with an external device. For example, the communication module (210) may include at least one piece of hardware necessary to implement short-range communication such as Wi-Fi or Bluetooth in a network provided by a communication network, or to implement various communications including the Internet when a LAN cable is connected.

[0050] Memory (14) is hardware that stores various data processed within the steering value correction device (11) and can store programs for processing and controlling the processor (13). Memory (14) may include RAM (random access memory) such as DRAM (dynamic random access memory) and SRAM (static random access memory), ROM (read-only memory), EEPROM (electrically erasable programmable read-only memory), CD-ROM, Blu-ray or other optical disc storage, HDD (hard disk drive), SSD (solid state drive), or flash memory.

[0051] The processor (13) can control the overall operation of the steering value correction device (11). For example, the processor (13) can control the operation of the input unit (not shown), display (not shown), communication module (12), memory (14), etc. included in the steering value correction device (11) by executing programs stored in the memory (14).

[0052] In one embodiment, the processor (13) of the steering value correction device (11) can, when a turning motion of a work vehicle in autonomous driving is detected, set a plurality of waypoints at equal intervals from the starting point where the turning motion begins, select some of the plurality of waypoints, calculate a curvature value for each selected part, calculate a first steering value corresponding to each selected part based on the calculated curvature value, calculate a deviation value by comparing the second steering value and the first steering value when the work vehicle passes the selected part for each selected waypoint, and if the deviation value exceeds a threshold, correct the second steering value of the work vehicle based on the deviation value.

[0053] In one embodiment, the processor (13) of the steering value correction device (11) can set five waypoints at intervals of 1 meter and obtain the coordinates of the set waypoints.

[0054] In one embodiment, the processor (13) of the steering value correction device (11) can select the remaining waypoints, excluding the first and last waypoints based on the work vehicle (10), among a plurality of waypoints.

[0055] In one embodiment, the first steering value calculated by the processor (13) of the steering value correction device (11) can be calculated using a Pure Pursuit algorithm based on the calculated curvature value.

[0056] In one embodiment, the processor (13) of the steering value correction device (11) determines whether the curvature value of the first waypoint located furthest from the starting point among the curvature values ​​for a selected portion is positive or negative, and calculates the first steering value for each only if there is a curvature value among the remaining waypoints excluding the first waypoint that is the same direction as the curvature value of the first waypoint.

[0057] In one embodiment, the first steering value and the second steering value calculated by the processor (13) of the steering value correction device (11) may depend on the wheelbase length of the work vehicle (10).

[0058] In one embodiment, the work vehicle (10) to which the steering value correction device (11) is applied may be an autonomous driving-based tractor.

[0059] The specific process performed by the processor (13) through the aforementioned embodiments will be described later through FIGS. 3 to FIGS. 10.

[0060] When the steering value correction device (11) is implemented as a physical device, the processor (13) may be implemented using at least one of ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), controllers, micro-controllers, microprocessors, and other electrical units for performing functions.

[0061] In addition, when the steering value correction device (11) in the present invention is implemented in the form of an application (program) that runs on an integrated data processing device such as a server, the processor (13) and memory (14) included in the steering value correction device (11) may be implemented in the form of a virtual machine that implements hardware such as DSPs, microcontrollers, RAM, ROM, HDD, etc., as software (command script).

[0062] The server (20) can support telematics services for a work vehicle (10) equipped with a steering value correction device (11). To this end, the server (20) includes a communication module (21) and can be electrically connected to the work vehicle (10) (e.g., the steering value correction device (11) of the work vehicle (10)) through the communication module (21).

[0063] Additionally, the server (20) includes memory (23) that stores a program (25) that supports telematics services. A processor (22) of the server (20) can execute the program (25) stored in memory (23) to perform data processing or calculations for telematics services. The processor (22) can load commands or data into memory (23) (e.g., volatile memory), process the stored commands or data, and store the result data in memory (23) (e.g., non-volatile memory). As an example, the server (20) may be a cloud server, but is not limited thereto.

[0064] Various information regarding the work vehicle (10) may be stored in the memory (23) of the server (20). According to one embodiment, information regarding the steering value correction device (11) may be the serial number of a telematics terminal installed in the work vehicle (10). Additionally, information regarding a driver who is driving the work vehicle (10) while riding in the work vehicle (10) may be stored in the memory (23) of the server (20).

[0065] The communication network (3) performs the function of connecting the work vehicle (10), server (20), and user terminal (50), which are components of the entire system (1), and may include various wired and wireless communication networks such as data networks, mobile communication networks, and the Internet. In particular, in the present invention, the communication network (3) includes not only the mobile communication network currently in use but also the old generation mobile communication network that has already been used and discarded, and the next generation mobile communication network for which infrastructure is to be built and used in the future. Therefore, it may be one of GSM (Global System for Mobile communications), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), CDMA 2000, LTE (Long Term Evolution), LTE-A (Long Term Evolution Advanced), 5G (5-Generation), and the 6G mobile communication network scheduled to be serviced in 2030. In addition, the communication network (3) may include a network implemented through satellite communication, such as STARLINK.

[0066] The user terminal (50) is an electronic device of a buyer who has purchased a work vehicle (10) equipped with a steering value correction device (11), and may include, for example, a desktop PC, tablet PC, laptop, smartphone, etc., but is not limited thereto. In addition, the user terminal (50) may store a program (e.g., an application) for implementing various telematics services.

[0067] An application necessary to implement the method according to the present invention may be installed on the user terminal (50). The application installed on the user terminal (50) can visually output information received from the work vehicle (10) and the steering value correction device (11) so that the user can verify it, and can calculate and output a correction value to correct information about the work vehicle (10) and the work device attached to the work vehicle (10) based on various information entered by the user. The types of information about the work vehicle (10) and the information about the work device attached to the work vehicle (10) that are output from the user terminal (50) will be described later.

[0068] The GPS satellite (70) orbits around the Earth and transmits GPS information to the GPS receiver of the work vehicle (10), thereby enabling the work vehicle (10) to estimate the heading angle by utilizing the received GPS information.

[0069] The present invention is not limited to the components shown in FIG. 2. For example, the system (1) may include additional components other than the steering value correction device (11), server (20), and user terminal (50). Additionally, other components may be added to each of the work vehicle (10), steering value correction device (11), server (20), user terminal (50), and GPS satellite (70), or some components may be omitted.

[0070] FIG. 3 is a set of drawings illustrating an example of controlling a work vehicle according to one embodiment.

[0071] FIG. 3(a) illustrates an example of a conventional work vehicle in operation, and FIG. 3(b) illustrates an example of a work vehicle in operation according to one embodiment.

[0072] Referring to FIG. 3(a), the existing work vehicle can be operated and controlled by the direct involvement of the worker (30). Specifically, after the worker (30) boards the work vehicle, the vehicle is operated by the worker (30) directly adjusting the steering device, acceleration device, and deceleration device included in the work vehicle. In addition, the worker (30) performs agricultural work by directly loading work tools onto the work vehicle or connecting a work implement to the work vehicle.

[0073] Referring to FIG. 3(b), the work vehicle (10) according to the present invention can be operated and controlled even without the worker (30) directly riding on it. Specifically, the work vehicle (10) can perform autonomous driving and autonomous work according to a control signal transmitted from an external device (e.g., the worker's (30) device, server (20), etc.).

[0074] For example, a controller capable of controlling a steering device, an acceleration device, and a deceleration device is installed in the work vehicle (10), and the work vehicle (10) can be operated according to a control signal input to the controller. In particular, the above-described controller can be implemented universally, and by being installed in the above-described existing work vehicle, autonomous driving and autonomous work can be performed without separating or modifying the elements included in the existing work vehicle.

[0075] FIG. 4 is a diagram illustrating examples of data obtained from a work vehicle according to one embodiment.

[0076] Referring to FIG. 4, the work vehicle (10) can communicate with an external device (300). Here, the external device (300) may be the server (20) or user terminal (50) of FIG. 1. The external device (300) may be any device capable of communicating with other devices, performing data computation or processing, and storing data without limitation. For example, the external device (300) may be a PC, tablet PC, smartphone, wearable device, etc., but is not limited thereto.

[0077] Various data may be generated depending on the operation and agricultural work of the work vehicle (10). For example, as the work vehicle (10) is produced, data regarding the work vehicle (10) itself (e.g., model name, horsepower, year of release, price, transmission type, appearance, specifications, etc.) may be generated. In addition, as the work vehicle (10) is operated, CAN (Controller Area Network) data, data related to accidents, data related to breakdowns, and other driving data (e.g., engine torque ratio, engine load rate, engine RPM (Revolutions Per Minute), engine operation time, cumulative fuel consumption, fuel efficiency, engine breakdown information, engine oil temperature, engine room temperature, coolant temperature, current gear ratio, transmission oil temperature, driving distance, driving time, etc.) may be generated. In addition, as agricultural work is performed with the work vehicle (10), data related to agricultural equipment, data related to crops, and data regarding the farmland where agricultural work was performed may be generated.

[0078] Data generated according to the operation of the work vehicle (10) and agricultural work can be transmitted to an external device (300). The external device (300) can output and store the transmitted data, and can also process the transmitted data according to a predetermined standard. Accordingly, various solutions related to the work vehicle (10) can be provided to the worker (30).

[0079] For example, through an external device (300), the worker (30) can perform agricultural work management, maintenance of the work vehicle (10), remote diagnosis of the work vehicle (10), and management of fuel efficiency of the work vehicle (10).

[0080] As another example, through an external device (300), the worker (30) can track the current location of the work vehicle (10) or monitor the current agricultural work of the work vehicle (10). Additionally, through an external device (300), the worker (30) can remotely start or turn off the work vehicle (10) and turn the air conditioning system of the work vehicle (10) on or off.

[0081] As another example, through an external device (300), the worker (30) can prevent the theft of the work vehicle (10) and can start or stop the work vehicle (10) without the key of the work vehicle (10). Additionally, through an external device (300), the worker (30) can detect an accident involving the work vehicle (10) or report an emergency situation (e.g., injury to the worker (30), breakdown of the work vehicle (10), etc.).

[0082] FIG. 5 is a drawing for explaining another example of controlling a work vehicle according to one embodiment.

[0083] Referring to FIG. 5, the external device (400) can output information about the current state of the work vehicle (10) through communication with the work vehicle (10). For example, the external device (400) can output information about the current location of the work vehicle (10) obtained through a GPS signal. In addition, if the work vehicle (10) is currently driving, the external device (400) can output information about the engine RPM, current speed, fuel efficiency, operating time, current gear ratio, etc. of the work vehicle (10).

[0084] Accordingly, the worker (30) can determine the current status of the work vehicle (10) using information output from the external device (400) and control the work vehicle (10) remotely. In other words, autonomous driving and / or autonomous work can be implemented by the worker (30) checking the information output from the external device (400) without boarding the work vehicle (10) and controlling various functions of the work vehicle (10) through the external device (400).

[0085] Figure 6 is a diagram illustrating the curved path driving of a work vehicle as an example.

[0086] FIG. 6 is a diagram illustrating the process of a work vehicle driving a curved path in the present invention. For convenience of explanation, it is illustrated as a two-dimensional diagram consisting of x-axis and y-axis coordinates, but according to the embodiment, the path driving process illustrated in FIG. 6 can be extended to three dimensions.

[0087] In Fig. 6, when the work vehicle is at the initial start time, init, the starting point (x init , y init steering value θ in ) init Starts driving with, and at the next point in time (x init+1 , y init+1 It can move to ). At this time, the time difference between time point init and time point init+1 may be one unit time rather than one second. Here, one unit time refers to the cycle in which the steering value correction device (11) according to the present invention performs a process of calculating the curvature at each waypoint and calculating information for correcting the steering value based on the curvature after setting waypoints on a curved path. That is, the process according to the present invention can be performed cumulatively and repeatedly while the work vehicle travels along a curved path. In FIG. 6, the work vehicle is (x t-1 , y t-1 After reaching ), if 1 unit of time has elapsed, (x t , y tIt reaches ), and at that time, the steering value of the work vehicle is θ t It could be.

[0088] FIG. 7 is a flowchart exemplarily illustrating the process of calculating a correction value to correct a steering value in the present invention.

[0089] First, the work vehicle (10) can start driving on a curved path (S710). The work vehicle (10) can specify the point where straight driving ends and curved driving begins on the path input to the work vehicle (10).

[0090] The steering value correction device (11) can predict the curvature of the curved path (S720). In step S720, while the steering value correction device (11) predicts the curvature of the curved path, it can recognize that the curved path is a path along the left or right side, and if it is still predicted to be a straight drive, the steering value δ k can be set to 0. Below, the steering value δ k It is decided to refer to it as the first steering value.

[0091] The steering value correction device (11) can calculate a correction value (S730). And, the steering value correction device (11) can set a correction target value (S740).

[0092] The steering value correction device (11) determines whether to add a correction value s to the second steering value δ calculated by the existing Pure Pursuit algorithm in step S730 (S750), and if it is necessary to add, determines a value added by 0.1 to the current s as the new correction value s (S760), otherwise determines a value added by -0.1 to the current s as the new correction value s and can accumulate it in the second steering value (S770). As shown in FIG. 7, the condition for determining whether to add a correction value s to the second steering value in step S750 is the first steering value δ kThe condition may be for determining whether the result of subtracting the second steering value δ is greater than 0, and depending on the embodiment, a preset threshold value that is not 0 may be set.

[0093] In particular, in the method according to the present invention, steps S720 to S750 can be performed repeatedly every unit of time while the work vehicle (10) is driving along a curved path. Since the method according to the present invention is performed repeatedly every unit of time while the work vehicle (10) is driving along a curved path, the steering value is continuously corrected, so that the work vehicle (10) does not deviate beyond a preset limit distance while driving along the curved path, thereby enabling accurate autonomous driving and preventing the work vehicle (10) from colliding with another work vehicle during the work process.

[0094] FIGS. 8 and 9 are drawings illustrating an example in which a work vehicle predicts the curvature of a curved path.

[0095] In FIG. 8, the steering value correction device (11) can set multiple waypoints at equal intervals along the path of the work vehicle (10) after recognizing that the curved path of the work vehicle (10) has started. In FIG. 8, a total of 5 waypoints are set, and depending on the embodiment, the number of waypoints set may be more than 5 or less than 5.

[0096] In FIG. 9, the steering value correction device (11) can select the remaining waypoints (P2, P3, P4) among the multiple waypoints (5 waypoints) in FIG. 8, excluding the first and last waypoints based on the work vehicle (10). The steering value correction device (11) can calculate the curvature κ1 between the starting point P and P2 where the curved path begins, the curvature κ2 between the starting point P and P3, and the curvature κ3 between the starting point P and P4, respectively.

[0097] The steering value correction device (11) determines whether the curvature value of the first waypoint located furthest from the starting point of the curved path is positive or negative, and can calculate the first steering value only if there is a curvature value among the remaining waypoints excluding the first waypoint that is the same as the direction of the curvature value of the first waypoint.

[0098]

[0099] Mathematical formula 1 represents the formula used by the steering value correction device (11) when calculating the first steering value. In mathematical formula 1, δ k Is The first steering value of the work vehicle (10), L represents the length of the wheelbase of the work vehicle (10), and κ represents the curvature between points.

[0100] In FIG. 9, the lateral error is defined based on the starting point P of the curved path. When the work vehicle (10) travels along the curved path, if it travels further to the right than the predetermined curved path, the lateral error of the work vehicle (10) is positive, and if it travels further to the left than the predetermined curved path, the lateral error of the work vehicle (10) is negative. The steering value correction device (11) can determine whether the work vehicle (10) is deviating from the path by comparing the direction (positive or negative) of the lateral error of the work vehicle (10) with the left or right direction (positive or negative) of the curvature value of the first waypoint located furthest away, and if the value is a preset value (e.g., 0.05m), the current steering value can be maintained without performing the steering value correction process.

[0101] FIG. 10 is a flowchart illustrating an example of a method according to the present invention.

[0102] Since the method according to FIG. 10 can be implemented by the steering value correction device (11) described in FIG. 2 and the sub-modules included in the device, the following description will be made with reference to FIG. 2 to FIG. 9, and descriptions that overlap with previously explained content will be omitted.

[0103] When the steering value correction device (11) detects turning (curved driving) of the autonomous driving work vehicle (10), it can set a plurality of waypoints at equal intervals from the starting point P where the turning starts (S1010). At this time, the waypoints set can be referred to as waypoints.

[0104] The steering value correction device (11) can calculate the curvature value at the waypoint (S1030). The steering value correction device (11) can select some of the multiple waypoints in step S1010 and calculate the curvature value for each of the selected parts.

[0105] The steering value correction device (11) can correct the curvature value based on the direction of movement of the work vehicle (10) (S1050). The steering value correction device (11) can calculate a first steering value corresponding to the selected part based on the curvature value calculated in step S1030.

[0106] The steering value correction device (11) can control the steering of the work vehicle based on the corrected curvature value (S1070). The steering value correction device (11) can calculate a deviation value by comparing the second steering value and the first steering value when the work vehicle (10) passes through a selected part, for each selected waypoint, and if the deviation value exceeds a threshold, the process of correcting the second steering value of the work vehicle based on the deviation value can be repeated every unit time while the work vehicle (10) is performing curve driving.

[0107] According to the present invention, when an autonomous driving-based work vehicle travels along a curved path, it can perform accurate driving based on the curvature of the curved path.

[0108] The embodiments according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. In this case, the medium may include a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a hardware device specifically configured to store and execute program instructions, such as a ROM, RAM, or flash memory.

[0109] Meanwhile, the above-mentioned computer program may be one specifically designed and configured for the present invention, or one known and available to those skilled in the art of computer software. Examples of computer programs may include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0110] The specific embodiments described in this invention are examples and do not limit the scope of the invention in any way. For the sake of brevity of the specification, descriptions of prior electronic configurations, control systems, software, and other functional aspects of said systems may be omitted. Additionally, the connections of lines or connecting members between components shown in the drawings are illustrative of functional connections and / or physical or circuit connections, and may be replaced or additionally represented as various functional connections, physical connections, or circuit connections in actual devices. Furthermore, unless specifically stated as “essential,” “importantly,” etc., a component may not be strictly necessary for the application of the invention.

[0111] In the specification of the present invention (particularly in the claims), the use of the term “above” and similar descriptive terms may be in both singular and plural. Furthermore, where a range is described in the present invention, it is to include the invention to which individual values ​​belonging to said range are applied (unless otherwise stated), and is equivalent to describing each individual value constituting said range in the detailed description of the invention. Finally, regarding the steps constituting the method according to the present invention, unless explicitly stated in order or otherwise stated, said steps may be performed in a suitable order. The present invention is not necessarily limited by the order in which said steps are described. The use of all examples or exemplary terms (e.g., etc.) in the present invention is merely for the purpose of describing the present invention in detail, and the scope of the present invention is not limited by said examples or exemplary terms unless limited by the claims. Furthermore, those skilled in the art will understand that various modifications, combinations, and changes may be made according to design conditions and factors within the scope of the claims or equivalents to which they are added.

Claims

1. When turning of a work vehicle in autonomous driving is detected, a plurality of waypoints are set at equal intervals from the starting point where the turning begins; A step of selecting some of the plurality of waypoints and calculating a curvature value for each of the selected some; A step of calculating a first steering value corresponding to each of the selected parts based on the above-calculated curvature value; and A method for correcting steering values ​​of an autonomous driving work vehicle, comprising the step of calculating a deviation value by comparing a second steering value and a first steering value for each selected waypoint when the work vehicle passes through a selected portion, and if the deviation value exceeds a threshold, correcting the second steering value of the work vehicle based on the deviation value.

2. In Paragraph 1, The step of setting the above plurality of waypoints at equal intervals is, A method for correcting steering values ​​of an autonomous driving work vehicle, which sets five waypoints at 1-meter intervals and obtains the coordinates of the set waypoints.

3. In Paragraph 1, The step of calculating the curvature value for the selected portion above is, A method for correcting steering values ​​of an autonomous work vehicle, wherein the first and last waypoints are excluded from the plurality of waypoints above based on the work vehicle, and the remaining waypoints are selected.

4. In Paragraph 1, The above first steering value is, A method for correcting steering values ​​of an autonomous work vehicle, calculated using a Pure Pursuit algorithm based on the above-determined curvature values.

5. In Paragraph 1, The step of calculating each of the above first steering values ​​is A method for correcting steering values ​​of an autonomous driving work vehicle, wherein among the curvature values ​​of the selected portion, the curvature value of the first waypoint located furthest from the starting point is determined to be positive or negative, and the first steering value is calculated only if among the curvature values ​​of the remaining waypoints excluding the first waypoint, there is a curvature value that is the same as the direction of the curvature value of the first waypoint.

6. In Paragraph 1, The above first steering value and second steering value are, A method for correcting steering values ​​of an autonomous work vehicle that depends on the wheelbase length of the above-mentioned work vehicle.

7. In Paragraph 1, The above work vehicle is, Method for correcting steering values ​​of an autonomous work vehicle, which is an autonomous driving-based tractor.

8. A computer-readable recording medium storing a program for executing the method according to paragraph 1.

9. Memory in which at least one program is stored; and By executing at least one of the above programs, the processor performs operations, and The above processor is, When turning motion of a work vehicle in autonomous driving is detected, multiple waypoints are set at equal intervals from the starting point where the turning motion begins, and Select some of the above multiple waypoints, and calculate the curvature value for each of the selected parts, and Based on the above-calculated curvature value, a first steering value corresponding to the above-selected part is calculated, and A steering value correction device for an autonomous work vehicle, which calculates a deviation value by comparing a second steering value and a first steering value for each selected waypoint when the work vehicle passes through a selected portion, and corrects the second steering value of the work vehicle based on the deviation value when the deviation value exceeds a threshold.

10. In Paragraph 9, The above processor is, A steering value correction device for an autonomous driving work vehicle that sets five waypoints at 1-meter intervals and obtains the coordinates of the set waypoints.

11. In Paragraph 9, The above processor is, A steering value correction device for an autonomous work vehicle that selects the remaining waypoints among the plurality of waypoints, excluding the first and last waypoints based on the work vehicle.

12. In Paragraph 9, The above first steering value is, A steering value correction device for an autonomous work vehicle, calculated using a Pure Pursuit algorithm based on the above-determined curvature value.

13. In Paragraph 9, The above processor is, A steering value correction device for an autonomous driving work vehicle, which determines whether the curvature value of the first waypoint located furthest from the starting point among the curvature values ​​of the selected portion is positive or negative, and calculates the first steering value each only if there is a curvature value among the remaining waypoints excluding the first waypoint that is the same direction as the curvature value of the first waypoint.

14. In Paragraph 9, The above first steering value and second steering value are, A steering value correction device for an autonomous work vehicle that depends on the wheelbase length of the above-mentioned work vehicle.

15. In Paragraph 9, The above work vehicle is, A steering value correction device for an autonomous work vehicle, which is an autonomous driving-based tractor.