Autonomous vehicle and object detection method therefor

Abstract

Provided is an object detection method for an autonomous vehicle, comprising the steps of: measuring a steering angle of a front wheel; selecting one object detection range from among a plurality of predetermined object detection ranges on the basis of the measured steering angle of the front wheel; and detecting an object in the vicinity of the autonomous vehicle on the basis of the selected object detection range.

Description

Autonomous vehicle and object detection method thereof

[0001] The present disclosure relates to an autonomous vehicle and an object detection method thereof.

[0002] As object detection sensors improve in performance and autonomous driving algorithms become more sophisticated, autonomous vehicles that can automatically adjust speed or change direction to avoid collisions with surrounding objects are becoming more widespread.

[0003] Object detection sensors can generate two-dimensional (2D) or three-dimensional (3D) images of the surrounding environment by irradiating electromagnetic waves in a fixed direction. They can then measure the distance and location of surrounding objects by using the time it takes for the electromagnetic waves to reflect off surrounding objects and return. The measured distances and locations of objects can be utilized in various applications, such as collision avoidance systems for autonomous vehicles, automatic parking assistance systems, and route planning.

[0004] However, because object detection sensors detect objects within a fixed distance and angle range, they have limitations in effectively detecting surrounding objects when the vehicle is turning left or right, or when passing over unpaved roads or uneven terrain, such as speed bumps. Furthermore, because of their fixed object detection range, object detection sensors often waste computational resources by detecting objects in the opposite direction of the vehicle's rotation, even when the possibility of collision is extremely low.

[0005] The present disclosure provides an object detection method that can effectively and efficiently detect surrounding objects when an autonomous vehicle turns or passes over irregular terrain.

[0006] According to one aspect of the present disclosure, a method for detecting an object in an autonomous vehicle may include the steps of measuring a steering angle of a front wheel, selecting one object detection range from among a plurality of predetermined object detection ranges based on the measured steering angle of the front wheel, and detecting an object around the autonomous vehicle based on the selected object detection range, wherein the plurality of object detection ranges may include at least a first object detection range, a second object detection range, and a third object detection range, and the step of selecting one object detection range from among the plurality of predetermined object detection ranges may include selecting the first object detection range when the measured steering angle of the front wheel is a first range corresponding to straight driving of the autonomous vehicle, selecting the second object detection range when the measured steering angle of the front wheel is a second range corresponding to a left turn of the autonomous vehicle, and selecting the third object detection range when the measured steering angle of the front wheel is a third range corresponding to a right turn of the autonomous vehicle.

[0007] In one embodiment, each of the plurality of object detection ranges may include a first area corresponding to the front center of the autonomous vehicle and determined by the second boundary and the third boundary, a second area corresponding to the front left side of the autonomous vehicle and determined by the third boundary and the fourth boundary, and a third area corresponding to the front right side of the autonomous vehicle and determined by the first boundary and the second boundary.

[0008] In one embodiment, the second boundary and the third boundary of the first object detection range may be symmetrical about the F axis so that the first area of ​​the first object detection range is symmetrical about the F axis corresponding to the front of the autonomous vehicle, and the second area of ​​the first object detection range is adjacent to the left side of the first area of ​​the first object detection range, the third area of ​​the first object detection range is adjacent to the right side of the first area of ​​the first object detection range, and the first boundary and the fourth boundary of the first object detection range may be symmetrical about the F axis so that the second area and the third area of ​​the first object detection range are symmetrical about the F axis.

[0009] In one embodiment, the angle of the second boundary of the second object detection range may be greater than the angle of the second boundary of the first object detection range by a first predetermined angle, and the angle of the third boundary of the second object detection range may be greater than the angle of the third boundary of the first object detection range by a second predetermined angle, so that the first area, the second area, and the third area of ​​the second object detection range are biased to the left of the first area, the second area, and the third area of ​​the first object detection range.

[0010] In one embodiment, the first region, the second region, and the third region of the third object detection range may be biased to the right relative to the first region, the second region, and the third region of the first object detection range, such that the angle of the second boundary of the third object detection range may be smaller by a third predetermined angle than the angle of the second boundary of the first object detection range, and the angle of the third boundary of the third object detection range may be smaller by a fourth predetermined angle than the angle of the third boundary of the first object detection range.

[0011] In one embodiment, the method may further include a step of receiving a user input for setting an object detection distance, and the step of selecting one object detection range from among the plurality of predetermined object detection ranges may further include selecting the one object detection range based on the object detection distance.

[0012] In one embodiment, the commercial method may further include the step of measuring a speed of the autonomous vehicle, and the step of determining an object detection distance based on the measured speed, and the step of selecting one object detection range from among the plurality of predetermined object detection ranges may further select the one object detection range based on the object detection distance.

[0013] In one embodiment, the first object detection range, the second object detection range, and the third object detection range may correspond to a first object detection distance, and the plurality of object detection ranges may further include a fourth object detection range corresponding to a second object detection distance greater than the first object detection distance and a straight movement of the autonomous vehicle, a fifth object detection range corresponding to the second object detection distance and a left turn of the autonomous vehicle, a sixth object detection range corresponding to the second object detection distance and a right turn of the autonomous vehicle, a seventh object detection range corresponding to a third object detection distance greater than the second object detection distance and a straight movement of the autonomous vehicle, an eighth object detection range corresponding to the third object detection distance and a left turn of the autonomous vehicle, and a ninth object detection range corresponding to the third object detection distance and a right turn of the autonomous vehicle.

[0014] In one embodiment, the straight ahead may be a backward straight ahead, the left turn may be a backward left turn, the right turn may be a backward right turn, and each of the plurality of object detection ranges may include a fourth area corresponding to the rear center of the autonomous vehicle, a fifth area corresponding to the rear left side of the autonomous vehicle, and a sixth area corresponding to the rear right side of the autonomous vehicle.

[0015] According to one aspect of the present disclosure, an autonomous vehicle may include a steering angle sensor that measures a steering angle of a front wheel, a control unit that selects one object detection range from among a plurality of predetermined object detection ranges based on the measured steering angle of the front wheel, and an object detection sensor that detects an object around the autonomous vehicle based on the selected object detection range, wherein the plurality of object detection ranges may include at least a first object detection range, a second object detection range, and a third object detection range, and wherein the control unit may select the first object detection range when the measured steering angle of the front wheel is a first range corresponding to straight driving of the autonomous vehicle, select the second object detection range when the measured steering angle of the front wheel is a second range corresponding to a left turn of the autonomous vehicle, and select the third object detection range when the measured steering angle of the front wheel is a third range corresponding to a right turn of the autonomous vehicle.

[0016] In one embodiment, each of the plurality of object detection ranges may include a first area corresponding to the front center of the autonomous vehicle and determined by the second boundary and the third boundary, a second area corresponding to the front left side of the autonomous vehicle and determined by the third boundary and the fourth boundary, and a third area corresponding to the front right side of the autonomous vehicle and determined by the first boundary and the second boundary.

[0017] In one embodiment, the second boundary and the third boundary of the first object detection range may be symmetrical about the F axis so that the first area of ​​the first object detection range is symmetrical about the F axis corresponding to the front of the autonomous vehicle, and the second area of ​​the first object detection range may be adjacent to the left side of the first area of ​​the first object detection range, and the third area of ​​the first object detection range may be adjacent to the right side of the first area of ​​the first object detection range, and the first boundary and the fourth boundary of the first object detection range may be symmetrical about the F axis so that the second area and the third area of ​​the first object detection range are symmetrical about the F axis.

[0018] In one embodiment, the angle of the second boundary of the second object detection range may be greater than the angle of the second boundary of the first object detection range by a first predetermined angle, and the angle of the third boundary of the second object detection range may be greater than the angle of the third boundary of the first object detection range by a second predetermined angle, so that the first area, the second area, and the third area of ​​the second object detection range are biased to the left of the first area, the second area, and the third area of ​​the first object detection range.

[0019] In one embodiment, the first region, the second region, and the third region of the third object detection range may be biased to the right relative to the first region, the second region, and the third region of the first object detection range, such that the angle of the second boundary of the third object detection range may be smaller by a third predetermined angle than the angle of the second boundary of the first object detection range, and the angle of the third boundary of the third object detection range may be smaller by a fourth predetermined angle than the angle of the third boundary of the first object detection range.

[0020] In one embodiment, the autonomous vehicle may further include a human-machine interface (HMI) that receives a user input for setting an object detection distance, and the control unit may further select the one object detection range based on the object detection distance.

[0021] In one embodiment, the autonomous vehicle may further include a speed sensor that measures the speed of the autonomous vehicle, and the control unit may determine an object detection distance based on the measured speed, and select the one object detection range further based on the object detection distance.

[0022] In one embodiment, the first object detection range, the second object detection range, and the third object detection range may correspond to a first object detection distance, and the plurality of object detection ranges may further include a fourth object detection range corresponding to a second object detection distance greater than the first object detection distance and a straight movement of the autonomous vehicle, a fifth object detection range corresponding to the second object detection distance and a left turn of the autonomous vehicle, a sixth object detection range corresponding to the second object detection distance and a right turn of the autonomous vehicle, a seventh object detection range corresponding to a third object detection distance greater than the second object detection distance and a straight movement of the autonomous vehicle, an eighth object detection range corresponding to the third object detection distance and a left turn of the autonomous vehicle, and a ninth object detection range corresponding to the third object detection distance and a right turn of the autonomous vehicle.

[0023] In one embodiment, the straight ahead may be a backward straight ahead, the left turn may be a backward left turn, the right turn may be a backward right turn, and each of the plurality of object detection ranges may include a fourth area corresponding to the rear center of the autonomous vehicle, a fifth area corresponding to the rear left side of the autonomous vehicle, and a sixth area corresponding to the rear right side of the autonomous vehicle.

[0024] An autonomous vehicle according to one embodiment can effectively and efficiently detect surrounding objects when turning or passing over irregular terrain by adjusting the object detection range according to speed and steering angle.

[0025] FIG. 1 is a block diagram illustrating components of an autonomous vehicle according to one embodiment.

[0026] FIGS. 2A to 2C are drawings for explaining an object detection range of an autonomous vehicle according to one embodiment.

[0027] FIG. 3 illustrates an object detection range according to an object detection distance and a steering angle of a front wheel according to one embodiment.

[0028] Figure 4 is a flowchart of an object detection method of an autonomous vehicle according to one embodiment.

[0029] The terms used in this disclosure are selected from widely used, common terms, taking into account the functions of the disclosure. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. In certain cases, terms may be arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the relevant description. Therefore, the terms used in this disclosure should not be defined simply as names, but rather based on the meanings of the terms and the overall content of the disclosure.

[0030] Singular expressions may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art described herein.

[0031] The term "and / or" in this disclosure includes any combination of a plurality of related described components or any one of a plurality of related described components.

[0032] Terms including ordinal numbers, such as "first" or "second," used in this disclosure may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

[0033] In this disclosure, the expression “at least one of a, b, or c” may refer to “a,” “b,” “c,” “a and b,” “a and c,” “b and c,” “all of a, b, and c,” or variations thereof.

[0034] When a part of the specification is said to "include" a component, this does not exclude other components, but rather implies the inclusion of other components, unless otherwise specifically stated. Furthermore, terms such as "part" and "module" used in the specification refer to a unit that processes at least one function or operation, which may be implemented in hardware, software, or a combination of hardware and software.

[0035] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings so that those skilled in the art can easily practice the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In addition, in the drawings, parts that are not related to the description are omitted to clearly explain the present disclosure, and similar parts are designated with similar reference numerals throughout the specification. In addition, the reference numerals used in each drawing are only for the purpose of describing each drawing, and different reference numerals used in different drawings do not indicate different elements.

[0036] FIG. 1 is a block diagram illustrating components of an autonomous vehicle according to one embodiment.

[0037] Referring to FIG. 1, an autonomous vehicle (100) may include an object detection sensor (110), a steering angle sensor (120), a speed sensor (130), a human-machine interface (HMI) (140), and a control unit (150). However, not all of the illustrated components are essential components. The autonomous vehicle (100) may be implemented with more components than those illustrated in FIG. 1, or may be implemented with fewer components.

[0038] An autonomous vehicle (100) may refer to a vehicle that is electronically controllable using a processing device such as an Electronic Control Unit (ECU), regardless of its intended use or power source. For example, the autonomous vehicle (100) may be, but is not limited to, a passenger car used as a means of transportation (e.g., a sedan, an SUV (Sports Utility Vehicle), etc.), a truck used for cargo transport, or an agricultural work vehicle used for farming (e.g., a tractor, a combine harvester, a rice transplanter, etc.). In addition, the autonomous vehicle (100) may be, but is not limited to, an internal combustion engine vehicle, an electric vehicle, or a hybrid vehicle.

[0039] In the present disclosure, autonomous driving may include not only fully autonomous driving (e.g., Level 5) that requires no driver intervention at all, but also advanced driver assistance systems (ADAS) (e.g., Level 1 or 2), such as collision avoidance, lane keeping, and adaptive cruise control. When the autonomous vehicle (100) is an agricultural work vehicle, autonomous driving may include autonomous work in which the autonomous vehicle (100) performs work along a predetermined path on its own without a user.

[0040] The object detection sensor (110) can detect objects around the autonomous vehicle (100). For example, the object detection sensor (110) can detect the distance between the autonomous vehicle (100) and the object, the size of the object (e.g., width, height, length, etc.), etc. The object detection sensor (190) may include at least one of an ultrasonic sensor, an infrared sensor, a radar (RADAR, Radio Detection And Ranging), a LiDAR (Light Detection and Ranging), and a camera, but is not limited thereto. For example, a LiDAR can detect the distance and position of an object around the autonomous vehicle (100) by irradiating light and using the time it takes for the light to reflect off a surrounding object and return.

[0041] The object detection sensor (110) may be installed at the front of the autonomous vehicle (100) to detect an object in front while the autonomous vehicle (100) moves forward, or may be installed at the rear of the autonomous vehicle (100) to detect an object at the rear while the autonomous vehicle (100) moves backward. Accordingly, depending on the implementation method, the autonomous vehicle (100) may include one or more object detection sensors (110).

[0042] As described below, the object detection range of the autonomous vehicle (100) may vary depending on certain conditions. Here, the object detection range may include an object detection angle and an object detection distance. The object detection angle may refer to a horizontal field of view (FOV) at which the autonomous vehicle (100) detects an object, and the object detection distance may refer to a maximum distance at which the autonomous vehicle (100) can detect an object. The object detection angle may be determined based on a steering angle of the front wheels, and the object detection distance may be determined based on a speed of the autonomous vehicle (100) or set by a user input via the HMI (140). Here, the speed of the autonomous vehicle (100) may refer to a forward speed when the autonomous vehicle (100) is moving forward, and may refer to a reverse speed when the autonomous vehicle (100) is moving backward.

[0043] For example, when the object detection distance is determined based on the speed of the autonomous vehicle (100), the object detection distance may be 3 m when the speed of the autonomous vehicle (100) is less than 6 km / h, the object detection distance may be 3.5 m when the speed of the autonomous vehicle (100) is 6 km / h or more and less than 10 km / h, and the object detection distance may be 4 m when the speed of the autonomous vehicle (100) is 10 km / h or more, but is not limited thereto.

[0044] For example, if the object detection distance is set by user input, the user can select one of 3 m, 3.5 m, and 4 m through the HMI (140), and the autonomous vehicle (100) can set the distance selected by the user as the object detection distance.

[0045] The change in the object detection range may be implemented by the control unit (150) or by the object detection sensor (110). This will be described later with reference to FIG. 3.

[0046] The steering angle sensor (120) can measure the steering angle of the front wheel. The steering angle sensor (120) can be any one of a rotary angle sensor, a hall effect sensor, a potentiometer, or a linear position sensor, but is not limited thereto. For example, the rotary angle sensor can be mounted on a steering knuckle or a steering link to detect the absolute angle of the rotary shaft, the hall effect sensor can be mounted inside a steering shaft or steering rack to detect the angle by a change in a magnetic field, the potentiometer can be mounted on a steering shaft or a rotary joint to measure the angle by using a change in electrical resistance, and the linear position sensor can be mounted on a piston rod of a hydraulic steering cylinder or outside the cylinder to measure the linear displacement of the steering cylinder to calculate the steering angle.

[0047] The speed sensor (130) can measure the speed of the autonomous vehicle (100). The speed sensor (130) can be any one of a wheel speed sensor, an output shaft speed sensor, a crankshaft speed sensor, or a GPS speed sensor, but is not limited thereto. For example, the wheel speed sensor can be mounted on a hub near a wheel to measure the rotational speed of the wheel, the output shaft speed sensor can be mounted on a transmission or transfer case to measure the rotational speed of a rotational shaft inside the gearbox, the crankshaft speed sensor can estimate the speed of the autonomous vehicle (100) using the rotational speed of the crankshaft, and the GPS speed sensor can calculate the speed of the autonomous vehicle (100) based on a GPS satellite signal.

[0048] The HMI (140) may provide an interface through which a user and an autonomous vehicle (100) may interact. The HMI (140) may include an input interface for receiving user input and an output interface for displaying information related to the autonomous vehicle (100). The HMI (140) may receive a user input for setting an object detection distance. In one embodiment, the HMI (140) may be implemented as a touch screen capable of receiving a touch input. In this case, the user may set the object detection distance through the touch input. For example, the object detection distance that the user can set may be one of 3 m, 3.5 m, or 4 m, but is not limited thereto.

[0049] The control unit (150) can control the overall operations of the autonomous vehicle (100). The control unit (150) can include a memory that stores one or more commands or programs, and a processor that executes one or more commands or programs stored in the memory to enable the autonomous vehicle (100) to detect an object.

[0050] For example, the memory may include, but is not limited to, at least one of flash memory, a hard disk, random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and programmable read-only memory (PROM).

[0051] For example, the processor may be configured as at least one of, but is not limited to, a CPU (Central Processing Unit), a microprocessor, an AP (Application Processor), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), an ECU (Electronic Control Unit), a TCU (Transmission Control Unit), and a VCU (Vehicle Control Unit).

[0052] FIGS. 2A to 2C are drawings for explaining an object detection range of an autonomous vehicle according to one embodiment.

[0053] In FIGS. 2A to 2C, examples of detecting an object in front while the autonomous vehicle (100) moves forward are illustrated. However, as described above, the autonomous vehicle (100) may also detect an object in the rear while moving backward. Therefore, in the present disclosure, “straight ahead,” “left turn,” and “right turn” should be understood as being merely distinctions based on the steering angle of the front wheels, and are unrelated to whether the autonomous vehicle (100) moves forward or backward. For example, “straight ahead” should be understood as referring to both forward straight ahead and backward straight ahead indiscriminately, “left turn” should be understood as referring to both forward left turn and backward left turn indiscriminately, and “right turn” should be understood as referring to both forward right turn and backward right turn indiscriminately.

[0054] Below, an example of an autonomous vehicle (100) detecting an object in front will be described first, and then an example of detecting an object in the rear will be described.

[0055] FIG. 2a illustrates an object detection range when the steering angle of the front wheels is a first range corresponding to straight driving of the autonomous vehicle (100), FIG. 2b illustrates an object detection range when the steering angle of the front wheels is a second range corresponding to a left turn of the autonomous vehicle (100), and FIG. 2c illustrates an object detection range when the steering angle of the front wheels is a third range corresponding to a right turn of the autonomous vehicle (100). Here, the first range is a section where the steering angle of the front wheels is -20 degrees or more and +20 degrees or less, the second range is a section where the steering angle of the front wheels is more than +20 degrees, and the third range may be a section where the steering angle of the front wheels is less than -20 degrees, but is not limited thereto. At this time, a positive steering angle corresponds to a left turn, and a negative steering angle corresponds to a right turn.

[0056] The object detection range of the autonomous vehicle (100) may be composed of multiple regions. For example, as illustrated in FIGS. 2A to 2C , the object detection range may be composed of a first region (210) corresponding to the front center of the autonomous vehicle (100), a second region (220) corresponding to the front left side of the autonomous vehicle (100), and a third region (230) corresponding to the front right side of the autonomous vehicle (100). However, the number of regions constituting the object detection range is not limited thereto.

[0057] As illustrated in FIGS. 2A to 2C, each area constituting the object detection range can be determined by a boundary (indicated by an arrow). In FIGS. 2A to 2C, the first boundary refers to an arrow having a length of d1 and an angle of θ1, the second boundary refers to an arrow having a length of d2 and an angle of θ2, the third boundary refers to an arrow having a length of d3 and an angle of θ3, and the fourth boundary refers to an arrow having a length of d4 and an angle of θ4. Here, the 'angle' of each boundary refers to an angle in a counterclockwise direction with respect to the R axis, the origin (O) corresponds to the position of the object detection sensor (110), and the L axis, the R axis, and the F axis correspond to the left, right, and front of the object detection sensor (110), respectively. At this time, it is assumed that θ4 > θ3 > θ2 > θ1.

[0058] The outer boundary of each area constituting the object detection range can be determined in an appropriate shape by a person skilled in the art to which the present disclosure pertains, such as a regular shape such as a circle, an ellipse, a straight line, or an irregular, non-regular shape.

[0059] Referring to FIG. 2A, when the steering angle of the front wheels is in the first range corresponding to straight driving of the autonomous vehicle (100), the first region (210) may be symmetrical left and right with respect to the F axis, and the second region (220) and the third region (230) may be regions adjacent to the left and right sides of the first region (210), respectively, and may be symmetrical left and right with respect to each other with respect to the F axis. That is, when the steering angle of the front wheels is in the first range, the first boundary and the fourth boundary may be symmetrical left and right with respect to the F axis, and the second boundary and the third boundary may be symmetrical left and right with respect to the F axis. For example, the angles of the first boundary, the second boundary, the third boundary, and the fourth boundary may be determined to satisfy mathematical expression 1.

[0060]

[0061] For example, the angle (θ1) of the first boundary may be 0 degrees, the angle (θ2) of the second boundary may be 60 degrees, the angle (θ3) of the third boundary may be 120 degrees, and the angle (θ4) of the fourth boundary may be 180 degrees, but is not limited thereto.

[0062] When the steering angle of the front wheel is in the first range, the lengths of the first boundary, the second boundary, the third boundary, and the fourth boundary may be determined based on the speed of the autonomous vehicle (100) or based on the object detection distance set by the user input through the HMI (140). At this time, the lengths of the second boundary and the third boundary, which have a relatively smaller angle from the F axis, may be determined to be longer than the lengths of the first boundary and the fourth boundary, respectively. For example, when the steering angle of the front wheel is in the first range, the lengths of the first boundary, the second boundary, the third boundary, and the fourth boundary may be determined to satisfy mathematical expression 2.

[0063]

[0064] Referring to FIG. 2B, when the steering angle of the front wheels is in the second range corresponding to a left turn of the autonomous vehicle (100), the first region (210), the second region (220), and the third region (230) may be biased to the left compared to when the steering angle of the front wheels is in the first range. For example, the angle (θ1) of the first boundary may be 0 degrees, the angle (θ2) of the second boundary and the angle (θ3) of the third boundary may each increase by a predetermined angle compared to when the steering angle of the front wheels is in the first range, and the angle (θ4) of the fourth boundary may be 180 degrees, but is not limited thereto.

[0065] When the steering angle of the front wheels is in the second range, the lengths of the third boundary and the fourth boundary corresponding to the front left side of the autonomous vehicle (100) may each increase by a predetermined length, and the lengths of the first boundary and the second boundary corresponding to the front right side of the autonomous vehicle (100) may each decrease by a predetermined length. At this time, the lengths of the second boundary and the third boundary, which have a relatively smaller angle from the F axis, may be determined to be longer than the lengths of the first boundary and the fourth boundary, respectively. For example, when the steering angle of the front wheels is in the second range, the lengths of the first boundary, the second boundary, the third boundary, and the fourth boundary may be determined to satisfy mathematical expression 3.

[0066]

[0067] Referring to FIG. 2c, when the steering angle of the front wheels is in the third range corresponding to a right turn of the autonomous vehicle (100), the first region (210), the second region (220), and the third region (230) may be biased to the right compared to when the steering angle of the front wheels is in the first range. For example, the angle (θ1) of the first boundary may be 0 degrees, the angle (θ2) of the second boundary and the angle (θ3) of the third boundary may each be reduced by a predetermined angle compared to when the steering angle of the front wheels is in the first range, and the angle (θ4) of the fourth boundary may be 180 degrees, but is not limited thereto.

[0068] When the steering angle of the front wheels is in the third range, the lengths of the first boundary and the second boundary corresponding to the front right side of the autonomous vehicle (100) may each increase by a predetermined length, and the lengths of the third boundary and the fourth boundary corresponding to the front left side of the autonomous vehicle (100) may each decrease by a predetermined length. At this time, the lengths of the second boundary and the third boundary, which have a relatively smaller angle from the F axis, may be determined to be longer than the lengths of the first boundary and the fourth boundary, respectively. For example, when the steering angle of the front wheels is in the third range, the lengths of the first boundary, the second boundary, the third boundary, and the fourth boundary may be determined to satisfy mathematical expression 3.

[0069]

[0070] Meanwhile, in an example in which an autonomous vehicle (100) detects an object at the rear while moving backward, the object detection range may be composed of a fourth area corresponding to the rear center of the autonomous vehicle (100), a fifth area corresponding to the rear left side of the autonomous vehicle (100), and a sixth area corresponding to the rear right side of the autonomous vehicle (100). However, the number of areas constituting the object detection range is not limited thereto. In this case, the fourth area, the fifth area, and the sixth area may be areas symmetrical with respect to the first area (210), the second area (220), and the third area (230), respectively, with respect to the LR axis.

[0071] For example, the fourth region, the fifth region, and the sixth region can be determined by a fifth boundary having a length d1 and an angle of -θ1, a sixth boundary having a length d2 and an angle of -θ2, a seventh boundary having a length d3 and an angle of -θ3, and an eighth boundary having a length d4 and an angle of -θ4.

[0072] The shapes of the fourth, fifth, and sixth regions according to the steering angle of the front wheels are symmetrical with respect to the shapes of the first region (210), the second region (220), and the third region (230) with respect to the LR axis, respectively, and similarly, the angles and lengths of the fifth boundary, the sixth boundary, the seventh boundary, and the eighth boundary may also be symmetrical with respect to the angles and lengths of the first boundary, the second boundary, the third boundary, and the fourth boundary with respect to the LR axis.

[0073] FIG. 3 illustrates an object detection range according to an object detection distance and a steering angle of a front wheel according to one embodiment.

[0074] FIG. 3 illustrates examples of multiple object detection ranges (301, 302, 303, 304, 305, 306, 307, 308, and 309) according to the steering angle of the front wheels when the agricultural work vehicle (100) moves forward, in examples where the object detection distances are 3 m, 3.5 m, and 4 m. Since the object detection range when the agricultural work vehicle (100) moves backward is a form that is flipped upside down from the form illustrated in FIG. 3, only the object detection range when moving forward will be described below.

[0075] For example, if the object detection distance is 3 m and the steering angle of the front wheels is a first range corresponding to straight driving of the autonomous vehicle (100), the autonomous vehicle (100) can select the first object detection range (301) among a plurality of object detection ranges (301, 302, 303, 304, 305, 306, 307, 308, and 309).

[0076] For example, if the object detection distance is 3 m and the steering angle of the front wheels is a second range corresponding to a left turn of the autonomous vehicle (100), the autonomous vehicle (100) can select the second object detection range (302) among a plurality of object detection ranges (301, 302, 303, 304, 305, 306, 307, 308, and 309).

[0077] For example, if the object detection distance is 3 m and the steering angle of the front wheels is in the third range corresponding to a right turn of the autonomous vehicle (100), the autonomous vehicle (100) can select the third object detection range (303) among the plurality of object detection ranges (301, 302, 303, 304, 305, 306, 307, 308, and 309).

[0078] For example, if the object detection distance is 3.5 m and the steering angle of the front wheels is the first range corresponding to the straight movement of the autonomous vehicle (100), the autonomous vehicle (100) can select the fourth object detection range (304) among the plurality of object detection ranges (301, 302, 303, 304, 305, 306, 307, 308, and 309).

[0079] For example, if the object detection distance is 3.5 m and the steering angle of the front wheels is the second range corresponding to a left turn of the autonomous vehicle (100), the autonomous vehicle (100) can select the fifth object detection range (305) among the plurality of object detection ranges (301, 302, 303, 304, 305, 306, 307, 308, and 309).

[0080] For example, if the object detection distance is 3.5 m and the steering angle of the front wheels is the third range corresponding to a right turn of the autonomous vehicle (100), the autonomous vehicle (100) can select the sixth object detection range (306) among the plurality of object detection ranges (301, 302, 303, 304, 305, 306, 307, 308, and 309).

[0081] For example, if the object detection distance is 4 m and the steering angle of the front wheels is the first range corresponding to the straight movement of the autonomous vehicle (100), the autonomous vehicle (100) can select the seventh object detection range (307) among the plurality of object detection ranges (301, 302, 303, 304, 305, 306, 307, 308, and 309).

[0082] For example, if the object detection distance is 4 m and the steering angle of the front wheels is the second range corresponding to a left turn of the autonomous vehicle (100), the autonomous vehicle (100) can select the eighth object detection range (308) among the plurality of object detection ranges (301, 302, 303, 304, 305, 306, 307, 308, and 309).

[0083] For example, if the object detection distance is 4 m and the steering angle of the front wheels is the third range corresponding to a right turn of the autonomous vehicle (100), the autonomous vehicle (100) can select the ninth object detection range (309) among the plurality of object detection ranges (301, 302, 303, 304, 305, 306, 307, 308, and 309).

[0084] Multiple object detection ranges (301, 302, 303, 304, 305, 306, 307, 308 and 309) can be predetermined and stored in the object detection sensor (110) or the control unit (150).

[0085] As described above, changing the object detection range may be implemented by the control unit (150) or by the object detection sensor (110).

[0086] In an example where the object detection range is changed by the control unit (150), the control unit (150) can select one object detection range from among a plurality of predetermined object detection ranges (301, 302, 303, 304, 305, 306, 307, 308 and 309) (stored in the control unit (150)) based on the object detection distance and the steering angle of the front wheels.

[0087] In this example, the object detection sensor (110) can detect an object for a range set as an initial value by the manufacturer, regardless of the object detection range selected by the control unit (150). The control unit (150) can receive measurement data from the object detection sensor (110), and if an object is detected outside the selected object detection range, it does not treat it as detected, but only treats it as detected when the object is detected within the selected object detection range.

[0088] Here, treating an object as detected means that the control unit (150) takes follow-up action on the detected object, such as setting a driving path to avoid the object, stopping the autonomous vehicle (100) to avoid collision with the object, or generating an alert to notify the user that the object has been detected.

[0089] In an example where the object detection range changes by the object detection sensor (110), the object detection sensor (110) can receive the object detection distance and the steering angle of the front wheel from the control unit (150), and can select one object detection range from among a plurality of predetermined object detection ranges (301, 302, 303, 304, 305, 306, 307, 308, and 309) (stored in the object detection sensor (110)) based on the received object detection distance and the steering angle of the front wheel.

[0090] In this example, the object detection sensor (110) can detect an object for a selected object detection range, and the control unit (150) can take follow-up actions as described above when an object is detected.

[0091] Figure 4 is a flowchart of an object detection method of an autonomous vehicle according to one embodiment.

[0092] The operations of FIG. 4 can be performed when the autonomous vehicle (100) is driving autonomously.

[0093] Referring to FIG. 4, in operation 410, the autonomous vehicle (100) can measure the steering angle of the front wheels. Operation 410 can be performed by a steering angle sensor (120).

[0094] In operation 420, the autonomous vehicle (100) may select one object detection range from among a plurality of predetermined object detection ranges based on the measured steering angle of the front wheels. Here, the object detection range may include an object detection angle.

[0095] Each object detection range may be composed of a first area (210) corresponding to the front center of the autonomous vehicle (100), a second area (220) corresponding to the front left side of the autonomous vehicle (100), and a third area (230) corresponding to the front right side of the autonomous vehicle (100).

[0096] In operation 430, the autonomous vehicle (100) can detect objects around the autonomous vehicle (100) based on the selected object detection range.

[0097] The embodiments of the present disclosure described above may be implemented in the form of a recording medium containing computer-executable instructions, such as program modules, executed by a computer. Computer-readable media may include any volatile and nonvolatile media, removable and non-removable media that can be accessed by a computer. Furthermore, computer-readable media may include computer storage media and communication media. Computer storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Communication media may include computer-readable instructions, data structures, or other data in a modulated data signal, such as program modules.

[0098] The above description of the present disclosure is provided for illustrative purposes only, and those skilled in the art will readily appreciate that the present disclosure can be readily modified into other specific forms without altering the technical spirit or essential characteristics of the present disclosure. Therefore, the above descriptions should be understood as illustrative and not limiting. For example, components described in a single form may be implemented in a distributed manner, and similarly, components described in a distributed manner may be implemented in a combined manner.

[0099] The scope of the present disclosure is indicated by the claims set forth below rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present disclosure.

Claims

1. Step of measuring the steering angle of the front wheel; A step of selecting one object detection range among a plurality of predetermined object detection ranges based on the measured steering angle of the front wheel; and A step of detecting an object around an autonomous vehicle based on the selected object detection range is included, The above multiple object detection ranges include at least a first object detection range, a second object detection range, and a third object detection range, The step of selecting one object detection range from among the plurality of predetermined object detection ranges is: If the steering angle of the front wheel measured above is a first range corresponding to straight driving of the autonomous vehicle, the first object detection range is selected, If the steering angle of the front wheel measured above is in the second range corresponding to a left turn of the autonomous vehicle, the second object detection range is selected, If the steering angle of the front wheel measured above is in the third range corresponding to the right turn of the autonomous vehicle, the third object detection range is selected. A method for object detection in autonomous vehicles.

2. In paragraph 1, Each of the above multiple object detection ranges is A first area corresponding to the front center of the autonomous vehicle and determined by the second boundary and the third boundary, A second area corresponding to the front left side of the autonomous vehicle and determined by the third boundary and the fourth boundary, and A third area corresponding to the front right side of the autonomous vehicle and determined by the first boundary and the second boundary, A method for object detection in autonomous vehicles.

3. In paragraph 2, The second boundary and the third boundary of the first object detection range are symmetrical left and right with respect to the F axis, so that the first area of ​​the first object detection range is symmetrical left and right with respect to the F axis corresponding to the front of the autonomous vehicle. The first boundary and the fourth boundary of the first object detection range are symmetrical left and right with respect to the F axis, such that the second area of ​​the first object detection range is adjacent to the left side of the first area of ​​the first object detection range, the third area of ​​the first object detection range is adjacent to the right side of the first area of ​​the first object detection range, and the second area and the third area of ​​the first object detection range are symmetrical left and right with respect to the F axis. Object detection method for autonomous vehicles.

4. In paragraph 3, The angle of the second boundary of the second object detection range is larger by a first predetermined angle than the angle of the second boundary of the first object detection range, and the angle of the third boundary of the second object detection range is larger by a second predetermined angle than the angle of the third boundary of the first object detection range, so that the first area, the second area, and the third area of ​​the second object detection range are biased to the left compared to the first area, the second area, and the third area of ​​the first object detection range. Object detection method for autonomous vehicles.

5. In paragraph 3, The angle of the second boundary of the third object detection range is smaller by a third predetermined angle than the angle of the second boundary of the first object detection range, and the angle of the third boundary of the third object detection range is smaller by a fourth predetermined angle than the angle of the third boundary of the first object detection range, so that the first area, the second area, and the third area of ​​the third object detection range are biased to the right compared to the first area, the second area, and the third area of ​​the first object detection range. Object detection method for autonomous vehicles.

6. In paragraph 1, The method further comprises the step of receiving a user input setting an object detection distance, The step of selecting one object detection range from among the plurality of predetermined object detection ranges comprises selecting the one object detection range further based on the object detection distance. A method for object detection in autonomous vehicles.

7. In paragraph 1, The above method, Step of measuring the speed of an autonomous vehicle; and Further comprising a step of determining an object detection distance based on the measured speed, The step of selecting one object detection range from among the plurality of predetermined object detection ranges comprises selecting the one object detection range further based on the object detection distance. A method for object detection in autonomous vehicles.

8. In paragraph 6 or 7, The first object detection range, the second object detection range, and the third object detection range correspond to the first object detection distance, The above multiple object detection ranges are: A second object detection distance greater than the first object detection distance and a fourth object detection range corresponding to the straight movement of the autonomous vehicle, The second object detection distance and the fifth object detection range corresponding to the left turn of the autonomous vehicle, The second object detection distance and the sixth object detection range corresponding to the right turn of the autonomous vehicle, A third object detection distance greater than the second object detection distance and a seventh object detection range corresponding to the straight movement of the autonomous vehicle, The third object detection distance and the eighth object detection range corresponding to the left turn of the autonomous vehicle, and Further including the third object detection distance and the ninth object detection range corresponding to the right turn of the autonomous vehicle. A method for object detection in autonomous vehicles.

9. In paragraph 1, The above straight line is a straight line backwards, The above left turn is a rear left turn, The above right turn is a rear right turn, Each of the above multiple object detection ranges is A fourth area corresponding to the rear center of the autonomous vehicle, A fifth area corresponding to the rear left side of the autonomous vehicle, and Including a sixth area corresponding to the rear right side of the autonomous vehicle, A method for object detection in autonomous vehicles.

10. In an autonomous vehicle (100), A steering angle sensor (120) that measures the steering angle of the front wheel; A control unit (150) that selects one object detection range among a plurality of predetermined object detection ranges based on the measured steering angle of the front wheel; and It includes an object detection sensor (110) that detects objects around the autonomous vehicle based on the selected object detection range, The above multiple object detection ranges include at least a first object detection range, a second object detection range, and a third object detection range, The above control unit (150) If the steering angle of the front wheel measured above is in the first range corresponding to straight driving of the autonomous vehicle (100), the first object detection range is selected, If the steering angle of the front wheel measured above is in the second range corresponding to a left turn of the autonomous vehicle (100), the second object detection range is selected, If the steering angle of the front wheel measured above is in the third range corresponding to the right turn of the autonomous vehicle (100), the third object detection range is selected. Self-driving cars.

11. In paragraph 10, Each of the above multiple object detection ranges is A first area corresponding to the front center of the autonomous vehicle (100) and determined by the second boundary and the third boundary, A second area corresponding to the front left side of the autonomous vehicle (100) and determined by the third boundary and the fourth boundary, and A third area corresponding to the front right side of the autonomous vehicle (100) and determined by the first boundary and the second boundary, Self-driving cars.

12. In paragraph 11, The second boundary and the third boundary of the first object detection range are symmetrical left and right with respect to the F axis, so that the first area of ​​the first object detection range is symmetrical left and right with respect to the F axis corresponding to the front of the autonomous vehicle (100). The first boundary and the fourth boundary of the first object detection range are symmetrical left and right with respect to the F axis, such that the second area of ​​the first object detection range is adjacent to the left side of the first area of ​​the first object detection range, the third area of ​​the first object detection range is adjacent to the right side of the first area of ​​the first object detection range, and the second area and the third area of ​​the first object detection range are symmetrical left and right with respect to the F axis. Autonomous vehicle.

13. In paragraph 12, The angle of the second boundary of the second object detection range is larger by a first predetermined angle than the angle of the second boundary of the first object detection range, and the angle of the third boundary of the second object detection range is larger by a second predetermined angle than the angle of the third boundary of the first object detection range, so that the first area, the second area, and the third area of ​​the second object detection range are biased to the left compared to the first area, the second area, and the third area of ​​the first object detection range. Autonomous vehicle.

14. In paragraph 12, The first area, the second area, and the third area of ​​the third object detection range are biased to the right of the first area and the third area of ​​the first object detection range, so that the angle of the second boundary of the third object detection range is smaller by a third predetermined angle than the angle of the second boundary of the first object detection range, and the angle of the third boundary of the third object detection range is smaller by a fourth predetermined angle than the angle of the third boundary of the first object detection range. Autonomous vehicle.

15. In paragraph 10, The above autonomous vehicle (100) further includes an HMI (Human-Machine Interface) (140) that receives user input for setting an object detection distance, The above control unit (150) selects the one object detection range based on the object detection distance. Self-driving cars.

16. In paragraph 10, The autonomous vehicle (100) further includes a speed sensor (130) that measures the speed of the autonomous vehicle (100). The above control unit (150) determines the object detection distance based on the measured speed, and selects the one object detection range further based on the object detection distance. Self-driving cars.

17. In paragraph 15 or 16, The first object detection range, the second object detection range, and the third object detection range correspond to the first object detection distance, The above multiple object detection ranges are: A second object detection distance greater than the first object detection distance and a fourth object detection range corresponding to the straight movement of the autonomous vehicle (100), The second object detection distance and the fifth object detection range corresponding to the left turn of the autonomous vehicle (100), The second object detection distance and the sixth object detection range corresponding to the right turn of the autonomous vehicle (100), A third object detection distance greater than the second object detection distance and a seventh object detection range corresponding to the straight movement of the autonomous vehicle (100), The third object detection distance and the eighth object detection range corresponding to the left turn of the autonomous vehicle (100), and Further including the third object detection distance and the ninth object detection range corresponding to the right turn of the autonomous vehicle (100). Self-driving cars.

18. In paragraph 10, The above straight line is a straight line backwards, The above left turn is a rear left turn, The above right turn is a rear right turn, Each of the above multiple object detection ranges is A fourth area corresponding to the rear center of the autonomous vehicle (100), A fifth area corresponding to the rear left side of the autonomous vehicle (100), and Including a sixth area corresponding to the rear right side of the autonomous vehicle (100), A method for object detection in autonomous vehicles.

Images