Automatic travel device

Abstract

Provided is a technology enabling travel control so that uniform traveling can be performed regardless of the actual environment. A camera 101 photographs an object to be detected in the traveling direction of an automatic travel device 100 and acquires image data. An adjustment unit 104 adjusts the traveling direction of the automatic travel device 100 on the basis of the image data. The adjustment unit 104 abstracts an image of a crop S, which is the object to be detected in the image data, and adjusts the traveling direction of the automatic travel device 100 on the basis of the result. According to the present disclosure, it is possible to adjust the traveling direction according to the arrangement of crops regardless of the actual environment. For example, the traveling direction can be adjusted stably regardless of the growth states of the crops.

Description

Automatic driving device

[0001] The present invention relates to an automatic driving device that drives automatically.

[0002] Patent Document 1 discloses a technique for a path generation method that generates a target path for a work vehicle to travel automatically in a field where work objects are arranged in multiple rows. Patent Document 2 discloses a technique for a paddy field weeding robot that includes a body, drive units provided on the left and right sides of the body, sensors provided at the front center and on the left and right sides of the body, and a paddy field surface soil agitator, and that travels while avoiding obstacles and agitates the surface soil.

[0003] JP 2021-166559 A JP 2007-129910 A

[0004] However, with the techniques described in Patent Documents 1 and 2, it is difficult to perform driving control that takes into account the actual environment.

[0005] The present disclosure provides a technology that enables driving control so that an automated driving device that works along crops planted under predetermined conditions can drive consistently regardless of the actual environment.

[0006] The autonomous driving device of the present invention is an autonomous driving device that performs predetermined tasks on detected objects arranged in the direction of travel, and is equipped with an acquisition unit that acquires image data of the detected objects photographed in the direction of travel of the autonomous driving device, and an adjustment unit that adjusts the direction of travel of the autonomous driving device based on the image data, wherein the adjustment unit performs abstraction processing on the detected objects in the image data and adjusts the direction of travel of the autonomous driving device based on the results.

[0007] According to the present invention, consistent driving can be achieved regardless of the actual environment.

[0008] FIG. 1 is an external perspective view of an automatic driving device 100 according to the present disclosure. FIG. 2 is a schematic diagram of an automatic driving device 100 according to the present embodiment traveling through a field H. FIG. 3 is a block diagram showing the functional configuration of the automatic driving device 100. FIG. 4 is a diagram showing abstraction processing. FIG. 5 is a diagram showing an overview of the recognition processing to tilt detection processing of the automatic driving device 100 according to the present disclosure. FIG. 6 is a flowchart showing the operation of the automatic driving device 100 according to the present disclosure. FIG. 7 is a diagram showing the range photographed by the automatic driving device 100 according to the present disclosure. FIG. 8 is a diagram showing an example of the hardware configuration of the automatic driving device 100 according to an embodiment of the present disclosure.

[0009] The present invention will be described with reference to the accompanying drawings. Whenever possible, the same parts are designated by the same reference numerals and redundant explanations will be omitted.

[0010] 1, an automated driving device 100 travels across a field H and crops S using crawlers (wheel drive mechanism and steering mechanism 106). The automated driving device 100 has a camera 101, and travels according to the arrangement of crops S in the field H photographed by the camera 101.

[0011] 2 is a schematic diagram of the automated driving device 100 of this embodiment traveling through a field H. As shown in FIG. 2, the automated driving device 100 recognizes the arrangement of the crops S planted in the field H, and travels along a travel route R that follows that arrangement. The automated driving device 100 makes a U-turn at the end of the field H and travels through the entire field H.

[0012] The automated driving device 100 is equipped with a camera 101, and recognizes the arrangement of the crops S based on image data captured by the camera 101. The automated driving device 100 is equipped with a wheel drive mechanism, a steering mechanism 106, and a working unit 107. The working unit 107 is, for example, a weeding mechanism. The automated driving device 100 drives through the field H to weed weeds other than the crops S. The weeding mechanism is one example, and the working unit 107 may be configured to perform other working functions.

[0013] 3 is a block diagram showing the functional configuration of the automated driving device 100. As shown in the figure, the automated driving device 100 includes a camera 101, a recognition unit 102, a WARP conversion unit 103, an adjustment unit 104, a speed control unit 105, a wheel drive mechanism and steering mechanism 106, and a working unit 107.

[0014] Camera 101 is arranged facing the direction of travel of automatic driving device 100, and is a part that photographs crops and the like arranged in the direction of travel and acquires still image data thereof, and functions as an acquisition unit that acquires image data. Camera 101 may capture a video and extract still image data from it, or may capture still images at predetermined intervals.

[0015] The recognition unit 102 is a part that recognizes the end of the crop area and the field H. In other words, the recognition unit 102 is a part that recognizes the crops and weeds, which are the detection targets, from the image data captured by the camera 101. The recognition unit 102 recognizes the arrangement direction of the crops, etc. from the image data.

[0016] The WARP conversion unit 103 is a part that performs WARP conversion processing on image data acquired by the camera 101. The WARP conversion unit 103 is a part that performs coordinate conversion so that the crop rows become straight, and converts image data of the crops photographed from the front by the camera 101 into image data viewed from a viewpoint above the center of the photographing range.

[0017] The adjustment unit 104 is a part that superimposes multiple judgment windows on a recognition target (for example, a crop S in a field H) included in the image data captured by the camera 101, and adjusts the deviation in the traveling direction of the automated driving device 100 relative to the arrangement of the recognition target based on the degree of overlap between the judgment windows and the recognition target. The adjustment unit 104 also performs abstraction processing on the image of the crop S. The abstraction processing compresses the image of the crop S (recognition target) upward to abstract it. Abstraction will be described later.

[0018] The speed control unit 105 is a part that adjusts the traveling speed according to the position of the automatic traveling device 100 in the field H and its positional relationship with the crops S determined by the adjustment unit 104.

[0019] The wheel drive mechanism and steering mechanism 106 are mechanical parts of the automatic driving device 100. The wheel drive mechanism is a mechanism for moving at a speed according to the control by the adjustment unit 104. The wheel drive mechanism and steering mechanism 106 are mechanisms for moving in a direction according to the traveling direction set by the adjustment unit 104. The automatic driving device 100 has other mechanisms, but they will not be described here.

[0020] The working unit 107 is a part that performs weeding processing as the automatic traveling device 100 moves. The working unit 107 is equipped with a claw-shaped tool, and performs weeding by dragging the claw-shaped tool as the automatic traveling device 100 moves. However, the working unit 107 is not limited to this, and may also be a mechanism for top dressing or spraying pesticides. It may also be equipped with a robotic arm to thin and harvest the crops S. It may also be equipped with a camera (for a different purpose from the camera 101) and photograph the crops, making it possible to predict yields and determine the occurrence of pests and diseases.

[0021] The abstraction process performed by the adjustment unit 104 will now be described. Fig. 4 shows a specific example of this abstraction process. Fig. 4(a) shows an image of a photographed recognition target (crop S) that has been WARP converted. The crop S is recognized in this image. Through WARP conversion, the crop is converted so that it is aligned vertically (in the Y-axis direction). The abstraction target window w1 indicates the range of abstraction for this crop.

[0022] 4A, the adjustment unit 104 abstracts the crop within each of the abstraction target windows w1 to w6. That is, the adjustment unit 104 slices (divides) the image after WARP conversion along the X axis, and adds the sliced ​​(divided) images (images for each of the abstraction target windows w1 to w6) along the Y axis to reduce the dimensions. The same process is performed for the other abstraction target windows.

[0023] 4B is a diagram showing an image of a row of crops in which the crop S has been abstracted. As shown in the figure, the diagram shows the result of adding images in the Y-axis direction for each abstraction target window w. Adding images means adding the pixels of the images that make up the crop S in the Y-axis direction.

[0024] More specifically, the image shown in FIG. 4C is divided in the horizontal direction, i.e., in the x-axis direction. The number of divisions is defined as image div n Then, the number of vertical pixels of the image is imgh, the number of horizontal pixels is imgw, and the pixel value at (x,y) is im(x,y). The number of vertical pixels of the divided image is imgh / image div n Next, in the divided image, pixel values ​​are added vertically. At this time, the pixel value of the nth divided image is expressed by the following formula. Note that the pixel value is expressed as 1 / 0, but it may also be expressed in multiple stages.

[0025] This formula takes a larger value the more pixels there are along the vertical axis in the image in Figure 4(a). In other words, the value increases in areas where crops are arranged in rows. In Figure 4(b), x-coordinates where the formula exceeds the threshold are represented as white, and other areas are represented as black.

[0026] This processing allows accurate determination of the arrangement of rows of crops S in the early stages of growth. Generally, crops S in the early stages of growth have small leaf areas, and due to variations in germination, they may be photographed as regions that are closer to dotted lines rather than solid lines, i.e., discontinuous regions. Therefore, in order to recognize these regions as a single line, the image is compressed vertically, i.e., in the y-axis direction, to make the regions continuous and abstract.

[0027] Next, an overview of the recognition process to the tilt detection process of the automated driving device 100 of the present disclosure will be described. Fig. 5 is a schematic diagram thereof. As shown in the figure, Fig. 5(a) shows an image PT captured by the camera 101. The symbol DR indicates the traveling direction.

[0028] 5B shows an image recognized by the recognition unit 102. In this image, the white portion of the image expressed in black and white is recognized as the crop S.

[0029] FIG. 5C is a diagram showing this recognition in chronological order. As the automated driving device 100 advances, it moves to the edge of the field H. In this case, the crops S are not recognized, and the recognized image contains many black areas. Specifically, the adjustment unit 104 arranges the areas of the crop regions in chronological order, and when the moving average falls below a threshold, it detects the end of the field. Then, when the adjustment unit 104 determines that it has moved to the edge of the field H, it performs U-turn control.

[0030] Fig. 5(d) shows the image shown in Fig. 5(b) after WARP conversion processing. As shown in the figure, coordinate conversion is performed on the recognized image including the crops S shown in Fig. 5(b) so that the arrangement of the crops S becomes a straight line. The processing of Fig. 5(c) and the processing of Fig. 5(d) to Fig. 4(g) are performed in parallel.

[0031] 5(e) is a diagram showing the collision detection of the crawler (wheel drive mechanism 106). As shown in the figure, the adjustment unit 104 performs global processing (crawler collision detection) when the result is within a threshold, calculates the area of ​​the crop area that contacts two preset regions R1 and R2, and controls the robot in a direction that removes the crop from the ROI. These regions R1 and R2 are so-called ROIs (regions of interest), and their positions are set according to the crawler width and position.

[0032] Region R1 is represented by two adjacent rectangles, a left region and a right region. In this border determination process, the difference between the number of pixels contained in the left region and the number of pixels contained in the right region of the crop region is used to calculate how far the vehicle should be shifted to the right or left. The same applies to region R2.

[0033] FIG. 5(f) is a diagram illustrating the abstraction process as described above.

[0034] FIG. 5( g) illustrates the inclination recognition of the crop S. The adjustment unit 104 detects a circumscribing rectangle GK that takes into account the inclination of the region representing the abstracted crop, and recognizes the inclination as the inclination of the crop. This circumscribing rectangle GK is a rectangle recognized using known technology, and the adjustment unit 104 searches for the one with the smallest area, taking into account the rotation (the traveling direction of the automated driving device 100). If the number of recognized rows of crops S is small, the adjustment unit 104 issues a warning to the user and adjusts the speed to slow down. Furthermore, the circumscribing rectangle GK that is longest in the vertical axis direction, i.e., the longest row of crops S that can be recognized, is designated as the representative circumscribing rectangle, and its rotation angle (angle relative to the vertical direction) is output as the inclination of the crop row.

[0035] The abstraction process and crop row gradient detection process described above mainly involve addition in the row direction of the array and searching for closed regions, and can be performed very quickly.

[0036] 6 is a flowchart showing the operation of the automated driving device 100 of the present disclosure. As shown in the figure, in the automated driving device 100, the camera 101 captures an image of a crop while the automated driving device 100 is traveling (S101: FIG. 5(a)). The recognition unit 102 performs a recognition process on the crop to obtain a recognized image (S102: FIG. 5(b)). The WARP conversion unit 103 performs a WARP conversion (perspective conversion) on the recognized image to obtain an image in which the crop S is represented as a straight line (S103: FIG. 5(d)).

[0037] The adjustment unit 104 performs a crawler hit determination on the recognized image (before WARP conversion) obtained in process S102 (S104: FIG. 5(e)). In parallel, the adjustment unit 104 performs an abstraction process (S105: FIG. 5(f)). The adjustment unit 104 also recognizes the end of the field H (S106: FIG. 5(c)). These processes S104 to S106 are executed in coordination. For example, if the adjustment unit 104 determines that the field has turned at a predetermined angle through the abstraction process, it performs a crawler hit determination and controls the steering.

[0038] The adjustment unit 104 then controls the driving mechanism and the steering mechanism 106 to control the traveling direction (S107). Specifically, if the end of the field H is not detected, the adjustment unit 104 instructs the vehicle to travel at a constant speed in the straight-line direction. On the other hand, if the end of the field H is detected, the adjustment unit 104 instructs the vehicle to linearly reduce the speed and make a U-turn. The threshold value for the simple moving average slope of the crop region area is determined based on the number of frames from when the crops are displayed on the entire screen during constant speed traveling until they reach the end of the field H and completely disappear from the screen.

[0039] If the angle of the recognized abstract crop CS deviates from the front by more than a certain amount, the adjustment unit 104 steers in a direction to correct the angle of the crop row. If the angle deviation of the crop row is within a certain range, the adjustment unit 104 steers in a direction to reduce the area of ​​the crop that comes into contact with the crawler contact determination windows R1 and R2. This process corrects angle deviations that cannot be corrected by the crawler contact determination process based on the detected crop row inclination, and also makes it possible to perform fine adjustments using the crawler contact determination process. Furthermore, proportional-integral-differential (PID) control is used in steering angle command to suppress steering wobble.

[0040] Based on these recognition results, the adjustment unit 104 causes the wheel drive mechanism and steering mechanism 106 to adjust the speed, adjust the steering, and perform a U-turn.

[0041] In the present disclosure, the depth used for the determination may be automatically changed when performing global processing and determining the presence or absence of crop rows. Figure 7 is a diagram showing the range photographed by the automated driving device 100 of the present disclosure. For example, when the automated driving device 100 enters a crop row, travels through an area lacking stalks, or when crop growth is minimal, the angle of the camera 101 is raised or lowered to view more of the crop S1 at the depth. Specifically, when the crop row area is less than a certain size, the recognition amount dc of the crop S in the Y-axis direction (depth) is reduced to enable viewing further away.

[0042] On the other hand, when following normal rows of crops, it is sufficient to look only at the vicinity, and increasing the number of crops S recognized by image will make traveling more stable.

[0043] Next, a description will be given of the effects of the presently disclosed automated driving device 100. In the present disclosure, the automated driving device 100 is a vehicle that performs a predetermined task on detection targets arranged in the traveling direction.

[0044] The camera 101 captures and acquires image data of a detection object facing the traveling direction of the automated driving device 100. The adjustment unit 104 adjusts the traveling direction of the automated driving device 100 based on the image data. The adjustment unit 104 performs abstraction processing on the image of the crop S, which is the detection object in the image data, and adjusts the traveling direction of the automated driving device 100 based on the result of the abstraction processing.

[0045] According to this disclosure, it is possible to adjust the direction of travel in accordance with the arrangement of crops regardless of the actual environment. For example, it is possible to stably adjust the direction of travel regardless of the state of growth of the crops. By abstracting, stable recognition can be performed even in situations where crops are not growing and image processing is difficult.

[0046] In the present disclosure, the adjustment unit 104 performs WARP conversion on the image data and performs abstraction processing on the converted image, thereby enabling stable determination of the traveling direction.

[0047] The abstraction process performed by the adjustment unit 104 in the present disclosure compresses the converted image of the detection target (crop S) in the vertical axis direction so that the image is continuous, thereby enabling recognition of the crop even when the crop is not growing.

[0048] Compressing in the vertical axis direction involves cutting out the converted image of the detection object (crop S) in the horizontal axis direction at a predetermined width and adding them in the vertical axis direction to perform compression.

[0049] Such abstraction reduces the amount of calculation and simplifies the process.

[0050] The adjustment unit 104 detects a circumscribing rectangle for the image of the abstracted detection object (crop S), and recognizes the inclination of the circumscribing rectangle as the inclination of the detection object.

[0051] If the tilt of the detected object satisfies a predetermined condition, the adjustment unit 104 superimposes a collision detection window (detection windows R1 and R2) on the converted image and adjusts the traveling direction based on the degree of contact between the automated driving device 100 and the detected object (crop S). For example, the predetermined condition is that the adjustment unit 104 performs steering processing in a direction that reduces the area of ​​the crop S that contacts the collision detection windows R1 and R2.

[0052] The contact determination windows R1 and R2 are set along the trajectory of the automatic driving device 100. More specifically, they are set at positions corresponding to the positions of the crawlers.

[0053] The automated driving device 100 of the present disclosure has the following configuration.

[0054] [1] An automated driving device that performs a predetermined task on a detected object arranged in a traveling direction, comprising: an acquisition unit that acquires image data of the detected object photographed in the traveling direction of the automated driving device; and an adjustment unit that adjusts the traveling direction of the automated driving device based on the image data, wherein the adjustment unit performs abstraction processing on the detected object in the image data and adjusts the traveling direction of the automated driving device based on the result of the processing.

[0055] [2] The automatic driving device according to [1], wherein the adjustment unit performs WARP conversion on the image data and performs abstraction processing on the converted image.

[0056] [3] The automatic driving device according to [2], wherein the abstraction process in the adjustment unit compresses the converted image of the detection object in the vertical axis direction so that the image is continuous.

[0057] [4] The automatic driving device according to [3], wherein the compression in the vertical axis direction is performed by cutting out the converted image of the detection object in a predetermined width in the horizontal axis direction and adding them in the vertical axis direction.

[0058] [5] The automatic driving device according to [4], wherein the adjustment unit detects a circumscribing rectangle for the image of the abstracted detection object, and recognizes the inclination of the circumscribing rectangle as the inclination of the detection object.

[0059] [6] The automatic driving device described in [5], wherein, when the tilt of the detection object satisfies a predetermined condition, the adjustment unit superimposes a collision detection window on the converted image and adjusts the direction of travel based on the degree of contact between the automatic driving device and the detection object.

[0060] [7] The automatic driving device according to [6], wherein the collision detection window is set along the trajectory of the automatic driving device.

[0061] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0062] For example, the automated driving device 100 according to an embodiment of the present disclosure may function as a computer that performs processing of the automated driving method of the present disclosure. Fig. 8 is a diagram illustrating an example of a hardware configuration of the automated driving device 100 according to an embodiment of the present disclosure. The automated driving device 100 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0063] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the automated driving apparatus 100 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0064] Each function of the automatic driving device 100 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0065] The processor 1001, for example, runs an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control unit, an arithmetic unit, a register, etc. For example, the above-mentioned recognition unit 102, WARP conversion unit 103, adjustment unit 104, etc. may be realized by the processor 1001.

[0066] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with the programs. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the recognition unit 102 of the automated driving device 100 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be used for other functional blocks. While the above-described various processes have been described as being executed by one processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0067] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be referred to as a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing the autonomous driving method according to one embodiment of the present disclosure.

[0068] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0069] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD).

[0070] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0071] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0072] Each aspect / embodiment described in the present disclosure may be applied to at least one of systems using LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (New Radio), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, UWB (Ultra-Wide Band), Bluetooth (registered trademark), or other suitable systems, and next-generation systems enhanced based on these. Furthermore, a combination of multiple systems (e.g., a combination of at least one of LTE and LTE-A with 5G, etc.) may also be applied.

[0073] Furthermore, the automated driving device 100 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), or a graphics processing unit (GPU), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0074] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0075] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0076] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0077] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0078] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0079] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0080] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0081] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0082] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0083] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0084] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0085] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0086] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0087] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0088] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0089] 100...automatic driving device, 101...camera, 102...recognition unit, 103...WARP conversion unit, 104...adjustment unit, 105...speed control unit, 106...wheel drive mechanism and steering mechanism, 107...working unit

Claims

1. An autonomous driving device that performs a specified task on a detected object arranged in a traveling direction of the autonomous driving device, comprising: an acquisition unit that acquires image data of the detected object photographed in the traveling direction of the autonomous driving device; and an adjustment unit that adjusts the traveling direction of the autonomous driving device based on the image data, wherein the adjustment unit performs abstraction processing on the detected object in the image data and adjusts the traveling direction of the autonomous driving device based on the result of the abstraction processing.

2. The automatic driving device according to claim 1, wherein the adjustment unit performs WARP conversion on the image data and performs abstraction processing on the converted image.

3. The automatic driving device according to claim 2, wherein the abstraction process in the adjustment unit compresses the converted image of the detection object in the vertical axis direction so that the image is continuous.

4. The automatic driving device according to claim 3, wherein the compression in the vertical axis direction is performed by cutting out the converted image of the detection object in the horizontal axis direction at a predetermined width and adding them in the vertical axis direction.

5. The automatic driving device according to claim 4, wherein the adjustment unit detects a circumscribing rectangle for the image of the abstracted detection object, and recognizes the inclination of the circumscribing rectangle as the inclination of the detection object.

6. The automatic driving device according to claim 5, wherein, when the inclination of the detected object satisfies a predetermined condition, the adjustment unit superimposes a collision detection window on the converted image and adjusts the traveling direction based on the degree of contact between the automatic driving device and the detected object.

7. The automatic driving device according to claim 6, wherein the collision detection window is set along the trajectory of the automatic driving device.

Images