Autonomous driving vehicle, autonomous driving method, and autonomous driving program

Abstract

To prevent an autonomous traveling vehicle from avoiding an obstacle or stopping more than necessary, by advancing if advancing is possible even if there is an obstacle in an advancing direction.SOLUTION: An autonomous traveling vehicle 100 includes a pushing-away determination unit 130 that determines whether or not it is possible to push away an obstacle and advance when presence of the obstacle in an advancing direction is detected. The autonomous traveling vehicle 100 includes a state detection sensor 11 that detects a state of the autonomous traveling vehicle 100. The pushing-away determination unit 130 determines whether or not the autonomous traveling vehicle can advance while pushing away the obstacle, based on a state of the autonomous traveling vehicle 100 detected by the state detection sensor 11 when the obstacle is pushed away.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an autonomous vehicle, an autonomous driving method, and an autonomous driving program. [Background technology]

[0002] A typical autonomous robot is equipped with a laser and a camera, and has the ability to avoid collisions or stop when it predicts a collision with an obstacle. Therefore, if an autonomous robot is surrounded by obstacles, it will stop and become unable to operate.

[0003] In recent years, autonomous mobile robots for agricultural use have been developed to work in greenhouses or in mountainous areas. These robots also have the same function as the autonomous mobile robots described above when predicting collisions with obstacles.

[0004] On the other hand, large autonomous agricultural machines used in large-scale agriculture in plain areas such as the United States operate on the premise that they will tolerate collisions with branches and leaves that arise as plants grow, etc. Therefore, they generally do not have the lasers and cameras necessary to avoid collisions.

[0005] Patent Document 1 discloses a mobile platform that recognizes crop plants from images captured by a camera, avoids the crop plants, and sweeps away weeds between the plants. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Publication No. 2022-052948 Summary of the Invention [Problem to be solved by the invention]

[0007] An autonomous agricultural robot travels along a predetermined route to perform its main function, such as watering or transporting crops. Generally, plants in greenhouses or mountainous areas, including crops, trees, and weeds, grow quickly and can impede the progress of autonomous robots. In reality, autonomous robots can simply push through obstacles such as leaves, twigs, weeds, or scraps of plastic. However, current autonomous robots only detect the presence of an obstacle, which can lead to the robot avoiding or stopping even when it encounters a minor obstacle, hindering the autonomous robot's ability to perform its primary function. Furthermore, the technology in Patent Document 1 recognizes crop stalks from images captured by a camera, and if they are crop stalks, it avoids them, and sweeps up weeds. However, even with the technology in Patent Document 1, it only avoids crop stalks, but avoids or stops if it encounters other obstacles such as leaves, twigs, or pieces of plastic, which again hinders the autonomous robot from performing its main function.

[0008] The present disclosure aims to prevent an autonomous vehicle from needlessly avoiding or stopping an obstacle by allowing the autonomous vehicle to proceed if possible even if an obstacle is in its path of travel. [Means for solving the problem]

[0009] The autonomous vehicle according to the present disclosure is an autonomous vehicle that drives autonomously, an obstacle sensor that detects obstacles present in the direction of travel; a state detection sensor that detects the state of the autonomous vehicle; an autonomous travel control unit that controls the autonomous travel to occur at a speed below a predetermined threshold speed when the obstacle sensor detects an obstacle; and a push-aside determination unit that determines whether or not it is possible to push aside the obstacle detected by the obstacle sensor and proceed based on the state of the autonomous vehicle detected by the state detection sensor when the obstacle detected by the obstacle sensor is pushed while the autonomous travel control unit is controlling the autonomous travel to occur at a speed below the threshold speed. Equipped with. [Effects of the Invention]

[0010] The autonomous vehicle according to the present disclosure includes a push-aside determination unit that, when an obstacle is detected in the traveling direction, determines whether it is possible to push the obstacle aside and proceed. Thus, the autonomous vehicle according to the present disclosure has the effect of being able to proceed even if there is an obstacle in the traveling direction if it is possible, and preventing the autonomous vehicle from avoiding or stopping more than necessary. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of an autonomous vehicle according to a first embodiment. [Figure 2] FIG. 1 is a diagram showing an example of a typical operation of an autonomous mobile robot. [Figure 3] FIG. 2 is a diagram showing an example of operation of an autonomous vehicle according to the first embodiment. [Figure 4] 4 is a flowchart showing an example of the operation of the autonomous vehicle according to the first embodiment. [Figure 5] 1 is a schematic diagram of an autonomous vehicle according to a first embodiment. [Figure 6] FIG. 10 is a diagram showing an example of the configuration of an autonomous vehicle according to a modification of the first embodiment. [Figure 7] FIG. 10 is a flowchart showing an example of the operation of an autonomous vehicle according to the second embodiment. [Figure 8] FIG. 10 is a diagram showing an example of types of obstacles and obstacle information according to the second embodiment. [Figure 9] FIG. 10 is a diagram showing another example of types of obstacles and obstacle information according to the second embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of an autonomous vehicle according to a modification of the second embodiment. [Figure 11] FIG. 10 is a diagram showing an example of an obstacle that must not be pushed aside according to a modification of the second embodiment. [Figure 12] FIG. 10 is a diagram showing an example of operation of an autonomous vehicle according to a modification of the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] The present embodiment will be described below with reference to the drawings. In each drawing, identical or corresponding parts are designated by the same reference numerals. In the description of the embodiment, the description of identical or corresponding parts will be omitted or simplified as appropriate. Furthermore, the size relationships of the components in the drawings below may differ from the actual ones. Furthermore, in the description of the embodiment, directions or positions such as up, down, left, right, front, rear, front and back may be indicated. These notations are provided for the convenience of explanation and do not limit the arrangement, direction or orientation of devices, instruments or parts.

[0013] Embodiment 1 ***Configuration Description*** FIG. 1 is a diagram showing an example of the configuration of an autonomous vehicle 100 according to this embodiment. The autonomous vehicle 100 is a mobile body that travels autonomously. The autonomous vehicle 100 is also an autonomous robot that travels autonomously and performs a main function. The autonomous vehicle 100 may be an AMR that performs work unmanned. Alternatively, it may be a PMV that carries a person on board and performs work. AMR is an abbreviation for Autonomous Mobile Robot. PMV is an abbreviation for Personal Mobility Vehicle.

[0014] Autonomous vehicle 100 is a mobile object equipped with a computer. Specifically, autonomous vehicle 100 includes processor 910, as well as other hardware such as memory 921, auxiliary storage device 922, input interface 930, output interface 940, and communication device 950. Processor 910 is connected to the other hardware via wired or wireless communication and controls the other hardware. Autonomous vehicle 100 also includes a state detection sensor 11, an obstacle sensor 12, a speaker 13, a main function device 14, and a driving device 15. State detection sensor 11 specifically includes a thrust sensor 111 and a pressure sensor 112. Obstacle sensor 12 specifically includes a camera 121 and a laser scanner 122. These pieces of hardware are also connected to other pieces of hardware via wired or wireless communication.

[0015] Autonomous vehicle 100 includes, as functional elements, an autonomous driving control unit 110, an obstacle detection unit 120, a push-aside determination unit 130, an obstacle display unit 140, and a memory unit 150. The functions of the autonomous driving control unit 110, obstacle detection unit 120, push-aside determination unit 130, and obstacle display unit 140 are realized by software. A threshold speed 51, a threshold thrust force 52, and a threshold pressure 53 are stored in the storage unit 150. The storage unit 150 is provided in the memory 921. The storage unit 150 may be provided in the auxiliary storage device 922, or may be provided separately in the memory 921 and the auxiliary storage device 922.

[0016] The processor 910 is a device that executes an autonomous driving program. The autonomous driving program is a program that realizes the functions of the autonomous driving control unit 110, the obstacle detection unit 120, the push-aside determination unit 130, and the obstacle display unit 140. The processor 910 is an IC that performs arithmetic processing. Specific examples of the processor 910 are a CPU, a DSP, and a GPU. IC is an abbreviation for Integrated Circuit. CPU is an abbreviation for Central Processing Unit. DSP is an abbreviation for Digital Signal Processor. GPU is an abbreviation for Graphics Processing Unit.

[0017] The memory 921 is a storage device that temporarily stores data. Specific examples of the memory 921 are SRAM and DRAM. SRAM is an abbreviation for Static Random Access Memory. DRAM is an abbreviation for Dynamic Random Access Memory. The auxiliary storage device 922 is a storage device that stores data. A specific example of the auxiliary storage device 922 is a HDD. The auxiliary storage device 922 may also be a portable storage medium such as an SD (registered trademark) memory card, CF, NAND flash, a flexible disk, an optical disk, a compact disk, a Blu-ray (registered trademark) disk, or a DVD. Note that HDD is an abbreviation for Hard Disk Drive. SD (registered trademark) is an abbreviation for Secure Digital. CF is an abbreviation for CompactFlash (registered trademark). DVD is an abbreviation for Digital Versatile Disk.

[0018] The input interface 930 is a port connected to an input device such as a mouse, keyboard, or touch panel. Specifically, the input interface 930 is a USB terminal. The input interface 930 may also be a port connected to a LAN. USB is an abbreviation for Universal Serial Bus. LAN is an abbreviation for Local Area Network.

[0019] The output interface 940 is a port to which a cable of an output device such as a display is connected. Specifically, the output interface 940 is a USB terminal or an HDMI (registered trademark) terminal. Specifically, the display is an LCD. The output interface 940 is also called a display interface. HDMI (registered trademark) is an abbreviation for High Definition Multimedia Interface. LCD is an abbreviation for Liquid Crystal Display.

[0020] The communication device 950 has a receiver and a transmitter. The communication device 950 is connected to a communication network such as a LAN, the Internet, Wi-Fi (registered trademark), or a telephone line. The communication device 950 is specifically a communication chip or NIC. NIC is an abbreviation for Network Interface Card.

[0021] The autonomous driving program is executed in autonomous vehicle 100. The autonomous driving program is read into processor 910 and executed by processor 910. Memory 921 stores not only the autonomous driving program but also an OS (Operating System). Processor 910 executes the autonomous driving program while running the OS. The autonomous driving program and OS may be stored in auxiliary storage device 922. The autonomous driving program and OS stored in auxiliary storage device 922 are loaded into memory 921 and executed by processor 910. Note that part or all of the autonomous driving program may be incorporated into the OS.

[0022] Autonomous vehicle 100 may include multiple processors that replace processor 910. These multiple processors share the task of executing the autonomous driving program. Each processor is a device that executes the autonomous driving program, just like processor 910.

[0023] Data, information, signal values, and variable values ​​used, processed, or output by the autonomous driving program are stored in memory 921, auxiliary storage device 922, or registers or cache memory within processor 910.

[0024] The "unit" of each of the autonomous driving control unit 110, obstacle detection unit 120, push-aside determination unit 130, and obstacle display unit 140 may be interpreted as a "circuit," "step," "procedure," "process," "device," or "circuitry." The autonomous driving program causes a computer to execute each of the autonomous driving control process, obstacle detection process, push-aside determination process, and obstacle display process. The "processing" of the autonomous driving control process, obstacle detection process, push-aside determination process, and obstacle display process may be interpreted as a "program," "program product," "computer-readable storage medium storing a program," or "computer-readable recording medium recording a program." Furthermore, the autonomous driving method is a method performed by autonomous vehicle 100 executing the autonomous driving program. The autonomous driving program may be provided by being stored on a computer-readable recording medium. Alternatively, the autonomous driving program may be provided as a program product.

[0025] The main function device 14 is a device that performs the main functions that the autonomous vehicle 100 should achieve in addition to the autonomous driving function. The autonomous vehicle 100 is also called an autonomous driving robot. For example, if autonomous vehicle 100 is a sprinkler vehicle, it is a sprinkler device that sprinkles water. If autonomous vehicle 100 is a spray vehicle, it is a fertilizer spray device that sprays fertilizer. If autonomous vehicle 100 is a transport vehicle, it is a device that holds luggage. Furthermore, in this embodiment, an agricultural autonomous robot is used as an example of autonomous vehicle 100, but this embodiment can also be applied to applications other than agriculture. Application examples in fields other than agriculture will be described later.

[0026] Traveling device 15 is a device that causes autonomous vehicle 100 to travel autonomously based on autonomous travel control information generated by autonomous travel control unit 110. The autonomous travel control information includes information such as travel route, attitude, and speed.

[0027] FIG. 2 is a diagram showing an example of the operation of a normal autonomous mobile robot. Figure 2 shows an example of an autonomous mobile robot whose main function is to sprinkle water. The autonomous mobile robot autonomously travels within a greenhouse along a predetermined route while sprinkling water. As shown in Figure 2, the path of an autonomous mobile robot may be covered with vinyl to prevent it from being obstructed by leaves that grow and protrude into the path. However, because plants grow quickly inside a greenhouse, leaves may protrude into the path, obstructing the autonomous mobile robot's movement.

[0028] In this embodiment, an autonomous vehicle 100 having a function for determining whether it can proceed by pushing aside obstacles such as leaves that have protruded into the path will be described.

[0029] ***Explanation of Operation*** Next, the operation of autonomous vehicle 100 according to this embodiment will be described. The operating procedure of autonomous vehicle 100 corresponds to an autonomous driving process and an autonomous driving method. Furthermore, the program that realizes the operation of autonomous vehicle 100 corresponds to an autonomous driving program.

[0030] FIG. 3 is a diagram showing an example of operation of autonomous vehicle 100 according to this embodiment. In the example of FIG. 3, the autonomous vehicle 100 is provided with a sprinkler device as the main functional device 14 for sprinkling water. The autonomous vehicle 100 autonomously travels along a route within a greenhouse while spraying water. When the presence of an obstacle 80 in the traveling direction is detected, the push-aside determination unit 130 determines whether or not it is possible to push aside the obstacle 80 and proceed. If it is determined that the obstacle 80 can be pushed aside and progress can be made, the autonomous driving control unit 110 continues the autonomous driving as is.

[0031] Specifically, it is as follows:

[0032] FIG. 4 is a flow diagram showing an example of the operation of autonomous vehicle 100 according to this embodiment. In autonomous vehicle 100, autonomous driving control unit 110 transmits autonomous driving control information to driving device 15. Driving device 15 autonomously drives the driving route in accordance with the autonomous driving control information.

[0033] In step S101, obstacle detection unit 120 uses obstacle sensor 12 to detect whether or not obstacle 80 is present in the traveling direction of autonomous vehicle 100. The obstacle sensor 12 is a device such as a laser scanner 122 and a camera 121. The obstacle detection unit 120 receives sensor data from each of the laser scanner 122 and the camera 121, and detects whether or not an obstacle 80 is present in the traveling direction based on the sensor data. Note that the obstacle detection unit 120 may detect the obstacle 80 using sensor data from either the laser scanner 122 or the camera 121. If the presence of an obstacle 80 is detected in the traveling direction, the process proceeds to step S102.

[0034] In step S102, when the presence of obstacle 80 is detected, autonomous driving control unit 110 controls the speed of autonomous vehicle 100 to be equal to or less than predetermined threshold speed 51. Note that if the speed of autonomous vehicle 100 is always controlled to be equal to or less than threshold speed 51, this process is not necessary.

[0035] Next, push-aside determination unit 130 determines whether or not autonomous vehicle 100 can proceed based on the state of autonomous vehicle 100 detected by state detection sensor 11 when obstacle 80 is pushed. State detection sensor 11 is a sensor that detects the state of autonomous vehicle 100. State detection sensor 11 includes thrust sensor 111 and pressure sensor 112.

[0036] FIG. 5 is a schematic diagram of autonomous vehicle 100 according to this embodiment. Propulsion force sensor 111 detects the propulsion force of autonomous vehicle 100 while it is traveling as a state of autonomous vehicle 100 . Pressure sensor 112 detects the pressure acting on the front of autonomous vehicle 100 as a state of autonomous vehicle 100. Pressure sensor 112 is installed in the front of autonomous vehicle 100, for example. Specifically, the following applies:

[0037] In step S103, the push-aside determination unit 130 acquires the state of the autonomous vehicle detected by the state detection sensor 11 when the obstacle 80 is pushed. For example, push-aside determination unit 130 acquires the thrust detected by thrust sensor 111 when obstacle 80 is pushed as the state of autonomous vehicle 100. Alternatively, push-aside determination unit 130 acquires, as the state of autonomous vehicle 100, the pressure detected by pressure sensor 112 when obstacle 80 is pushed.

[0038] In step S104, the push-aside determination unit 130 determines whether or not it is possible to push aside the obstacle 80 and proceed, based on the state of the autonomous vehicle detected by the state detection sensor 11 when the obstacle 80 is pushed. For example, based on the propulsive force detected by the propulsive force sensor 111 when pushing the obstacle 80, if the obstacle 80 cannot be passed even when pushed with a predetermined threshold propulsive force 52, the push-aside determination unit 130 determines that it is not possible to push the obstacle 80 aside and proceed. Alternatively, the push-aside determination unit 130 determines that it is not possible to push aside the obstacle 80 and proceed if the obstacle 80 cannot be passed even when pushed with a predetermined threshold pressure 53, based on the pressure detected by the pressure sensor 112 when the obstacle 80 is pushed.

[0039] In other words, the push-aside determination unit 130 determines that progress is possible if the obstacle 80 can be pushed aside with a thrust force equal to or less than the threshold thrust 52 and progress can be made. Furthermore, the push-aside determination unit 130 determines that progress is possible if the obstacle 80 can be pushed aside with a pressure equal to or less than the threshold pressure 53 and progress can be made.

[0040] Note that push-aside determination unit 130 may determine whether autonomous vehicle 100 can proceed using both the propulsive force and the pressure as the state of autonomous vehicle 100. Alternatively, push-aside determination unit 130 may determine whether autonomous vehicle 100 can proceed using either the propulsive force or the pressure as the state of autonomous vehicle 100. Furthermore, autonomous vehicle 100 may have a function of using "wind" or a "robot arm" to try moving obstacle 80 before pushing it to determine whether obstacle 80 is hard and immovable or whether it moves easily when pushed. The "wind" used to check the movement of obstacle 80 may be naturally occurring, or autonomous vehicle 100 may be equipped with a fan. Furthermore, autonomous vehicle 100 may be equipped with a robot arm.

[0041] If it is determined that the vehicle can proceed, the autonomous driving control unit 110 continues the autonomous driving. If it is determined that the game cannot proceed, the process proceeds to step S105.

[0042] In step S105, the push-aside determination unit 130 stores in the storage unit 150 the position of the obstacle 80 that has been determined to be impassable. For example, the obstacle display unit 140 displays a message indicating that progress was prevented by the obstacle, together with the location of the obstacle, on the display device 941. Alternatively, the obstacle display unit 140 may transmit the message indicating that progress was prevented by the obstacle, together with the location of the obstacle, to a smartphone or the like of the user via the communication device 950.

[0043] 3, autonomous vehicle 100 is autonomously traveling while spraying water. Obstacle detection unit 120 detects a leaf sticking out in the traveling direction as obstacle 80. The push-aside determination unit 130 continues autonomous travel at a speed equal to or less than the threshold speed, and slowly tries to push the leaf that is the obstacle 80. The push-aside determination unit 130 tries to see if the obstacle 80 moves, that is, if it becomes an obstacle to progress. As described above, push-aside determination unit 130 determines whether autonomous vehicle 100 can proceed based on the magnitude of the propulsive force or applied pressure applied to autonomous vehicle 100 when pushing a leaf that is obstacle 80. Alternatively, push-aside determination unit 130 may determine whether autonomous vehicle 100 can proceed based on the amount of movement compared to the magnitude of the propulsive force or applied pressure applied to autonomous vehicle 100 when pushing a leaf that is obstacle 80.

[0044] 3, obstacle 80 is a leaf, and therefore autonomous vehicle 100 is likely to be able to push the leaf aside and proceed. The leaf does not interfere with autonomous vehicle 100's watering operation, and autonomous vehicle 100 is able to continue its main function. If obstacle 80 is a heavy object, such as an iron bar left in the passageway, it is highly likely that autonomous vehicle 100 will not move even if it tries to push it slowly. In this case, autonomous vehicle 100 first slows down, and if obstacle 80 does not move even when it tries to push it slowly, it immediately stops. Therefore, there is no need to worry about autonomous vehicle 100 being damaged by obstacle 80.

[0045] ***Other Configurations*** <Variation 1> In this embodiment, the functions of the autonomous driving control unit 110, the obstacle detection unit 120, the push-aside determination unit 130, and the obstacle display unit 140 are realized by software. As a variation, the functions of the autonomous driving control unit 110, the obstacle detection unit 120, the push-aside determination unit 130, and the obstacle display unit 140 may be realized by hardware. Specifically, autonomous vehicle 100 includes electronic circuitry 909 instead of processor 910.

[0046] FIG. 6 is a diagram showing an example of the configuration of autonomous vehicle 100 according to a modification of this embodiment. The electronic circuit 909 is a dedicated electronic circuit that realizes the functions of the autonomous driving control unit 110, the obstacle detection unit 120, the push-aside determination unit 130, and the obstacle display unit 140. Specifically, the electronic circuit 909 is a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, a GA, an ASIC, or an FPGA. GA is an abbreviation for Gate Array. ASIC is an abbreviation for Application Specific Integrated Circuit. FPGA is an abbreviation for Field-Programmable Gate Array.

[0047] The functions of the autonomous driving control unit 110, obstacle detection unit 120, push-aside determination unit 130, and obstacle display unit 140 may be realized by a single electronic circuit, or may be realized by distributing them across multiple electronic circuits.

[0048] As another variation, some of the functions of the autonomous driving control unit 110, the obstacle detection unit 120, the push-aside determination unit 130, and the obstacle display unit 140 may be implemented by electronic circuits, with the remaining functions being implemented by software. Also, some or all of the functions of the autonomous driving control unit 110, the obstacle detection unit 120, the push-aside determination unit 130, and the obstacle display unit 140 may be implemented by firmware.

[0049] Each of the processor and electronic circuitry is also called processing circuitry. That is, the functions of the autonomous driving control unit 110, obstacle detection unit 120, push-aside determination unit 130, and obstacle display unit 140 are realized by the processing circuitry.

[0050] ***Explanation of the effect of this embodiment*** As described above, the autonomous vehicle according to this embodiment is able to proceed if it is able to proceed even if there is an obstacle in its direction of travel, thereby preventing the autonomous vehicle from avoiding obstacles or stopping more than necessary. Therefore, the autonomous vehicle according to this embodiment is able to proceed if it is able to proceed even if there is an obstacle in its direction of travel, thereby improving the feasibility of performing the main function of the autonomous vehicle.

[0051] Furthermore, the autonomous vehicle according to this embodiment determines whether it can pass by pushing it slightly and judging whether it can pass through. In other words, it is equipped with a function that tests whether it can actually be pushed through even if there is an obstacle. These functions can be realized by installing devices such as a pressure sensor and a thrust sensor. Therefore, the autonomous vehicle according to this embodiment can realize effective devices at low cost. In addition, it will be able to go into areas that normal autonomous robots would otherwise be unable to go, expanding the robot's working range. This is particularly useful for agricultural robots that move around inside greenhouses where plants grow quickly, or in the complex terrain of mountainous areas where weeds tend to grow.

[0052] Embodiment 2 In this embodiment, differences from and additions to the first embodiment will be mainly described. In this embodiment, components having the same functions as those in the first embodiment are given the same reference numerals, and the description thereof will be omitted.

[0053] In the first embodiment, when the presence of obstacle 80 is detected in the direction of travel, autonomous vehicle 100 first tries to push slowly. Then, push-aside determination unit 130 determines whether autonomous vehicle 100 can push aside obstacle 80 and proceed. If it is determined that autonomous vehicle 100 can push aside obstacle 80 and proceed, autonomous vehicle 100 pushes aside obstacle 80 and continues to proceed.

[0054] In this embodiment, a mode will be described in which the possibility of progression is determined based on the color and size of an obstacle that is impeding progression. In this embodiment, whether it is possible to proceed by pushing aside the obstacle is determined by, for example, performing AI processing on sensor data acquired by the obstacle sensor 12. AI is an abbreviation for Artificial Intelligence.

[0055] ***Configuration Description*** The configuration of autonomous vehicle 100 according to this embodiment is similar to that described in the first embodiment. Autonomous vehicle 100 is equipped with obstacle sensors 12 that detect the characteristics of obstacles 80. Obstacle sensors 12 are devices such as cameras 121 and laser scanners 122. Camera 121 captures images in the direction in which autonomous vehicle 100 is traveling. Laser scanner 122 detects objects by emitting a laser in the direction of travel of autonomous vehicle 100.

[0056] ***Explanation of Operation*** Next, the operation of autonomous vehicle 100 according to this embodiment will be described. The operating procedure of autonomous vehicle 100 corresponds to an autonomous driving process and an autonomous driving method. Furthermore, the program that realizes the operation of autonomous vehicle 100 corresponds to an autonomous driving program.

[0057] FIG. 7 is a flow diagram showing an example of the operation of autonomous vehicle 100 according to this embodiment. The processes in steps S201 and S202 are the same as those in steps S101 and S102 described in the first embodiment.

[0058] In step S203, the push-aside determination unit 130 acquires the sensor data acquired by the obstacle sensor 12 as the characteristics of the obstacle 80. The characteristics of the obstacle 80 include the color and shape of the obstacle 80. Specifically, the push-aside determination unit 130 acquires a camera image of the obstacle 80 captured by the camera 121 and a laser scanner image of the obstacle 80 detected by the laser scanner 122.

[0059] In steps S204 to S208, the push-aside determination unit 130 determines obstacle information indicating the obstacle status of the obstacle 80 based on the characteristics of the obstacle 80 acquired by the obstacle sensor 12. Then, the push-aside determination unit 130 determines, based on the obstacle information, whether or not it is possible to proceed by pushing aside the obstacle 80. Here, the obstacle information includes an obstacle amount indicating the size of the obstacle when an object becomes an obstacle, information on whether or not the object can move by itself, or information on whether or not the object can be pushed aside.

[0060] Specifically, it is as follows:

[0061] In step S204, the push-aside determination unit 130 determines the type of the obstacle 80 using the characteristics of the obstacle 80, including the color and shape of the obstacle 80. Then, the push-aside determination unit 130 determines the obstacle information using the type of the obstacle 80. For example, the push-aside determination unit 130 determines the type of obstacle 80 by performing AI processing on the camera image and the laser scanner image.

[0062] For example, the push-aside determination unit 130 stores an obstacle information correspondence table in the storage unit 150, which associates the type of object with obstacle information about the object. The push-aside determination unit 130 may acquire obstacle information about the obstacle 80 from the type of obstacle 80 by referring to the obstacle information correspondence table. Alternatively, the push-aside determination unit 130 may acquire the type of obstacle 80 and obstacle information as a processing result by performing AI processing on the camera image and the laser scanner image. The obstacle information includes at least one of the amount of obstruction of the obstacle 80, information on whether the object can move by itself, and information on whether the object can be pushed aside.

[0063] FIG. 8 is a diagram showing an example of types of obstacles 80 and obstacle information according to this embodiment. In the example shown on the left in FIG. 8, the type of obstacle 80 that is thin, green, and hanging down is determined to be a "leaf." Furthermore, the obstacle amount is determined to be small as obstacle information for the type "leaf." Therefore, the push-aside determination unit 130 determines that the obstacle 80 shown on the left in FIG. 8 can be pushed aside and progress can be made. In addition to leaves, twigs, weeds, or pieces of plastic may also be set as obstacle information that can be pushed aside and progress can be made.

[0064] In the example of the center diagram in FIG. 8, the type of obstacle 80, which is somewhat thick, dark brown, and approximately straight, is determined to be a "tree or branch." Furthermore, the obstacle amount is determined to be large as obstacle information for the type "tree or branch." Therefore, the push-aside determination unit 130 determines that it is not possible to proceed by pushing aside the obstacle 80 in the center diagram in FIG. 8. In addition to trees or branches, rocks or blocks may also be set as obstacle information that it is not possible to proceed by pushing aside.

[0065] In the example on the right side of FIG. 8, the round, red obstacle 80 is determined to be a "strawberry." Furthermore, the obstacle information for the type "strawberry" is determined to be a small obstacle that should not be pushed aside. Therefore, the push-aside determination unit 130 determines that the obstacle 80 on the right side of FIG. 8 cannot be pushed aside and passed through. Delicate fruits such as strawberries and peaches can be pushed aside and passed through, but damaging them will make them worthless. For such objects, the obstacle information is set to indicate that passing through is not permitted.

[0066] FIG. 9 is a diagram showing another example of types of obstacles 80 and obstacle information according to this embodiment. The example in FIG. 9 shows a case where the type of obstacle 80 is determined to be "person or animal." The obstacle information of the type "person or animal" is set to indicate that the obstacle 80 is capable of moving on its own. Therefore, when the push-aside determination unit 130 determines that the type of obstacle 80 is "person or animal," it can determine that the obstacle 80 is capable of moving on its own based on the obstacle information. Then, the push-aside determination unit 130 outputs a notification to the obstacle 80 urging it to move, as will be described later.

[0067] In step S205, the push-aside determination unit 130 determines, based on the obstacle information, whether the type of obstacle 80 is one that can be moved by itself. If the type of obstacle 80 is one that can move by itself, the process proceeds to step S206. If the type of obstacle 80 is not one that can move by itself, the process proceeds to step S207.

[0068] In step S206, the push-aside determination unit 130 outputs a notification to the obstacle 80 urging it to move.

[0069] FIG. 9 shows an example of a notification urging an obstacle 80 to move. For example, if the obstacle 80 is a person, the autonomous vehicle 100 will request by voice or other means that the person be moved. However, the voice output will depend on the situation. Normally, people have priority, so this function is assumed to only work when the movement or transportation is particularly important. For example, it is similar to an ambulance calling out "This is an emergency transport, please let me through" when passing through a red light. In addition, in the case of emergency transport, the device may have a function of alerting the driver with light or sound, like an ambulance siren, to allow the driver to pass through. Also, if the obstacle 80 is an animal, it can be made to move by frightening it with sound or light, like frightening birds with sound to make them disperse.

[0070] In step S207, the push-aside determination unit 130 determines, based on the obstacle information, whether the type of obstacle 80 is one that should not be pushed aside. For example, it is an obstacle that can be pushed aside and passed through, such as delicate fruit, but if damaged, it will lose its commercial value. If the object should not be pushed aside, the process proceeds to step S209. If it is OK to push it aside, the process proceeds to step S208.

[0071] In step S208, the push-aside determination unit 130 determines whether or not it is possible to push aside and proceed based on the obstacle information. If it is possible to push aside and proceed, the autonomous driving control unit 110 continues the autonomous driving as is. If it is not possible to push aside and proceed, the process proceeds to step S209.

[0072] The process in step S209 is the same as the process in step S105 described in the first embodiment.

[0073] ***Other Configurations*** <Variation 2> FIG. 10 is a diagram showing an example of an autonomous vehicle according to a modification of this embodiment. An autonomous vehicle may be equipped with a device to remove obstacles. Figure 10 shows an example of (C) a pump truck with an obstacle removal function. This also depends on the situation, but even if a road is impassable, for example, if cutting off a branch would make it passable, the vehicle could be equipped with a "branch cutting" function.

[0074] Furthermore, autonomous vehicles may be designed to have a shape that makes it easy to push away objects. Figure 10 shows (A) an example of a vehicle with a structure that makes it easy to push away objects, and (B) an example of a snowplow vehicle for removing snow. If the obstacle is ahead, it is possible to equip the vehicle with an obstacle removal device, such as (C) a pump truck with an obstacle removal function. It is also effective to make the vehicle shaped in such a way that it can easily push the obstacle aside, such as (B) a snowplow vehicle for removing snow. In the case of agricultural machinery, the ground is usually not paved, so it is effective to make it easy to push through and not damage the object, such as a rounded shape, in addition to the tire shape. Alternatively, it is possible to equip it with a robotic arm, which can slowly move strawberries aside before proceeding.

[0075] <Variation 3> FIG. 11 is a diagram showing an example of an obstacle that must not be pushed aside according to a modification of this embodiment. Figure 11 (a) to (d) show examples of obstacles that are problematic to push aside. However, there are situations where pushing through is the correct thing to do, so it cannot be said that you should not push through them in all cases.

[0076] The push-avoidance determination unit 130 has a function to determine whether pushing through would be a problem based on the object and the situation. It also has a function to set the push-through level (urgency). It may also have a function to assign an ID tag or QR code (registered trademark) to objects that should not be pushed, to determine that they should not be pushed. This function is effective in situations where it is difficult to distinguish between objects that are OK to push and those that are not, even if they are exactly the same.

[0077] <Variation 4> FIG. 12 is a diagram showing an example of operation of autonomous vehicle 100 according to a modification of this embodiment. Typically, autonomous agricultural robots patrol the same area or follow people, so it may not be necessary to create a situation where the robot can pass by itself.

[0078] The autonomous vehicle 100 has the function of recording impassable areas and informing the user. The user can take action based on this information, such as removing obstacles. It may also have a function to inform the user of places that are currently passable but are likely to become impassable in the future due to the growth of living creatures, etc. For example, it may detect a situation where the passable width is narrowing day by day and notify the user that it will become impassable in the future. Based on this information, the user can remove the obstacle before it becomes impassable. Furthermore, when autonomous vehicle 100 is following a person, it has a function to notify the user that it cannot pass, allowing the user to remove the obstacle on the spot.

[0079] ***Explanation of the effect of this embodiment*** As described above, in addition to the effects of embodiment 1, the autonomous vehicle according to this embodiment can finely set whether or not it can push aside an obstacle in its traveling direction. Therefore, the autonomous vehicle according to this embodiment can take more appropriate measures against obstacles.

[0080] In the above first and second embodiments, each unit of each device of autonomous vehicle 100 has been described as an independent functional block. However, the configuration of each device of autonomous vehicle 100 does not have to be as in the above-described embodiments. The functional blocks of each device of autonomous vehicle 100 may have any configuration as long as they can realize the functions described in the above-described embodiments. Furthermore, it is possible to combine multiple parts of the first and second embodiments. Alternatively, it is possible to implement only one part of these embodiments. In addition, it is possible to implement any combination of these embodiments, either as a whole or in part. That is, in the first and second embodiments, the respective embodiments can be freely combined, or any of the components in the respective embodiments can be modified, or any of the components in the respective embodiments can be omitted.

[0081] It should be noted that the above-described embodiments are essentially preferred examples and are not intended to limit the scope of the present disclosure, the scope of application of the present disclosure, and the scope of use of the present disclosure. The above-described embodiments can be modified in various ways as necessary.

[0082] In particular, in the above-mentioned first and second embodiments, an autonomous vehicle used in the agricultural field has been described as an example. However, the technology described in the first and second embodiments can also be used on public roads, and is particularly effective in emergencies and other situations where it is necessary to move even if it means pushing aside small obstacles.

[0083] The techniques described in the first and second embodiments are also effective for a PMV that autonomously travels with a person on board. An example of autonomous vehicle 100 according to the first and second embodiments is a PMV. For example, in a PMV, the push-aside determination function can be switched between enabled and disabled by turning a selection button on and off.

[0084] PMV is effective when traveling on paths with lots of weeds and vegetation, such as the one below. Sidewalks overgrown with weeds Parks with lots of plants Unmaintained causeway

[0085] Also, store curtains and other items can be obstacles, so it's a good idea to turn on the push-aside detection function when entering a store with a curtain.

[0086] It is also effective in emergencies, situations where not proceeding would involve greater risks. - Evacuation in the event of a disaster - When passengers need emergency transportation - Emergency movement of PMV

[0087] For example, if the PMV battery is running low and you need to get to the charging port as quickly as possible, it is effective to turn on the push-aside detection function. Alternatively, turning on the push-aside detection function is also effective when using a PMV for emergency evacuation in the event of a fire. When responding to a fire, smoke may be detected as an obstacle that can be pushed aside. For this reason, it is effective to equip the PMV with a temperature sensor. It is preferable for the PMV to have the function to travel in as low a temperature as possible, even when pushing smoke aside.

[0088] Various aspects of the present disclosure are summarized below as appendices.

[0089] (Appendix 1) In autonomous vehicles that drive autonomously, An autonomous vehicle comprising a push-aside determination unit that, when the presence of an obstacle is detected in the direction of travel, determines whether or not it is possible to push aside the obstacle and proceed. (Appendix 2) The autonomous vehicle includes: a state detection sensor that detects a state of the autonomous vehicle; The push-aside determination unit 2. An autonomous vehicle as described in claim 1, which determines whether or not it is possible to proceed based on the state of the autonomous vehicle detected by the state detection sensor when the obstacle is pushed. (Appendix 3) The autonomous vehicle includes: a propulsive force sensor configured to detect a propulsive force during travel as a state of the autonomous vehicle; The push-aside determination unit 3. The autonomous vehicle of claim 2, wherein the autonomous vehicle determines that it is not possible to proceed by pushing the obstacle aside if the obstacle cannot be passed through even when pushed with a predetermined threshold thrust, based on the thrust detected by the thrust sensor when the obstacle is pushed. (Appendix 4) The autonomous vehicle includes: a pressure sensor configured to detect a pressure applied to a front side of the autonomous vehicle as a state of the autonomous vehicle, as the state detection sensor; The push-aside determination unit 4. The autonomous vehicle according to claim 2 or 3, wherein the autonomous vehicle determines that it is not possible to proceed by pushing the obstacle aside if the obstacle cannot be passed even when pushed with a predetermined threshold pressure, based on the pressure detected by the pressure sensor when the obstacle is pushed. (Appendix 5) the autonomous vehicle includes an autonomous driving control unit that controls autonomous driving, The autonomous driving control unit 5. The autonomous vehicle of claim 1, wherein, when the presence of the obstacle is detected, the speed of the autonomous vehicle is controlled to be equal to or less than a predetermined threshold speed. (Appendix 6) The autonomous vehicle includes: an obstacle sensor that detects characteristics of the obstacle; The push-aside determination unit 6. The autonomous vehicle of claim 1, wherein, when the presence of the obstacle is detected, obstacle information indicating the obstacle status of the obstacle is determined based on characteristics of the obstacle acquired by the obstacle sensor, and whether or not the autonomous vehicle can proceed is determined based on the obstacle information. (Appendix 7) The autonomous vehicle includes: The obstacle sensor includes a camera and a laser scanner, The push-aside determination unit 7. The autonomous vehicle of claim 6, wherein the type of the obstacle is determined using features of the obstacle, including the color and shape of the obstacle, acquired by the camera and the laser scanner, and the obstacle information is determined using the type of the obstacle. (Appendix 8) The push-aside determination unit 8. The autonomous vehicle of claim 6, wherein, when it determines based on the obstacle information that the type of the obstacle is one that the autonomous vehicle can move by itself, it outputs a notification to the obstacle urging it to move. (Appendix 9) The push-aside determination unit 9. The autonomous vehicle according to claim 6, wherein the autonomous vehicle is stopped when it is determined based on the obstacle information that the type of the obstacle is one that should not be pushed aside. (Appendix 10) The autonomous vehicle includes: 10. The autonomous vehicle according to any one of Supplementary Note 1 to Supplementary Note 9, further comprising an obstacle display unit that, when the obstacle cannot be pushed aside, stores the position of the obstacle as an obstacle position and displays the obstacle position on a display device. (Appendix 11) The autonomous vehicle includes: 10. The autonomous vehicle according to any one of Supplementary Note 1 to Supplementary Note 9, further comprising an obstacle display unit that, when the obstacle cannot be pushed aside, stores the position of the obstacle as an obstacle position and displays the obstacle position on a display device. (Appendix 12) The autonomous vehicle according to any one of Supplementary Note 1 to Supplementary Note 11, wherein the autonomous vehicle is an agricultural robot. (Appendix 13) An autonomous driving method used in an autonomous vehicle that drives autonomously, An autonomous driving method in which, when a computer detects the presence of an obstacle in the direction of travel of the autonomous vehicle, it determines whether it is possible to push aside the obstacle and continue on. (Appendix 14) In an autonomous driving program used in an autonomous vehicle that drives autonomously, An autonomous driving program that causes a computer to execute a push-aside determination process that, when an obstacle is detected in the direction of travel of the autonomous driving vehicle, determines whether it is possible to push aside the obstacle and proceed. [Explanation of symbols]

[0090] 11 Status detection sensor, 111 Propulsion force sensor, 112 Pressure sensor, 12 Obstacle sensor, 121 Camera, 122 Laser scanner, 13 Speaker, 14 Main function device, 15 Running device, 51 Threshold speed, 52 Threshold propulsion force, 53 Threshold pressure, 80 Obstacle, 100 Autonomous vehicle, 110 Autonomous driving control unit, 120 Obstacle detection unit, 130 Push-aside determination unit, 140 Obstacle display unit, 150 Memory unit, 909 Electronic circuit, 910 Processor, 921 Memory, 922 Auxiliary storage device, 930 Input interface, 940 Output interface, 941 Display device, 950 Communication device.

Claims

1. In autonomous vehicles that drive autonomously, an obstacle sensor that detects obstacles present in the traveling direction; a state detection sensor that detects a state of the autonomous vehicle; an autonomous driving control unit that controls the vehicle to autonomously drive at a speed equal to or lower than a predetermined threshold speed when the obstacle sensor detects an obstacle; a push-aside determination unit that, when an obstacle detected by the obstacle sensor is pushed during autonomous driving control by the autonomous driving control unit at or below the threshold speed, determines whether it is possible to push aside the obstacle detected by the obstacle sensor and proceed based on the state of the autonomous driving vehicle detected by the state detection sensor; and An autonomous vehicle equipped with

2. An autonomous vehicle that drives autonomously, an obstacle sensor that detects obstacles present in the traveling direction; a propulsive force sensor that detects a propulsive force during travel as a state of the autonomous vehicle; a push-aside determination unit that, when an obstacle is detected by the obstacle sensor, determines whether or not it is possible to push aside the obstacle detected by the obstacle sensor and proceed; Equipped with The push-aside determination unit determines that the autonomous vehicle cannot proceed by pushing the obstacle if the obstacle cannot be passed even when pushed with a predetermined threshold thrust, based on the thrust detected by the thrust sensor when the obstacle is pushed.

3. The autonomous vehicle includes: a pressure sensor configured to detect a pressure applied to a front side of the autonomous vehicle as a state of the autonomous vehicle, as the state detection sensor; The push-aside determination unit 2. The autonomous vehicle of claim 1, wherein the autonomous vehicle determines that it is not possible to push the obstacle aside and proceed if the obstacle cannot be passed even when pushed with a predetermined threshold pressure, based on the pressure detected by the pressure sensor when the obstacle is pushed.

4. the autonomous vehicle includes an autonomous driving control unit that controls autonomous driving, The autonomous driving control unit The autonomous vehicle according to claim 2 , wherein when the presence of the obstacle is detected, the speed of the autonomous vehicle is controlled to be equal to or lower than a predetermined threshold speed.

5. An autonomous vehicle that drives autonomously, an obstacle sensor that detects characteristics including the color and shape of an obstacle present in the traveling direction; a push-aside determination unit that, when the presence of the obstacle is detected, identifies the type of the obstacle using characteristics of the obstacle including the color and shape of the obstacle acquired by the obstacle sensor, determines obstacle information indicating the obstacle status of the obstacle using the obstacle type, and determines whether it is possible to push aside the obstacle and proceed based on the obstacle information; and Equipped with The autonomous vehicle, wherein the obstacle sensors are cameras and laser scanners.

6. The push-aside determination unit The autonomous vehicle according to claim 5 , wherein, when it is determined based on the obstacle information that the type of the obstacle is one that the autonomous vehicle can move by itself, a notification is output to the obstacle urging it to move.

7. The push-aside determination unit The autonomous vehicle according to claim 5 , wherein the autonomous vehicle is stopped when it is determined based on the obstacle information that the type of the obstacle is one that should not be pushed aside.

8. The autonomous vehicle includes:

6. The autonomous vehicle according to claim 1, further comprising an obstacle display unit that, when the obstacle cannot be pushed aside, stores the position of the obstacle as an obstacle position and displays the obstacle position on a display device.

9. The autonomous vehicle according to claim 1 , wherein the autonomous vehicle is an agricultural robot.

10. An autonomous driving method used in an autonomous vehicle that drives autonomously, The computer When an obstacle is detected by an obstacle sensor that detects an obstacle present in the traveling direction, controlling the autonomous traveling so that the vehicle travels at a speed equal to or less than a predetermined threshold speed; determining whether or not it is possible to push aside the obstacle detected by the obstacle sensor and proceed based on the state of the autonomous vehicle detected by a state detection sensor that detects the state of the autonomous vehicle when the obstacle detected by the obstacle sensor is pushed at a speed equal to or less than the threshold speed; An autonomous driving method for performing the above.

11. In an autonomous driving program used in an autonomous vehicle that drives autonomously, an autonomous driving control process that controls the autonomous driving so that the vehicle travels at a speed equal to or less than a predetermined threshold speed when an obstacle is detected by an obstacle sensor that detects an obstacle present in the traveling direction; a push-aside determination process that determines whether or not it is possible to proceed by pushing aside the obstacle detected by the obstacle sensor, based on the state of the autonomous vehicle detected by a state detection sensor that detects the state of the autonomous vehicle, when the autonomous vehicle pushes an obstacle detected by the obstacle sensor at a speed equal to or less than the threshold speed; An autonomous driving program that causes a computer to execute the following.

Images