Moving body, control method thereof, and control program thereof

Abstract

To realize accurate autonomous movement in areas with heavy snowfall.SOLUTION: There is provided a moving body that moves autonomously, comprising: a sensor that detects information about the surrounding environment of the moving body; a recognition unit that performs recognition processing of snowfall prevention objects around the moving body based on the detection information from the sensor; a positioning unit that performs positioning processing of the moving body based on the result of the recognition processing; and a movement control unit that performs movement control processing of the moving body based on the result of the positioning processing.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to a mobile body, and more particularly to a mobile body suitable for traveling in areas with heavy snowfall. [Background technology]

[0002] In recent years, autonomous vehicles have been attracting attention as a way to solve various social issues in areas facing population decline and aging.

[0003] However, this type of autonomous vehicle is required to be able to run stably under various weather conditions, for example, in areas with heavy snowfall. Various research and development efforts have been conducted on autonomous driving technology in snowy environments (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-26387 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the road environment in snowy regions, especially the objects installed on the road, has not been sufficiently considered so far. As a result, there is room for improvement in the accuracy of autonomous driving in snowy regions.

[0006] The present invention has been made in view of the above-mentioned technical background, and has an object to realize highly accurate autonomous movement in areas with heavy snowfall. [Means for solving the problem]

[0007] The above-mentioned technical problems can be solved by a moving object having the following configuration, and a control method, program, etc. thereof.

[0008] In other words, the moving body of the present invention is an autonomously moving body and is equipped with a sensor that detects information about the surrounding environment of the moving body, a recognition unit that performs a recognition process of snowfall prevention objects around the moving body based on the detection information from the sensor, a positioning unit that performs a positioning process of the moving body based on the result of the recognition process, and a movement control unit that performs a movement control process of the moving body based on the result of the positioning process.

[0009] According to this configuration, it is possible to perform positioning for autonomous movement by using snow prevention objects installed on roads in areas with heavy snowfall, thereby realizing highly accurate autonomous movement in areas with heavy snowfall.

[0010] The snowfall prevention object may be a snow melting pipe.

[0011] With this configuration, it is possible to realize highly accurate autonomous movement by utilizing equipment installed on roads in areas with heavy snowfall.

[0012] The sensor may be a camera, and the recognition unit may perform recognition processing of the nozzle portion of the snow melting pipe based on image information from the camera.

[0013] According to this configuration, the recognition process can be performed by utilizing the nozzle portion of the snow melting pipe that is exposed to the road surface.

[0014] The recognition unit may perform the recognition process by utilizing a trained model.

[0015] With this configuration, it is possible to realize highly accurate recognition processing by utilizing the generalization effect of machine learning.

[0016] The snow prevention object may be a snow pole.

[0017] With this configuration, it is possible to realize highly accurate autonomous movement by utilizing equipment installed on roads in areas with heavy snowfall.

[0018] The positioning unit may further perform the positioning process by utilizing a positioning technique using radio waves.

[0019] With this configuration, the positioning accuracy can be further improved.

[0020] The positioning unit may perform the positioning process by correcting the position obtained by the positioning technology using radio waves based on a result of the recognition process.

[0021] With this configuration, the accuracy of other positioning techniques can be further improved by utilizing the snow countermeasure object.

[0022] The positioning technique using radio waves may be a positioning technique using a GPS sensor.

[0023] With this configuration, the positioning accuracy can be further improved.

[0024] The snow prevention device may further include an inspection unit that detects damage to the snow prevention object based on information detected by the sensor.

[0025] According to such a configuration, any damage to the snow prevention object caused by the movement of the mobile object can also be detected, enabling efficient inspection and maintenance of the snow prevention object.

[0026] Viewed from another angle, the present invention is a method for controlling an autonomously moving body, which includes a recognition step of performing a recognition process of snowfall prevention objects around the moving body based on detection information from a sensor that detects information about the surrounding environment of the moving body, a positioning step of performing a positioning process of the moving body based on the result of the recognition process, and a movement control step of performing a movement control process of the moving body based on the result of the positioning process.

[0027] Viewed from another angle, the present invention is a control program for an autonomously moving body, which executes the following steps: a recognition step of performing a recognition process of snowfall prevention objects around the moving body based on detection information from a sensor that detects information about the surrounding environment of the moving body; a positioning step of performing a positioning process of the moving body based on the result of the recognition process; and a movement control step of performing a movement control process of the moving body based on the result of the positioning process. Effect of the Invention

[0028] According to the present invention, highly accurate autonomous movement can be achieved in areas with heavy snowfall. [Brief description of the drawings]

[0029] [Figure 1] FIG. 1 is a perspective view of the appearance of an autonomous vehicle. [Diagram 2] FIG. 2 is a functional block diagram of an autonomous vehicle. [Diagram 3] FIG. 3 is a general flowchart of the movement of an autonomous vehicle. [Figure 4] FIG. 4 is an explanatory diagram showing an example of the arrangement of the nozzle portion of the snow melting pipe. [Diagram 5] FIG. 5 is an enlarged plan view of the nozzle portion. [Figure 6] Figure 6 shows an example of installing snow poles on a road. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0030] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0031] 1. First Embodiment As a first embodiment, an example in which the present invention is applied to an autonomous vehicle 100 among moving objects will be described.

[0032] (1.1 Configuration of an autonomous vehicle) 1 is a perspective view of the exterior of an autonomous vehicle 100 according to this embodiment. As is clear from the figure, the autonomous vehicle 100 has a generally box-like shape. A movement mechanism 26 having four wheels 16 is provided on the bottom surface of the autonomous vehicle 100, and driving this movement mechanism 26 enables the autonomous vehicle 100 to move freely.

[0033] A pair of doors 15 are provided on the sides of autonomous vehicle 100. By opening these doors 15, people and luggage can be transported.

[0034] A display 13 is provided on the front of the autonomous vehicle 100, and various images and videos are displayed on the display. A pair of lights 11 are also provided on the front of the autonomous vehicle 100, and can illuminate the area ahead of the autonomous vehicle 100. Furthermore, a camera 12 is provided on the front of the autonomous vehicle 100, and can be used to acquire images. The position of the camera 12 can be changed depending on the object to be recognized.

[0035] Although not shown, autonomous vehicle 100 is equipped with a computing unit such as a CPU, GPU, etc. that executes programs, a storage unit such as a ROM / RAM, a hard disk, flash memory, etc. that stores programs and data, a communication unit that communicates with external devices, etc. Also, various sensors, which will be described later, are attached to autonomous vehicle 100. These implement the functional blocks, which will be described later.

[0036] 2 is a functional block diagram of autonomous vehicle 100 according to this embodiment. As is clear from the diagram, autonomous vehicle 100 includes at least camera 12, recognition processing unit 21, GPS module 22, positioning processing unit 23, movement control processing unit 25, and movement mechanism 26.

[0037] The recognition processing unit 21 performs a predetermined recognition processing based on the image information acquired by the camera 12, and provides the recognition processing result to the positioning processing unit 23. The GPS module 22 acquires position information of the autonomous vehicle 100, and provides it to the positioning processing unit 23.

[0038] The positioning processing unit 23 performs positioning processing regarding the current position of the autonomous vehicle 100 based on the recognition processing result and the position information from the GPS module 22, and provides the positioning result to the mobility control processing unit 25.

[0039] The movement control processing unit 25 generates a command for autonomous movement based on the positioning result and provides it to the movement mechanism 26. The movement mechanism 26 is driven in response to this command.

[0040] In this embodiment, the GPS module 22 is used as a positioning means, but the present invention is not limited to such a configuration. In addition to positioning technology using radio waves such as GPS, other positioning means may be used.

[0041] (1.2 Autonomous Vehicle Operation) 3 is a general flowchart regarding the movement of the autonomous vehicle 100. As is clear from the figure, when the movement process starts, the recognition processing unit 21 performs a process of acquiring an image from the camera 12 (S11). After the image acquisition process, the recognition processing unit 21 performs an object recognition process on the camera image (S12). Specifically, a process is performed using object recognition technology to recognize the snow melting pipe in the image, in particular the nozzle part of the snow melting pipe. The object recognition result is provided to the positioning processing unit 23.

[0042] A snow melting pipe is a pipe that is buried underground under roads in areas with heavy snowfall. The snow melting pipe can melt snow by pumping up groundwater and spraying it onto the road surface from a nozzle unit 31 installed on the ground surface.

[0043] Fig. 4 is an explanatory diagram of an example of the arrangement of nozzle units 31 for snow-melting pipes. The figure depicts a two-lane road 30 with one lane on each side. A snow-melting pipe is buried in the center of the two-lane road 30. Nozzle units 31 for sprinkling water are arranged at equal intervals on the ground surface in the area where the snow-melting pipe is buried. The recognition processing unit 21 recognizes the nozzle units 31 from the image.

[0044] 5 is an enlarged plan view of the nozzle portion 31. As is clear from the figure, the nozzle portion 31 is circular, with a square mounting hole 33 provided in the center. In addition, four water spray holes 32 are provided at positions that divide the circumference into approximately equal parts. This characteristic appearance can be used to perform recognition processing.

[0045] According to this configuration, the recognition process can be carried out by utilizing the fact that the nozzle portion 31 of the snow melting pipe is exposed to the road surface.

[0046] Note that various known techniques can be used for object recognition from an image. For example, object recognition may be performed using a trained model obtained by performing machine learning.

[0047] With this configuration, even if the image is somewhat distorted due to driving, it is possible to realize highly accurate recognition processing by utilizing the generalization effect of machine learning.

[0048] After the recognition process, the positioning processing unit 23 performs a process of acquiring the output from the GPS module 22, that is, the positioning information (or location information) of the autonomous vehicle 100 (S13).

[0049] After acquiring the output from the GPS module 22, the positioning processing unit 23 performs a positioning process for the autonomous vehicle 100 based at least on the recognition result of the snow-melting pipe and the positioning information from the GPS module 22 (S15). The result of this positioning process is provided to the movement control processing unit 25.

[0050] Various known methods can be used for the positioning process. For example, the position information from the GPS module 22 may be corrected using the recognition result of the snow melting pipe. In addition, for example, the position information may be calculated from prior information on the road environment and the recognition result of the camera image, and the final positioning result may be calculated based on the position information and the position information from the GPS module 22.

[0051] With this configuration, the accuracy of other positioning techniques can be further improved by utilizing the snow countermeasure object.

[0052] After the positioning process, the movement control processing unit 25 performs movement control processing of the autonomous vehicle 100 based on the provided positioning result (S16). Specifically, based on the positioning result, a command for moving along a predetermined route is provided to the movement mechanism 26. Note that various known methods can be used for this movement control.

[0053] Autonomous vehicle 100 moves by repeating the above steps (S11 to S16).

[0054] With this configuration, it is possible to perform positioning for autonomous movement using snowfall prevention objects (snow melting pipes) installed on roads in areas with heavy snowfall, thereby enabling highly accurate autonomous movement in areas with heavy snowfall.

[0055] (2. Modifications) The present invention can be implemented in various modified forms.

[0056] In the first embodiment, a snow melting pipe (or its nozzle) is used as the object to be recognized as a countermeasure against snowfall, but the present invention is not limited to such a configuration. Therefore, other objects or structures installed in areas with heavy snowfall, such as snow poles, may be used as the object to be recognized.

[0057] Fig. 6 shows an example of snow poles 51 installed on a road 50. Snow poles 51 are road sign posts or delineators that are installed on the center lines or roadsides of roads in areas with heavy snowfall, with the aim of clearly indicating the road alignment. In the example shown in the figure, they are installed at regular intervals on the roadside.

[0058] The snow poles 51 are colored red and white, and may be installed together with the delineators 52. Positioning processing may be performed by performing recognition processing using the external characteristics of the snow poles 51 from an image.

[0059] In the first embodiment, the recognition process of the snowfall countermeasure object (such as a snow melting pipe) is performed based on the camera image, but the present invention is not limited to such a configuration. Therefore, a sensor for detecting surrounding environment information other than a camera may be used, for example, a sensor for detecting metal, an ultrasonic sensor, or a beacon.

[0060] In the first embodiment, a car that runs on a road is used as the moving body, but the present invention is not limited to such a configuration. Therefore, other movable devices, such as a robot with legs, a drone or other UAV (Unmanned Aerial Vehicle), etc. may be used.

[0061] In the first embodiment, a configuration was described in which the recognition results of snow-prevention objects are used together with a positioning means such as a GPS module 22 for final positioning, but the positioning process may also be performed based only on the recognition results of snow-prevention objects.

[0062] In the first embodiment, the camera-acquired image is used for recognition, but the camera-acquired image can be used in various ways. For example, it may be determined whether the nozzle part 31 is damaged from the camera-acquired image. In this case, if the damage is stored together with the position information, the position of the damaged nozzle part 31 can be provided.

[0063] According to such a configuration, damage to the snowfall prevention object can also be detected (or inspected) as autonomous vehicle 100 moves, enabling efficient inspection, maintenance, etc. of the snowfall prevention object.

[0064] Although the embodiments of the present invention have been described above, the above embodiments merely show some of the application examples of the present invention, and the technical scope of the present invention is not limited to the specific configurations of the above embodiments. Moreover, the above embodiments can be appropriately combined within a range where no contradiction occurs. [Industrial Applicability]

[0065] The present invention can be used in industries that manufacture moving objects such as autonomous vehicles. [Explanation of symbols]

[0066] 11 Light 12 Camera 13. Display 15 Door 16 wheels 21 Recognition processing section 22 GPS Module 23 Positioning processing unit 25 Movement control processing section 26 Moving mechanism 30 2-lane road 31 Nozzle section 32 Watering hole 33 Mounting hole 50 road 51 Snow Pole 52 Delineator 100 Autonomous Vehicles

Claims

1. A moving body that moves autonomously, A sensor that detects information about a surrounding environment of the moving object; A recognition unit that performs a recognition process of a snowfall countermeasure object around the moving object based on the detection information from the sensor; a positioning unit that performs a positioning process for the moving object based on a result of the recognition process; A movement control unit that performs a movement control process for the moving object based on a result of the positioning process; A mobile body equipped with the above.

2. The moving body according to claim 1 , wherein the snowfall prevention object is a snow melting pipe.

3. The sensor is a camera, The moving body according to claim 2 , wherein the recognition unit performs a recognition process for the nozzle portion of the snow melting pipe based on image information from the camera.

4. The mobile body according to claim 3 , wherein the recognition unit performs the recognition process by using a trained model.

5. The moving body according to claim 1 , wherein the snow prevention object is a snow pole.

6. The mobile body according to claim 1 , wherein the positioning unit further performs the positioning process by utilizing a positioning technique using radio waves.

7. The mobile body according to claim 6 , wherein the positioning unit performs the positioning process by correcting the position obtained by the positioning technique using radio waves based on a result of the recognition process.

8. The mobile body according to claim 6 , wherein the positioning technique using radio waves is a positioning technique using a GPS sensor.

9. The moving body according to claim 1 , further comprising an inspection unit that detects damage to the snow prevention object based on information detected by the sensor.

10. A method for controlling an autonomously moving object, comprising: a recognition step of performing a process of recognizing a snowfall prevention object around the moving body based on detection information from a sensor that detects surrounding environment information of the moving body; a positioning step of performing a positioning process of the moving object based on a result of the recognition process; a movement control step of performing a movement control process for the moving object based on a result of the positioning process; The control method comprises:

11. A control program for an autonomously moving object, comprising: a recognition step of performing a process of recognizing a snowfall prevention object around the moving body based on detection information from a sensor that detects surrounding environment information of the moving body; a positioning step of performing a positioning process of the moving object based on a result of the recognition process; a movement control step of performing a movement control process for the moving object based on a result of the positioning process; A control program that executes the

Images