Mobile body control system, mobile body control method, mobile body, computer program product, and recording medium

Abstract

The present application provides a mobile body control system, a mobile body control method, a mobile body, a computer program product, and a recording medium. The mobile body control system has: an acquisition mechanism that acquires an image of an outside of a mobile body that travels in a first direction toward an intersection area; a determination mechanism that determines a size of the intersection area, a position, and a speed of a second mobile body that travels in a second direction intersecting the first direction toward the intersection area; and a determination mechanism that determines a risk of collision in the intersection area of the second mobile body present at the position and the mobile body. Here, the determination mechanism classifies the speed of the second mobile body in the second direction into any one of a plurality of stages of speed, and the determination mechanism uses the size of the intersection area determined based on the image and the classified stage of speed for the determination of the condition, and determines the risk of collision in the intersection area of the second mobile body present at the position.

Description

Technical Field

[0001] This invention relates to a mobile body control system, a mobile body control method, a mobile body, a computer program product, and a recording medium. Background Technology

[0002] In recent years, small mobile vehicles (also known as micro-mobile vehicles) have been known for supporting the movement of people in small areas. Such mobile vehicles also exist that possess autonomous movement technology that allows them to operate within lanes and utilize free spaces such as sidewalks for pedestrian movement (Patent Document 1). In such mobile vehicles, since they travel in both vehicle and pedestrian movement areas, it is necessary to use images to navigate appropriately in a variety of areas without relying on pre-installed high-precision maps.

[0003] Existing technical documents Patent documents Patent Document 1: Japanese Patent Application Publication No. 2024-064218. Summary of the Invention

[0004] The problem that the invention aims to solve However, mobile vehicles need to navigate safely even in the absence of traffic lights, such as at parking lot entrances and exits on pedestrian walkways, intersections on driveways, and areas where mobile vehicles and regular vehicles intersect (intersection areas). However, when using image recognition to assess the external environment, there are situations where it is impossible to accurately infer the size of the intersection area, the speed of regular vehicles, and other information necessary to avoid collisions.

[0005] The present invention was made in view of the above-mentioned problems, and its object is to realize a technology that can properly determine the collision between moving bodies and other moving bodies in an intersection area.

[0006] means for solving problems According to the present invention, a mobile body control system is provided, which is a mobile body control system for controlling the movement of a mobile body, wherein, The mobile body control system has: An acquisition mechanism that acquires an image of the outside world of the moving body traveling in a first direction toward the intersection area; A determining mechanism, based on the image, determines the size of the intersection region, the position and speed of a second moving body traveling toward the intersection region along a second direction intersecting the first direction; and The determining mechanism assesses the risk of a collision between the second moving body and the first moving body at the intersection area based on the condition that one of the moving body and the second moving body leaves the intersection area before the other enters it. The determining mechanism classifies the velocity of the second moving body toward the second direction into any one of a plurality of stage velocities. The determination mechanism uses the size of the intersection region determined based on the image and the speed of the classified stage to determine the conditions and the risk of the second moving body present at the location colliding with the intersection region.

[0007] Furthermore, according to the present invention, a mobile body is provided, wherein... The mobile body has: An acquisition mechanism that acquires an image of the outside world of the moving body traveling in a first direction toward the intersection area; A decision mechanism, based on the image, determines the size of the intersection region, the position and speed of the second moving body traveling toward the intersection region along a second direction intersecting the first direction; The determining body determines the risk of a collision between the second mobile body and the first mobile body at the location in the intersection area based on the condition that one of the mobile body and the second mobile body leaves the intersection area before the other enters the intersection area; and The control mechanism, based on the risk assessment, determines whether to stop near the intersection area or enter the intersection area. The determining mechanism classifies the velocity of the second moving body toward the second direction into any one of a plurality of stage velocities. The determination mechanism uses the size of the intersection region determined based on the image and the speed of the classified stage to determine the conditions and the risk of the second moving body present at the location colliding with the intersection region.

[0008] Furthermore, according to the present invention, a control method for a mobile body control system is provided, which is a control method for a mobile body control system that controls the actions of a mobile body, wherein... The control method of the mobile body control system has the following characteristics: In the acquisition step, an image of the outside of the moving body traveling in a first direction toward the intersection area is acquired; A decision step, in which the size of the intersection region, the position and speed of the second moving body traveling toward the intersection region along a second direction intersecting the first direction are determined based on the image; and In this determination step, the risk of collision between the second moving body and the first moving body at the location is determined based on the condition that one of the moving body and the second moving body leaves the intersection area before the other enters the intersection area. In the decision-making step, the velocity of the second moving body toward the second direction is classified into any one of a plurality of stage velocities. In the determination step, the size of the intersection region determined based on the image and the speed of the classified stage are used to determine the condition and the risk of the second moving body present at the location colliding with the intersection region.

[0009] Invention Effects According to the present invention, it is possible to appropriately determine the collision between moving bodies and other moving bodies in the intersection area. Attached Figure Description

[0010] Figure 1A , Figure 1B This is a diagram illustrating an example of the configuration of a movable body according to an embodiment of the present invention.

[0011] Figure 2 This is a block diagram illustrating an example of the configuration of a control system for a mobile body according to an embodiment.

[0012] Figure 3 This is a block diagram illustrating a functional configuration example related to the control unit of the mobile body involved in the embodiment.

[0013] Figure 4 This is a diagram that schematically illustrates an example of an intersection area involved in an implementation method.

[0014] Figure 5A This diagram illustrates the conditions related to collisions involved in the implementation method.

[0015] Figure 5B This diagram illustrates an example of a hazardous area involved in the implementation method.

[0016] Figure 6 It is a flowchart illustrating a series of actions involved in the collision avoidance process in the implementation method.

[0017] Figure 7 Figure (1) is an example illustrating the determination of the intersection area in the lane involved in the implementation method.

[0018] Figure 8 Figure (2) is an example illustrating the determination of the intersection area in the lane involved in the implementation method.

[0019] Figure 9 Figure (3) is an example of determining the intersection area in the lane involved in the implementation method.

[0020] Explanation of reference numerals in the attached figures 100: Moving body; 130: Control unit; 301: Information acquisition unit; 302: Attribute determination unit; 304: Driving control unit. Detailed Implementation

[0021] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Furthermore, the following embodiments are not intended to limit the invention to which the technical solution pertains. Additionally, not all combinations of features described in the embodiments are necessarily essential to the invention. Two or more features from the plurality of features described in the embodiments may be arbitrarily combined. Furthermore, identical or identical components are labeled with the same reference numerals, and repeated descriptions are omitted.

[0022] In the following embodiments, a miniature mobile vehicle, as an example of a mobile body, will be used for explanation. The miniature mobile vehicle can be an electric vehicle with a passenger capacity of approximately one person, or it can be a miniature mobile vehicle that transports goods while traveling alongside people, replacing the passenger. Furthermore, this embodiment is not limited to examples where the mobile body is an electric vehicle; it can also be applied to mobile bodies other than electric vehicles. Further, in the following description, a mobile body with one driven wheel will be used as an example, but it is not necessary to have a driven wheel; more than one driven wheel may also be used. Furthermore, the mobile body is not limited to vehicles and may also include robots capable of autonomous movement (e.g., capable of walking).

[0023] <The Composition of a Moving Body> The structure of the movable body 100 will be described with reference to FIG1. Figure 1A This indicates the side surface of the movable body 100 involved in this embodiment. Figure 1B This diagram shows the internal structure of the moving body 100. Arrow X in the diagram indicates the forward / backward direction of the moving body 100, F indicates forward, and R indicates backward. Arrows Y and Z indicate the width (left / right) and height (up / down) directions of the moving body 100.

[0024] The mobile body 100 includes a driving unit 112 and moves autonomously using a battery 113 as its main power source. The battery 113 is, for example, a rechargeable battery such as a lithium-ion battery. The mobile body 100 uses the power supplied from the battery 113 to move automatically via the driving unit 112. The driving unit 112 is in the form of a tricycle, having a pair of left and right drive wheels 120 as front wheels and a driven wheel 121 as a rear wheel. Alternatively, the driving unit 112 can also be in the form of a four-wheeled vehicle or other forms. The mobile body 100 includes, for example, a seat 111 for one person.

[0025] The traveling unit 112 includes a drive mechanism 122. The drive mechanism 122 is a mechanism that uses motors 122a and 122b as drive sources to rotate corresponding drive wheels 120. The drive mechanism 122 can cause the moving body 100 to move forward or backward by rotating each of the drive wheels 120. The drive mechanism 122 can also change the direction of travel of the moving body 100 by generating a rotational difference between motors 122a and 122b. The traveling unit 112 includes a driven wheel 121. The driven wheel can rotate about the Z-axis.

[0026] The moving body 100 includes detection units 114-116 for detecting targets around the moving body 100. Detection units 114-116 are a group of external sensors that monitor the surroundings of the moving body 100. In this embodiment, detection units 114-116 are imaging devices that capture images of the surroundings of the moving body 100, for example, equipped with an optical system such as a lens and an image sensor. However, radar or optical radar (Light Detection and Ranging) may be used instead of imaging devices or based on imaging devices.

[0027] For example, two detection units 114 are arranged at intervals along the Y direction at the front of the moving body 100, mainly for detecting targets in front of the moving body 100. Detection units 115 are respectively arranged at the left and right sides of the moving body 100, mainly for detecting targets to the sides of the moving body 100. Detection unit 116 is arranged at the rear of the moving body 100, mainly for detecting targets behind the moving body 100.

[0028] Figure 2 This is a block diagram of the control system of the mobile body 100. The mobile body 100 includes a control unit (ECU) 130. The control unit 130 includes one or more processors, such as a CPU, storage devices (recording media) such as semiconductor memory, and interfaces for external devices. The memory devices store programs executed by the processor and data used by the processor for processing. The processor, memory devices, and interfaces can also be configured in multiple groups according to the functions of the mobile body 100, enabling them to communicate with each other.

[0029] The control unit 130 acquires the outputs (e.g., images) from the detection units 114-116, input information to the operation unit 131, and sound information from the sound input device 133, and performs processing corresponding to each piece of information. The control unit 130 controls the motors 122a and 122b (driving control of the driving unit 112), controls the display of the display panel included in the operation unit 131, provides sound-based reports to the occupants of the moving body 100, and outputs information. The control unit 130 can also perform processing using a machine learning model (e.g., a deep neural network) for image recognition on the images from the detection units 114-116. Furthermore, the control unit 130 can also perform processing using a machine learning model (e.g., a deep neural network) for sound recognition on the sound information from the sound input device 133.

[0030] The sound output device 132 includes, for example, a speaker, which outputs sound according to instructions from the control unit 130. The sound input device 133 includes, for example, a microphone, which picks up the voices of the occupants of the mobile body 100. The control unit 130 is able to recognize the input sound and perform corresponding processing. The GNSS (Global Navigation Satellite System) sensor 134 receives GNSS signals to detect the current position of the mobile body 100.

[0031] Storage device 135 includes a non-volatile recording medium for storing various types of data. Storage device 135 may also store programs executed by the processor, data used by the processor for processing, etc. Storage device 135 may also store various parameters (e.g., learning completion parameters and hyperparameters of deep neural networks) of machine learning models used for voice recognition and image recognition executed by control unit 130.

[0032] The communication device 136 is, for example, a communication device capable of communicating with an external device (such as a user-owned communication terminal 140) via wireless communication such as Wi-Fi or fifth-generation mobile communication.

[0033] Next, refer to Figure 3 An example of the functional configuration of the control unit 130 will be described. The control unit 130 includes, for example, an information acquisition unit 301, an attribute determination unit 302, a collision determination unit 303, and a driving control unit 304.

[0034] The information acquisition unit 301 acquires user instructions input via the operation unit 131 or the voice input device 133. The user instructions include a designation of the final target location that the mobile body 100 should reach. The final target location may also be the location of a target object identified within the image output by the detection units 114-116 and designated by spoken voice. Furthermore, during the movement of the mobile body 100, the user instructions may also include instructions for changing the driving trajectory, such as turning right, turning left, accelerating, or decelerating.

[0035] Additionally, the information acquisition unit 301 acquires the output (e.g., an image) of the detection units 114-116 and identifies the position, shape, etc., of the driving road and obstacles based on the image. The identification of the position, shape, etc., of the driving road and obstacles in front of the moving body 100 includes, for example, calculating the depth distance from the moving body 100 using the image obtained from the detection unit 114. Furthermore, identifying the driving road and obstacles includes using a pre-learned machine learning model (e.g., a deep neural network) for image recognition on monocular or stereo images.

[0036] Information acquisition unit 301 can identify, for example, the boundaries (edges) of sidewalks, the boundaries of lanes, and stop lines disposed on lanes and sidewalks based on images. Furthermore, information acquisition unit 301 can identify the distance between the boundaries of sidewalks, the distance between the boundaries of lanes, and the position of stop lines (e.g., their relative position from the moving body 100). Additionally, information acquisition unit 301 can identify the position (e.g., relative position from the moving body 100) and speed of other moving bodies besides the moving body 100 based on image recognition.

[0037] Reference Figure 4 The intersection areas where the mobile body 100 travels in this embodiment will be described. Figure 4 In the example of the intersection shown, the intersection exists on a sidewalk. For example, there is a lane 401 and a sidewalk 403 adjacent to the lane 401. Furthermore, a parking lot 404 is adjacent to the sidewalk 403, for example. At this time, vehicle 402 is traveling in a first direction toward the intersection. On the other hand, other moving bodies (such as vehicle 402) traveling in lane 401 are traveling in a second direction that intersects the first direction. That is, vehicle 402 is moving toward the parking lot 404 by crossing the intersection 408 of the sidewalk 403. A stop line 407 indicating the start position of the intersection 408 and a stop line 409 indicating the end position are provided on the sidewalk 403.

[0038] exist Figure 4In the example shown, the information acquisition unit 301 can identify the boundary 405 of the lane 401, the boundary 406 of the two sidewalks, and the stop line 407 from the image. Furthermore, the information acquisition unit 301 can identify the distance between the boundaries 406 of the sidewalks 403, the distance between the boundaries of the lanes 401, and the position of the stop line 407 (e.g., its relative position from the moving body 100). However, it is possible that the information acquisition unit 301 cannot identify the stop line 409 on the side furthest from the moving body 100, for example, because it is not included in the image or the area of ​​the stop line is small.

[0039] The attribute determination unit 302 determines the attributes of other moving bodies (vehicle 402) and the attributes of the intersection area 408 based on the image. For example, the attribute determination unit 302 determines the size of the intersection area 408, the position of the vehicle 402 traveling in the second direction toward the intersection area 408, and its speed.

[0040] Since the stop line 409 is not identified from the image, the attribute determination unit 302 uses a predetermined distance from the position of the stop line identified from the image as the distance in the first direction of the intersection area 408. Additionally, the attribute determination unit 302 uses the distance between the boundaries 406 of the lanes (pedestrian walkways 403) on which the mobile vehicle 100 travels as the distance in the second direction of the intersection area 408. Therefore, even when the stop line 409 on the side away from the mobile vehicle 100 cannot be identified from the image, the size of the intersection area 408 can be determined based on the image. Furthermore, the size of the intersection area when the mobile vehicle 100 is traveling on a pedestrian walkway can be determined based on the image.

[0041] Furthermore, the attribute determination unit 302 determines the attributes (position and speed) of the vehicle 402 traveling in the second direction toward the intersection area based on the image. For example, the attribute determination unit 302 uses the position of the vehicle 402 as the distance from the moving body 100. Additionally, the attribute determination unit 302 classifies the speed of the vehicle 402 toward the second direction into any one of a plurality of staged speeds. Generally, the vehicle 402 in the image is homography-converted and positioned... Figure 4 In the bird's-eye view shown, there are many cases where the error increases when inferring the moving speed of the vehicle 402 positioned on the bird's-eye view. Therefore, in this embodiment, the speed of the vehicle 402 in the second direction is classified into several stages such as "stop", "low speed" and "medium speed".

[0042] For example, when the speed v of the vehicle 402 in the second direction is 0 km / h ≤ v < 2 km / h, the attribute determination unit 302 classifies the speed as "stopped". When the speed v of the vehicle 402 in the second direction is 2 km / h ≤ v < 6 km / h, the attribute determination unit 302 classifies the speed as "low speed". When the speed v of the vehicle 402 in the second direction is 6 km / h ≤ v, the attribute determination unit 302 classifies the speed as "medium speed".

[0043] The collision determination unit 303 determines the risk of a collision between the vehicle 402 and the moving body 100, which are located at a presumed position, in the intersection area 408 based on the condition that one of the moving body 100 and the vehicle 402 leaves the intersection area 408 before the other enters it. (Refer to...) Figure 5A as well as Figure 5B The determination based on the collision determination unit 303 will be explained.

[0044] V veh It is the speed of vehicle 402 heading in the second direction. Additionally, t... ego，ent It is the first time 501, t, before the moving body 100 enters the intersection area 408. ego，exit This is the second time 502 until the moving body 100 detaches from the intersection area 408. veh，ent It is the distance 503 from vehicle 402 to the intersection area 408. veh，exit It is the distance 504 until vehicle 402 leaves the intersection area 408. share It is the distance of 505 in the second direction of the intersection region 408. Furthermore, t ego，ent and t ego，exit The calculation is based on the moving speed obtained from the drive mechanism 122 of the moving body 100, the distance to the stop line 407, and the size of the intersection area 408.

[0045] In order to prevent the moving body 100 and the vehicle 402 from colliding in the intersection area 408, the priority condition of the vehicle following mathematical formula (1) and the priority condition of other vehicles following mathematical formula (2) are satisfied.

[0046]

[0047]

[0048] On the other hand, based on these conditions, the conditions under which the moving body 100 and the vehicle 402 may collide in the intersection area 408 (the risk increases) are expressed by mathematical formula (3).

[0049]

[0050] In other words, the distance traveled by vehicle 402 before moving body 100 enters intersection area 408 is shorter than the distance 504 (vehicle 402 exists within intersection area 408), and the distance traveled by vehicle 402 before moving body 100 leaves intersection area 408 is longer than the distance 503.

[0051] Next, refer to Figure 5B The degree of danger involved in this embodiment will be explained. As mentioned above, due to the large error in the speed of vehicle 402, it is difficult to make a correct collision determination. Therefore, in this embodiment, based on the collision conditions shown in mathematical formula (3), danger zones corresponding to multiple stage speeds (e.g., stop, low speed, medium speed, etc.) are set.

[0052] The collision determination unit 303 sets up danger zones corresponding to multiple stage speeds (low speed, etc.) based on the speed in the second direction, the first time until the moving body 100 enters the intersection area 408, the second time until it leaves the intersection area 408, and the size of the intersection area 408. For example, if the speed of vehicle 402 is "stopped," and vehicle 402 is present in the danger zone 510 for stopping, the probability of a collision increases. Or, if the speed of vehicle 402 is "low speed," and vehicle 402 is present in the danger zone 511 for low speed, the probability of a collision increases. Furthermore, if the speed of vehicle 402 is "medium speed," and vehicle 402 is present in the danger zone 512 for medium speed, the probability of a collision increases. Thus, if the collision determination unit 303 finds a position where vehicle 402 is present in a danger zone corresponding to a classified speed (e.g., low speed) within the set danger zones, it determines that there is a possibility of a collision (high risk). On the other hand, if the collision determination unit 303 finds that the vehicle 402 is not located in the designated danger zone corresponding to the classified speed (e.g., low speed danger zone), it determines that the probability of a collision is low (low risk). With this setting, even if the accuracy of the inferred speed of the vehicle 402 is low, the probability of a collision can be determined by using the vehicle's location, which can be calculated with higher accuracy.

[0053] The driving control unit 304 controls whether to stop the vehicle 100 near the intersection area 408 or to enter the intersection area 408 based on the risk determination result of the collision determination unit 303. For example, if the collision determination unit 303 determines that there is a possibility of collision, the driving control unit 304 controls the vehicle 100 to stop near the intersection area 408. On the other hand, if the collision determination unit 303 determines that the possibility of collision is low (low risk), the driving control unit 304 controls the vehicle 100 to enter the intersection area 408.

[0054] Next, refer to Figure 6 A series of actions for collision avoidance processing in the moving body 100 will be described. Furthermore, this processing is achieved by the control unit 130 loading a program stored in the storage device 135 into the memory device of the control unit 130 and executing it.

[0055] In S601, the information acquisition unit 301 of the control unit 130 acquires images of the outside world of the moving body captured by the detection units 114-116. The information acquisition unit 301 uses, for example, a deep neural network to identify, as described above, the boundaries of the sidewalk, the boundaries of the lane, and the stop lines arranged on the lane and the sidewalk based on the images, and identifies the distance between the boundaries of the sidewalk, the distance between the boundaries of the lane, and the position of the stop line (e.g., the relative position from the moving body 100).

[0056] In S602, the attribute determination unit 302 of the control unit 130 determines the size of the intersection area 408. As described above, the attribute determination unit 302 uses a predetermined distance from the position of the stop line recognized by the image as the distance in the first direction of the intersection area 408. In addition, the attribute determination unit 302 uses the distance between the boundaries 406 of the lanes (pedestrian walkways 403) on which the moving body 100 travels as the distance in the second direction of the intersection area 408.

[0057] In S603, as described above, the information acquisition unit 301 identifies the position (e.g., relative position from the moving body 100) and speed of another moving body (a second moving body, such as vehicle 402) other than the image recognition moving body 100.

[0058] In S604, the attribute determination unit 302 determines the speed of the second moving body by classifying the speed of the second moving body into multiple stage speeds. For example, the attribute determination unit 302 classifies the speed of the vehicle 402 in the second direction into multiple stage speeds such as "stop", "low speed" and "medium speed".

[0059] In S605, the collision determination unit 303 of the control unit 130 sets the danger zone for each stage based on the determination conditions based on the priority conditions of the vehicle itself and the priority conditions of other vehicles. For example, the collision determination unit 303 sets the danger zone corresponding to multiple stage speeds (e.g., stop, low speed, medium speed, etc.) according to the above mathematical formula (3).

[0060] In S606, the collision determination unit 303 determines whether the moving body 100 will collide with the second moving body (e.g., vehicle 402). For example, if the speed of vehicle 402 is "stopped" and vehicle 402 is present in the danger zone 510 for stopping, the collision determination unit 303 determines that the probability of a collision is high.

[0061] In S607, the driving control unit 304 of the control unit 130 controls the movement of the moving body 100 based on the determination result. For example, as described above, if the collision determination unit 303 determines that there is a possibility of collision, the driving control unit 304 controls the moving body 100 to stop near the intersection area 408. On the other hand, if the collision determination unit 303 determines that the possibility of collision is low (low risk), the driving control unit 304 controls the moving body 100 to enter the intersection area 408. If the control unit 130 controls the movement of the moving body 100, the process of this series ends.

[0062] Furthermore, in the above embodiment, the example described is based on determining the probability of a collision in the intersection area 408 on the sidewalk 403. However, this embodiment can also be applied to determining the probability of a collision in the intersection area on a roadway.

[0063] Furthermore, considering the possibility that the intersection area on the driveway is larger than the intersection area 408 on the pedestrian walkway 403, the size of the intersection area cannot be determined all at once. Therefore, it is also possible to reset the size of the intersection area as the moving body 100 approaches the intersection area.

[0064] For example, such as Figure 7 As shown, when the mobile body 100 is traveling in lane 701, the attribute determination unit 302 determines the distance in the first direction of the intersection area 704 from a predetermined distance from the position of the first stop line 702 based on the case that the first stop line 702 near the mobile body 100 is identified from the image. At this time, the attribute determination unit 302 determines the distance in the second direction of the intersection area 704 based on the distance between the boundaries 703 of the lanes 701 in which the mobile body 100 is traveling, based on the case that the boundaries 703 of the lanes 701 in which the mobile body 100 is traveling are identified from the image.

[0065] Figure 8 The diagram schematically illustrates the intersection 802 after the moving body 100 has traveled toward the intersection and identified a portion of the second lane based on the image. The attribute determination unit 302 uses information about the boundary 801 of the second lane, which intersects with lane 701, identified from the image to correct the distance in the second direction of the intersection 704. The corrected intersection becomes... Figure 8The intersection area 802 is shown. The attribute determination unit 302 expands the width of the intersection area 802, for example, along the boundary 801 of the second lane.

[0066] Figure 9 The illustration shows the moving body 100 further moving towards the intersection area and identifying the intersection area 902 after the second stop line 901, which is located further than the first stop line 702, based on the image. The attribute determination unit 302, based on the identification of the second stop line, which is located further than the first stop line, uses the distance between the first stop line 702 and the second stop line 901 as the distance in a first direction for the intersection area 902. In this way, even when the size of the intersection area is large and cannot be determined all at once based on the image, the moving body 100 can sequentially correct the size of the intersection area while moving.

[0067] Furthermore, the aforementioned control unit 130 can also function as a mobile body control system in various ways. For example, the mobile body control system can be configured such that at least a portion of the control unit 130 is an external device of the mobile body 100, such as an external server. That is, this embodiment can also be used to control the mobile body 100 remotely from and independently of the mobile body 100. Alternatively, the mobile body control system can be the mobile body 100 itself, or it can be configured to be installed inside the mobile body 100 (i.e., it can also be the control unit 130). In addition, the computer program that operates the mobile body 100 can also be a computer program that enables one or more computers to function as units of the mobile body control system.

[0068] <Summary of Implementation Methods> (Component 1) A mobile body control system, which controls the movement of a mobile body (100), wherein, The mobile body control system has: Acquisition mechanism (301) acquires an image of the outside of the moving body traveling in a first direction toward the intersection area; The determining mechanism (302) determines, based on the image, the size of the intersection region (408, 704), the position and speed of the second moving body (402) traveling toward the intersection region in a second direction intersecting the first direction; and The determination mechanism (303) determines the risk of collision between the second mobile body and the first mobile body at the location in the intersection area based on the condition that one of the mobile body and the second mobile body leaves the intersection area before the other enters the intersection area. The determining mechanism classifies the velocity of the second moving body toward the second direction into any one of a plurality of stage velocities (510, 511, 512). The determination mechanism uses the size of the intersection region determined based on the image and the speed of the classified stage to determine the conditions and the risk of the second moving body present at the location colliding with the intersection region.

[0069] Based on this configuration, it is possible to properly determine the collision between moving objects and other moving objects in the intersection area.

[0070] (Component 2) According to the mobile body control system of configuration 1, the determining mechanism determines the size of the intersection area using the position of the stop line recognized by the image and the boundary of the lane in which the mobile body is traveling.

[0071] Based on this structure, the size of the intersection area can be determined from the image.

[0072] (Component 3) According to the mobile body control system of configuration 1, the determining mechanism determines the size of the intersection area by taking a predetermined distance from the position of the stop line recognized according to the image as the distance in the first direction of the intersection area, and taking the distance between the boundaries of the lanes in which the mobile body travels as the distance in the second direction of the intersection area.

[0073] According to this configuration, even if the stop line 409 on the side away from the moving body 100 cannot be identified from the image, the size of the intersection region 408 can be determined based on the image. Furthermore, the distance in the second direction of the intersection region can be easily determined from the image.

[0074] (Component 4) According to the mobile body control system of configuration 1, when the mobile body is traveling on a sidewalk, the determining mechanism uses the position of the stop line recognized by the image and the boundary of the sidewalk on which the mobile body is traveling to determine the size of the intersection area.

[0075] Based on this configuration, the size of the intersection area when the moving body 100 is traveling on the sidewalk can be determined from the image.

[0076] (Component 5) According to the mobile body control system described in configuration 1, wherein... When the moving body is traveling in the lane The decision-making mechanism identifies a first stop line near the moving body based on the image, and defines the distance in the first direction of the intersection area as a predetermined distance from the position of the first stop line. Subsequently, based on the case where a second stop line is identified at a position farther than the first stop line according to the image, the distance between the first stop line and the second stop line is taken as the distance in the first direction of the intersection area.

[0077] According to this configuration, even when the size of the intersection area is large and the size of the intersection area cannot be determined at once based on the image, the moving body 100 can adjust the size of the intersection area sequentially while moving.

[0078] (Composition 6) According to the mobile body control system described in configuration 1, wherein... When the moving body is traveling in the lane The decision-making mechanism identifies the boundaries of the lanes in which the mobile vehicle is traveling based on the image, and uses the distance between the boundaries of the lanes in which the mobile vehicle is traveling as the distance in the second direction of the intersecting area. Subsequently, based on the identification of the boundary of the second lane intersecting the lane according to the image, the distance in the second direction of the intersection area is corrected using the information of the boundary of the second lane.

[0079] Based on this configuration, the accuracy of the width of the intersection region can be improved over time. Even when the size of the intersection region is large and cannot be determined at once based on the image, the moving body 100 can sequentially correct the size of the intersection region as it moves.

[0080] (Component 7) According to the mobile body control system described in configuration 1, wherein... The determination mechanism sets danger zones corresponding to the multiple phased speeds based on the size of the intersection area, the speed towards the second direction, the first time from when the moving body enters the intersection area to when it leaves the intersection area. The risk is determined based on the dangerous area corresponding to the classified speed within the defined dangerous area and the position of the second moving body.

[0081] Based on this configuration, even when the accuracy of the inferred speed of vehicle 402 is low, the probability (risk) of a collision can be determined by using the vehicle's position, which can be calculated with higher accuracy.

[0082] (Composition 8) According to the mobile body control system described in configuration 1, wherein... When the condition satisfies mathematical expression (3), it indicates that there is a risk of collision between the moving body and the second moving body in the intersection area.

[0083] V veh It is the velocity in the second direction, t ego，ent The first time t is the time until the moving body enters the intersection area. ego，exit It is the second time until the point of separation from the intersection region, l veh，ent It is the distance from when the second moving body enters the intersection area, l share This represents the distance in the second direction of the intersecting region.

[0084] Based on this structure, the likelihood (risk) of a collision can be determined using information primarily obtained from images.

[0085] (Composition 9) A mobile body (100), wherein, The mobile body (100) has: Acquisition mechanism (301) acquires an image of the outside of the moving body traveling in a first direction toward the intersection area; The determining mechanism (302) determines, based on the image, the size of the intersection area (408, 704), the position and speed of the second moving body (402) traveling toward the intersection area in a second direction intersecting the first direction; The determination mechanism (303) determines the risk of collision between the second mobile body and the first mobile body at the location in the intersection area based on the condition that one of the mobile body and the second mobile body leaves the intersection area before the other enters the intersection area; and The control mechanism, based on the risk assessment, determines whether to stop near the intersection area or enter the intersection area. The determining mechanism classifies the velocity of the second moving body toward the second direction into any one of a plurality of stage velocities (510, 511, 512). The determination mechanism uses the size of the intersection region determined based on the image and the speed of the classified stage to determine the conditions and the risk of the second moving body present at the location colliding with the intersection region.

[0086] Based on this configuration, it is possible to appropriately determine the collision between moving objects and other moving objects in the intersection area, and to appropriately control the passage or stopping of the intersection area.

[0087] The invention is not limited to the above-described embodiments and can be modified and altered in various ways within the scope of the invention's intent.

Claims

1. A mobile body control system, which controls the movement of a mobile body, wherein, The mobile body control system has: An acquisition mechanism that acquires an image of the outside world of the moving body traveling in a first direction toward the intersection area; A determining mechanism, based on the image, determines the size of the intersection region, the position and speed of a second moving body traveling toward the intersection region along a second direction intersecting the first direction; and The determining mechanism assesses the risk of a collision between the second moving body and the first moving body at the intersection area based on the condition that one of the moving body and the second moving body leaves the intersection area before the other enters it. The determining mechanism classifies the velocity of the second moving body toward the second direction into any one of a plurality of stage velocities. The determination mechanism uses the size of the intersection region determined based on the image and the speed of the classified stage to determine the conditions and the risk of the second moving body present at the location colliding with the intersection region.

2. The mobile body control system according to claim 1, wherein, The decision-making mechanism determines the size of the intersection area using the position of the stop line recognized from the image and the boundary of the lane in which the moving vehicle is traveling.

3. The mobile body control system according to claim 1, wherein, The determining mechanism determines the size of the intersection area by taking a predetermined distance from the position of the stop line recognized according to the image as the distance in the first direction of the intersection area, and the distance between the boundaries of the lanes on which the moving body travels as the distance in the second direction of the intersection area.

4. The mobile body control system according to claim 1, wherein, When the moving vehicle is traveling on a sidewalk, the decision-making mechanism uses the position of the stop line recognized from the image and the boundary of the sidewalk on which the moving vehicle is traveling to determine the size of the intersection area.

5. The mobile body control system according to claim 1, wherein, When the moving body is traveling in the lane The decision-making mechanism identifies a first stop line near the moving body based on the image, and defines the distance in the first direction of the intersection area as a predetermined distance from the position of the first stop line. Subsequently, based on the case where a second stop line is identified at a position farther than the first stop line according to the image, the distance between the first stop line and the second stop line is taken as the distance in the first direction of the intersection area.

6. The mobile body control system according to claim 1, wherein, When the moving body is traveling in the lane The decision-making mechanism identifies the boundaries of the lanes in which the mobile vehicle is traveling based on the image, and uses the distance between the boundaries of the lanes in which the mobile vehicle is traveling as the distance in the second direction of the intersecting area. Subsequently, based on the identification of the boundary of the second lane intersecting the lane according to the image, the distance in the second direction of the intersection area is corrected using the information of the boundary of the second lane.

7. The mobile body control system according to claim 1, wherein, The determination mechanism sets danger zones corresponding to the multiple phased speeds based on the size of the intersection area, the speed towards the second direction, the first time from when the moving body enters the intersection area to when it leaves the intersection area. The risk is determined based on the dangerous area corresponding to the classified speed within the defined dangerous area and the position of the second moving body.

8. The mobile body control system according to claim 1, wherein, When the condition satisfies mathematical expression (3), it indicates that there is a risk of collision between the moving body and the second moving body in the intersection area. V veh It is the velocity in the second direction, t ego，ent The first time t is the time until the moving body enters the intersection area. ego，exit It is the second time until the point of separation from the intersection region, l veh，ent It is the distance from when the second moving body enters the intersection area, l share This represents the distance in the second direction of the intersecting region.

9. A mobile body, wherein, The mobile body has: An acquisition mechanism that acquires an image of the outside world of the moving body traveling in a first direction toward the intersection area; A determining mechanism, based on the image, determines the size of the intersection region, the position and speed of a second moving body traveling toward the intersection region along a second direction intersecting the first direction; and The determining mechanism determines the risk of collision between the second mobile body and the first mobile body at the location in the intersection area based on the condition that one of the mobile body and the second mobile body leaves the intersection area before the other enters the intersection area; as well as The control mechanism, based on the risk assessment, determines whether to stop near the intersection area or enter the intersection area. The determining mechanism classifies the velocity of the second moving body toward the second direction into any one of a plurality of stage velocities. The determination mechanism uses the size of the intersection region determined based on the image and the speed of the classified stage to determine the conditions and the risk of the second moving body present at the location colliding with the intersection region.

10. A control method for a mobile body control system, wherein, The control method of the mobile body control system has the following characteristics: In the acquisition step, an image of the outside of the moving body traveling in a first direction toward the intersection area is acquired; A decision step, in which the size of the intersection region, the position and speed of the second moving body traveling toward the intersection region along a second direction intersecting the first direction are determined based on the image; and In this determination step, the risk of collision between the second moving body and the first moving body at the location is determined based on the condition that one of the moving body and the second moving body leaves the intersection area before the other enters the intersection area. In the decision-making step, the velocity of the second moving body toward the second direction is classified into any one of a plurality of stage velocities. In the determination step, the size of the intersection region determined based on the image and the speed of the classified stage are used to determine the condition and the risk of the second moving body present at the location colliding with the intersection region.

11. A computer program product comprising a computer program and / or instructions, wherein, If the computer program and / or commands are executed by the processor, the steps of the control method of claim 10 are implemented.

12. A computer-readable recording medium, which is a computer-readable recording medium for storing computer programs / commands, wherein, If the computer program and / or commands are executed by the processor, the steps of the control method of claim 10 are implemented.

Images