Vehicle determination device

Abstract

To provide a vehicle determination device that can accurately determine whether or not a vehicle can pass a traffic light when the vehicle attempts to pass the traffic light.SOLUTION: A processor 152 of an ECU 150 comprises: a traffic light determination unit 152a for determining whether or not a traffic light 30 located in front of a vehicle 10 indicates that the vehicle 10 is permitted to pass; an another vehicle behavior determination unit 152b for determining a behavior of another vehicle 20 existing in the vicinity of the vehicle 10; and a passing permission determination unit 152c for determining whether or not the vehicle 10 is permitted to pass the traffic light 30 based on the behavior of another vehicle 20 located in the vicinity of the vehicle 10 when it is determined that the traffic light 30 indicates that the vehicle 10 is permitted to pass.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a vehicle determination device. [Background technology]

[0002] Conventionally, a signal display estimation system has been known that is designed to accurately estimate the signal display of a traffic light ahead in the direction of travel that a vehicle should follow when multiple traffic lights to be recognized are detected (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-018737 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the status of a traffic light is indicated by the color of the light or the arrow displayed, without involving the movement of objects. Therefore, when determining the status of a traffic light, in principle, only image information from a camera can be used, and considering the possibility of errors in recognizing image information due to external factors such as backlighting, it is difficult to improve the reliability of the determination. For example, when a vehicle attempts to pass through an intersection with traffic lights, if the decision on whether to pass is made based solely on the status of the traffic light, the decision will rely solely on the status of the traffic light as seen in the camera image, which could result in a decrease in reliability.

[0005] Furthermore, recognizing the status of traffic lights using camera images is technically relatively difficult, and there are expected to be limits to how accurately the status of traffic lights can be recognized. For this reason, it is preferable to improve the accuracy of the overall system by using other means in addition to recognizing the status of traffic lights using camera images.

[0006] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a vehicle determination device that can accurately determine whether a vehicle is able to pass through a traffic light when the vehicle is about to pass through the traffic light. [Means for solving the problem]

[0007] The gist of the present disclosure is as follows.

[0008] (1) a traffic light determination unit that determines whether a traffic light ahead of the vehicle indicates that the vehicle can pass; an other vehicle behavior determination unit that determines the behavior of other vehicles present around the vehicle; a pass possibility determination unit that, when it is determined that the traffic light indicates that the vehicle is permitted to pass, determines whether the vehicle is permitted to pass through the traffic light based on the behavior of other vehicles present around the vehicle; A vehicle determination device comprising:

[0009] (2) The vehicle determination device described in (1) above, wherein the passage possibility determination unit determines that the vehicle is able to start when the vehicle is stopped at the traffic light and determines that the traffic light indicates that the vehicle is able to pass, and when it determines that another vehicle traveling in the same direction or opposite direction as the vehicle has started to move.

[0010] (3) The vehicle determination device described in (1) above, wherein the passage possibility determination unit determines that the vehicle can pass through the traffic light when the vehicle attempts to pass through the traffic light while traveling and determines that other vehicles traveling in the same direction as the vehicle are not slowing down by more than a predetermined value. [Effects of the Invention]

[0011] According to the present invention, a vehicle determination device is provided that can accurately determine whether a vehicle is allowed to pass through a traffic light when the vehicle is about to pass through the traffic light. [Brief explanation of the drawings]

[0012] [Figure 1]1 is a schematic configuration diagram of a vehicle driving assistance system 1000 according to one embodiment. [Figure 2] 1 is a schematic diagram showing a state in which a vehicle 10 is stopped on a road with two lanes on each side. [Figure 3] FIG. 2 is a schematic diagram showing functional blocks of a processor of an ECU. [Figure 4] 4 is a flowchart showing a process performed by a processor of the ECU at each predetermined control period. [Figure 5] 4 is a flowchart showing a process performed by a processor of the ECU at each predetermined control period. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, several embodiments of the present invention will be described with reference to the drawings. However, these descriptions are intended to be merely examples of preferred embodiments of the present invention and are not intended to limit the present invention to such specific embodiments.

[0014] 1 is a schematic configuration diagram of a vehicle cruise assistance system 1000 according to one embodiment. The cruise assistance system 1000 is mounted on a vehicle such as an automobile, and includes an on-board camera 110, a periphery monitoring sensor 120, a vehicle control device 130, an electronic control unit (ECU, hereinafter referred to as ECU) 150, a warning device 160, and a positioning information receiver 170. The on-board camera 110, the periphery monitoring sensor 120, the vehicle control device 130, the ECU 150, the warning device 160, and the positioning information receiver 170 are each connected to be able to communicate with each other via an in-vehicle network that complies with a standard such as a Controller Area Network (CAN).

[0015] The vehicle-mounted camera 110 has a two-dimensional detector configured with an array of photoelectric conversion elements, such as a CCD or C-MOS, that are sensitive to visible light, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. The vehicle-mounted camera 110 photographs the surroundings of the vehicle (for example, the area in front of the vehicle) and generates an image representing the environment around the vehicle. The vehicle-mounted camera 110 may include a front camera, two side cameras (left and right), and a rear camera. The vehicle-mounted camera 110 photographs at a predetermined photographing interval (for example, 1 / 30 to 1 / 10 seconds). The vehicle-mounted camera 110 may be configured as a stereo camera and may be configured to obtain the distance to each structure on the image from the parallax between the left and right images. Each time the vehicle-mounted camera 110 generates an image, it outputs the generated image to the ECU 150 via the in-vehicle network.

[0016] The periphery monitoring sensor 120 is a sensor for monitoring the periphery of the vehicle. The periphery monitoring sensor 120 includes, for example, sensors such as Lidar (Light Detection and Ranging) and Radar. The radar includes a front side radar sensor located inside the front bumper and a rear side radar sensor located inside the rear bumper.

[0017] The vehicle control equipment 130 is various equipment related to vehicle control, and includes a drive device such as an internal combustion engine or an electric motor as a drive source for driving the vehicle, a transmission, a braking device for braking the vehicle, a steering device for turning the vehicle, and the like.

[0018] The ECU 150 is one aspect of a vehicle determination device according to the present disclosure. The ECU 150 includes a processor 152, a memory 154, and a communication interface 156. The processor 152 includes one or more central processing units (CPUs) and their peripheral circuits. The processor 152 may further include other arithmetic circuits such as a logic unit, a numerical calculation unit, or a graphics processing unit. The memory 154 includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory, and stores data related to the processing according to this embodiment. The communication interface 156 includes an interface circuit for connecting the ECU 150 to an in-vehicle network.

[0019] The warning device 160 includes a display device and a speaker. The display device is configured, for example, by a liquid crystal display (LCD) and is provided near the meter panel or the dashboard, and displays and outputs a warning in response to an instruction from the ECU 150. The speaker outputs the warning as sound in response to an instruction from the ECU 150.

[0020] The positioning information receiver 170 acquires positioning information that indicates the current position and attitude of the vehicle. For example, the positioning information receiver 170 can be a GPS (Global Positioning System) receiver.

[0021] In this embodiment, a driving assistance system 1000 that assists in starting, stopping, accelerating, decelerating, steering, etc. of a vehicle assists in a scene where the vehicle passes through a traffic light. Fig. 2 is a schematic diagram showing a state in which a vehicle 10 is stopped on a road with two lanes in each direction, and shows a state in which a traffic light 30 in front of the vehicle 10 has changed from red to green. The vehicle 10 is equipped with the driving assistance system 1000 shown in Fig. 1. As shown in Fig. 2, when the traffic light 30 changes to green, another vehicle 20 that has been stopped to the right of the vehicle 10 starts moving.

[0022] The driving assistance system 1000 determines whether the color of the traffic light 30 has changed from red to green based on the image generated by the in-vehicle camera 110. Then, when it is determined that the color of the traffic light 30 has changed from red to green and the other vehicle 20 that has been stopped on the right side has started to move, the driving assistance system 1000 determines that the vehicle 10 can start moving.

[0023] If the determination of whether or not the vehicle 10 can start is based solely on the change in the color of the traffic light 30 from red to green, the determination of whether or not the vehicle 10 can start is made using only the change in color of the traffic light 30 based on the image from the in-vehicle camera 110. In this case, considering the possibility that an error may occur in the determination of the color of the traffic light 30 based on the image due to factors such as backlighting, there is a possibility that the reliability of the determination of whether or not the vehicle 10 can start may not be sufficiently ensured.

[0024] In this embodiment, the vehicle 10 is permitted to start based on the behavior of the other vehicle 20 in addition to determining the state of the traffic light 30 based on the image from the in-vehicle camera 110. This makes it possible to increase the reliability of the determination of whether the vehicle 10 is permitted to start by taking into consideration not only the determination of the traffic light state based on the image but also the behavior of the other vehicle 20 in the vicinity. Specifically, even if it is determined that the color of the traffic light 30 has changed from red to green, the vehicle 10 will not start unless the other vehicle 20 starts. This ensures the reliability of the determination of whether the vehicle 10 is permitted to start even if there is an error in the determination of the color of the traffic light 30 based on the image.

[0025] 3 is a schematic diagram showing functional blocks of the processor 152 of the ECU 150 for realizing the above-described processing. The processor 152 of the ECU 150 has a traffic light determination unit 152a, an other vehicle behavior determination unit 152b, a passage possibility determination unit 152c, and a driving assistance unit 152d. Each of these units of the processor 152 is a functional module realized by, for example, a computer program running on the processor 152. That is, the functional blocks of the processor 152 are configured by the processor 152 and a program (software) for causing the processor 152 to function. The program may be recorded in the memory 154 included in the ECU 150 or in a recording medium connected from outside. Alternatively, each of these units of the processor 152 may be a dedicated arithmetic circuit provided in the processor 152.

[0026] The traffic light determination unit 152a determines the presence of a traffic light 30 ahead of the vehicle 10 based on an image showing the area ahead of the vehicle 10 generated by the in-vehicle camera 110, and further determines whether the traffic light 30 indicates that the vehicle 10 may pass. That is, the traffic light determination unit 152a determines whether the traffic light 30 indicates a green light, a yellow light, a red light, a straight arrow signal, a right / left turn arrow signal, a flashing yellow (or red) signal, or a combination thereof, and determines whether the traffic light 30 indicates that the vehicle 10 may pass. In this case, the traffic light 30 is detected from the image by, for example, template matching between a template image and the image generated by the in-vehicle camera 110, or by inputting the image generated by the in-vehicle camera 110 into a classifier trained in machine learning for target detection, and determines whether the traffic light 30 indicates that the vehicle 10 may pass.

[0027] The traffic light determination unit 152a may use, as the classifier, a segmentation classifier that is trained in advance to output, for each pixel of an input image, the likelihood that the pixel represents an object for each type of object that may be represented at that pixel, and to identify the object with the highest likelihood as being represented.The traffic light determination unit 152a may use, as such a classifier, a deep neural network (DNN) having a convolutional neural network (CNN) architecture for segmentation, such as a fully convolutional network (FCN).

[0028] The other vehicle behavior determination unit 152b determines the presence of another vehicle 20 in the vicinity of the vehicle 10 and determines the behavior of the other vehicle 20 based on at least one of an image representing the environment around the vehicle 10 generated by the on-board camera 110 and information detected by the periphery monitoring sensor 120. Specifically, when the vehicle 10 is stopped at a traffic light 30, the other vehicle behavior determination unit 152b determines whether the other vehicle 20 traveling in the same direction as the vehicle 10 or in the opposite direction has started moving. Furthermore, when the vehicle 10 is about to pass through the traffic light 30, the other vehicle behavior determination unit 152b determines whether the other vehicle 20 traveling in the same direction as the vehicle 10 has decelerated by a predetermined value or more. In the determination based on the image from the on-board camera 110, the other vehicle 20 is detected from the image and the distance from the vehicle 10 to the other vehicle 20 is acquired, for example, by template matching between a template image and the image generated by the on-board camera 110, or by inputting the image generated by the on-board camera 110 into a classifier trained in machine learning for target detection. The classifier may be configured in the same manner as above. In the determination based on the information detected by the periphery monitoring sensor 120, the distance from the vehicle 10 to the other vehicle 20 is acquired from the information of the detected other vehicle 20. Then, the behavior of the other vehicle 20 is determined based on the information of the detected other vehicle 20 and the distance from the vehicle 10 to the other vehicle 20.

[0029] Note that there may be multiple other vehicles 20. Furthermore, the other vehicles 20 traveling in the same direction as or opposite to the vehicle 10 may be vehicles in front or behind the vehicle 10 in the same lane, vehicles in another lane traveling in the same direction as the vehicle 10, vehicles in the oncoming lane, or a combination of these vehicles. When the other vehicles 20 are in front or behind the vehicle 10 in the same lane as the vehicle 10, the vehicle 10 does not have to be positioned at the front. Furthermore, when making a determination based on an image from the onboard camera 110, if there is a possibility that the determination based on the front camera image is unreliable due to factors such as backlighting, the behavior of the other vehicle 20 may be determined using images from a side camera or a rear camera.

[0030] When the traffic light determination unit 152a determines that the traffic light 30 indicates that the vehicle 10 can pass, the passing possibility determination unit 152c determines whether the vehicle 10 can pass through the traffic light 30 based on the behavior of other vehicles 20 present in the vicinity of the vehicle 10.

[0031] Specifically, when the vehicle 10 is stopped at a traffic light 30, the passing possibility determination unit 152c determines that the vehicle 10 is able to start if the traffic light determination unit 152a determines that the traffic light 30 indicates that the vehicle 10 is able to pass, and if the other vehicle behavior determination unit 152b determines that another vehicle 20 traveling in the same direction as or opposite to the vehicle 10 has started to start.

[0032] In addition, when there is a preceding vehicle in front of vehicle 10 and the preceding vehicle has not started moving, the passage possibility determination unit 152c can determine to maintain the stopped state of vehicle 10 without determining that vehicle 10 is able to start, even if another vehicle 20 other than the preceding vehicle in front of vehicle 10 starts moving.

[0033] Furthermore, when the vehicle 10 is traveling and attempts to pass through a traffic light 30, the passing possibility determination unit 152c determines that the vehicle 10 can pass through the traffic light 30 if the traffic light determination unit 152a determines that the traffic light 30 indicates that the vehicle 10 can pass and if the other vehicle behavior determination unit 152b determines that another vehicle 20 traveling in the same direction as the vehicle 10 is not decelerating by a predetermined value or more. Deceleration of a predetermined value or more may mean that the absolute value of the deceleration is equal to or greater than a predetermined value. Since the other vehicle 20 may decelerate when passing through a traffic light in preparation for a change in the color of the traffic light or the like, the passing possibility determination unit 152c determines that the vehicle 10 can pass through the traffic light 30 if the other vehicle 20 is not decelerating by a predetermined value or more, and determines that the vehicle 10 cannot pass through the traffic light if the other vehicle 20 is decelerating by a predetermined value or more. Deceleration of a predetermined value or more may be determined based on the deceleration of the other vehicle 20, which is calculated from the relative distance between the vehicle 10 and the other vehicle 20, the vehicle speed difference between the vehicle 10 and the other vehicle 20, or a combination thereof.

[0034] The driving assistance unit 152d assists the driver of the vehicle 10 in driving. Based on an image representing the environment around the vehicle generated by the in-vehicle camera 110, information detected by the periphery monitoring sensor 120, map information stored in the memory 154, etc., the driving assistance unit 152d controls the vehicle control device 130 to assist the driver in driving, and also controls the output of a warning by the warning device 160.

[0035] When the vehicle 10 is stopped at the traffic light 30, if the passing possibility determination unit 152c determines that the vehicle 10 can start, the driving assistance unit 152d controls the vehicle control device 130 to start the vehicle 10. In this case, the driving assistance unit 152d may also cause the warning device 160 to output a warning that the vehicle 10 can start, in order to prompt the driver to start the vehicle 10 by operating the accelerator or a switch.

[0036] When the passing possibility determination unit 152c cannot determine whether or not to start based on the behavior of the other vehicle 20, the driving assistance unit 152d may output a notification of the driver's operation to start the vehicle 10 and prompt the vehicle 10 to start. Situations in which it is not possible to determine whether or not to start based on the behavior of the other vehicle 20 include a situation in which there is no other vehicle 20 around the vehicle 10, a situation in which the driver of the other vehicle 20 does not look at the traffic light 30, a situation in which the other vehicle 20 is following the vehicle 10 and has stopped to maintain a safe distance from the vehicle 10, or a situation in which the other vehicle 20 is unable to start due to other traffic conditions. These situations are determined from an image representing the environment around the vehicle 10 generated by the on-board camera 110 and information detected by the periphery monitoring sensor 120. In this case, it is preferable that the notification of the driver's operation to start the vehicle 10 be issued after a predetermined period of time has passed since it was not possible to determine whether or not to start based on the behavior of the other vehicle 20.

[0037] Furthermore, when the vehicle 10 is about to pass through the traffic light 30, if the passing possibility determination unit 152c determines that the vehicle 10 can pass through the traffic light 30, the driving assistance unit 152d controls the vehicle control device 130 so that the vehicle 10 passes through the traffic light 30. In this case, the driving assistance unit 152d may cause the warning device 160 to output a warning that the vehicle 10 can pass through the traffic light 30, in order to encourage the driver to operate the vehicle 10.

[0038] In determining whether vehicle 10 can start based on the behavior of other vehicles 20 traveling in the same direction as vehicle 10, the passing possibility determination unit 152c may determine whether vehicle 10 can start including the behavior of other vehicles 20 traveling in the right / left turn only lane, or may determine whether vehicle 10 can start without taking into account the behavior of other vehicles 20 traveling in the right / left turn only lane.

[0039] When determining whether vehicle 10 is permitted to start, taking into account the behavior of other vehicle 20 traveling in a right-turn-only lane, at a traffic light 30 with an arrow signal, the arrow signal can be determined from its shape, as opposed to the color of a normal traffic light, thereby ensuring a better chance of determination and reliability of the determination. For example, at a traffic light 30 that displays a green arrow for a right turn, if traffic light determination unit 152a determines that the color of traffic light 30 is a green light and another vehicle 20 stopped in the straight lane starts, the passing possibility determination unit 152c may determine that vehicle 10 is permitted to start. On the other hand, in this case, if another vehicle 20 in the right-turn-only lane starts, the passing possibility determination unit 152c may determine that vehicle 10 is not permitted to start, because there is a possibility that traffic light determination unit 152a may have determined that an actually red light was a green light. Whether the vehicle 10 or the other vehicle 20 is located in a straight lane or a right-turn lane (or a left-turn lane) can be determined by applying the position of the vehicle 10 or the other vehicle 20 to a high-resolution map that displays detailed information such as straight lanes and right- and left-turn lanes. The high-resolution map may be stored in the memory 154 of the ECU 150. The position of the other vehicle 20 can be determined from the position of the vehicle 10 and the relative position of the other vehicle 20 with respect to the vehicle 10.

[0040] Furthermore, when the traffic light determination unit 152a determines that the color of the traffic light 30 is red and that the traffic light 30 is displaying a green arrow for going straight, if another vehicle 20 that was stopped in the straight lane starts to move, the passing possibility determination unit 152c may determine that the vehicle 10 is allowed to move. On the other hand, in this case, if another vehicle 20 in the right-turn-only lane starts to move, the traffic light determination unit 152a may have erroneously determined the direction indicated by the green arrow, and therefore the passing possibility determination unit 152c may determine that the vehicle 10 is not allowed to move.

[0041] Furthermore, when the traffic light determination unit 152a determines that the color of the traffic light 30 is red and determines that the traffic light 30 is displaying a green arrow for going straight and a green arrow for turning right, if another vehicle 20 that was stopped in the straight lane starts to move, the passing possibility determination unit 152c may determine that the vehicle 10 is allowed to start. In this case, if another vehicle 20 in the right-turn-only lane starts to move, the passing possibility determination unit 152c may determine that the vehicle 10 is allowed to start, because it is unlikely that the traffic light determination unit 152a has erroneously determined the direction indicated by the green arrow.

[0042] On the other hand, when determining whether or not the vehicle 10 can start without taking into account the behavior of other vehicles 20 traveling in the right-left turn-only lane, the reliability of the determination of whether or not the vehicle 10 can start can be improved because the determination is not based on other vehicles 20 stopped in the right-left turn-only lane when the traffic light 30 is in a state where starting is only permitted in the straight lane, such as a straight arrow signal.

[0043] In addition, when determining whether or not a vehicle 10 can pass through a traffic light 30 while traveling, other vehicles 20 in the right / left turn lane may slow down due to oncoming vehicles or pedestrians crossing the road even if the traffic light 30 is green, so the movement of other vehicles 20 in the right / left turn lane is excluded from the determination of whether or not the vehicle can pass.

[0044] 4 is a flowchart showing the processing performed by the processor 152 of the ECU 150 at each predetermined control cycle, and shows the processing when the vehicle 10 is stopped at a red light. First, it is determined whether the vehicle 10 is stopped at a red light (step 10). If the vehicle 10 is stopped at a red light, the traffic light determination unit 152a determines whether the traffic light 30 indicates that the vehicle 10 can pass (step 12).

[0045] If it is determined in step S12 that the traffic light 30 indicates that the vehicle 10 is allowed to pass, the other vehicle behavior determination unit 152b determines whether or not the other vehicle 20 traveling in the same direction as the vehicle 10 or in the opposite direction has started (step S14). If it is determined in step S14 that the other vehicle 20 traveling in the same direction as the vehicle 10 or in the opposite direction has started, the passage possibility determination unit 152c determines that the vehicle 10 is allowed to start (step S16).

[0046] On the other hand, if it is determined in step S12 that the traffic light 30 does not indicate that the vehicle 10 can pass, or if it is determined in step S14 that another vehicle 20 traveling in the same direction as or opposite to the vehicle 10 has not started, the passage possibility determination unit 152c determines that the vehicle 10 cannot start (step S18).

[0047] After steps S16 and S18, the process for this control cycle ends. Also, if the vehicle 10 is not stopped at a red light in step S10, the process for this control cycle ends.

[0048] 5 is a flowchart showing the processing performed by the processor 152 of the ECU 150 at each predetermined control cycle, and shows the processing when the vehicle 10 approaches a traffic light 30 while traveling. First, the traffic light determination unit 152a determines whether the vehicle 10 is approaching a traffic light 30 in front of the vehicle while traveling (step S20). If it is determined in step S20 that the vehicle 10 is approaching a traffic light 30, the traffic light determination unit 152a determines whether the traffic light 30 indicates that the vehicle 10 can pass (step S22).

[0049] If it is determined in step S22 that the traffic light 30 indicates that the vehicle 10 can pass, the other vehicle behavior determination unit 152b determines whether the other vehicle 20 traveling in the same direction as the vehicle 10 has decelerated by a predetermined value or more (step S24). If it is determined in step S24 that the other vehicle 20 traveling in the same direction as the vehicle 10 has not decelerated by a predetermined value or more, the passage possibility determination unit 152c determines that the vehicle 10 can pass through the traffic light 30 (step S26). Note that if it is determined in step S22 that the traffic light 30 indicates that the vehicle 10 can pass, but the reliability of the determination is expected to be relatively low, it may be determined in step S26 that the vehicle 10 can pass, and a warning may be output to alert the driver.

[0050] On the other hand, if the traffic light 30 does not indicate that the vehicle 10 can pass in step S22, or if another vehicle 20 traveling in the same direction as the vehicle 10 decelerates by a predetermined value or more in step S24, the passage possibility determination unit 152c determines that the vehicle 10 cannot pass through the traffic light 30 (step S28).

[0051] After steps S26 and S28, the process for this control cycle ends. Also, if the vehicle 10 is not approaching the traffic light 30 in step S20, the process for this control cycle ends.

[0052] As described above, according to this embodiment, it is possible to accurately determine whether or not a vehicle 10 can pass through a traffic light 30 based not only on the state of the traffic light 30 being recognized by the onboard camera 110, but also on the behavior of other vehicles 20 in the vicinity. [Explanation of symbols]

[0053] 10 vehicles 20 other cars 30 Traffic Light 150 Electronic Control Unit (ECU) 152 processors 152a Traffic light determination section 152b Other vehicle behavior determination unit 152c Passability determination section 1000 Driving Assistance System

Claims

1. a traffic light determination unit that determines whether a traffic light ahead of the vehicle indicates that the vehicle is allowed to pass; an other vehicle behavior determination unit that determines the behavior of other vehicles present around the vehicle; a pass possibility determination unit that, when it is determined that the traffic light indicates that the vehicle is permitted to pass, determines whether the vehicle is permitted to pass through the traffic light based on the behavior of other vehicles present around the vehicle; A vehicle determination device comprising:

2. 2. The vehicle determination device of claim 1, wherein the passage possibility determination unit determines that the vehicle is permitted to start when, when the vehicle is stopped at the traffic light, it determines that the traffic light indicates that the vehicle is permitted to pass, and when it determines that another vehicle traveling in the same direction or the opposite direction as the vehicle has started to move.

3. 2. The vehicle determination device of claim 1, wherein the passage possibility determination unit determines that the vehicle can pass through the traffic light when the vehicle attempts to pass through the traffic light while traveling and when it determines that the traffic light indicates that the vehicle can pass and that other vehicles traveling in the same direction as the vehicle are not slowing down by more than a predetermined value.

Images