Vehicle control method, vehicle control system, and vehicle control program

Abstract

To improve the recognition accuracy for a signal in a dark environment.SOLUTION: A vehicle comprises a light with a variable light distribution state. A vehicle control system recognizes a signal candidate position at which a signal can possibly exist around the vehicle by using a sensor mounted to the vehicle. The vehicle control system performs light control processing for controlling a light of the vehicle in response to the recognition of the signal candidate position. The light control processing includes at least one of making irradiation light to the signal candidate position stronger than that before the recognition of the signal candidate position, and making the irradiation light to the signal candidate position stronger than irradiation light to positions other than the signal candidate position.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present disclosure relates to vehicle control for recognizing traffic lights. [Background technology]

[0002] Patent Document 1 discloses a traffic light recognition system. The traffic light recognition system detects target traffic lights around a vehicle based on images captured by an onboard camera and acquires signal detection information. The signal detection information indicates at least the appearance of each of the multiple detected parts of the target traffic light. Meanwhile, the light pattern information indicates the relative positional relationship between the multiple light parts of the traffic light and the appearance of each of the multiple light parts when lit. The traffic light recognition system recognizes the lighting state of the target traffic light by comparing the signal detection information with the light pattern information. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-002275 Summary of the Invention [Problem to be solved by the invention]

[0004] Consider a situation where a vehicle uses an onboard camera to recognize traffic lights. In dark environments such as at night or in the evening, the accuracy of traffic light recognition may decrease.

[0005] For example, at night, there are various types of light, not just traffic light. Even if red, yellow, or green light is recognized, it does not necessarily mean that it is actually a traffic light. In order to determine whether a recognized light is a traffic light, it is necessary to recognize whether a traffic light exists at the position of the light. To recognize the presence of a traffic light, for example, it is possible to recognize the casing of the traffic light. However, at night, it is difficult to see non-luminous objects, and the casing of the traffic light is also difficult to see. Therefore, the probability of correctly recognizing the presence of a traffic light decreases. In other words, the accuracy of traffic light recognition decreases at night.

[0006] An object of the present disclosure is to provide a technology that can improve the accuracy of recognizing traffic signals in dark environments. [Means for solving the problem]

[0007] A first aspect relates to a vehicle control method for controlling a vehicle. The vehicle is equipped with a light whose light distribution state is variable. The vehicle control method is Recognizing signal candidate positions where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to recognition of the signal candidate position; Includes. The first light control process includes at least one of making the light irradiated onto the signal candidate position stronger than before the signal candidate position was recognized, and making the light irradiated onto the signal candidate position stronger than the light irradiated onto positions other than the signal candidate position.

[0008] The second aspect relates to a vehicle control system that controls a vehicle. The vehicle is equipped with a light whose light distribution state is variable. The vehicle control system includes one or more processors. The one or more processors A process of recognizing potential signal positions where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to recognition of the signal candidate position; is configured to execute The first light control process includes at least one of making the light irradiated onto the signal candidate position stronger than before the signal candidate position was recognized, and making the light irradiated onto the signal candidate position stronger than the light irradiated onto positions other than the signal candidate position.

[0009] A third aspect relates to a vehicle control program that is executed by a computer and controls a vehicle. The vehicle is equipped with a light whose light distribution state is variable. The vehicle control program A process of recognizing potential signal positions where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to recognition of the signal candidate position; to be executed by the computer. The first light control process includes at least one of making the light irradiated onto the signal candidate position stronger than before the signal candidate position was recognized, and making the light irradiated onto the signal candidate position stronger than the light irradiated onto positions other than the signal candidate position. [Effects of the Invention]

[0010] According to the present disclosure, signal candidate positions where there is a possibility that a traffic light exists are recognized around a vehicle. Then, in response to the recognition of the signal candidate positions, a first light control process is executed. The first light control process includes at least one of making the light irradiated onto the signal candidate positions stronger than before the signal candidate positions were recognized, and making the light irradiated onto the signal candidate positions stronger than the light irradiated onto positions other than the signal candidate positions. This first light control process makes the signal candidate positions easier to see even in dark environments, increasing the probability of recognizing traffic lights in dark environments. In other words, the accuracy of traffic light recognition is improved. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a conceptual diagram for explaining an overview of a vehicle control system applied to a vehicle according to an embodiment. [Figure 2] FIG. 1 is a conceptual diagram for explaining a problem. [Figure 3] 1 is a conceptual diagram for explaining a light mounted on a vehicle according to an embodiment; [Figure 4] 1 is a conceptual diagram for explaining a light mounted on a vehicle according to an embodiment; [Figure 5] FIG. 4 is a conceptual diagram for explaining a signal candidate position according to the embodiment. [Figure 6] FIG. 4 is a conceptual diagram for explaining an example of a light control process according to the embodiment. [Figure 7] FIG. 10 is a conceptual diagram for explaining another example of the light control process according to the embodiment. [Figure 8] FIG. 10 is a conceptual diagram for explaining yet another example of the light control process according to the embodiment. [Figure 9] FIG. 10 is a conceptual diagram for explaining yet another example of the light control process according to the embodiment. [Figure 10] FIG. 10 is a conceptual diagram for explaining a screening process according to an embodiment. [Figure 11] FIG. 2 is a conceptual diagram for explaining an example of a traffic light that is an illumination target in the embodiment. [Figure 12] FIG. 10 is a conceptual diagram for explaining another example of a traffic light that is an illumination target in the embodiment. [Figure 13] 1 is a block diagram showing an example of the configuration of a vehicle control system according to an embodiment; [Figure 14] 3 is a block diagram showing an example of driving environment information according to an embodiment; FIG. [Figure 15] 5 is a flowchart showing a process related to a light control process according to the embodiment. [Figure 16] 10A and 10B are conceptual diagrams for explaining switching of an irradiation target according to an embodiment. [Figure 17]10A and 10B are conceptual diagrams for explaining switching of an irradiation target according to an embodiment. [Figure 18] 10 is a flowchart illustrating a process related to switching of an irradiation target according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] Embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0013] 1. Overview of the vehicle control system FIG. 1 is a conceptual diagram for explaining an overview of a vehicle control system 10 applied to a vehicle 1 according to this embodiment. The vehicle control system 10 controls the vehicle 1. Typically, the vehicle control system 10 is mounted on the vehicle 1. Alternatively, at least a part of the vehicle control system 10 may be included in a remote system external to the vehicle 1, and the vehicle 1 may be remotely controlled. In other words, the vehicle control system 10 may be distributed between the vehicle 1 and the remote system.

[0014] The vehicle 1 may be an autonomous vehicle. In this case, the vehicle control system 10 executes autonomous driving control for the vehicle 1. For example, the autonomous driving level is based on the premise that the driver does not necessarily have to concentrate 100% on driving. The vehicle 1 may also be a driverless autonomous vehicle.

[0015] Consider a situation in which the vehicle control system 10 recognizes traffic lights around the vehicle 1. For example, the vehicle control system 10 recognizes traffic lights and their signal indications (red, green, yellow, arrow, etc.) ahead of the vehicle 1, and performs automatic driving control based on the recognition results. As another example, the vehicle control system 10 may notify the driver of the recognition results of the traffic lights or signal indications ahead of the vehicle 1 to assist the driver in driving. As yet another example, the vehicle control system 10 may transmit the recognition results of the traffic lights or signal indications to an external management device (e.g., a map management device). In either case, it is desirable to recognize traffic lights with high accuracy.

[0016] The vehicle control system 10 recognizes traffic lights around the vehicle 1 using a camera C mounted on the vehicle 1. More specifically, the camera C acquires an image IMG showing the situation around the vehicle 1. The vehicle control system 10 recognizes traffic lights around the vehicle 1 based on the image IMG acquired by the camera C. For example, the vehicle control system 10 recognizes traffic lights in the image IMG using image recognition AI (Artificial Intelligence) obtained by machine learning.

[0017] However, there is a risk that the accuracy of traffic signal recognition based on the image IMG may decrease in dark environments such as at night or in the evening. Figure 2 is a conceptual diagram for explaining this issue.

[0018] For example, at night, there are various types of light in addition to traffic lights. Even if a light of a color such as red, yellow, or green is recognized, it does not necessarily mean that it is actually a traffic light. For example, there is the red light of the taillights of a preceding vehicle. Another example is the yellow light of the turn signal of a preceding vehicle. Yet another example is the green or yellow light of the ceiling light (lantern) of a taxi. In situations where lights similar to traffic lights exist, it is not desirable to determine the traffic light based solely on the light recognition results. For example, during autonomous driving control, the vehicle control system 10 may determine that a red light is a red signal and automatically decelerate the vehicle 1, only to discover that there is no actual red signal. This is undesirable, as it reduces the accuracy of autonomous driving control.

[0019] In order to determine whether a recognized light is a traffic signal light, it is necessary to recognize whether a traffic light exists at the position of that light. Recognizing the presence of a traffic light can be done, for example, by recognizing the traffic light's housing. During the day, the traffic light's housing is relatively easy to recognize. However, at night, non-luminous objects are difficult to see, and the traffic light's housing is also difficult to see. Therefore, the probability of correctly recognizing (detecting) the presence of a traffic light decreases. In other words, the accuracy of traffic light recognition decreases at night.

[0020] As another example, consider an arrow signal accompanying a main signal. Even if the main signal is "red (progress prohibited)," the arrow signal may be "green (progress permitted)." However, because the light intensity of the arrow signal is smaller than that of the main signal, it is possible that the arrow signal display will not be accurately recognized until vehicle 1 approaches the traffic light to a certain extent. Automatically slowing vehicle 1 when the arrow signal display is not recognized and only the red light is recognized leads to a decrease in the accuracy of automated driving control. To prevent such premature automated driving control, it is desirable to first recognize whether or not the arrow signal itself is present. However, at night, the casing of the arrow signal is also difficult to see. Therefore, the probability of correctly recognizing the presence of the arrow signal decreases. In other words, the accuracy of traffic light recognition decreases at night.

[0021] Similar issues exist with "occlusion signals," which are not visible until you get close enough.

[0022] The above-mentioned issues become more pronounced as the distance from the traffic light increases. On the other hand, to achieve autonomous driving control with ample margin, it is also necessary to accurately recognize traffic lights from a distance of about 100 m. It is desirable to increase the accuracy of traffic light recognition as much as possible even at locations far from the traffic light.

[0023] Improving the accuracy of traffic light recognition based on image IMG is also useful when remote assistance is provided for the vehicle 1. When remote assistance is provided for the vehicle 1, the image IMG obtained by the camera C is transmitted to a remote operator terminal on the remote operator's side. The remote operator terminal is equipped with a display device and displays the received image IMG on the display device. The remote operator views the image IMG displayed on the display device to understand the situation around the vehicle 1 and remotely assists the operation of the vehicle 1. Examples of remote assistance provided by the remote operator include recognition assistance, judgment assistance, and remote driving. In any case, if the traffic lights in the image IMG are difficult to see, the accuracy of the remote assistance provided by the remote operator may be reduced. Therefore, making the traffic lights in the image IMG easy to see is preferable from the perspective of the accuracy of remote assistance.

[0024] From the above viewpoints, this embodiment proposes a technique that can improve the accuracy of traffic light recognition in dark environments such as at night, in the evening, etc. Specifically, a vehicle control system 10 according to this embodiment uses a light 50 mounted on a vehicle 1 to improve the accuracy of traffic light recognition.

[0025] 3 is a conceptual diagram illustrating the light 50 mounted on the vehicle 1. The light 50 irradiates light to the outside of the vehicle 1. The light 50 has a variable light distribution state. In other words, the light 50 is configured so that the range and intensity of light irradiation can be freely changed.

[0026] More specifically, the maximum illumination range of the light 50 is set to be wide, and the illumination range can be freely set within that maximum illumination range. In other words, the light 50 is configured to selectively illuminate only a portion of the maximum illumination range. For example, the light 50 includes multiple light sources. For example, if the light source is an LED (Light Emitting Diode), the light 50 includes an LED array consisting of multiple LEDs. The multiple light sources can be independently controlled to turn on and off. By independently controlling the multiple light sources to turn on and off, the illumination range can be freely set within the maximum illumination range. As shown in FIG. 3, the illumination range can be changed in both the horizontal direction (XY direction) and the vertical direction (Z direction).

[0027] In addition, the illumination intensity (output, power) of each of the multiple light sources can be freely changed. Typically, to reduce power consumption, the default illumination intensity of each light source is set to less than the maximum illumination intensity. However, it is possible to temporarily increase or decrease the illumination intensity of each light source as needed.

[0028] For example, the light 50 is incorporated into the headlight of the vehicle 1. In particular, the light 50 here is a high beam (a low beam is provided separately). The high beam can illuminate a position at traffic light height. The high beam can also illuminate at least up to about 100 meters ahead of the vehicle 1. For example, an adaptive high beam system (AHS) installed in recent vehicles 1 can be used as the light 50.

[0029] As shown in Fig. 4, the vehicle 1 may be equipped with a left light 50L and a right light 50R. It is also possible to "focus" the light emitted from the left light 50L and the light emitted from the right light 50R, superimposing them on each other. By focusing the light, it is possible to increase the illumination intensity for a certain illumination range.

[0030] The vehicle control system 10 according to this embodiment executes a "light control process" that controls the lights 50 mounted on the vehicle 1. In particular, the vehicle control system 10 performs the light control process so as to improve the accuracy of traffic light recognition in a dark environment. The light control process performed by the vehicle control system 10 according to this embodiment will be described in more detail below.

[0031] 2. Light control processing First, with reference to FIG. 5, the "signal candidate position SC" used in the light control process will be described. The signal candidate position SC is a position around the vehicle 1 where a traffic light may exist. Here, "position" is a concept that encompasses "area" and "space." Furthermore, the "position" may be a position in real space or a position within the image IMG. The size of the signal candidate position SC is finite. The size of a single signal candidate position SC within the image IMG is smaller than the size of the entire image IMG.

[0032] The vehicle control system 10 recognizes (acquires) signal candidate positions SC around the vehicle 1 using a sensor 20 mounted on the vehicle 1.

[0033] For example, the sensor 20 includes a recognition sensor 21 that recognizes the situation around the vehicle 1. Examples of the recognition sensor 21 include a camera C and a LIDAR (Laser Imaging Detection and Ranging). The vehicle control system 10 recognizes the signal candidate position SC based on the recognition result by the recognition sensor 21. At this time, there may be no certainty that a traffic light exists at the signal candidate position SC. When a light, object, or the like related to a traffic light is recognized, the recognized position may be acquired as the signal candidate position SC.

[0034] As another example, the sensor 20 includes a position sensor 23 that acquires the position of the vehicle 1. An example of the position sensor 23 is a GPS (Global Positioning System) sensor. There is a high possibility that traffic lights are installed at the intersection. Therefore, the vehicle control system 10 may acquire the positions of intersections around the vehicle 1 based on the position information of the vehicle 1 and map information, and recognize the positions of the intersections as signal candidate positions SC.

[0035] There are various other possible methods for recognizing the signal candidate positions SC, and various examples of the methods for recognizing the signal candidate positions SC will be described later.

[0036] The vehicle control system 10 recognizes (acquires) one or more signal candidate positions SC around the vehicle 1. A plurality of signal candidate positions SC may be recognized simultaneously. Then, the vehicle control system 10 executes a light control process in response to the recognition of the signal candidate positions SC. Various examples of the light control process will be described below.

[0037] 2-1. Brightening treatment 6 is a conceptual diagram illustrating a "light increase process," which is an example of a light control process. The light increase process is a process of increasing the intensity of the light (output of the light 50) irradiated onto the signal candidate position SC in response to a certain trigger. The trigger here is the recognition of the signal candidate position SC. In other words, in response to the recognition of the signal candidate position SC, the vehicle control system 10 increases the intensity of the light irradiated onto the signal candidate position SC compared to before the recognition of the signal candidate position SC.

[0038] In the example shown in Figure 6, the intensity of the light irradiated onto the signal candidate position SC increases at time ts. Time ts is the timing at which the signal candidate position SC is recognized or immediately after that recognition timing. Meanwhile, the intensity of the light irradiated onto positions other than the signal candidate position SC remains unchanged. Typically, after time ts, the light irradiated onto the signal candidate position SC becomes stronger than the light irradiated onto positions other than the signal candidate position SC.

[0039] For example, before timing ts, the light 50 (high beam) is OFF. After that, in response to the recognition of the signal candidate position SC, the vehicle control system 10 partially turns ON the light 50 so as to illuminate only the recognized signal candidate position SC. In other words, the vehicle control system 10 selectively illuminates the signal candidate position SC without illuminating anything other than the signal candidate position SC. This type of light control processing can also be called "selective lighting."

[0040] As another example, before time ts, light 50 may be on. Typically, the illumination intensity before time ts is a default value. Thereafter, in response to recognizing a signal candidate position SC, vehicle control system 10 may increase the illumination intensity at the recognized signal candidate position SC above the default value.

[0041] Note that if an object such as a traffic light is illuminated more strongly than necessary, it may become difficult to see due to factors such as reflected light and flare. Therefore, it is not necessarily necessary to increase the illumination intensity at the signal candidate position SC to the maximum illumination intensity. An appropriate target illumination intensity may be calculated in advance through simulations, experiments, etc. In this case, the vehicle control system 10 performs light control processing so that the illumination intensity at the signal candidate position SC becomes the appropriate target illumination intensity.

[0042] The effects obtained by the above-described brightening treatment are as follows.

[0043] First, the light irradiated onto the signal candidate position SC becomes stronger, increasing the brightness (illuminance) of the signal candidate position SC. Therefore, if a traffic light is actually present at the signal candidate position SC, the brightness of the casing of the traffic light also increases, making it easier to see visually. Therefore, even in a dark environment, it becomes easier to recognize (detect) the presence of a traffic light based on the image IMG. As a result, the probability of recognizing (detecting) the traffic light based on the image IMG increases. In other words, the accuracy of traffic light recognition improves.

[0044] Furthermore, the high beams can illuminate at least up to about 100 meters ahead of the vehicle 1. Therefore, even if the vehicle 1 is about 100 meters away from the traffic light, the traffic light can be brightened and made more visible. In other words, the recognition accuracy of the traffic light can be improved even at a distance from the traffic light. This is desirable from the perspective of realizing automated driving control with ample margins.

[0045] Furthermore, when the light irradiated onto the signal candidate position SC is stronger than the light irradiated onto positions other than the signal candidate position SC, the contrast of the image IMG increases. By applying a filter or the like to the image IMG to remove noise light at positions other than the signal candidate position SC, the signal candidate position SC can be made clearer. This also contributes to an increase in the probability of recognition (detection probability) of a traffic light based on the image IMG. Furthermore, because the noise light is removed, the false recognition of the noise light as a traffic light is suppressed. In other words, the accuracy of traffic light recognition is improved.

[0046] Improving the accuracy of traffic light recognition will contribute to improving the accuracy of automated driving control based on the traffic light recognition results.

[0047] Furthermore, brightening the signal candidate position SC is also useful in remote assistance by a remote operator. In the case of remote assistance, an image IMG obtained by the camera C is transmitted to a remote operator terminal on the remote operator's side. The remote operator looks at the image IMG to understand the situation around the vehicle 1. At this time, if the signal candidate position SC in the image IMG is brightened, the remote operator can more easily recognize whether or not a traffic light is present. Furthermore, even if the signal display is not visible, the remote operator can more easily recognize whether or not an arrow signal or an obstructed signal is present. These are preferable from the viewpoint of the accuracy of remote assistance.

[0048] 2-2. Light reduction processing 7 is a conceptual diagram for explaining "dimming processing," another example of light control processing. The dimming processing is processing for weakening the light (output of the light 50) emitted to areas other than the signal candidate position SC in response to a certain trigger. The trigger here is the recognition of the signal candidate position SC. In other words, in response to the recognition of the signal candidate position SC, the vehicle control system 10 weakens the light emitted to areas other than the signal candidate position SC compared to before the signal candidate position SC was recognized.

[0049] In the example shown in FIG. 7, before time ts, the light 50 (high beam) is ON. Typically, the illumination intensity before time ts is a default value. Then, at time ts, the intensity of the light irradiated to areas other than the signal candidate position SC decreases. The light 50 may be partially turned off so that areas other than the signal candidate position SC are not illuminated. Meanwhile, the intensity of the light irradiated to the signal candidate position SC remains unchanged. As a result, as in the example shown in FIG. 6, the light irradiated to the signal candidate position SC becomes stronger than the light irradiated to areas other than the signal candidate position SC.

[0050] The effects obtained by this light reduction process are as follows.

[0051] The contrast of the image IMG is increased because the light irradiated onto the signal candidate position SC is stronger than the light irradiated onto other positions. By applying a filter or the like to the image IMG to remove noise light at positions other than the signal candidate position SC, the signal candidate position SC can be made clearer. This also contributes to an increase in the probability of recognition (detection probability) of a traffic light based on the image IMG. Furthermore, because the noise light is removed, the false recognition of the noise light as a traffic light is suppressed. In other words, the accuracy of traffic light recognition is improved.

[0052] In addition, roads and roadside structures often have reflectors attached. The light reflected from such reflectors becomes noise light for signal recognition. By weakening the light irradiated onto areas other than the signal candidate position SC, it is possible to suppress the generation of noise light. This improves the recognition accuracy of traffic lights.

[0053] Furthermore, the light irradiated to areas other than the signal candidate position SC becomes weaker, reducing the brightness (illuminance) of positions other than the signal candidate position SC. This makes it difficult to see objects at positions other than the signal candidate position SC. As a result, the probability of misidentifying an object other than a traffic light as a traffic light decreases. This also contributes to improving the accuracy of traffic light recognition.

[0054] Furthermore, by partially weakening the irradiated light, it is possible to reduce power consumption.

[0055] 2-3. Combination of light-boosting and light-reducing processes 8 shows a combination of the above-mentioned "brightening process" and "dimming process." In response to recognizing a signal candidate position SC, the vehicle control system 10 illuminates the signal candidate position SC with more light than before the signal candidate position SC was recognized, and illuminates areas other than the signal candidate position SC with less light than before the signal candidate position SC was recognized. This achieves the effects of both the brightening process and the dimming process.

[0056] 2-4. Brightening process followed by attenuation process FIG. 9 is a conceptual diagram illustrating the "attenuation process" that follows the brightening process. As described above, the brightening process intensifies the light irradiated onto the signal candidate position SC, increasing the illuminance at the signal candidate position SC. The vehicle 1 then travels and approaches the signal candidate position SC. If the intensity of the light emitted from the light 50 of the vehicle 1 does not change, the illuminance at the signal candidate position SC increases as the vehicle 1 approaches the signal candidate position SC. However, if an object such as a traffic light is illuminated more strongly than necessary, it may become difficult to see due to factors such as reflected light and flare.

[0057] Therefore, in order to prevent the signal candidate position SC from being illuminated more strongly than necessary, the vehicle control system 10 may execute an attenuation process following the illumination process. Specifically, after the illumination process, the vehicle control system 10 weakens the light irradiated onto the signal candidate position SC as the vehicle 1 travels.

[0058] The attenuation rate of the irradiated light intensity in the attenuation process may be dynamically set according to the speed of the vehicle 1. In this case, the attenuation rate of the irradiated light intensity is set to increase as the speed of the vehicle 1 increases.

[0059] The irradiated light intensity in the attenuation process may be set according to the distance from the vehicle 1 to the signal candidate position SC. In this case, the irradiated light intensity is set to decrease as the distance from the vehicle 1 to the signal candidate position SC decreases.

[0060] During the attenuation process, the intensity of the light emitted from the output light 50 may be set so that the illuminance at the signal candidate position SC on the receiving side is a constant value. The constant value is the illuminance that allows appropriate signal recognition.

[0061] The attenuation process described above prevents the signal candidate position SC from being illuminated more strongly than necessary after the brightening process. As a result, it is possible to prevent objects such as traffic lights from becoming difficult to see. This also contributes to improving the accuracy of traffic light recognition.

[0062] 2-5.Effects As described above, according to this embodiment, signal candidate positions SC where there is a possibility that a traffic light exists around the vehicle 1 are recognized. Then, in response to the recognition of the signal candidate positions SC, the above-mentioned light control process is executed. The light control process includes at least one of making the light irradiated onto the signal candidate positions SC stronger than before the signal candidate positions SC were recognized, and making the light irradiated onto the signal candidate positions SC stronger than the light irradiated onto positions other than the signal candidate positions SC. This light control process makes the signal candidate positions easier to see even in dark environments, increasing the probability of recognition (detection probability) of traffic lights in dark environments. In other words, the accuracy of traffic light recognition is improved.

[0063] 3. Screening Process As described above, a light control process is performed in response to the recognition of the signal candidate position SC. For convenience, this light control process is referred to as the "first light control process." The first light control process increases the accuracy of traffic light recognition based on the image IMG. As a result, it may be determined that a traffic light actually exists at the signal candidate position SC, or that the possibility of its existence is extremely high. Conversely, it may be determined that no traffic light exists at the signal candidate position SC, or that the possibility of its existence is extremely low. Therefore, it is possible to further narrow down the signal candidate positions SC after the first light control process. In other words, it becomes possible to screen the signal candidate positions SC.

[0064] 10 is a conceptual diagram for explaining the screening process. One or more signal candidate positions SC are captured in an image IMG acquired by a camera C. After the first light control process, the vehicle control system 10 further performs signal recognition based on the image IMG to narrow down the signal candidate positions SC. At this time, the vehicle control system 10 may narrow down the "number" of signal candidate positions SC or the "size" of the signal candidate positions SC.

[0065] For example, if the vehicle control system 10 determines that no traffic light exists at a certain signal candidate position SC or that the likelihood of a traffic light existing thereat is less than a threshold, the vehicle control system 10 excludes the signal candidate position SC from subsequent signal candidate positions SC. As another example, if the vehicle control system 10 determines that no traffic light exists in at least a portion of a range within a certain signal candidate position SC or that the likelihood of a traffic light existing thereat is less than a threshold, the vehicle control system 10 excludes a portion of the range within the signal candidate position SC from the signal candidate positions SC.

[0066] The positions excluded from the signal candidate positions SC by the screening process will be referred to as "exclusion positions EX." There is a low possibility that a traffic light exists at the exclusion positions EX. On the other hand, there is a high possibility that a traffic light exists at the signal candidate positions SC after the screening process.

[0067] In this way, narrowing down the signal candidate positions SC to those where there is a high possibility that a traffic signal exists makes it possible to recognize the traffic signal more accurately and more quickly. In other words, the screening process makes it possible to improve both the accuracy and speed of traffic signal recognition.

[0068] The vehicle control system 10 may further perform a light control process following the screening process. For convenience, the light control process performed after the screening process is hereinafter referred to as a "second light control process." The second light control process is triggered by the execution of the screening process.

[0069] For example, there is no need to continue illuminating the exclusion position EX that has been excluded from the signal candidate positions SC. Continuing to illuminate the exclusion position EX may result in the generation of unnecessary noise light or the misrecognition of objects other than traffic lights as traffic lights. Therefore, in the second light control process, the vehicle control system 10 performs a dimming process (see Figures 7 and 8) on the exclusion position EX. In other words, the vehicle control system 10 weakens the light irradiated onto the exclusion position EX compared to before the screening process. This dimming process achieves the above-mentioned effects, further improving the accuracy of traffic light recognition.

[0070] As another example, in the second light control process, the vehicle control system 10 may further perform a light increasing process (see FIGS. 6 and 8) on the signal candidate position SC. That is, the vehicle control system 10 may further increase the intensity of the light irradiated onto the signal candidate position SC compared to before the screening process. At this time, the vehicle control system 10 may perform "light focusing" using the left light 50L and the right light 50R shown in FIG. 4 to increase the intensity of the light irradiated onto the signal candidate position SC. This light increasing process achieves the above-mentioned effect, further improving the accuracy of traffic light recognition.

[0071] Furthermore, the vehicle control system 10 may perform an attenuation process (see FIG. 9) following the brightening process. This prevents the signal candidate position SC from being illuminated more strongly than necessary after the brightening process. As a result, it prevents objects such as traffic lights from becoming difficult to see. This also contributes to improving the accuracy of traffic light recognition.

[0072] 4.Examples of irradiation targets FIG. 11 is a conceptual diagram for explaining an example of a traffic light that is an illumination target in this embodiment. The first lane L1 is the lane in which the vehicle 1 is traveling. The first traffic light SG1 is a traffic light for the first lane L1. In particular, the first traffic light SG1 is located ahead of the vehicle 1. The vehicle 1 travels according to the signal display of the first traffic light SG1. This first traffic light SG1 is at least an illumination target. The signal candidate position SC includes a position where the first traffic light SG1 may be present.

[0073] FIG. 12 is a conceptual diagram illustrating another example of a traffic light to be illuminated in this embodiment. The second lane L2 is a lane that intersects with the first lane L1. Another vehicle 2 is present in the second lane L2. The second traffic light SG2 is a traffic light for the second lane L2. The other vehicle 2 travels according to the signal display of the second traffic light SG2. This second traffic light SG2 may also be an illumination target. In other words, the signal candidate position SC may include not only a position where the first traffic light SG1 may be present, but also a position where the second traffic light SG2 may be present. By having the vehicle control system 10 of the vehicle 1 in the first lane L1 also illuminate the second traffic light SG2 in the second lane L2, the other vehicle 2 in the second lane L2 can more easily recognize the second traffic light SG2. In other words, the vehicle control system 10 of the vehicle 1 can assist the other vehicle 2 in recognizing signals.

[0074] 5. Example of a vehicle control system 5-1.Configuration example 13 is a block diagram showing an example of the configuration of a vehicle control system 10 according to this embodiment. The vehicle control system 10 includes a sensor group 20, a driving device 30, a communication device 40, a light 50, and a control device 100.

[0075] The sensor group 20 is mounted on the vehicle 1. The sensor group 20 includes a recognition sensor 21, a vehicle state sensor 22, a position sensor 23, and the like.

[0076] The recognition sensor 21 recognizes (detects) the situation around the vehicle 1. The recognition sensor 21 includes a camera C. The recognition sensor 21 may include a LIDAR (Laser Imaging Detection and Ranging), a radar, or the like.

[0077] The vehicle state sensor 22 detects the state of the vehicle 1. For example, the vehicle state sensor 22 includes a speed sensor, an acceleration sensor, a yaw rate sensor, a steering angle sensor, and the like.

[0078] The position sensor 23 detects the position and direction of the vehicle 1. An example of the position sensor 23 is a GPS (Global Positioning System) sensor.

[0079] The traveling device 30 includes a steering device, a drive device, and a braking device. The steering device steers the wheels. For example, the steering device includes an electric power steering (EPS) device. The drive device is a power source that generates driving force. Examples of the drive device include an engine, an electric motor, and an in-wheel motor. The braking device generates braking force.

[0080] The communication device 40 communicates with the outside of the vehicle 1. For example, the communication device 40 communicates with a management device outside the vehicle 1. Examples of the management device include a map management device that manages map information, an automatic driving management device that manages the automatic driving of the vehicle 1, etc. As yet another example, the communication device 40 may communicate with a remote operator terminal that provides remote support for the vehicle 1.

[0081] The light 50 is mounted on the vehicle 1 and emits light to the outside of the vehicle 1. The light 50 has a variable light distribution state. That is, the light 50 is configured so that the illumination range and illumination intensity can be freely changed. For example, the light 50 includes multiple light sources. When the light source is an LED, the light 50 includes an LED array made up of multiple LEDs. Each of the multiple light sources can be controlled independently.

[0082] The control device 100 controls the vehicle 1. The control device 100 includes one or more processors 110 (hereinafter simply referred to as processors 110) and one or more storage devices 120 (hereinafter simply referred to as storage devices 120). The processor 110 executes various processes. For example, the processor 110 includes a CPU (Central Processing Unit). The storage device 120 stores various information. Examples of the storage device 120 include a volatile memory, a non-volatile memory, an HDD (Hard Disk Drive), and an SSD (Solid State Drive). The control device 100 may include one or more ECUs (Electronic Control Units). Part of the control device 100 may be an information processing device external to the vehicle 1. In this case, part of the control device 100 communicates with the vehicle 1 and remotely controls the vehicle 1.

[0083] The vehicle control program PROG is a computer program for controlling the vehicle 1. The processor 110 executes the vehicle control program PROG, thereby realizing various processes by the control device 100. The vehicle control program PROG is stored in the storage device 120. Alternatively, the vehicle control program PROG may be recorded on a computer-readable recording medium.

[0084] 5-2. Driving environment information The control device 100 uses the sensor group 20 to acquire driving environment information 200 that indicates the driving environment of the vehicle 1. The driving environment information 200 is stored in the storage device 120.

[0085] 14 is a block diagram showing an example of the driving environment information 200. The driving environment information 200 includes surrounding situation information 210, vehicle state information 220, vehicle position information 230, and map information 240.

[0086] The surrounding situation information 210 is information indicating the situation around the vehicle 1. The control device 100 recognizes the situation around the vehicle 1 using the recognition sensor 21 and acquires the surrounding situation information 210. For example, the surrounding situation information 210 includes an image IMG captured by the camera C. As another example, the surrounding situation information 210 includes point cloud information obtained by LIDAR.

[0087] The surrounding situation information 210 further includes object information 212 related to objects around the vehicle 1. Examples of objects include pedestrians, bicycles, motorcycles, other vehicles (preceding vehicles, parked vehicles, etc.), white lines, traffic lights, structures (e.g., utility poles, pedestrian bridges), signs, and obstacles. The object information 212 indicates the relative position and relative speed of the object with respect to the vehicle 1. For example, by analyzing the image IMG acquired by the camera C, the object can be identified and the relative position of the object can be calculated. For example, the control device 100 uses image recognition AI acquired by machine learning to identify objects such as traffic lights in the image IMG. It is also possible to identify objects and obtain the relative position and relative speed of the object based on point cloud information acquired by LIDAR.

[0088] The vehicle state information 220 is information indicating the state of the vehicle 1, and includes vehicle speed, acceleration, yaw rate, steering angle, etc. The control device 100 acquires the vehicle state information 220 from the vehicle state sensor 22. The vehicle state information 220 may indicate the driving state (automatic driving / manual driving) of the vehicle 1.

[0089] The vehicle position information 230 is information indicating the current position of the vehicle 1. The control device 100 acquires the vehicle position information 230 from the detection result of the position sensor 23. The control device 100 may also acquire highly accurate vehicle position information 230 by a well-known self-position estimation process (localization) using the object information 212 and map information 240.

[0090] The map information 240 includes a general navigation map. The map information 240 may indicate lane layouts and road shapes. The map information 240 may also include location information of structures, traffic lights, signs, and the like. The control device 100 acquires the map information 240 of a required area from a map database. The map database may be stored in the storage device 120, or may be stored in a map management device external to the vehicle 1. In the latter case, the control device 100 communicates with the map management device via the communication device 40 to acquire the required map information 240. The map information 240 is stored in the storage device 120.

[0091] 5-3.Vehicle driving control The control device 100 performs "vehicle driving control" to control the driving of the vehicle 1. The vehicle driving control includes steering control, acceleration control, and deceleration control. The control device 100 performs vehicle driving control by controlling the driving device 30. Specifically, the control device 100 performs steering control by controlling the steering device. The control device 100 also performs acceleration control by controlling the drive device. The control device 100 also performs deceleration control by controlling the braking device.

[0092] Furthermore, the control device 100 performs automatic driving control based on the driving environment information 200. More specifically, the control device 100 generates a driving plan for the vehicle 1 based on the driving environment information 200. Examples of the driving plan include maintaining the current driving lane, changing lanes, turning right or left, and avoiding obstacles. Furthermore, the control device 100 generates a target trajectory required for the vehicle 1 to drive according to the driving plan based on the driving environment information 200. The target trajectory includes a target position and a target speed. Then, the control device 100 performs vehicle driving control so that the vehicle 1 follows the target trajectory.

[0093] 5-4.Communication processing The control device 100 communicates with the outside of the vehicle 1 via the communication device 40. For example, the control device 100 communicates with a management device outside the vehicle 1 via the communication device 40. Examples of the management device include a map management device that manages map information, and an automatic driving management device that manages automatic driving of the vehicle 1. The control device 100 may perform vehicle-to-vehicle communication with other vehicles via the communication device 40.

[0094] Furthermore, when the vehicle 1 is a target for remote assistance from a remote operator, the control device 100 communicates with a remote operator terminal on the remote operator's side via the communication device 40. Examples of remote assistance from a remote operator include recognition assistance, decision-making assistance, and remote driving. When the control device 100 determines that remote assistance from a remote operator is necessary, it transmits an assistance request to the remote operator terminal. Furthermore, the control device 100 transmits at least a portion of the driving environment information 200 to the remote operator terminal. In particular, the control device 100 transmits an image IMG acquired by a camera C to the remote operator terminal. The remote operator terminal displays the received image IMG on a display device. The remote operator views the image IMG displayed on the display device to understand the situation around the vehicle 1 and remotely assists the operation of the vehicle 1. The control device 100 receives instruction information indicating instructions from the remote operator from the remote operator terminal. Then, the control device 100 performs vehicle driving control in accordance with the instruction information.

[0095] 5-5. Light control processing The control device 100 executes a light control process to control the light 50. As described above, the light distribution state of the light 50 is variable. In other words, the light 50 is configured to be able to freely change the illumination range and illumination intensity. The control device 100 controls the light 50 to change the illumination range and illumination intensity of the light 50.

[0096] The control device 100 according to this embodiment performs light control processing so as to improve the accuracy of traffic light recognition in a dark environment. Fig. 15 is a flowchart showing processing related to such light control processing.

[0097] 5-5-1. Signal candidate position recognition process (step S110) In step S110, the control device 100 recognizes a signal candidate position SC where a traffic light may exist around the vehicle 1 (see FIG. 5). The sensor group 20 is used to recognize this signal candidate position SC. Various examples of methods for recognizing the signal candidate position SC will be described below. Note that there may not be any certainty that a traffic light exists at the signal candidate position SC.

[0098] <First Example> The control device 100 acquires an image IMG obtained by a camera C. Furthermore, the control device 100 analyzes the image IMG and provisionally recognizes traffic lights in the image IMG. For example, an image recognition AI obtained by machine learning is used. A group of traffic lights at an intersection may also be provisionally recognized. Then, the control device 100 sets a position (a certain range) around the provisionally recognized traffic light as a signal candidate position SC. The relative position of the signal candidate position SC with respect to the vehicle 1 is calculated based on the image IMG.

[0099] <Second Example> The control device 100 acquires an image IMG captured by the camera C. Furthermore, the control device 100 analyzes the image IMG to recognize the light source of the signal color (green, yellow, red) in the image IMG. The control device 100 then sets a position (a certain range) around the light source of the signal color as a signal candidate position SC. The relative position of the signal candidate position SC with respect to the vehicle 1 is calculated based on the image IMG.

[0100] <Third Example> When the traffic light ahead of vehicle 1 is red, there is a possibility that a preceding vehicle is stopped below it. The taillights of the stopped preceding vehicle are red. Therefore, the control device 100 analyzes the image IMG and recognizes the red light of the preceding vehicle in the image IMG. Then, the control device 100 sets a position (within a certain range) above the recognized red light as the signal candidate position SC. The relative position of the signal candidate position SC with respect to vehicle 1 is calculated based on the image IMG.

[0101] <Fourth Example> There is a high possibility that a traffic light is installed at the intersection. Therefore, the control device 100 analyzes the image IMG and recognizes the intersection in the image IMG. Alternatively, the control device 100 may acquire the position of the intersection around the vehicle 1 based on the vehicle position information 230 and map information 240 obtained by the position sensor 23. Then, the control device 100 sets a position (within a certain range) above the intersection as the signal candidate position SC. The relative position of the signal candidate position SC with respect to the vehicle 1 is calculated based on the image IMG, or based on the vehicle position information 230 and map information 240.

[0102] <Fifth Example> Traffic lights may be installed on structures such as utility poles and pedestrian bridges. Such structures related to traffic lights are hereinafter referred to as "traffic light-related structures." The control device 100 recognizes traffic light-related structures around the vehicle 1 based on the recognition results of the recognition sensor 21 (e.g., camera, LIDAR). That is, the control device 100 recognizes traffic light-related structures based on surrounding situation information 210 (images IMG, object information 212). As another example, map information 240 in which the positions of structures are registered may be prepared. In this case, the control device 100 can acquire the positions of traffic light-related structures around the vehicle 1 based on the vehicle position information 230 obtained by the position sensor 23 and the map information 240. Then, the control device 100 sets the positions (a certain range) around the traffic light-related structures as the signal candidate position SC. The relative position of the signal candidate position SC with respect to the vehicle 1 is calculated based on the object information 212 or the vehicle position information 230 and the map information 240.

[0103] 5-5-2. First Light Control Process (Step S120) In step S120 after step S110, the control device 100 performs a "first light control process" to control the light 50 based on the signal candidate position SC. The first light control process is as described in Section 2 above, and includes at least one of a "brightness increase process" and a "brightness decrease process" (see FIGS. 6 to 8). The first light control process may also include an "attenuation process" following the brightness increase process (see FIG. 9).

[0104] The relative position of the signal candidate position SC with respect to the vehicle 1 is calculated as described above. The installation position of the light 50 on the vehicle 1, the installation direction of the light 50, and the optical axis direction of each light source included in the light 50 are known information. Therefore, the control device 100 can control the light 50 so that the signal candidate position SC is selectively illuminated.

[0105] 5-5-3. Screening process (step S130) In step S130 after step S120, the control device 100 performs a "screening process" to narrow down the signal candidate positions SC (see Section 3 above). For example, the control device 100 uses image recognition AI to recognize traffic lights in the image IMG. As a result of the first light control process in step S120, the accuracy of traffic light recognition has improved. Therefore, in this step S130, the control device 100 can recognize traffic lights in the image IMG with relatively high accuracy.

[0106] When the control device 100 determines that there is no traffic light at a certain signal candidate position SC or that the likelihood of a traffic light being present is less than a threshold, the control device 100 excludes the signal candidate position SC from subsequent signal candidate positions SC. As another example, when the control device 100 determines that there is no traffic light in at least a portion of a certain signal candidate position SC or that the likelihood of a traffic light being present is less than a threshold, the control device 100 excludes a portion of the signal candidate position SC from the signal candidate positions SC. The positions excluded from the signal candidate positions SC are excluded positions EX (see FIG. 10).

[0107] 5-5-4. Second Light Control Process (Step S140) In step S140 after step S130, the control device 100 performs a "second light control process" to control the light 50 based on the signal candidate position SC or the excluded position EX. The second light control process is as described in section 3 above and includes at least one of a "brightening process" and a "dimming process." The second light control process may also include an "attenuation process" following the brightening process.

[0108] The second light control process does not necessarily have to be performed.

[0109] 6. Switching illumination targets at intersections 16 and 17 are conceptual diagrams for explaining switching of illumination targets at an intersection. Here, consider a case where multiple traffic lights are installed consecutively at a single intersection ahead of vehicle 1. The multiple traffic lights include a first traffic light SGa and a second traffic light SGb. The second traffic light SGb is farther from vehicle 1 than the first traffic light SGa. In other words, as viewed from vehicle 1, the first traffic light SGa is located closer to the vehicle, and the second traffic light SGb is located further back.

[0110] The image IMG obtained by the camera C includes both the first traffic light SGa and the second traffic light SGb. The control device 100 recognizes both the first traffic light SG1 and the second traffic light SGb based on the image IMG. However, the control device 100 does not simultaneously target both the first traffic light SG1 and the second traffic light SGb for illumination by the light 50. The control device 100 switches the target for illumination by the light 50.

[0111] More specifically, as shown in FIG. 16, when the vehicle 1 is relatively far from the intersection, it is sufficient to be able to recognize the signal display of the first traffic light SGa. There is no need to recognize the signal display of the second traffic light SGb. Therefore, the control device 100 sets the first traffic light SGa as the illumination target and excludes the second traffic light SGb from the illumination target. In other words, the control device 100 controls the light 50 so that the first traffic light SGa is illuminated and the second traffic light SGb is not illuminated. This suppresses unnecessary reflected light (noise light) from the second traffic light SGb. Furthermore, power consumption is reduced.

[0112] 17, when the vehicle 1 approaches the intersection to a certain extent, the illumination target is switched from the first traffic light SGa to the second traffic light SGb. That is, the control device 100 controls the light 50 so that the second traffic light SGb is illuminated and the first traffic light SGa is not illuminated. This suppresses unnecessary reflected light (noise light) from the first traffic light SGa. Also, power consumption is reduced.

[0113] FIG. 18 is a flowchart showing the processing related to switching of the irradiation target.

[0114] In step S200, the control device 100 recognizes a traffic light ahead of the vehicle 1 using the camera C. If multiple traffic lights installed at the same intersection have been recognized (step S200; Yes), the process proceeds to step S210.

[0115] In step S210, the control device 100 sets the first traffic signal SGa on the near side as the illumination target and excludes the second traffic signal SGb on the far side from the illumination target. In other words, the control device 100 controls the light 50 so that the first traffic signal SGa is illuminated and the second traffic signal SGb is not illuminated.

[0116] In step S220, the control device 100 predicts the time it will take for the vehicle 1 to reach the position of the first traffic light SGa. Instead of the position of the first traffic light SGa, the position of the stop line (see FIG. 16) near the first traffic light SGa may be used. The distance from the vehicle 1 to the first traffic light SGa or the stop line is obtained from the object information 212. The speed and acceleration of the vehicle 1 are obtained from the vehicle state information 220. Therefore, the control device 100 can calculate the predicted time it will take for the vehicle 1 to reach the position of the first traffic light SGa based on the object information 212 and the vehicle state information 220.

[0117] In step S230, the control device 100 determines whether or not the switching condition is met. The switching condition includes at least "the predicted time is less than a threshold value." The switching condition may further include "the vehicle 1 proceeds straight through the intersection." Whether or not the vehicle 1 proceeds straight through the intersection can be determined, for example, based on the target trajectory of the vehicle 1 in autonomous driving control. If the predicted time is equal to or greater than the threshold value, the switching condition is not met (step S230; No). In this case, the process returns to step S210. On the other hand, if the switching condition is met (step S230; Yes), the process proceeds to step S240.

[0118] In step S240, the control device 100 switches the illumination target from the first traffic light SGa to the second traffic light SGb. That is, the control device 100 controls the light 50 so that the second traffic light SGb is illuminated and the first traffic light SGa is not illuminated. [Explanation of symbols]

[0119] 1 vehicle 10 Vehicle Control System 20 Sensors 21 Recognition Sensor 22 Vehicle condition sensor 23 Position Sensor 30 Running gear 40 Communication equipment 50 Light 100 control device 110 processors 120 Storage device 200 Driving Environment Information 212 Object information 220 Vehicle status information 230 Vehicle location information 240 Map Information C Camera IMG image SC signal candidate position PROG Vehicle control program

Claims

1. A vehicle control method for controlling a vehicle equipped with a light having a variable light distribution state, comprising: Recognizing a signal candidate position where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to the recognition of the signal candidate position; Including, the first light control process includes irradiating the signal candidate position with light that is stronger than light emitted before the signal candidate position was recognized, The first light control process includes selectively illuminating the signal candidate position without illuminating any other position than the signal candidate position. Vehicle control method.

2. A vehicle control method for controlling a vehicle equipped with a light whose light distribution state is variable, comprising: Recognizing a signal candidate position where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to the recognition of the signal candidate position; Including, The first light control process includes irradiating the signal candidate position with light stronger than before the signal candidate position is recognized, and then weakening the light irradiated to the signal candidate position as the vehicle travels. Vehicle control method.

3. A vehicle control method for controlling a vehicle equipped with a light whose light distribution state is variable, comprising: Recognizing a signal candidate position where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to the recognition of the signal candidate position; Including, the first light control process includes irradiating the signal candidate position with light that is stronger than light emitted before the signal candidate position was recognized, The first light control process further includes reducing the intensity of light irradiated to areas other than the signal candidate position compared to before the signal candidate position was recognized. Vehicle control method.

4. A vehicle control method for controlling a vehicle equipped with a light whose light distribution state is variable, comprising: Recognizing a signal candidate position where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to the recognition of the signal candidate position; Including, the first light control process includes at least one of: irradiating the signal candidate position with light that is stronger than that before the signal candidate position was recognized; and irradiating the signal candidate position with light that is stronger than that of light that is irradiated to positions other than the signal candidate position, The vehicle control method includes: acquiring an image of the surroundings of the vehicle using a camera mounted on the vehicle; a screening process for narrowing down the signal candidate positions based on the image after the first light control process; a second light control process for controlling the light after the screening process; Further includes Vehicle control method.

5. 5. The vehicle control method according to claim 4, the excluded positions are positions that have been excluded from the signal candidate positions by the screening process; The second light control process includes weakening the light irradiated onto the exclusion position compared to before the screening process. Vehicle control method.

6. 6. A vehicle control method according to claim 4 or 5, The second light control process includes making the irradiating light onto the signal candidate position stronger than before the screening process. Vehicle control method.

7. 7. A vehicle control method according to claim 6, The second light control process includes irradiating the signal candidate position with light stronger than before the screening process, and then weakening the light irradiated to the signal candidate position as the vehicle travels. Vehicle control method.

8. A vehicle control method for controlling a vehicle equipped with a light having a variable light distribution state, comprising: Recognizing a signal candidate position where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to the recognition of the signal candidate position; Including, the first light control process includes at least one of: irradiating the signal candidate position with light that is stronger than that before the signal candidate position was recognized; and irradiating the signal candidate position with light that is stronger than that of light that is irradiated to positions other than the signal candidate position, The signal candidate location is a possible location of the traffic light relative to a first lane in which the vehicle is traveling; and a possible location of the traffic light for a second lane intersecting the first lane; Contains Vehicle control method.

9. A vehicle control method for controlling a vehicle equipped with a light having a variable light distribution state, comprising: Recognizing a signal candidate position where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to the recognition of the signal candidate position; Including, the first light control process includes at least one of: irradiating the signal candidate position with light that is stronger than that before the signal candidate position was recognized; and irradiating the signal candidate position with light that is stronger than that of light that is irradiated to positions other than the signal candidate position, The sensors mounted on the vehicle include a recognition sensor that recognizes a situation around the vehicle and a position sensor that acquires a position of the vehicle, The recognition sensor includes a camera that acquires an image of the surroundings of the vehicle; Recognizing the signal candidate locations includes: tentatively recognizing a traffic light in the image and setting a position around the tentatively recognized traffic light as the signal candidate position; Recognizing a light source of a signal display color in the image, and setting a position around the light source of the signal display color as the signal candidate position; Recognizing a red light of a preceding vehicle in the image and setting a position above the red light as the signal candidate position; Recognizing an intersection in the image, or acquiring a position of an intersection around the vehicle based on the position of the vehicle and map information, and setting a position above the intersection as the signal candidate position; Recognizing traffic light-related structures around the vehicle using the recognition sensor, or acquiring the positions of the traffic light-related structures based on the position of the vehicle and map information, and setting the positions around the traffic light-related structures as the signal candidate positions. Contains at least one of Vehicle control method.

10. A vehicle control method for controlling a vehicle equipped with a light having a variable light distribution state, comprising: Recognizing a signal candidate position where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to the recognition of the signal candidate position; Including, the first light control process includes at least one of: irradiating the signal candidate position with light that is stronger than that before the signal candidate position was recognized; and irradiating the signal candidate position with light that is stronger than that of light that is irradiated to positions other than the signal candidate position, The vehicle control method includes: Recognizing a plurality of traffic lights installed at an intersection ahead of the vehicle using a camera mounted on the vehicle; wherein the plurality of traffic lights include a first traffic light and a second traffic light that is farther from the vehicle than the first traffic light, calculating a predicted time until the vehicle reaches the location of the first traffic light; If the predicted time is equal to or greater than a threshold, the first traffic light is set as a target to be illuminated by the light, and the second traffic light is excluded from the target to be illuminated by the light; When a switching condition including the predicted time being less than the threshold is satisfied, the illumination target is switched from the first traffic light to the second traffic light. Further includes Vehicle control method.

11. A vehicle control system for controlling a vehicle equipped with a light having a variable light distribution state, one or more processors; the one or more processors: A process of recognizing a signal candidate position where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to the recognition of the signal candidate position; configured to run the first light control process includes irradiating the signal candidate position with light that is stronger than light emitted before the signal candidate position was recognized, The first light control process further includes reducing the intensity of light irradiated to areas other than the signal candidate position compared to before the signal candidate position was recognized. Vehicle control system.

12. A vehicle control program for controlling a vehicle equipped with a light having a variable light distribution state, The vehicle control program is executed by a computer, A process of recognizing a signal candidate position where a traffic signal may exist around the vehicle using a sensor mounted on the vehicle; a first light control process for controlling the light in response to the recognition of the signal candidate position; causing the computer to execute the first light control process includes irradiating the signal candidate position with light that is stronger than light emitted before the signal candidate position was recognized, The first light control process further includes reducing the intensity of light irradiated to areas other than the signal candidate position compared to before the signal candidate position was recognized. Vehicle control program.

Images