Traffic light occlusion reasoning method, readable storage medium and intelligent device

Abstract

This application relates to the field of autonomous driving technology, specifically to a traffic light occlusion reasoning method, a readable storage medium, and an intelligent device, aiming to solve the problem of effectively reasoning about the state of traffic lights under occlusion conditions, thereby improving the traffic capacity of intersections. To this end, this application obtains the traffic light state reasoning result of the occluded traffic light based on the countdown sequence of the occluded traffic light corresponding to the vehicle's location, the driving status of other vehicles in the traffic flow where the vehicle is located, and the status of other traffic lights other than the occluded traffic light. Through the above configuration method, this application does not rely on high-precision maps; it only requires the countdown sequence of the traffic light corresponding to the vehicle, the driving status of other vehicles perceived by the vehicle, and the status of other traffic lights to achieve the reasoning result of the occluded traffic light state. This enables accurate reasoning of the occluded traffic light state, improves the traffic capacity of intersections, and provides higher safety.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a traffic light occlusion reasoning method, a readable storage medium, and an intelligent device. Background Art

[0002] In the autonomous driving system, traffic light state perception is very important for traffic at intersections. In a scene where the traffic lights are fully visible and well-lit, a good traffic light report can be completed by simply relying on perception model detection and recognition plus time-series post-processing tracking. However, in actual traffic light intersections, the traffic lights in the field of view of the vehicle are often blocked. Generally, the blockage is divided into static blockage and dynamic blockage: static blockage is defined as green plants, traffic signs, light poles, etc.; dynamic blockage is defined as blockage by a large vehicle in front of the vehicle. A common way to deal with the problem of traffic light blockage is to brake the vehicle slowly to the stop line when the control receives the traffic light blockage status, and then adopt a new control strategy according to the status of the traffic light after the traffic light can be seen again. This method is conservative, especially when braking under the actual green light condition may cause the risk of rear-end collision by the following vehicle. Therefore, traffic light reasoning under blockage is particularly important.

[0003] In the non-map perception solution, it is difficult to determine whether there is a traffic light behind the static elements due to the lack of high-precision maps. In addition, for situations that have been occluded from the beginning, it is difficult to know in advance whether there is a traffic light at the intersection ahead without a priori knowledge. The existing single-frame and 4Dgt annotation methods only annotate partial occlusions that are visible to the annotator, and there is no prompt information for complete occlusion. Therefore, in the reasoning process, in addition to the 2D and 3D results perceived by the model, it is necessary to rely on upstream OD (object detection) and lane information. In scenarios where the traffic light is obscured, the perception model fails and the traffic light cannot be correctly detected.

[0004] Accordingly, the art needs a new solution for acquiring traffic light status to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects, the present application is proposed to solve or at least partially solve the technical problem of how to effectively infer the status of traffic lights under occlusion conditions, thereby improving the traffic capacity of intersections.

[0006] In a first aspect, a traffic light occlusion reasoning method is provided, the method being applied to a vehicle; the method comprising:

[0007] The traffic light state inference result of the blocked traffic light is obtained based on the countdown timing of the blocked traffic light corresponding to the position of the vehicle, the driving status of other vehicles in the traffic flow where the vehicle is located, and at least one of the status of other traffic lights except the blocked traffic light.

[0008] In a technical solution of the above-mentioned traffic light occlusion inference method, obtaining the traffic light state inference result of the blocked traffic light according to the countdown timing of the blocked traffic light corresponding to the position of the vehicle includes:

[0009] Acquire the state of the traffic light sensed by the vehicle before the traffic light is blocked and the countdown timing of the traffic light;

[0010] According to the countdown sequence, obtaining the countdown value of the traffic light that is currently blocked;

[0011] If the countdown value is greater than zero, the state of the traffic light before being blocked is used as the traffic light state inference result of the blocked traffic light at the current moment.

[0012] In a technical solution of the above-mentioned traffic light occlusion reasoning method, the method further includes:

[0013] If the countdown value is zero, the traffic light state inference result of the blocked traffic light is obtained according to the driving states of other vehicles in the traffic flow in which the vehicle is located.

[0014] In a technical solution of the above-mentioned traffic light occlusion inference method, obtaining the traffic light state inference result of the occluded traffic light according to the driving state of other vehicles in the traffic flow in which the vehicle is located includes:

[0015] Determining whether the vehicle is a leading vehicle according to the position of the vehicle in the traffic flow;

[0016] If the vehicle is not the leading vehicle, obtaining the traffic light state inference result according to the driving state of the vehicle preceding the vehicle;

[0017] If the vehicle is the lead vehicle, the traffic light state inference result is obtained according to the driving states of other vehicles in other lanes semantically related to the lane where the vehicle is located.

[0018] In a technical solution of the above-mentioned traffic light occlusion inference method, obtaining the traffic light state inference result according to the driving state of the preceding vehicle of the vehicle includes:

[0019] If the stagnation time of the preceding vehicle is greater than a preset time, the traffic light state inference result is obtained according to the driving states of other vehicles in other lanes with the same semantics as the lane where the vehicle is located.

[0020] In a technical solution of the above-mentioned traffic light occlusion inference method, obtaining the traffic light state inference result according to the driving states of other vehicles in other lanes semantically related to the lane in which the vehicle is located includes:

[0021] Acquire a first influencing factor of different driving actions of the vehicle according to the driving states of other vehicles on the other lanes;

[0022] According to the first influencing factor, a traffic light state inference result of the traffic light corresponding to the driving action is obtained.

[0023] In a technical solution of the above-mentioned traffic light occlusion reasoning method, the method further includes:

[0024] If the traffic light status inference result is not obtained based on the position of the vehicle in the traffic flow and the driving status of other vehicles in the traffic flow, the traffic light status inference result of the blocked traffic light is obtained based on the status of other traffic lights except the blocked traffic light.

[0025] In a technical solution of the above-mentioned traffic light occlusion reasoning method, the method further includes:

[0026] If the countdown value is zero, the traffic light state inference result of the blocked traffic light is obtained according to the states of other traffic lights except the blocked traffic light.

[0027] In a technical solution of the above-mentioned traffic light occlusion inference method, obtaining the traffic light state inference result of the blocked traffic light according to the states of other traffic lights except the blocked traffic light includes:

[0028] If the non-motor vehicle traffic light in the same direction as the blocked traffic light is not blocked, obtaining the traffic light state inference result according to the state of the non-motor vehicle traffic light;

[0029] If the non-motor vehicle traffic light in the same direction as the blocked traffic light is also blocked, the traffic light state inference result is obtained according to the state of the lateral traffic light adjacent to the blocked traffic light.

[0030] In a technical solution of the above-mentioned traffic light obstruction reasoning method, the step of obtaining the traffic light state reasoning result according to the state of the lateral traffic light adjacent to the obstructed traffic light includes:

[0031] According to the state of the lateral traffic light, obtaining a second influencing factor of different driving actions of the vehicle;

[0032] According to the second influencing factor, a traffic light state inference result of the traffic light corresponding to the driving action is obtained.

[0033] In a second aspect, a smart device is provided, comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method described in any one of the technical solutions of the above-mentioned traffic light occlusion inference method is implemented.

[0034] In a third aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, wherein the program codes are suitable for being loaded and run by a processor to execute the method described in any one of the technical solutions of the above-mentioned traffic light occlusion inference method.

[0035] The above one or more technical solutions of the present application have at least one or more of the following beneficial effects:

[0036] In implementing the technical solution of the traffic light occlusion reasoning method provided by this application, this application obtains the traffic light state reasoning result of the obscured traffic light according to the countdown timing of the obscured traffic light corresponding to the position of the vehicle, the driving status of other vehicles in the traffic flow where the vehicle is located, and the status of other traffic lights other than the obscured traffic light. Through the above configuration, this application does not need to rely on high-precision maps. It only needs the countdown timing of the traffic light corresponding to the vehicle, and the driving status of other vehicles and the status of other traffic lights perceived by the vehicle to realize the state reasoning of the obscured traffic light, and can realize accurate reasoning of the state of the obscured traffic light, improve the traffic capacity of the intersection, and have higher safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The disclosure of the present application will become easier to understand with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present application. Among them:

[0038] Figure 1 It is a flowchart of the main steps of the traffic light occlusion reasoning method according to an embodiment of the present application;

[0039] Figure 2 This is an example schematic diagram of a traffic light being blocked;

[0040] Figure 3 It is a flowchart of the main steps of a traffic light occlusion reasoning method according to an implementation of an embodiment of the present application;

[0041] Figure 4 It is a flowchart of the main steps of obtaining the traffic light state inference result according to the driving state of other vehicles in the traffic flow in which the vehicle is located according to an implementation method of an embodiment of the present application;

[0042] Figure 5 A schematic diagram of an example of a first influencing factor for traffic light straight driving reasoning according to an example of an embodiment of the present application;

[0043] Figure 6 It is a schematic diagram of the main structure of a smart device according to an embodiment of the present application.

[0044] Reference numerals:

[0045] 11: memory; 12: processor. DETAILED DESCRIPTION

[0046] Some embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the protection scope of the present application.

[0047] In the description of the present application, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, memory, and may also include software parts, such as program code, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware or a combination of the two. Computer-readable storage media include any suitable medium that can store program code, such as a disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B" and may include only A, only B or A and B. The singular terms "one" and "the" may also include plural forms.

[0048] The relevant user personal information that may be involved in the various embodiments of this application is strictly in accordance with the requirements of laws and regulations, following the principles of legality, legitimacy and necessity, based on the reasonable purposes of business scenarios, to process the personal information that users actively provide during the use of products / services or generated due to the use of products / services, as well as the personal information obtained with the user's authorization.

[0049] The user personal information processed by this application will vary depending on the specific product / service scenario, and shall be based on the specific scenario in which the user uses the product / service, and may involve the user's account information, device information, driving information, vehicle information or other related information. This application will treat the user's personal information and its processing with a high degree of diligence.

[0050] This application attaches great importance to the security of user personal information and has taken reasonable and feasible security protection measures that meet industry standards to protect user information and prevent personal information from being accessed, disclosed, used, modified, damaged or lost without authorization.

[0051] See attached Figure 1 , Figure 1 FIG. 1 is a flow chart of the main steps of a traffic light occlusion reasoning method according to an embodiment of the present application. Figure 1 As shown, the traffic light occlusion reasoning method in the embodiment of the present application is applied to a vehicle, and the traffic light occlusion reasoning method mainly includes the following step S101.

[0052] Step S101: Obtain the traffic light state inference result of the blocked traffic light according to at least one of the countdown timing of the blocked traffic light corresponding to the position of the vehicle, the driving status of other vehicles in the traffic flow where the vehicle is located, and the status of other traffic lights except the blocked traffic light.

[0053] In this embodiment, the state of the blocked traffic light can be inferred by combining one or more of the countdown sequence of the blocked traffic light, the driving state of other vehicles in the traffic flow where the vehicle is located, and the state of other traffic lights except the blocked traffic light to obtain the traffic light state inference result. The traffic light state inference result includes whether the blocked traffic light is a red light, a green light, or a yellow light.

[0054] The status of the blocked traffic lights can be found in the attached Figure 2 , Figure 2 This is an example diagram of a traffic light being blocked. Figure 2 The left side is static occlusion. Figure 2 The right side shows dynamic occlusion.

[0055] In one implementation, reasoning priorities may be set for the countdown timing of the obstructed traffic light, the driving status of other vehicles in the traffic flow in which the vehicle is located, and the status of other traffic lights except the obstructed traffic light, and the status of the obstructed traffic light may be reasoned based on the reasoning priorities.

[0056] In one embodiment, please refer to the attached Figure 3 , Figure 3 FIG. 1 is a flow chart of the main steps of a traffic light occlusion reasoning method according to an implementation of an embodiment of the present application. Figure 3As shown, in this embodiment, the priority of traffic light state inference is: the countdown time sequence priority of the blocked traffic light is higher than the driving state of other vehicles in the traffic flow where the vehicle is located, and the driving state priority of other vehicles in the traffic flow where the vehicle is located is higher than the state of other traffic lights except the blocked traffic light. Specifically, the traffic light state inference result can be obtained according to the following steps S501 to S507:

[0057] Step S501: perform inference based on the countdown timing of the blocked traffic light.

[0058] Step S502: Determine whether the reasoning is successful; if so, execute step S507; if not, execute step S503.

[0059] Step S503: Inferring based on the driving status of other vehicles in the traffic flow in which the vehicle is located.

[0060] Step S504: Determine whether the reasoning is successful; if so, execute step S507; if not, execute step S505.

[0061] Step S505: Inferring based on the states of other traffic lights except the blocked traffic light.

[0062] Step S506: Determine whether the reasoning is successful; if so, execute step S507; if not, end.

[0063] Step S507: Output the traffic light status inference result.

[0064] In this embodiment, if the countdown time sequence reasoning based on the blocked traffic light is successful, the traffic light state reasoning result is directly output. If the countdown time sequence reasoning based on the blocked traffic light is unsuccessful, the reasoning is performed based on the driving state of other vehicles in the traffic flow where the vehicle is located; if the reasoning is successful based on the driving state of other vehicles in the traffic flow where the vehicle is located, the traffic light state reasoning result is output; if the reasoning is unsuccessful based on the driving state of other vehicles in the traffic flow where the vehicle is located, the reasoning is performed based on the state of other traffic lights except the blocked traffic light, and if the reasoning is successful, the traffic light state reasoning result is output; if the reasoning is unsuccessful, the process ends.

[0065] In one implementation, the state of the blocked traffic light may be inferred based on the countdown timing of the blocked traffic light. If the inference is unsuccessful, the inference may be performed based on the states of other traffic lights except the blocked traffic light.

[0066] In other embodiments, the state of the obstructed traffic light may be inferred based on the states of other traffic lights except the obstructed traffic light, or the state of the obstructed traffic light may be inferred based on the driving states of other vehicles in the traffic flow in which the vehicle is located. These are all within the scope of protection of the present application.

[0067] In one implementation, the state of the obstructed traffic light can be inferred based on the countdown timing of the obstructed traffic light, the driving status of other vehicles in the traffic flow in which the vehicle is located, and the status of other traffic lights except the obstructed traffic light, so as to obtain a first reasoning result, a second reasoning result, and a third reasoning result, respectively, and then obtain a traffic light state reasoning result based on the first reasoning result, the second reasoning result, and the third reasoning result.

[0068] For example, if two of the first reasoning result, the second reasoning result, and the third reasoning result are the same, the same result can be used as the traffic light state reasoning result. For example, if two of the first reasoning result, the second reasoning result, and the third reasoning result are not obtained, the other obtained result can be used as the traffic light state acquisition result. It should be noted that the above is only an example, and those skilled in the art can configure specific rules for obtaining the traffic light state reasoning result based on the first reasoning result, the second reasoning result, and the third reasoning result according to the needs of actual applications.

[0069] Based on the method described in step S101 above, the embodiment of the present application obtains the traffic light state inference result of the blocked traffic light according to the countdown sequence of the blocked traffic light corresponding to the position of the vehicle, the driving status of other vehicles in the traffic flow where the vehicle is located, and the status of other traffic lights other than the blocked traffic light. Through the above configuration, the embodiment of the present application does not need to rely on high-precision maps, but only needs the countdown sequence of the traffic light corresponding to the vehicle, and the driving status of other vehicles and the status of other traffic lights perceived by the vehicle, so as to realize the state inference of the blocked traffic light, realize accurate inference of the state of the blocked traffic light, improve the traffic capacity of the intersection, and have higher safety.

[0070] The following describes the specific process of obtaining the traffic light state inference result of the obscured traffic light based on the countdown timing of the obscured traffic light, the driving status of other vehicles in the traffic flow in which the vehicle is located, and the status of other traffic lights except the obscured traffic light.

[0071] In one implementation of the embodiment of the present application, the traffic light state inference result of the blocked traffic light can be obtained according to the countdown timing of the blocked traffic light according to the following steps S201 to S203:

[0072] Step S201: Acquire the traffic light status and the countdown sequence of the traffic light before the traffic light is blocked as sensed by the vehicle.

[0073] In this embodiment, environmental data can be collected through the vehicle's camera, and the environmental data can be identified based on the perception model to obtain the state of the traffic light before it is blocked (that is, whether it is red, green or yellow), as well as the countdown timing of the traffic light.

[0074] In one implementation, the countdown sequence of the traffic light can be obtained through vehicle perception. In the case where the countdown of the traffic light is blocked, the current countdown sequence of the blocked traffic light can also be inferred based on the countdown sequence of the traffic light perceived before the blockage to obtain the countdown sequence.

[0075] Step S202: according to the countdown sequence, obtain the countdown value of the traffic light that is currently blocked.

[0076] Step S203: If the countdown value is greater than zero, the state of the traffic light before being blocked is used as the traffic light state inference result of the blocked traffic light at the current moment.

[0077] In this embodiment, if the countdown value of the traffic light is always greater than zero, the state of the traffic light before being blocked is maintained. That is, if the state of the traffic light before being blocked is red, the traffic light state inference result is red; if the state of the traffic light before being blocked is green, the traffic light state inference result is green.

[0078] In one implementation, if the countdown value of the blocked traffic light is zero, the traffic light state inference result of the blocked traffic light can be obtained according to the driving states of other vehicles in the traffic flow in which the vehicle is located.

[0079] In another implementation, if the countdown value of the blocked traffic light is zero, the traffic light state inference result of the blocked traffic light may be obtained based on the states of other traffic lights except the blocked traffic light.

[0080] In one implementation of the embodiment of the present application, the traffic light state inference result of the blocked traffic light can be obtained according to the driving states of other vehicles in the traffic flow in which the vehicle is located according to the following steps S301 to S303:

[0081] Step S301: Determine whether the vehicle is the lead vehicle based on the vehicle's position in the traffic flow; if not, execute step S302; if so, execute step S303.

[0082] In this embodiment, the leading vehicle refers to the position of the first vehicle in the traffic flow in the current lane (the own vehicle).

[0083] Step S302: Obtain the traffic light status inference result according to the driving status of the vehicle in front of the vehicle.

[0084] In this embodiment, if the vehicle (self-vehicle) is not the leading vehicle, the traffic light state inference result can be obtained according to the driving state of the preceding vehicle. For example, if the preceding vehicle is driving at a constant speed or accelerating, the traffic light state inference result can be considered to be a green light; if the preceding vehicle is decelerating or stagnating, the traffic light state inference result can be considered to be a red light.

[0085] In one embodiment, if the stagnation time of the front vehicle is longer than the preset time, the traffic light state inference result can be obtained based on the driving state of other vehicles in other lanes with the same semantics as the lane where the vehicle is located. That is, if the front vehicle does not move for a long time (longer than the preset time), the traffic light state inference result can be obtained based on the driving state of other vehicles in other lanes with the same semantics. If the vehicle (the self-vehicle) is in a straight lane, the obscured traffic light state can be inferred by referring to the driving state of other vehicles in the same straight lane. Those skilled in the art can set the value of the preset time according to the needs of actual applications.

[0086] Step S303: Obtain traffic light status inference results based on the driving status of other vehicles in other lanes that are semantically related to the lane in which the vehicle is located.

[0087] In this embodiment, if the vehicle (the ego vehicle) is the leading vehicle, the obstructed traffic light state can be inferred based on the driving states of other vehicles in other lanes that are semantically related to the lane where the ego vehicle is located. Among them, the semantically related other lanes refer to lanes in the same intersection that are semantically related to the lane where the ego vehicle is located. If the lane where the ego vehicle is located is a straight lane, the straight direction of the ego vehicle can be defined as the longitudinal direction, and the direction perpendicular to the straight direction of the ego vehicle can be defined as the lateral direction, then the other lanes that are semantically related to the lane where the ego vehicle is located can include a lateral straight lane, a lateral left-turn lane, an opposite straight lane, an opposite left-turn lane, etc. If the driving state of the vehicle in the opposite straight lane is a deceleration or parking state, it can be explained that the traffic light state corresponding to the opposite straight lane may be a red light, and the traffic light state inference result of the obstructed traffic light can be judged by referring to the driving state of the vehicle in the opposite straight lane.

[0088] In some cases, it is not sufficient to obtain accurate traffic light status inference results based only on the driving status of a vehicle in another lane that is semantically associated with the lane in which the vehicle is located. The traffic light status inference result of the obscured traffic light can be obtained by combining the driving status of multiple vehicles in other lanes that are semantically associated with the lane in which the vehicle is located.

[0089] Specifically, step S303 may further include the following steps S3031 and S3032:

[0090] Step S3031: According to the driving status of other vehicles in other lanes, obtain the first influencing factor of different driving actions of the vehicle.

[0091] Step S3032: According to the first influencing factor, the traffic light state inference result of the traffic light corresponding to the driving action is obtained.

[0092] Please refer to the attached Figure 5 , Figure 5 A schematic diagram of an example of a first influencing factor for traffic light straight driving reasoning according to an example of an embodiment of the present application. Figure 5 As shown in the figure, taking the reasoning of the straight traffic light as an example, that is, the lane the vehicle is currently in is the straight lane, the rectangular box labeled 1 in the figure is the vehicle, the rectangular box labeled 2 is other vehicles that are slowing down or stopping, and the rectangular box labeled 3 is other vehicles that are traveling at a constant speed or accelerating. For the vehicle traveling straight, the semantically related other lanes are the opposite lane, the opposite left turn lane, the lateral lane, and the lateral left turn lane. It is necessary to refer to the driving status of other vehicles in the above other lanes to infer the blocked traffic light status.

[0093] Please refer to Table 1, which is a table of the first influencing factors of different lanes' constant speed or acceleration on different driving actions of the vehicle. The first row in Table 1 is the driving status of other vehicles in other lanes, and the first column in Table 1 is the driving action of the vehicle. Among them, a positive value of the first influencing factor indicates support for the corresponding driving action of the vehicle, a negative value indicates opposition to the corresponding driving action of the vehicle, and 0 indicates no influence. Figure 5 In the driving action of the self-vehicle going straight, according to the first influencing factor, the passable score of the self-vehicle going straight is -1+1-1+1-1=-1<0, so it can be determined that the inference result of the traffic light state corresponding to the straight driving is red.

[0094] Table 1 The first influencing factors of different lanes' constant speed or acceleration on different driving actions of the vehicle

[0095]

[0096] In one embodiment, if the traffic light status inference result is not obtained based on the position of the vehicle in the traffic flow and the driving status of other vehicles in the traffic flow, the traffic light status inference result of the blocked traffic light can be obtained based on the status of other traffic lights except the blocked traffic light.

[0097] In one embodiment, please refer to the attached Figure 4 , Figure 4 FIG. 1 is a flow chart of the main steps of obtaining the traffic light state inference result according to the driving state of other vehicles in the traffic flow in which the vehicle is located according to an implementation of an embodiment of the present application. Figure 4As shown, the traffic light state inference result can be obtained according to the driving states of other vehicles in the traffic flow in which the vehicle is located according to the following steps S601 to S609:

[0098] Step S601: Determine whether the vehicle is the lead vehicle. If so, execute step S602; if not, execute step S606.

[0099] Step S602: Calculate the semantic passability score of the lane according to the first influencing factor.

[0100] Step S603: Determine whether the passability score is greater than or equal to zero; if so, execute step S604; if not, execute step S605.

[0101] Step S604: The traffic light state inference result is green light.

[0102] Step S605: The traffic light state inference result is red light.

[0103] Step S606: Determine the status of the vehicle in front of the own vehicle.

[0104] Step S607: Determine whether the preceding vehicle stagnation time is greater than a preset time; if so, execute step S608; if not, execute step S609.

[0105] Step S608: Obtain the traffic light status inference result by referring to the driving status of other vehicles in the same semantic lane.

[0106] Step S609: Obtain the traffic light status inference result according to the driving status of the preceding vehicle.

[0107] It should be noted that although the obscured traffic light status is inferred here based on the driving status of other vehicles in the traffic flow, the obscured traffic light status can also be inferred based on other dynamic targets in the lane, such as non-motor vehicles, pedestrians, etc., which are all within the scope of protection of this application.

[0108] In one implementation of the embodiment of the present application, the traffic light state inference result of the blocked traffic light can be obtained according to the states of other traffic lights except the blocked traffic light according to the following steps S401 to S402:

[0109] Step S401: If the non-motor vehicle traffic light in the same direction as the blocked traffic light is not blocked, obtain the traffic light state inference result according to the state of the non-motor vehicle traffic light.

[0110] In this embodiment, if the non-motor vehicle traffic light in the same direction as the blocked traffic light is not blocked, the traffic light state inference result of the blocked traffic light can be obtained according to the state of the non-motor vehicle traffic light. For example, if the state of the non-motor vehicle traffic light is red, the traffic light state inference result of the blocked traffic light can also be red.

[0111] In one case, since the countdown process of non-motor vehicle traffic lights and traffic lights for vehicles at different intersections is often different, such as not turning red at the same time, different intersections can be classified and the traffic light countdown relationship between non-motor vehicle traffic lights and traffic lights for vehicles at different categories of intersections can be established, so as to further obtain the traffic light state inference result of the blocked traffic light according to the intersection type of the intersection where the vehicle is currently located and the state of the non-motor vehicle traffic light when the non-motor vehicle traffic light is not blocked.

[0112] Step S402: If the non-motor vehicle traffic light in the same direction as the blocked traffic light is also blocked, the traffic light state inference result is obtained according to the state of the lateral traffic light adjacent to the blocked traffic light.

[0113] In this embodiment, if the non-motor vehicle traffic light in the same direction as the blocked traffic light is also blocked, the traffic light state inference result of the blocked traffic light can be obtained according to the following steps S4021 and S4022.

[0114] Step S4021: Obtain second influencing factors of different driving actions of the vehicle according to the state of the side traffic light.

[0115] Step S4022: According to the second influencing factor, the traffic light state inference result of the traffic light corresponding to the driving action is obtained.

[0116] In this embodiment, reference may be made to Table 2, which is a second influencing factor table of green (red is the opposite) lateral traffic lights in different directions on different driving actions of the ego vehicle, based on the ego vehicle. The first row in Table 2 is lateral traffic lights in different directions, and the first column in Table 2 is different driving actions of the ego vehicle. The lateral traffic lights are traffic lights in other directions that are adjacent to the blocked traffic lights at the same intersection and can be sensed by the ego vehicle.

[0117] Table 2 The second influencing factors of green traffic lights in different directions on different driving actions of the vehicle

[0118]

[0119] As shown in Table 2, the score of the driving action can be obtained according to the second influencing factor of the lateral traffic lights in different directions on the driving action of the vehicle. When the score is less than 0, it means that the corresponding driving action is not supported, and the corresponding traffic light state reasoning result is red light. When the score is greater than or equal to 0, it means that the corresponding driving action is supported, and the corresponding traffic light state reasoning result is green light.

[0120] It should be noted that Table 2 only shows the second impact factor when the lateral traffic lights in different directions are green. The second impact factor when the lateral traffic lights in different directions are red is opposite to the second impact factor when they are green. For example, the second impact factor when they are green is -1, and the second impact factor when they are red is 1.

[0121] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effect of the present application, different steps do not have to be executed in such an order, and they can be executed simultaneously (in parallel) or in other orders. These adjusted schemes are equivalent to the technical schemes described in this application, and therefore will also fall within the scope of protection of this application.

[0122] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above-mentioned embodiment of the present application can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code.

[0123] Another aspect of the present application also provides a computer-readable storage medium.

[0124] In an embodiment of a computer-readable storage medium according to the present application, the computer-readable storage medium may be configured to store a program for executing the traffic light occlusion reasoning method of the above method embodiment, and the program may be loaded and run by a processor to implement the above traffic light occlusion reasoning method. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The computer-readable storage medium may be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present application is a non-temporary computer-readable storage medium.

[0125] Another aspect of the present application also provides a smart device.

[0126] In an embodiment of an intelligent device according to the present application, the intelligent device may include at least one processor; and a memory connected to the at least one processor in communication; wherein a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method described in any of the above embodiments is implemented. The intelligent device described in the present application may include a driving device, a smart car, a robot, and the like. Figure 6 , Figure 6 FIG. 4 exemplarily shows that the memory 11 and the processor 12 are communicatively connected via a bus.

[0127] In some embodiments of the present application, the smart device may further include at least one sensor for sensing information. The sensor is communicatively connected to any type of processor mentioned in the present application. Optionally, the smart device may further include an autonomous driving system for guiding the smart device to drive itself or assist in driving. The processor communicates with the sensor and / or the autonomous driving system to complete the method described in any of the above embodiments.

[0128] So far, the technical solution of the present application has been described in conjunction with an embodiment shown in the accompanying drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principles of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present application.

Claims

1. A traffic light occlusion reasoning method, characterized in that: The method is applied to a vehicle; the method comprises: Obtaining a traffic light state inference result of the blocked traffic light according to the countdown timing of the blocked traffic light corresponding to the position of the vehicle; The obtaining, according to the countdown time sequence of the blocked traffic light corresponding to the position of the vehicle, a traffic light state inference result of the blocked traffic light comprises: Acquire the state of the traffic light sensed by the vehicle before the traffic light is blocked and the countdown timing of the traffic light; According to the countdown sequence, obtaining the countdown value of the traffic light that is currently blocked; If the countdown value is zero, the traffic light state inference result of the blocked traffic light is obtained according to the driving state of other vehicles in the traffic flow in which the vehicle is located; or, the traffic light state inference result of the blocked traffic light is obtained according to the state of other traffic lights except the blocked traffic light.

2. The traffic light occlusion reasoning method according to claim 1, characterized in that: According to the countdown time sequence of the blocked traffic light corresponding to the position of the vehicle, the traffic light state inference result of the blocked traffic light is obtained, including: If the countdown value is greater than zero, the state of the traffic light before being blocked is used as the traffic light state inference result of the blocked traffic light at the current moment.

3. The traffic light occlusion reasoning method according to claim 1, characterized in that: According to the driving status of other vehicles in the traffic flow in which the vehicle is located, obtaining the traffic light status inference result of the blocked traffic light, including: Determining whether the vehicle is a leading vehicle according to the position of the vehicle in the traffic flow; If the vehicle is not the leading vehicle, obtaining the traffic light state inference result according to the driving state of the vehicle preceding the vehicle; If the vehicle is the lead vehicle, the traffic light state inference result is obtained according to the driving states of other vehicles in other lanes semantically related to the lane where the vehicle is located.

4. The traffic light occlusion reasoning method according to claim 3, characterized in that: The obtaining the traffic light state inference result according to the driving state of the preceding vehicle of the vehicle includes: If the stagnation time of the preceding vehicle is greater than a preset time, the traffic light state inference result is obtained according to the driving states of other vehicles in other lanes with the same semantics as the lane where the vehicle is located.

5. The traffic light occlusion reasoning method according to claim 3, characterized in that: The obtaining the traffic light state inference result according to the driving states of other vehicles in other lanes semantically related to the lane in which the vehicle is located includes: Acquire a first influencing factor of different driving actions of the vehicle according to the driving status of other vehicles on the other lanes; According to the first influencing factor, a traffic light state inference result of the traffic light corresponding to the driving action is obtained.

6. The traffic light occlusion reasoning method according to claim 1, characterized in that: The method further comprises: If the traffic light status inference result is not obtained based on the position of the vehicle in the traffic flow and the driving status of other vehicles in the traffic flow, the traffic light status inference result of the blocked traffic light is obtained based on the status of other traffic lights except the blocked traffic light.

7. The traffic light occlusion reasoning method according to claim 1 or 6, characterized in that: The step of obtaining the traffic light state inference result of the blocked traffic light according to the states of other traffic lights except the blocked traffic light comprises: If the non-motor vehicle traffic light in the same direction as the blocked traffic light is not blocked, obtaining the traffic light state inference result according to the state of the non-motor vehicle traffic light; If the non-motor vehicle traffic light in the same direction as the blocked traffic light is also blocked, the traffic light state inference result is obtained according to the state of the lateral traffic light adjacent to the blocked traffic light.

8. The traffic light occlusion reasoning method according to claim 7, characterized in that: The obtaining the traffic light state inference result according to the state of the lateral traffic light adjacent to the blocked traffic light comprises: According to the state of the lateral traffic light, obtaining a second influencing factor of different driving actions of the vehicle; According to the second influencing factor, a traffic light state inference result of the traffic light corresponding to the driving action is obtained.

9. A smart device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; Wherein, a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the traffic light occlusion reasoning method described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the traffic light occlusion reasoning method according to any one of claims 1 to 8.

Images