WO2024082588A1 - 交通信号灯运行状态确定方法及装置、电子设备 - Google Patents

交通信号灯运行状态确定方法及装置、电子设备 Download PDF

Info

Publication number
WO2024082588A1
WO2024082588A1 PCT/CN2023/089926 CN2023089926W WO2024082588A1 WO 2024082588 A1 WO2024082588 A1 WO 2024082588A1 CN 2023089926 W CN2023089926 W CN 2023089926W WO 2024082588 A1 WO2024082588 A1 WO 2024082588A1
Authority
WO
WIPO (PCT)
Prior art keywords
stop line
light group
traffic light
target
vehicle
Prior art date
Application number
PCT/CN2023/089926
Other languages
English (en)
French (fr)
Inventor
张建伟
康瀚隆
徐卓然
Original Assignee
北京京东乾石科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京京东乾石科技有限公司 filed Critical 北京京东乾石科技有限公司
Publication of WO2024082588A1 publication Critical patent/WO2024082588A1/zh

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/097—Supervising of traffic control systems, e.g. by giving an alarm if two crossing streets have green light simultaneously
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems

Definitions

  • the present disclosure relates to the field of intelligent driving technology, and in particular to a method, device, equipment, medium and program product for determining the operating status of a traffic light.
  • Traffic light state perception is an important part of autonomous driving.
  • the complexity of traffic order at intersections and the uncertainty of traffic light distribution greatly increase the difficulty of traffic light perception.
  • Most existing traffic light perception technologies are based on traffic light attention strategies associated with a single stop line. Due to the limitation of scene understanding in local areas, there are some disadvantages. For example, it is limited to the change of the route of the unmanned vehicle at the intersection and the corresponding switching of the traffic lights it pays attention to, which easily leads to the problem of inconsistency between the traffic light perception state expected by the downstream module; for another example, due to insufficient global scene understanding, it fails to more comprehensively promote the downstream module to make decisions based on the perception results of the entire intersection, resulting in inaccurate downstream decision results.
  • the present disclosure provides a method, apparatus, device, medium and program product for determining the operating status of a traffic light.
  • a method for determining an operating state of a traffic light comprising:
  • the operating state of at least one target traffic light group is determined so that after the operating state is sent to the decision system, the decision system guides the vehicle to pass according to the operating state.
  • determining the operating state of at least one target traffic signal light group includes:
  • An operating state of at least one target traffic signal light group is determined according to a priority of at least one target traffic signal light group.
  • determining the priority of at least one target traffic light group according to the current position of the vehicle includes:
  • At least one target stop line includes a first stop line and a second stop line
  • the current position of the vehicle is located in an area between the first stop line and the second stop line
  • determining in at least one target traffic light group that the priority of the first light group and the second light group is higher than the priority of other target traffic light groups wherein the first stop line and the second stop line are: in the at least one target stop line, two stop lines that the vehicle navigation path passes continuously, the first light group is a traffic light group bound to the first stop line, and the second light group is a traffic light group bound to the second stop line.
  • determining the priority of at least one target traffic light group according to the current position of the vehicle further includes:
  • At least one target stop line includes a first stop line and a second stop line
  • the current position of the vehicle is located in an area between the first stop line and the second stop line, calculating a first distance between the current position of the vehicle and the first stop line, and a second distance between the current position of the vehicle and the second stop line;
  • the priorities of the first light group and the second light group are determined according to the first distance and the second distance.
  • determining the priority of the first light group and the second light group according to the first distance and the second distance includes:
  • determining the priority of the first light group and the second light group according to the first distance and the second distance includes:
  • determining the priority of at least one target traffic light group according to the current position of the vehicle includes:
  • the current position of the vehicle is located in the entry lane of the head stop line, it is determined that in at least one target traffic signal light group, the priority of the head light group is higher than the priority of other target traffic signal light groups, wherein the head stop The line is: the first stop line passed by the vehicle navigation path in at least one target stop line, and the head light group is the traffic signal light group bound to the head stop line.
  • determining the priority of at least one target traffic light group according to the current position of the vehicle includes:
  • the priority of the rear light group is higher than the priority of other target traffic light groups, wherein the rear stop line is: in the at least one target stop line, the last stop line passed by the vehicle navigation path, and the rear light group is the traffic light group bound to the rear stop line.
  • Another aspect of the present disclosure provides a device for determining an operating state of a traffic light, including a first determining module, a reading module, and a second determining module.
  • the first determination module is used to determine at least one stop line passed by the vehicle navigation path among all stop lines in the current intersection where the vehicle is located as the target stop line;
  • a reading module used for reading at least one traffic light group bound to at least one target stop line from the high-precision map as the target traffic light group, wherein one target stop line is associated with one traffic light group, and one traffic light group includes at least one traffic light;
  • the second determination module is used to determine the operating status of at least one target traffic light group, so that after the operating status is sent to the decision system, the decision system guides the vehicle to pass according to the operating status.
  • the second determination module includes a first determination submodule and a second determination submodule.
  • the first determination submodule is used to determine the priority of at least one target traffic light group according to the current position of the vehicle
  • the second determining submodule is used to determine the operating state of at least one target traffic light group according to the priority of at least one target traffic light group.
  • the first determination submodule includes a first determination unit, which is used to determine that in at least one target traffic light group, the priority of the first light group and the second light group is higher than the priority of other target traffic light groups when at least one target stop line includes the first stop line and the second stop line and the current position of the vehicle is located in the area between the first stop line and the second stop line, wherein the first stop line and the second stop line are: in at least one target stop line, two stop lines that the vehicle navigation path passes continuously, the first light group is the traffic light group bound to the first stop line, and the second light group is the traffic light group bound to the second stop line.
  • the first determining submodule further includes a calculating unit and a second determining unit.
  • the calculation unit is used to calculate a first distance between the current position of the vehicle and the first stop line, and a second distance between the current position of the vehicle and the second stop line when at least one target stop line includes a first stop line and a second stop line and the current position of the vehicle is located in an area between the first stop line and the second stop line;
  • the second determining unit is used to determine the priority of the first light group and the second light group according to the first distance and the second distance.
  • the second determining unit includes a first determining subunit, which is used to determine that the priority of the first light group is greater than the priority of the second light group when the first distance is less than or equal to the second distance.
  • the second determining unit includes a second determining subunit, which is used to determine that the priority of the second light group is greater than the priority of the first light group when the first distance is greater than the second distance.
  • the first determination submodule includes a third determination unit, which is used to determine that, in at least one target traffic light group, the priority of the head light group is higher than the priority of other target traffic light groups when the current position of the vehicle is located in the entry lane of the head stop line, wherein the head stop line is: the first stop line passed by the vehicle navigation path in at least one target stop line, and the head light group is the traffic light group bound to the head stop line.
  • the first determination submodule includes a fourth determination unit, which is used to determine that, in at least one target traffic light group, the priority of the tail light group is higher than the priority of other target traffic light groups when the current position of the vehicle is located in the exit lane of the tail stop line, wherein the tail stop line is: the last stop line passed by the vehicle navigation path in at least one target stop line, and the tail light group is the traffic light group bound to the tail stop line.
  • Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned method for determining the operating status of a traffic light.
  • Another aspect of the present disclosure further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above-mentioned method for determining the operating status of a traffic light.
  • Another aspect of the present disclosure further provides a computer program product, including a computer program, which implements the above-mentioned method for determining the operating status of a traffic light when executed by a processor.
  • the above-mentioned method of the embodiment of the present disclosure pays attention to all stop lines passed by the navigation path in the intersection, and further pays attention to the traffic light group associated with it.
  • the traffic light status information sent by the traffic light status perception module to the downstream module is not affected by the change of the position of the unmanned vehicle in the intersection, and is decoupled from the behavior of the unmanned vehicle in the intersection, and there will be no inconsistency between the traffic light perception status and the traffic light perception status expected by the downstream module.
  • the unmanned vehicle While driving, the unmanned vehicle will continue to pay attention to multiple groups of traffic lights, perceive and accumulate status within the perception field of view, which can improve the unmanned vehicle's global scene understanding ability, accumulate traffic light status such as duration in advance, and promote the downstream decision-making module to make more accurate and comprehensive decisions based on the traffic light perception results of the entire scene of the intersection, thereby improving the safety of unmanned driving.
  • FIG1 schematically shows an application scenario diagram of a method, apparatus, device, medium, and program product for determining the operating state of a traffic light according to an embodiment of the present disclosure
  • FIG2 schematically shows a flow chart of a method for determining the operating state of a traffic light according to an embodiment of the present disclosure
  • FIG3 schematically illustrates a scenario diagram in which the method for determining the operating state of a traffic light according to an embodiment of the present disclosure may be executed
  • FIG4 schematically shows a flow chart of a method for determining the operating state of a traffic light according to another embodiment of the present disclosure
  • FIG5 schematically shows a structural block diagram of a device for determining the operating state of a traffic light according to an embodiment of the present disclosure.
  • FIG6 schematically shows a block diagram of an electronic device suitable for implementing a method for determining the operating state of a traffic light according to an embodiment of the present disclosure.
  • An embodiment of the present disclosure provides a method for determining an operating state of a traffic light, comprising:
  • the operating state of at least one target traffic light group is determined so that after the operating state is sent to the decision system, the decision system guides the vehicle to pass according to the operating state.
  • FIG1 schematically shows an application scenario diagram of a method, apparatus, device, medium, and program product for determining an operating state of a traffic light according to an embodiment of the present disclosure.
  • the application scenario 100 may include an unmanned vehicle 101 , a ground traffic sign 102 , and a traffic light 103 .
  • the unmanned vehicle 101 is provided with a traffic light sensing module, and the traffic light sensing module and the downstream decision module exchange information and sense through the network to guide the unmanned vehicle 101 to pass.
  • the network may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.
  • the ground traffic sign 102 may include a stop line, a zebra crossing, a lane line, a directional arrow, etc.
  • the ground traffic sign 102 and the traffic light 103 at the intersection may be used as a reference to indicate the passage of vehicles.
  • the unmanned vehicle 101 drives to the current intersection and needs to pass the traffic Information perception and information exchange are carried out between the traffic light perception module and the downstream decision-making module.
  • the traffic light perception module first determines the location of the unmanned vehicle, and then determines the ground traffic signs 102 (mainly stop lines) that need to be concerned about on the route, and the traffic lights 103 associated with the stop lines, starts the perception process, determines the operating status of the traffic lights 103, and then sends the traffic lights 103 to the downstream decision-making module to realize traffic light information interaction.
  • the decision-making system guides the vehicle to pass according to the operating status of the traffic lights 103.
  • the forms and numbers of the unmanned vehicle 101, the ground traffic sign 102, and the traffic light 103 in FIG1 are merely illustrative. According to implementation requirements, any forms and numbers of the unmanned vehicle 101, the ground traffic sign 102, and the traffic light 103 may be provided.
  • Fig. 2 schematically shows a flow chart of a method for determining the operating state of a traffic light according to an embodiment of the present disclosure.
  • Fig. 3 schematically shows a schematic diagram of a scenario in which the method for determining the operating state of a traffic light according to an embodiment of the present disclosure can be executed. The method according to an embodiment of the present disclosure is described below in conjunction with Fig. 2 and Fig. 3.
  • the method for determining the operating state of a traffic light in this embodiment includes operations S201 to S203 .
  • At least one stop line passed by the vehicle navigation path among all stop lines in the current intersection where the vehicle is located is determined as a target stop line;
  • At least one traffic light group bound to at least one target stop line is read from the high-precision map as the target traffic light group, wherein one target stop line is associated with one traffic light group, and one traffic light group includes at least one traffic light;
  • the operating state of at least one target traffic light group is determined, so that after the operating state is sent to the decision system, the decision system guides the vehicle to pass according to the operating state.
  • the above method of the embodiment of the present disclosure is applied to the scene of unmanned driving, for example, it can be applied to the scene of automatic driving of unmanned delivery vehicles.
  • the perception of the state of traffic lights is an important link, and the state of traffic lights needs to be perceived according to the traffic sequence and the distribution of traffic lights at the intersection.
  • the above method of the embodiment of the present disclosure can be applied to the vehicle-side traffic light state perception module of unmanned vehicles.
  • the target stop line is determined through the above operation S201, specifically, firstly, the current position of the unmanned vehicle is obtained from the positioning system to determine the current intersection. Then, the full amount of stop line information in the current intersection is obtained in combination with the high-precision map. Then, the navigation path of the vehicle is obtained from the navigation system, and the vehicle is All stop lines that the vehicle's navigation path passes through are used as the above-mentioned target stop lines.
  • stop line described in the embodiment of the present disclosure may be an actual stop line or a virtual stop line.
  • a virtual stop line may be set near a zebra crossing at an intersection for vehicles to temporarily stop and wait for vehicles or pedestrians in other directions to pass.
  • all stop lines passed by the navigation path of the vehicle are taken as target stop lines that need to be paid attention to.
  • the unmanned delivery vehicle will experience two straight routes in the left turn scenario (such as the first section and the second section as shown in Figure 3), and successively pass through two stop lines (the current stop line and the next stop line as shown in Figure 3, wherein the next stop line is a virtual stop line), then the target stop lines that need to be paid attention to in the left turn scenario are the above two stop lines.
  • the unmanned delivery vehicle is in the straight scene, and the navigation path passes through a stop line (the current stop line as shown in Figure 3), then the target stop line that needs to be paid attention to in the execution scenario is this stop line.
  • the high-precision map also includes a binding relationship between traffic lights and stop lines, and each stop line is bound to a traffic light with the same traffic semantic logic.
  • the binding relationship between traffic lights and stop lines can be a many-to-many state, each traffic light can be bound to one or more different stop lines, and each stop line can also be bound to one or more different traffic lights.
  • At least one traffic light group bound to at least one target stop line is read from the high-precision map through operation S202 as the target traffic light group, wherein one target stop line is associated with one traffic light group, and one traffic light group includes at least one traffic light.
  • the traffic light group bound to stop line A is a light group consisting of traffic lights 1, 2, and 3.
  • the operating status of at least one target traffic light group is further determined by the traffic light status perception module, and the operating status is further sent to the decision-making system, and the decision-making system guides the vehicle to pass according to the operating status.
  • most of the traffic light perception technologies in the related art are based on the traffic light attention strategy associated with a single stop line. For example, only by determining a single stop line near the location of the unmanned vehicle, the traffic light group associated with it is determined for perception. In this way, when the unmanned vehicle is driving in an area where light cutting occurs, it is impossible to accurately determine at what position the light should be cut in order to be consistent with the traffic light perception state expected by the downstream module. In addition, because only the traffic lights associated with a single stop line are paid attention to, the global scene is not fully understood, and the downstream modules are not able to make decisions based on the perception results of the entire intersection in a more comprehensive manner, resulting in inaccurate downstream decision results.
  • the above method of the disclosed embodiment pays attention to all stop lines passed by the navigation path in the intersection, and further pays attention to the traffic light groups associated therewith.
  • the traffic light state information sent by the traffic light state perception module to the downstream module is not changed by the change of the position of the unmanned vehicle in the intersection, and is decoupled from the behavior of the unmanned vehicle in the intersection, and the problem of inconsistency with the traffic light perception state expected by the downstream module will not occur.
  • the unmanned vehicle will continue to pay attention to multiple groups of traffic lights, perceive and accumulate states within the perception field of view, which can improve the unmanned vehicle's global scene understanding ability, accumulate the traffic light states such as the duration in advance, and promote the downstream decision module to make more accurate and comprehensive decisions based on the traffic light perception results of the entire scene of the intersection, thereby improving the safety of unmanned driving.
  • determining the operating state of at least one target traffic signal light group includes:
  • the priority of at least one target traffic light group is determined according to the current position of the vehicle.
  • the operating state of at least one target traffic light group is determined based on the priority of at least one target traffic light group. For example, if computing power resources permit, the traffic light state perception is performed on the a priori area of the traffic lights in all target traffic light groups to determine the operating state of the traffic light groups in the light group. For example, if computing power resources are insufficient, the traffic light state perception is performed on the a priori area of the traffic lights in the target traffic light group with a higher priority to determine the operating state of the traffic light groups in some target traffic light groups.
  • the unmanned vehicle will maintain all stop lines passed by the local navigation path in the intersection, as well as the bound lights associated with them.
  • the use of computing resources may not be able to detect the prior areas of all the concerned traffic lights at the intersection at the same time.
  • the traffic light groups are prioritized according to certain sorting rules based on the location of the unmanned vehicle, and then the light group that needs the most attention at the current location is selected from the traffic light groups concerned at the intersection. Subsequently, the number of concerned traffic lights at the intersection, the position arrangement distribution and the number of detection areas can be restricted, and the concerned light groups can be selected in descending order of priority for perception. In this way, the efficiency of vehicle-side information processing can be improved while ensuring the accuracy of vehicle-side information.
  • the priorities of the multiple target traffic light groups can be determined according to the current position of the vehicle; when there is only one target traffic light group, there is no need to determine the priority of the traffic light groups.
  • the target stop lines that the unmanned delivery vehicle needs to pay attention to in the left turn scenario are the two stop lines that the navigation passes (the current stop line and the next stop line shown in Figure 3), and there are also two groups of traffic light groups that need to be paid attention to (the two groups of traffic light groups are bound to the two stop lines respectively), and the priority of the two groups of traffic light groups can be further determined by the priority algorithm.
  • the target stop line that the unmanned delivery vehicle needs to pay attention to is a stop line that the navigation passes (the current stop line shown in Figure 3), and there is only one group of traffic light groups that need to be paid attention to (bound to the current stop line), so there is no need to determine the priority of the traffic light groups.
  • each target traffic light group if the same light group includes multiple traffic lights, the priorities of the multiple traffic lights in the same light group can be further determined. Subsequently, some traffic lights can be selected from the target traffic light group according to the priority for state perception.
  • FIG4 schematically shows a flow chart of a method for determining the operating status of a traffic light according to another embodiment of the present disclosure.
  • the method of the embodiment of the present disclosure is further described below in conjunction with FIG4 and FIG3. It should be noted that when there are two or more target traffic light groups that require attention, the following method of the embodiment of the present disclosure may be used to further determine the priority of the light group. In the case where there is only one target traffic light group that requires attention, there is no need to determine the priority, and the following algorithm is not applicable.
  • the two routes divided by the stop line are respectively referred to as the entry lane (entry lane) and the exit lane (exit lane).
  • the entry lane of the head stop line is only used as the entry lane (the head stop line refers to the first stop line passed by the vehicle navigation path among at least one target stop line).
  • the exit lane of the tail stop line is only used as the exit lane (the tail stop line refers to the last stop line passed by the vehicle navigation path among at least one target stop line).
  • the lane between any two consecutive stop lines serves as both the entry lane and
  • the exit lane also serves as the exit lane for the preceding stop line and the entrance lane for the succeeding stop line.
  • the lane where the main vehicle is currently located is the entry lane of the current stop line, and the lane behind the current stop line (the first section) is the exit lane of the current stop line. At the same time, this lane is also the entry lane of the next stop line, and the lane behind the next stop line (the second section) is the exit lane of the next stop line.
  • the method for determining the operating state of a traffic light in an embodiment of the present disclosure uses intersection information as an interaction unit with a high-precision map, and specifically includes the following operations:
  • the current position of the driverless vehicle is obtained from the positioning system to determine the current intersection.
  • the navigation information and high-precision map are combined to search and record all the information of the intersection of interest, such as the local navigation path within the intersection, all the stop lines (target stop lines) passed by the local navigation path, and the traffic light information associated with it (target traffic light group).
  • the local navigation path in the intersection (indicated by the arrow in the figure) is a left turn route, indicating that the current scene is a left turn scene.
  • the unmanned vehicle will experience two straight routes in the left turn scene (the first section and the second section shown in the figure), and pass through two stop lines in succession (the current stop line and the next stop line shown in the figure, where the next stop line is a virtual stop line).
  • the traffic light group bound to the two stop lines is determined, as shown in the binding relationship in the figure.
  • This information is not changed by the change of the position of the unmanned vehicle in the intersection, and is decoupled from the behavior of the unmanned vehicle in the intersection.
  • the unmanned vehicle will continue to pay attention to the above two groups of traffic lights, and perform perception and state accumulation within the perception field of view.
  • the positioning system is responsible for providing the real-time position of the unmanned vehicle, and then the priority of the above-mentioned multiple target traffic light groups can be determined according to the real-time position of the unmanned vehicle.
  • the lane type of the area where the vehicle's current position is located can be first determined according to the vehicle's current position, such as whether it is an entry lane, an exit lane, or both an entry lane and an exit lane. Then, the priority of at least one target traffic light group is determined according to the lane type of the area where the vehicle's current position is located.
  • the priorities of multiple target traffic signal light groups are determined by the following method.
  • the lane type of the area where the current position of the vehicle is located is only the entry lane, and it is determined that in at least one target traffic light group, the priority of the head light group is higher than the priority of other target traffic light groups.
  • Priority where the head light group is the traffic signal light group bound to the head stop line. That is, in this case, priority is given to the light group associated with the preceding stop line.
  • the lane type of the area where the current position of the vehicle is located is only the exit lane, and it is determined that in at least one target traffic light group, the priority of the rear light group is higher than the priority of other target traffic light groups, wherein the rear light group is the traffic light group bound to the rear stop line. That is, in this case, priority is given to the light group associated with the subsequent stop line.
  • the unmanned vehicle in order to ensure the accuracy of information, when the unmanned vehicle is in the process of entering a lane, it is necessary to focus on the traffic lights associated with the stop line corresponding to the entry lane; when the unmanned vehicle is in the process of exiting a lane, it is necessary to focus on the traffic lights associated with the stop line corresponding to the exit lane. Therefore, when the vehicle is currently located at the entry lane of the head stop line, the head light group has the highest priority; when the vehicle is currently located at the exit lane of the tail stop line, the tail light group has the highest priority.
  • the lane between any two consecutive stop lines serves as both an entry lane and an exit lane, that is, it serves as an exit lane for the preceding stop line and an entry lane for the succeeding stop line.
  • the priorities of multiple target traffic light groups are determined by the following method.
  • At least one target stop line includes two consecutive stop lines: a first stop line and a second stop line
  • the current position of the vehicle is located in the area between the first stop line and the second stop line
  • the area where the current position of the vehicle is located serves as both the exit lane of the preceding stop line and the entry lane of the succeeding stop line.
  • the priorities of the first light group and the second light group are determined according to the first distance and the second distance.
  • the priority of the first light group is determined to be greater than the priority of the second light group. That is, in this case, priority is given to the light group associated with the preceding stop line.
  • the priority of the second light group is determined to be greater than the priority of the first light group. That is, in this case, priority is given to the subsequent stop line association. Light set.
  • light group A and light group B where light group A is bound to the current stop line shown in FIG3, and light group B is bound to the next stop line shown in FIG3.
  • light group A can be used as the first light group
  • light group B can be used as the second light group.
  • the above method of the embodiment of the present disclosure can be used to determine the priority of the first light group and the second light group.
  • the unmanned delivery vehicle needs to pay attention to three target traffic light groups when crossing the road, namely, light group A, light group B, and light group C, which are bound to stop lines A, stop line B, and stop line C respectively, and the navigation path passes through stop lines A, stop line B, and stop line C in sequence.
  • stop line A and stop line B serve as the first stop line and the second stop line respectively
  • light group A and light group B serve as the first light group and the second light group respectively
  • stop line B and stop line C serve as the first stop line and the second stop line respectively
  • light group B and light group C serve as the first light group and the second light group respectively.
  • the above method of the embodiment of the present disclosure can be used to determine the priority of the first light group and the second light group.
  • the unmanned vehicle when the area where the vehicle's current position is located serves as both the exit lane of the preceding stop line and the entry lane of the succeeding stop line, the unmanned vehicle will switch lights while driving in the intersection.
  • the first half of the lane it may mainly serve as the exit lane, paying the most attention to the traffic lights associated with the previous stop line
  • the second half of the lane it may mainly serve as the entry lane, paying the most attention to the traffic lights associated with the next stop line.
  • the priority of the traffic light group is determined by the above method of the embodiments of the present disclosure, which conforms to the attention logic of the unmanned vehicle's light switching behavior, and the status of the light group that needs the most attention is pushed to the downstream decision-making system first, further avoiding the problem of inconsistency with the traffic light perception state expected by the downstream module.
  • the unmanned delivery vehicle needs to pay attention to two target traffic light groups in the left turn scenario: light group A and light group B, where light group A is bound to the current stop line shown in Figure 3, and light group B is bound to the next stop line shown in Figure 3.
  • the lane it is in is the entry lane.
  • the main vehicle's attention order for traffic lights is the order of light group A-light group B; when the unmanned vehicle is in the first section after the current stop line and before the next stop line, the lane it is in is both the entry lane and the exit lane.
  • the relative position of the main vehicle to the lane needs to be considered in combination with the positioning information.
  • the attention should be paid to the order of light group A-light group B. If the main vehicle is in the second half of the lane, the attention should be paid to light group B-light group B.
  • Group A sequence when the unmanned vehicle is located in the second section after the next stop line, the lane it is in is the exit lane. At this time, the main vehicle's attention sequence for traffic lights is light group B-light group A.
  • the following method of an embodiment of the present disclosure can be used to further determine the priority of the light group.
  • the priority of at least one target traffic light group may be determined according to the current position of the vehicle by using the following method:
  • At least one target stop line includes a first stop line and a second stop line
  • the current position of the vehicle is located in an area between the first stop line and the second stop line
  • determining in at least one target traffic light group that the priority of the first light group and the second light group is higher than the priority of other target traffic light groups wherein the first stop line and the second stop line are: in the at least one target stop line, two stop lines that the vehicle navigation path passes continuously, the first light group is a traffic light group bound to the first stop line, and the second light group is a traffic light group bound to the second stop line.
  • the above priority algorithm can be applied in situations where there are more than two target traffic light groups that need attention. For example, at some complex intersections, when crossing the road, the unmanned vehicle may need to stop in the safe navigation area in the middle of the road to sense the status of the traffic light. In some driving scenarios (such as turning), there may be more than two stop lines along the navigation path, and there may also be more than two traffic light groups that need attention.
  • the first stop line and the second stop line are two stop lines that the vehicle navigation path passes continuously.
  • the traffic light groups corresponding to the first stop line and the second stop line are the ones that currently need the most attention. Therefore, the priority of the first light group and the second light group is higher than the priority of other target traffic light groups.
  • the above method for determining the priority of traffic lights starts from the perspective of the use of computing resources on the vehicle side, and dynamically selects the focus area in order from high to low priority, thereby ensuring that the unmanned vehicle can pay attention to the traffic information that must be taken care of and perform global scene understanding with the maximum capacity when driving at the current position.
  • the present disclosure further provides a device for determining the operating state of a traffic light, which will be described in detail below in conjunction with FIG.
  • FIG5 schematically shows a structural block diagram of a device for determining the operating state of a traffic light according to an embodiment of the present disclosure.
  • the traffic light operation state determination device 500 of this embodiment includes a first determination module 501, A reading module 502 and a second determining module 503 .
  • the first determination module 501 is used to determine at least one stop line passed by the vehicle navigation path among all stop lines in the current intersection where the vehicle is located as a target stop line;
  • a reading module 502 is used to read at least one traffic light group bound to at least one target stop line from the high-precision map as the target traffic light group, wherein one target stop line is associated with one traffic light group, and one traffic light group includes at least one traffic light;
  • the second determination module 503 is used to determine the operating status of at least one target traffic light group, so that after the operating status is sent to the decision system, the decision system guides the vehicle to pass according to the operating status.
  • the global scene understanding ability of the unmanned vehicle can be improved, and the traffic lights of the whole scene in the intersection can be continuously perceived within the perception range of the intersection. Therefore, the traffic light status information sent to the downstream module by the second determination module 503 is not changed by the change of the position of the unmanned vehicle in the intersection, and then decoupled from the behavior of the unmanned vehicle in the intersection, and the problem of inconsistent traffic light perception state expected by the downstream module will not occur.
  • the unmanned vehicle will continue to pay attention to multiple groups of traffic lights, perceive and accumulate states within the perception field of view, which can improve the global scene understanding ability of the unmanned vehicle, accumulate the traffic light states such as the duration in advance, and promote the downstream decision module to make more accurate and comprehensive decisions based on the traffic light perception results of the whole scene of the intersection, thereby improving the safety of unmanned driving.
  • the second determination module 503 includes a first determination submodule and a second determination submodule.
  • the first determination submodule is used to determine the priority of at least one target traffic light group according to the current position of the vehicle
  • the second determining submodule is used to determine the operating state of at least one target traffic light group according to the priority of at least one target traffic light group.
  • the first determination submodule includes a first determination unit, which is used to determine that, in at least one target stop line, the first stop line and the second stop line have a higher priority than other target traffic light groups when the at least one target stop line includes the first stop line and the second stop line and the current position of the vehicle is located in the area between the first stop line and the second stop line, wherein the first stop line and the second stop line are: in the at least one target stop line, two stop lines that the vehicle navigation path passes continuously, and the first stop line is the first stop line that is adjacent to the first stop line.
  • the first light group is a traffic signal light group bound to the first stop line
  • the second light group is a traffic signal light group bound to the second stop line.
  • the first determining submodule further includes a calculating unit and a second determining unit.
  • the calculation unit is used to calculate a first distance between the current position of the vehicle and the first stop line, and a second distance between the current position of the vehicle and the second stop line when at least one target stop line includes a first stop line and a second stop line and the current position of the vehicle is located in an area between the first stop line and the second stop line;
  • the second determining unit is used to determine the priority of the first light group and the second light group according to the first distance and the second distance.
  • the second determining unit includes a first determining subunit, which is used to determine that the priority of the first light group is greater than the priority of the second light group when the first distance is less than or equal to the second distance.
  • the second determining unit includes a second determining subunit, which is used to determine that the priority of the second light group is greater than the priority of the first light group when the first distance is greater than the second distance.
  • the first determination submodule includes a third determination unit, which is used to determine that, in at least one target traffic light group, the priority of the head light group is higher than the priority of other target traffic light groups when the current position of the vehicle is located in the entry lane of the head stop line, wherein the head stop line is: the first stop line passed by the vehicle navigation path in at least one target stop line, and the head light group is the traffic light group bound to the head stop line.
  • the first determination submodule includes a fourth determination unit, which is used to determine that, in at least one target traffic light group, the priority of the tail light group is higher than the priority of other target traffic light groups when the current position of the vehicle is located in the exit lane of the tail stop line, wherein the tail stop line is: the last stop line passed by the vehicle navigation path in at least one target stop line, and the tail light group is the traffic light group bound to the tail stop line.
  • any multiple modules of the first determination module 501, the reading module 502, and the second determination module 503 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.
  • At least one of the first determination module 501, the reading module 502, and the second determination module 503 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in an appropriate combination of any of them.
  • FPGA field programmable gate array
  • PLA programmable logic array
  • ASIC application-specific integrated circuit
  • the first determination module 501, the reading module 502, and the second determination module 503 can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in an appropriate combination of any of them. At least one of the two determination modules 503 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.
  • FIG6 schematically shows a block diagram of an electronic device suitable for implementing a method for determining the operating state of a traffic light according to an embodiment of the present disclosure.
  • the electronic device 600 includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603.
  • the processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and/or a related chipset and/or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc.
  • the processor 601 may also include an onboard memory for caching purposes.
  • the processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.
  • RAM 603 various programs and data required for the operation of the electronic device 600 are stored.
  • the processor 601, ROM 602 and RAM 603 are connected to each other through a bus 604.
  • the processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and/or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603.
  • the processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.
  • the electronic device 600 may further include an input/output (I/O) interface 605, which is also connected to the bus 604.
  • the electronic device 600 may further include one or more of the following components connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc.
  • the communication portion 609 performs communication processing via a network such as the Internet.
  • a drive 610 is also connected to the I/O interface 605 as needed.
  • a removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.
  • the present disclosure also provides a computer-readable storage medium, which may be included in the device/apparatus/system described in the above embodiments; or may exist independently without being assembled into the device/apparatus/system.
  • the above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.
  • a computer-readable storage medium may be a non-volatile computer-readable storage medium, such as but not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable storage medium may include the ROM 602 and/or RAM 603 described above and/or one or more memories other than ROM 602 and RAM 603.
  • the embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart.
  • the program code is used to enable the computer system to implement the traffic signal light operating state determination method provided by the embodiment of the present disclosure.
  • the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, etc.
  • the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 609, and/or installed from a removable medium 611.
  • the program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
  • the computer program can be downloaded and installed from the network through the communication part 609, and/or installed from the removable medium 611.
  • the computer program is executed by the processor 601, the above functions defined in the system of the embodiment of the present disclosure are performed.
  • the system, device, means, module, unit, etc. described above can be implemented by a computer program module.
  • the program code for executing the computer program provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages.
  • these computer programs can be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages.
  • Programming languages include but are not limited to programming languages such as Java, C++, Python, "C" language, or similar programming languages.
  • the program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or in some cases, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or it may be connected to an external computing device (e.g., through the Internet using an Internet service provider).
  • LAN local area network
  • WAN wide area network
  • each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function.
  • the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.
  • each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)
  • Navigation (AREA)

Abstract

一种交通信号灯运行状态确定方法及装置、电子设备，应用于智能驾驶技术领域。交通信号灯运行状态确定方法包括：将车辆所在当前路口内的全量停止线中，车辆导航路径途经的至少一条停止线确定为目标停止线(S201)；从高精地图中读取与至少一条目标停止线绑定的至少一个交通信号灯组，作为目标交通信号灯组(S202)，其中，一条目标停止线关联一个交通信号灯组，一个交通信号灯组中包括至少一个交通信号灯；确定至少一个目标交通信号灯组的运行状态，以便将运行状态发送至决策系统后，决策系统根据运行状态指导车辆通行(S203)。

Description

交通信号灯运行状态确定方法及装置、电子设备 技术领域
本公开涉及智能驾驶技术领域，具体地涉及一种交通信号灯运行状态确定方法、装置、设备、介质和程序产品。
背景技术
交通信号灯状态感知是自动驾驶中的重要环节，由于路口内交通顺序的复杂性和交通信号灯分布的不确定性极大地增加了交通信号灯感知的难度。现有的交通信号灯感知技术大多是基于单条停止线相关联的交通信号灯关注策略，因受限于局部区域的场景理解存在一些弊端，例如，局限于无人车在路口内所处路线的变换和相对应的所关注的交通信号灯切换，容易发生与下游模块所期望的交通信号灯感知状态不一致问题；再例如，因全局场景理解不充分，未能更加全面地促进下游模块基于全路口感知结果进行决策，导致下游决策结果不准确。
发明内容
鉴于上述问题，本公开提供了一种交通信号灯运行状态确定方法、装置、设备、介质和程序产品。
本公开的一个方面，提供了一种交通信号灯运行状态确定方法，包括：
将车辆所在当前路口内的全量停止线中，车辆导航路径途经的至少一条停止线确定为目标停止线；
从高精地图中读取与至少一条目标停止线绑定的至少一个交通信号灯组，作为目标交通信号灯组，其中，一条目标停止线关联一个交通信号灯组，一个交通信号灯组中包括至少一个交通信号灯；
确定至少一个目标交通信号灯组的运行状态，以便将运行状态发送至决策系统后，决策系统根据运行状态指导车辆通行。
根据本公开的实施例，其中，确定至少一个目标交通信号灯组的运行状态包括：
根据车辆当前位置确定至少一个目标交通信号灯组的优先级；
根据至少一个目标交通信号灯组的优先级，确定至少一个目标交通信号灯组的运行状态。
根据本公开的实施例，其中，根据车辆当前位置确定至少一个目标交通信号灯组的优先级包括：
在至少一条目标停止线包括第一停止线和第二停止线、且车辆当前位置位于第一停止线和第二停止线之间区域的情况下，确定至少一个目标交通信号灯组中，第一灯组和第二灯组的优先级高于其他目标交通信号灯组的优先级，其中，第一停止线和第二停止线为：至少一条目标停止线中，车辆导航路径连续途经的两条停止线，第一灯组为与第一停止线绑定的交通信号灯组，第二灯组为与第二停止线绑定的交通信号灯组。
根据本公开的实施例，其中，根据车辆当前位置确定至少一个目标交通信号灯组的优先级还包括：
在至少一条目标停止线包括第一停止线和第二停止线、且车辆当前位置位于第一停止线和第二停止线之间区域的情况下，计算车辆当前位置与第一停止线之间的第一距离，以及车辆当前位置与第二停止线之间的第二距离；
根据第一距离和第二距离确定第一灯组和第二灯组的优先级。
根据本公开的实施例，其中，根据第一距离和第二距离确定第一灯组和第二灯组的优先级包括：
在第一距离小于等于第二距离的情况下，确定第一灯组的优先级大于第二灯组的优先级。
根据本公开的实施例，其中，根据第一距离和第二距离确定第一灯组和第二灯组的优先级包括：
在第一距离大于第二距离的情况下，确定第二灯组的优先级大于第一灯组的优先级。
根据本公开的实施例，其中，根据车辆当前位置确定至少一个目标交通信号灯组的优先级包括：
在车辆当前位置位于头部停止线的进入车道的情况下，确定至少一个目标交通信号灯组中，头部灯组的优先级高于其他目标交通信号灯组的优先级，其中，头部停止 线为：至少一条目标停止线中，车辆导航路径途经的第一条停止线，头部灯组为与头部停止线绑定的交通信号灯组。
根据本公开的实施例，其中，根据车辆当前位置确定至少一个目标交通信号灯组的优先级包括：
在车辆当前位置位于尾部停止线的退出车道的情况下，确定至少一个目标交通信号灯组中，尾部灯组的优先级高于其他目标交通信号灯组的优先级，其中，尾部停止线为：至少一条目标停止线中，车辆导航路径途经的最后一条停止线，尾部灯组为与尾部停止线绑定的交通信号灯组。
本公开的另一个方面提供了一种交通信号灯运行状态确定装置，包括第一确定模块、读取模块、第二确定模块。
其中，第一确定模块，用于将车辆所在当前路口内的全量停止线中，车辆导航路径途经的至少一条停止线确定为目标停止线；
读取模块，用于从高精地图中读取与至少一条目标停止线绑定的至少一个交通信号灯组，作为目标交通信号灯组，其中，一条目标停止线关联一个交通信号灯组，一个交通信号灯组中包括至少一个交通信号灯；
第二确定模块，用于确定至少一个目标交通信号灯组的运行状态，以便将运行状态发送至决策系统后，决策系统根据运行状态指导车辆通行。
根据本公开的实施例，其中，第二确定模块包括第一确定子模块、第二确定子模块。
其中，第一确定子模块，用于根据车辆当前位置确定至少一个目标交通信号灯组的优先级；
第二确定子模块，用于根据至少一个目标交通信号灯组的优先级，确定至少一个目标交通信号灯组的运行状态。
根据本公开的实施例，其中，第一确定子模块包括第一确定单元，用于在至少一条目标停止线包括第一停止线和第二停止线、且车辆当前位置位于第一停止线和第二停止线之间区域的情况下，确定至少一个目标交通信号灯组中，第一灯组和第二灯组的优先级高于其他目标交通信号灯组的优先级，其中，第一停止线和第二停止线为：至少一条目标停止线中，车辆导航路径连续途经的两条停止线，第一灯组为与第一停止线绑定的交通信号灯组，第二灯组为与第二停止线绑定的交通信号灯组。
根据本公开的实施例，其中，第一确定子模块还包括计算单元、第二确定单元。
其中，计算单元，用于在至少一条目标停止线包括第一停止线和第二停止线、且车辆当前位置位于第一停止线和第二停止线之间区域的情况下，计算车辆当前位置与第一停止线之间的第一距离，以及车辆当前位置与第二停止线之间的第二距离；
第二确定单元，用于根据第一距离和第二距离确定第一灯组和第二灯组的优先级。
根据本公开的实施例，其中，第二确定单元包括第一确定子单元，用于在第一距离小于等于第二距离的情况下，确定第一灯组的优先级大于第二灯组的优先级。
根据本公开的实施例，其中，第二确定单元包括第二确定子单元，用于在第一距离大于第二距离的情况下，确定第二灯组的优先级大于第一灯组的优先级。
根据本公开的实施例，其中，第一确定子模块包括第三确定单元，用于在车辆当前位置位于头部停止线的进入车道的情况下，确定至少一个目标交通信号灯组中，头部灯组的优先级高于其他目标交通信号灯组的优先级，其中，头部停止线为：至少一条目标停止线中，车辆导航路径途经的第一条停止线，头部灯组为与头部停止线绑定的交通信号灯组。
根据本公开的实施例，其中，第一确定子模块包括第四确定单元，用于在车辆当前位置位于尾部停止线的退出车道的情况下，确定至少一个目标交通信号灯组中，尾部灯组的优先级高于其他目标交通信号灯组的优先级，其中，尾部停止线为：至少一条目标停止线中，车辆导航路径途经的最后一条停止线，尾部灯组为与尾部停止线绑定的交通信号灯组。
本公开的另一个方面提供了一种电子设备，包括：一个或多个处理器；存储器，用于存储一个或多个程序，其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得一个或多个处理器执行上述交通信号灯运行状态确定方法。
本公开的另一个方面还提供了一种计算机可读存储介质，其上存储有可执行指令，该指令被处理器执行时使处理器执行上述交通信号灯运行状态确定方法。
本公开的另一个方面还提供了一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现上述交通信号灯运行状态确定方法。
本公开实施例的上述方法通过关注路口内导航路径途经的全部停止线，并进一步关注与其相关联的交通信号灯组，相比于基于单条停止线的交通信号灯关注策略，能够提升无人车全局场景理解能力，在路口感知范围内持续感知路口内全场景的交通信 号灯。因此，交通信号灯状态感知模块发送给下游模块的交通信号灯状态信息不受无人车在路口内所处位置的变化而改变，进而与无人车在路口内的行为发生解耦，不会发生与下游模块所期望的交通信号灯感知状态不一致问题。同时，无人车在行驶过程中，会持续关注多组交通信号灯，在感知视野范围内进行感知和状态积累，能够提升无人车全局场景理解能力，提前累计持续时长等交通信号灯状态，促进下游决策模块基于路口全场景的交通信号灯感知结果进行更精准更全面的决策，提高了无人驾驶通行的安全性。
附图说明
通过以下参照附图对本公开实施例的描述，本公开的上述内容以及其他目的、特征和优点将更为清楚，在附图中：
图1示意性示出了根据本公开实施例的交通信号灯运行状态确定方法、装置、设备、介质和程序产品的应用场景图；
图2示意性示出了根据本公开实施例的交通信号灯运行状态确定方法的流程图；
图3示意性示例性示出了可执行本公开实施例的交通信号灯运行状态确定方法的场景示意图；
图4示意性示出了根据本公开另一实施例的交通信号灯运行状态确定方法的流程图；
图5示意性示出了根据本公开实施例的交通信号灯运行状态确定装置的结构框图；以及
图6示意性示出了根据本公开实施例的适于实现交通信号灯运行状态确定方法的电子设备的方框图。
具体实施方式
以下，将参照附图来描述本公开的实施例。但是应该理解，这些描述只是示例性的，而并非要限制本公开的范围。在下面的详细描述中，为便于解释，阐述了许多具体的细节以提供对本公开实施例的全面理解。然而，明显地，一个或多个实施例在没有这些具体细节的情况下也可以被实施。此外，在以下说明中，省略了对公知结构和 技术的描述，以避免不必要地混淆本公开的概念。
在此使用的术语仅仅是为了描述具体实施例，而并非意在限制本公开。在此使用的术语“包括”、“包含”等表明了所述特征、步骤、操作和/或部件的存在，但是并不排除存在或添加一个或多个其他特征、步骤、操作或部件。
在此使用的所有术语(包括技术和科学术语)具有本领域技术人员通常所理解的含义，除非另外定义。应注意，这里使用的术语应解释为具有与本说明书的上下文相一致的含义，而不应以理想化或过于刻板的方式来解释。
在使用类似于“A、B和C等中至少一个”这样的表述的情况下，一般来说应该按照本领域技术人员通常理解该表述的含义来予以解释(例如，“具有A、B和C中至少一个的系统”应包括但不限于单独具有A、单独具有B、单独具有C、具有A和B、具有A和C、具有B和C、和/或具有A、B、C的系统等)。
本公开的实施例提供了一种交通信号灯运行状态确定方法，包括：
将车辆所在当前路口内的全量停止线中，车辆导航路径途经的至少一条停止线确定为目标停止线；
从高精地图中读取与至少一条目标停止线绑定的至少一个交通信号灯组，作为目标交通信号灯组，其中，一条目标停止线关联一个交通信号灯组，一个交通信号灯组中包括至少一个交通信号灯；
确定至少一个目标交通信号灯组的运行状态，以便将运行状态发送至决策系统后，决策系统根据运行状态指导车辆通行。
图1示意性示出了根据本公开实施例的交通信号灯运行状态确定方法、装置、设备、介质和程序产品的应用场景图。
如图1所示，根据该实施例的应用场景100可以包括无人驾驶车辆101、地面交通指示标识102、交通信号灯103。
其中，无人驾驶车辆101设有交通信号灯感知模块，交通信号灯感知模块和下游决策模块之间通过网络进行信息交互和感知，以指导无人驾驶车辆101通行。网络可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
地面交通指示标识102可包括停止线、斑马线、车道线、指向箭头等等。地面交通指示标识102和路口的交通信号灯103可作为指示车辆通行的参照。
在本公开实施例的应用场景下，无人驾驶车辆101行驶至当前路口，需要通过交 通信号灯感知模块和下游决策模块之间进行信息感知和信息交互。例如，无人车在行进至路口时，交通信号灯感知模块先确定无人车所处的位置，进而确定在该路线上需要关心的地面交通指示标识102(主要是停止线)，以及与停止线相关联的交通信号灯103，开启感知流程，确定交通信号灯103的运行状态，而后将交通信号灯103的发送至下游决策模块，实现交通灯信息交互，决策系统根据交通信号灯103的运行状态指导车辆通行。
应该理解，图1中的无人驾驶车辆101、地面交通指示标识102、交通信号灯103的形式和数量仅仅是示意性的。根据实现需要，可以具有任意形式和数量的无人驾驶车辆101、地面交通指示标识102、和交通信号灯103。
以下将基于图1描述的场景，通过图2～图6对公开实施例的交通信号灯运行状态确定方法进行详细描述。
图2示意性示出了根据本公开实施例的交通信号灯运行状态确定方法的流程图。图3示意性示例性示出了可执行本公开实施例的交通信号灯运行状态确定方法的场景示意图。以下，结合图2、图3对本公开实施例的方法进行描述。
如图2所示，该实施例的交通信号灯运行状态确定方法包括操作S201～操作S203。
在操作S201，将车辆所在当前路口内的全量停止线中，车辆导航路径途经的至少一条停止线确定为目标停止线；
在操作S202，从高精地图中读取与至少一条目标停止线绑定的至少一个交通信号灯组，作为目标交通信号灯组，其中，一条目标停止线关联一个交通信号灯组，一个交通信号灯组中包括至少一个交通信号灯；
在操作S203，确定至少一个目标交通信号灯组的运行状态，以便将运行状态发送至决策系统后，决策系统根据运行状态指导车辆通行。
本公开实施例的上述方法应用于无人驾驶的场景，例如可应用于无人配送车自动驾驶的场景。在无人驾驶场景下，交通信号灯状态感知是一个重要环节，需要根据路口内交通顺序和交通信号灯分布对交通信号灯状态进行感知。本公开实施例的上述方法可应用于无人驾驶车辆的车端交通信号灯状态感知模块。
根据本公开的实施例，通过上述操作S201确定目标停止线，具体可以是：首先从定位系统中获取无人驾驶车辆当前位置，以确定当前所在的路口。再结合高精地图获取当前路口内的全量停止线信息。之后，再从导航系统中获取车辆的导航路径，将车 辆的导航路径途经的所有停止线作为上述目标停止线。
其中，高精地图中，事先对路口(Intersection)、小路(Lane)、停止线(Stop Line)和交通信号灯(Traffic Light,TL)等信息进行建模，因而可基于高精地图获取当前路口内的全量停止线信息。
需要说明的是，本公开实施例所述的停止线可以是实际停止线，也可以是虚拟停止线。例如，在高精地图中，路口斑马线附近可能会设置虚拟停止线，以供车辆临时停车等待其他方向车辆或者行人通行。
根据本公开的实施例，上述方法中，将车辆的导航路径途经的所有停止线作为需要关注的目标停止线。如图3所示的场景下，如若导航路径提示左转，按照导航路径，无人配送车在左转场景中会经历两段直行路线(如图3中所示的第一路段和第二路段)，并先后途经两条停止线(如图3所示的当前停止线和下一条停止线，其中下一条停止线为虚拟停止线)，则左转场景下需要关注的目标停止线为上述两条停止线。如若导航路径提示直行，按照导航路径，无人配送车在直行场景中，导航路径途经一条停止线(如图3所示的当前停止线)，则执行场景下需要关注的目标停止线为这一条停止线。
根据本公开的实施例，高精地图中还包括交通信号灯和停止线的绑定关系，绑定有每条停止线与具有相同交通语义逻辑的交通信号灯。具体地，交通信号灯与停止线的绑定关系可以是多对多的状态，每个交通信号灯可以绑定一条或多条不同的停止线，每条停止线也可绑定一个或多个不同的交通信号灯。
进一步地，在确定当前行驶场景(左转、直行、右转等)下需要关注的目标停止线后，通过操作S202从高精地图中读取与至少一条目标停止线绑定的至少一个交通信号灯组，作为目标交通信号灯组，其中，一条目标停止线关联一个交通信号灯组，一个交通信号灯组中包括至少一个交通信号灯。例如，从高精地图中读取到，停止线A绑定有1、2、3号交通信号灯，停止线A绑定的一个交通信号灯组，即为1、2、3号交通信号灯组成的灯组。
根据本公开的实施例，在确定了需要关注的停止线，以及与其存在绑定关系的交通信号灯组后，在上述操作S203，通过交通信号灯状态感知模块进一步确定至少一个目标交通信号灯组的运行状态，并进一步将运行状态发送至决策系统，决策系统根据运行状态指导车辆通行。
根据本公开的实施例，相关技术中的交通信号灯感知技术大多是基于单条停止线相关联的交通信号灯关注策略，例如仅通过确定无人车所处的位置附近的单条停止线，来确定与其相关联的交通信号灯组进行感知。这样，无人车在存在切灯行为的区域行驶时，无法准确判断应当在什么位置切灯才能与下游模块所期望的交通信号灯感知状态保持一致。并且，因仅关注单条停止线相关联的交通信号灯，对全局场景理解不充分，未能更加全面地促进下游模块基于全路口感知结果进行决策，导致下游决策结果不准确。
本公开实施例的上述方法通过关注路口内导航路径途经的全部停止线，并进一步关注与其相关联的交通信号灯组，相比于基于单条停止线的交通信号灯关注策略，能够提升无人车全局场景理解能力，在路口感知范围内持续感知路口内全场景的交通信号灯。因此，交通信号灯状态感知模块发送给下游模块的交通信号灯状态信息不受无人车在路口内所处位置的变化而改变，进而与无人车在路口内的行为发生解耦，不会发生与下游模块所期望的交通信号灯感知状态不一致问题。同时，无人车在行驶过程中，会持续关注多组交通信号灯，在感知视野范围内进行感知和状态积累，能够提升无人车全局场景理解能力，提前累计持续时长等交通信号灯状态，促进下游决策模块基于路口全场景的交通信号灯感知结果进行更精准更全面的决策，提高了无人驾驶通行的安全性。
根据本公开的实施例，在确定了当前行驶场景下需要关注的交通信号灯组后，进一步地，需要基于交通信号灯组内的交通信号灯的先验区域进行交通信号灯状态感知。
具体地，确定至少一个目标交通信号灯组的运行状态包括：
首先，根据车辆当前位置确定至少一个目标交通信号灯组的优先级。
之后，根据至少一个目标交通信号灯组的优先级，确定至少一个目标交通信号灯组的运行状态。例如可以是在算力资源允许的情况下，对所有目标交通信号灯组内的交通信号灯的先验区域进行交通信号灯状态感知，确定灯组内交通信号灯组的运行状态。例如还可以是，在算力资源不充足的情况下，对优先级较高的目标交通信号灯组内的交通信号灯的先验区域进行交通信号灯状态感知，确定部分目标交通信号灯组内交通信号灯组的运行状态。
根据本公开的实施例，通过上述交通信号灯运行状态确定方法，无人车会维护路口内局部导航路径途经的所有停止线，以及与其相关联的绑定灯。但是，受限于车端 算力资源的使用，可能并不能同时检测路口内所有已关注的交通信号灯的先验区域。通过上述方法根据无人车所处的位置，对的交通信号灯组按照一定的排序规则进行优先级划分，进而在路口内关注的交通信号灯组中挑选当前位置最需照看的灯组，后续可通过路口内关注交通信号灯的数量、位置排列分布和检测区域数量的限制，按照优先级从高到低顺序选择关注的灯组进行感知。如此，在保证车端信息准确度的前提下，可提高车端信息处理的效率。
根据本公开的实施例，在目标交通信号灯组有多个的情况下，可根据车辆当前位置确定多个目标交通信号灯组的优先级；在目标交通信号灯组仅有一个的情况下无需确定交通信号灯组的优先级。
如图3所示，无人配送车在左转场景下需要关注的目标停止线为导航途经的两条停止线(图3所示的当前停止线和下一条停止线)，进一步需关注的交通信号灯组也有两组(两组交通信号灯组分别与两条停止线绑定)，可进一步通过优先级算法确定两组交通信号灯组的优先级。而无人配送车在直行场景下需要关注的目标停止线为导航途经的一条停止线(如图3所示的当前停止线)，进一步需关注的交通信号灯组也只有一组(与当前停止线绑定)，则无需确定交通信号灯组的优先级。
根据本公开的实施例，进一步地，在每个目标交通信号灯组内，若同一灯组内包含多个交通信号灯，也可以进一步确定同一灯组内多个交通信号灯的优先级。后续，可从目标交通信号灯组内按照优先级选择部分交通信号灯进行状态感知。
图4示意性示出了根据本公开另一实施例的交通信号灯运行状态确定方法的流程图。以下结合图4、图3，对本公开实施例的方法进行进一步介绍。需要说明的是，在需关注的目标交通信号灯组有两个或两个以上的情形时，可采用本公开实施例的下述方法，进一步确定灯组的优先级。在需关注的目标交通信号灯组仅有一个的情形，无需确定优先级，不适用下述算法。
根据本公开的实施例，由停止线分割的两段路线分别被称为进入车道(进入lane)和退出车道(退出lane)。其中，在车辆导航路径连续途经至少两条停止线的情况下，需关注的目标停止线有至少两条。此时，头部停止线的进入车道仅作为进入车道(头部停止线指的是至少一条目标停止线中，车辆导航路径途经的第一条停止线)。尾部停止线的退出车道仅作为退出车道(尾部停止线指的是至少一条目标停止线中，车辆导航路径途经的最后一条停止线)。在任一组连续两条停止线之间的车道兼做进入车道和 退出车道，同时作为前序停止线的退出车道和后序停止线的进入车道。
如图3中所示，主车当前所在的lane为当前停止线的进入lane，当前停止线后方的lane(第一路段)为当前停止线的退出lane，同时，该条lane也是下一条停止线的进入lane，下一条停止线后方的lane(第二路段)为下一条停止线的退出lane。
根据本公开的实施例，如图4所示，本公开实施例的交通信号灯运行状态确定方法将路口信息作为与高精地图的交互单位，具体包括如下操作：
首先从定位系统中获取无人驾驶车辆当前位置，以确定当前所在的路口。再结合导航信息和高精地图(HD Map)搜索并记录感兴趣路口的全部信息，如路口内的局部导航路径、局部导航路径途经的全部停止线(目标停止线)、以及与其相关联的交通信号灯信息(目标交通信号灯组)。
如图3所示路口，在无人驾驶过程中，在路口内的局部导航路径(图中箭头所示)为左转路线，提示当前场景为左转场景，无人车在左转场景中会经历两段直行路线(图中所示第一路段和第二路段)，并先后途经两条停止线(图中所示当前停止线和下一条停止线，其中下一条停止线为虚拟停止线)，结合高精地图确定与这两条停止线绑定的交通信号灯组，如图中所示绑定关系。在第一次搜索到感兴趣路口时，会记录并维护上述局部导航路径途经的两条停止线，和与之相关联的交通信号灯。此信息不受无人车在路口内所处位置的变化而改变，进而与无人车在路口内的行为发生解耦。无人车在行驶过程中，会持续关注上述两组交通信号灯，在感知视野范围内进行感知和状态积累。
进一步地，通过定位系统负责提供无人车的实时位置，之后可根据无人车的实时位置确定上述多个目标交通信号灯组的优先级，具体而言，可首先根据车辆当前位置判断车辆当前位置所在区域所属的车道类型，例如是属于进入车道、或是属于退出车道、或是兼做进入车道和退出车道。之后，再根据车辆当前位置所在区域所属的车道类型，确定至少一个目标交通信号灯组的优先级。
具体地，在根据车辆当前位置判断车辆当前位置所在区域所属的车道类型仅为进入车道或仅为退出车道的情况下，通过下述方法确定多个目标交通信号灯组的优先级。
如图4所示，在车辆当前位置位于头部停止线(车辆导航路径途经的第一条停止线)的进入车道的情况下，车辆当前位置所在区域所属的车道类型仅为进入lane，确定至少一个目标交通信号灯组中，头部灯组的优先级高于其他目标交通信号灯组的优 先级，其中，头部灯组为与头部停止线绑定的交通信号灯组。即，这种情况下优先关注前序停止线关联的灯组。
如图4所示，在车辆当前位置位于尾部停止线(车辆导航路径途经的最后一条停止线)的退出车道的情况下，车辆当前位置所在区域所属的车道类型仅为退出lane，确定至少一个目标交通信号灯组中，尾部灯组的优先级高于其他目标交通信号灯组的优先级，其中，尾部灯组为与尾部停止线绑定的交通信号灯组。即，这种情况下优先关注后序停止线关联的灯组。
根据本公开的实施例，为了保证信息的准确度，在无人车处于进入lane的情况下，需要重点关注进入lane对应的停止线相关联的交通信号灯；当处于退出lane的情况下，需要重点关注退出lane对应的停止线相关联的交通信号灯。因此，在车辆当前位置位于头部停止线的进入车道的情况下，头部灯组的优先级最高；在车辆当前位置位于尾部停止线的退出车道的情况下，尾部灯组的优先级最高。
根据本公开的实施例，在车辆导航路径途经的停止线大于等于两条的情况下，在任一组连续两条停止线之间的车道兼做进入车道和退出车道，即，同时作为前序停止线的退出车道和后序停止线的进入车道。在这种场景下，通过下述方法确定多个目标交通信号灯组的优先级。
如图4所示，具体地，在至少一条目标停止线包括连续的两条停止线：第一停止线和第二停止线，且车辆当前位置位于第一停止线和第二停止线之间区域的情况下，车辆当前位置所在区域兼做前序停止线的退出lane和后序停止线的进入lane，此时执行下述操作：
首先，判断车辆所在车道的相对位置，即判断无人车当前位于这条lane前半程还是后半程，具体可通过计算车辆当前位置与第一停止线之间的第一距离，以及车辆当前位置与第二停止线之间的第二距离确定。
之后，根据第一距离和第二距离确定第一灯组和第二灯组的优先级。
在第一距离小于等于第二距离的情况下，判断无人车当前位于这条lane前半程，确定第一灯组的优先级大于第二灯组的优先级，即，这种情况下优先关注前序停止线关联的灯组。
在第一距离大于第二距离的情况下，判断无人车当前位于这条lane后半程，确定第二灯组的优先级大于第一灯组的优先级。即，这种情况下优先关注后序停止线关联 的灯组。
例如，如图3所示的路口，无人配送车在左转场景下需关注的目标交通信号灯组有两个：灯组A和灯组B，其中灯组A与图3所示的当前停止线绑定，灯组B与图3所示的下一条停止线绑定。这种场景下，灯组A可作为第一灯组，灯组B可作为第二灯组。可采用本公开实施例的上述方法，确定第一灯组和第二灯组的优先级。
再例如，在某些复杂路口，无人配送车在穿过马路的过程中需要关注的目标交通信号灯组有三个，灯组A、灯组B、灯组C，分别绑定停止线A、停止线B、停止线C，其中导航路径依次连续经过停止线A、停止线B、停止线C。当无人车当前位置位于停止线A和停止线B之间的情况下，停止线A和停止线B分别作为第一停止线和第二停止线，灯组A、灯组B分别作为第一灯组和第二灯组；当无人车当前位置位于停止线B和停止线C之间的情况下，停止线B和停止线C分别作为第一停止线和第二停止线，灯组B、灯组C分别作为第一灯组和第二灯组。上述任一场景下，均可采用本公开实施例的上述方法确定第一灯组和第二灯组的优先级。
根据本公开的实施例，车辆当前位置所在区域兼做前序停止线的退出lane和后序停止线的进入lane的情况下，无人车在路口内行驶过程中会发生切灯行为，在该条lane的前半段可能主要起到退出lane的作用，最关注上一条停止线关联的交通信号灯，在该条lane的后半段可能主要起到进入lane的作用，最关注下一条停止线相关联的交通信号灯。因此，通过本公开实施例的上述方法确定出交通信号灯组的优先级，符合无人车切灯行为的关注逻辑，优先向下游决策系统推送其最需要关注灯组的状态，进一步避免发生与下游模块所期望的交通信号灯感知状态不一致问题。
以下，结合图3所示场景，对上述根据无人车的实时位置确定多个目标交通信号灯组的优先级的方法进行示例性说明。
例如，如图3所示的路口，无人配送车在左转场景下需关注的目标交通信号灯组有两个：灯组A和灯组B，其中灯组A与图3所示的当前停止线绑定，灯组B与图3所示的下一条停止线绑定。当无人车位于当前停止线前时，所处lane为进入lane，此时主车关于交通信号灯的关注顺序是灯组A-灯组B的顺序；当无人车位于当前停止线后且下一条停止线前的第一路段时，所处lane既是进入lane，同时也是退出lane，需要结合定位信息考虑主车对于所处lane的相对位置，如果主车位于该条lane的前半程，则应关注灯组A-灯组B顺序。如果主车位于该条lane的后半程，则应关注灯组B-灯 组A顺序；当无人车位于下一条停止线后的第二路段时，所处lane为退出lane，此时主车关于交通信号灯的关注顺序是灯组B-灯组A的顺序。
根据本公开的实施例，进一步地，在车辆导航路径途经的停止线大于两条、需关注的目标交通信号灯组有两个以上的情形时，可采用本公开实施例的下述方法，进一步确定灯组的优先级。
根据本公开的实施例，具体地，根据车辆当前位置确定至少一个目标交通信号灯组的优先级可采用如下方法：
在至少一条目标停止线包括第一停止线和第二停止线、且车辆当前位置位于第一停止线和第二停止线之间区域的情况下，确定至少一个目标交通信号灯组中，第一灯组和第二灯组的优先级高于其他目标交通信号灯组的优先级，其中，第一停止线和第二停止线为：至少一条目标停止线中，车辆导航路径连续途经的两条停止线，第一灯组为与第一停止线绑定的交通信号灯组，第二灯组为与第二停止线绑定的交通信号灯组。
根据本公开的实施例，上述优先级算法可应用在需关注的目标交通信号灯组有两个以上的情形。例如，在某些复杂路口，无人车在过马路的过程中，可能还需要在马路中间的安全导航区域内暂停以感知交通信号灯状态，在某些行驶场景下(如转弯)，导航途经的停止线可能会有两条以上，进一步需关注的交通信号灯组也有两组以上。
上述场景下，第一停止线和第二停止线为车辆导航路径连续途经的两条停止线，当无人车位于第一停止线和第二停止线之间区域的情况下，第一停止线和第二停止线对应的交通信号灯组是当前最需要关注的，因此第一灯组和第二灯组的优先级高于其他目标交通信号灯组的优先级。
根据本公开的实施例，上述确定交通信号灯优先级的方法从车端算力资源使用角度出发，按照优先级从高到低的顺序动态性的选择关注区域，保证了无人车在当前位置行驶时能够关注到必须要照看的交通信息和最大容量的进行全局场景理解。
基于上述交通信号灯运行状态确定方法，本公开还提供了一种交通信号灯运行状态确定装置。以下将结合图5对该装置进行详细描述。
图5示意性示出了根据本公开实施例的交通信号灯运行状态确定装置的结构框图。
如图5所示，该实施例的交通信号灯运行状态确定装置500包括第一确定模块501、 读取模块502、第二确定模块503。
其中，第一确定模块501，用于将车辆所在当前路口内的全量停止线中，车辆导航路径途经的至少一条停止线确定为目标停止线；
读取模块502，用于从高精地图中读取与至少一条目标停止线绑定的至少一个交通信号灯组，作为目标交通信号灯组，其中，一条目标停止线关联一个交通信号灯组，一个交通信号灯组中包括至少一个交通信号灯；
第二确定模块503，用于确定至少一个目标交通信号灯组的运行状态，以便将运行状态发送至决策系统后，决策系统根据运行状态指导车辆通行。
通过本公开实施例的上述第一确定模块501关注路口内导航路径途经的全部停止线，并进一步通过读取模块502关注与其相关联的交通信号灯组，相比于基于单条停止线的交通信号灯关注策略，能够提升无人车全局场景理解能力，在路口感知范围内持续感知路口内全场景的交通信号灯。因此，通过第二确定模块503发送给下游模块的交通信号灯状态信息不受无人车在路口内所处位置的变化而改变，进而与无人车在路口内的行为发生解耦，不会发生与下游模块所期望的交通信号灯感知状态不一致问题。同时，无人车在行驶过程中，会持续关注多组交通信号灯，在感知视野范围内进行感知和状态积累，能够提升无人车全局场景理解能力，提前累计持续时长等交通信号灯状态，促进下游决策模块基于路口全场景的交通信号灯感知结果进行更精准更全面的决策，提高了无人驾驶通行的安全性。
根据本公开的实施例，其中，第二确定模块503包括第一确定子模块、第二确定子模块。
其中，第一确定子模块，用于根据车辆当前位置确定至少一个目标交通信号灯组的优先级；
第二确定子模块，用于根据至少一个目标交通信号灯组的优先级，确定至少一个目标交通信号灯组的运行状态。
根据本公开的实施例，其中，第一确定子模块包括第一确定单元，用于在至少一条目标停止线包括第一停止线和第二停止线、且车辆当前位置位于第一停止线和第二停止线之间区域的情况下，确定至少一个目标交通信号灯组中，第一灯组和第二灯组的优先级高于其他目标交通信号灯组的优先级，其中，第一停止线和第二停止线为：至少一条目标停止线中，车辆导航路径连续途经的两条停止线，第一灯组为与第一停 止线绑定的交通信号灯组，第二灯组为与第二停止线绑定的交通信号灯组。
根据本公开的实施例，其中，第一确定子模块还包括计算单元、第二确定单元。
其中，计算单元，用于在至少一条目标停止线包括第一停止线和第二停止线、且车辆当前位置位于第一停止线和第二停止线之间区域的情况下，计算车辆当前位置与第一停止线之间的第一距离，以及车辆当前位置与第二停止线之间的第二距离；
第二确定单元，用于根据第一距离和第二距离确定第一灯组和第二灯组的优先级。
根据本公开的实施例，其中，第二确定单元包括第一确定子单元，用于在第一距离小于等于第二距离的情况下，确定第一灯组的优先级大于第二灯组的优先级。
根据本公开的实施例，其中，第二确定单元包括第二确定子单元，用于在第一距离大于第二距离的情况下，确定第二灯组的优先级大于第一灯组的优先级。
根据本公开的实施例，其中，第一确定子模块包括第三确定单元，用于在车辆当前位置位于头部停止线的进入车道的情况下，确定至少一个目标交通信号灯组中，头部灯组的优先级高于其他目标交通信号灯组的优先级，其中，头部停止线为：至少一条目标停止线中，车辆导航路径途经的第一条停止线，头部灯组为与头部停止线绑定的交通信号灯组。
根据本公开的实施例，其中，第一确定子模块包括第四确定单元，用于在车辆当前位置位于尾部停止线的退出车道的情况下，确定至少一个目标交通信号灯组中，尾部灯组的优先级高于其他目标交通信号灯组的优先级，其中，尾部停止线为：至少一条目标停止线中，车辆导航路径途经的最后一条停止线，尾部灯组为与尾部停止线绑定的交通信号灯组。
根据本公开的实施例，第一确定模块501、读取模块502、第二确定模块503中的任意多个模块可以合并在一个模块中实现，或者其中的任意一个模块可以被拆分成多个模块。或者，这些模块中的一个或多个模块的至少部分功能可以与其他模块的至少部分功能相结合，并在一个模块中实现。根据本公开的实施例，第一确定模块501、读取模块502、第二确定模块503中的至少一个可以至少被部分地实现为硬件电路，例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC)，或可以通过对电路进行集成或封装的任何其他的合理方式等硬件或固件来实现，或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或者，第一确定模块501、读取模块502、第 二确定模块503中的至少一个可以至少被部分地实现为计算机程序模块，当该计算机程序模块被运行时，可以执行相应的功能。
图6示意性示出了根据本公开实施例的适于实现交通信号灯运行状态确定方法的电子设备的方框图。
如图6所示，根据本公开实施例的电子设备600包括处理器601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储部分608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。处理器601例如可以包括通用微处理器(例如CPU)、指令集处理器和/或相关芯片组和/或专用微处理器(例如，专用集成电路(ASIC))等等。处理器601还可以包括用于缓存用途的板载存储器。处理器601可以包括用于执行根据本公开实施例的方法流程的不同动作的单一处理单元或者是多个处理单元。
在RAM 603中，存储有电子设备600操作所需的各种程序和数据。处理器601、ROM 602以及RAM 603通过总线604彼此相连。处理器601通过执行ROM 602和/或RAM 603中的程序来执行根据本公开实施例的方法流程的各种操作。需要注意，所述程序也可以存储在除ROM 602和RAM 603以外的一个或多个存储器中。处理器601也可以通过执行存储在所述一个或多个存储器中的程序来执行根据本公开实施例的方法流程的各种操作。
根据本公开的实施例，电子设备600还可以包括输入/输出(I/O)接口605，输入/输出(I/O)接口605也连接至总线604。电子设备600还可以包括连接至I/O接口605的以下部件中的一项或多项：包括键盘、鼠标等的输入部分606；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分607；包括硬盘等的存储部分608；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分609。通信部分609经由诸如因特网的网络执行通信处理。驱动器610也根据需要连接至I/O接口605。可拆卸介质611，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器610上，以便于从其上读出的计算机程序根据需要被安装入存储部分608。
本公开还提供了一种计算机可读存储介质，该计算机可读存储介质可以是上述实施例中描述的设备/装置/系统中所包含的；也可以是单独存在，而未装配入该设备/装置/系统中。上述计算机可读存储介质承载有一个或者多个程序，当上述一个或者多个程序被执行时，实现根据本公开实施例的方法。
根据本公开的实施例，计算机可读存储介质可以是非易失性的计算机可读存储介质，例如可以包括但不限于：便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。例如，根据本公开的实施例，计算机可读存储介质可以包括上文描述的ROM 602和/或RAM 603和/或ROM 602和RAM 603以外的一个或多个存储器。
本公开的实施例还包括一种计算机程序产品，其包括计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。当计算机程序产品在计算机系统中运行时，该程序代码用于使计算机系统实现本公开实施例所提供的交通信号灯运行状态确定方法。
在该计算机程序被处理器601执行时执行本公开实施例的系统/装置中限定的上述功能。根据本公开的实施例，上文描述的系统、装置、模块、单元等可以通过计算机程序模块来实现。
在一种实施例中，该计算机程序可以依托于光存储器件、磁存储器件等有形存储介质。在另一种实施例中，该计算机程序也可以在网络介质上以信号的形式进行传输、分发，并通过通信部分609被下载和安装，和/或从可拆卸介质611被安装。该计算机程序包含的程序代码可以用任何适当的网络介质传输，包括但不限于：无线、有线等等，或者上述的任意合适的组合。
在这样的实施例中，该计算机程序可以通过通信部分609从网络上被下载和安装，和/或从可拆卸介质611被安装。在该计算机程序被处理器601执行时，执行本公开实施例的系统中限定的上述功能。根据本公开的实施例，上文描述的系统、设备、装置、模块、单元等可以通过计算机程序模块来实现。
根据本公开的实施例，可以以一种或多种程序设计语言的任意组合来编写用于执行本公开实施例提供的计算机程序的程序代码，具体地，可以利用高级过程和/或面向对象的编程语言、和/或汇编/机器语言来实施这些计算程序。程序设计语言包括但不限于诸如Java，C++，python，“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、部分在远程计算设备上执行、或 者完全在远程计算设备或服务器上执行。在涉及远程计算设备的情形中，远程计算设备可以通过任意种类的网络，包括局域网(LAN)或广域网(WAN)，连接到用户计算设备，或者，可以连接到外部计算设备(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，上述模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图或流程图中的每个方框、以及框图或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
本领域技术人员可以理解，本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合或/或结合，即使这样的组合或结合没有明确记载于本公开中。特别地，在不脱离本公开精神和教导的情况下，本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合。所有这些组合和/或结合均落入本公开的范围。
以上对本公开的实施例进行了描述。但是，这些实施例仅仅是为了说明的目的，而并非为了限制本公开的范围。尽管在以上分别描述了各实施例，但是这并不意味着各个实施例中的措施不能有利地结合使用。本公开的范围由所附权利要求及其等同物限定。不脱离本公开的范围，本领域技术人员可以做出多种替代和修改，这些替代和修改都应落在本公开的范围之内。

Claims (12)

  1. 一种交通信号灯运行状态确定方法，包括：
    将车辆所在当前路口内的全量停止线中，车辆导航路径途经的至少一条停止线确定为目标停止线；
    从高精地图中读取与至少一条所述目标停止线绑定的至少一个交通信号灯组，作为目标交通信号灯组，其中，一条所述目标停止线关联一个交通信号灯组，一个所述交通信号灯组中包括至少一个交通信号灯；
    确定至少一个所述目标交通信号灯组的运行状态，以便将所述运行状态发送至决策系统后，所述决策系统根据所述目标交通信号灯组的运行状态指导车辆通行。
  2. 根据权利要求1所述的方法，其中，所述确定至少一个所述目标交通信号灯组的运行状态包括：
    根据车辆当前位置确定至少一个所述目标交通信号灯组的优先级；
    根据至少一个所述目标交通信号灯组的优先级，确定至少一个所述目标交通信号灯组的运行状态。
  3. 根据权利要求2所述的方法，其中，所述根据车辆当前位置确定至少一个所述目标交通信号灯组的优先级包括：
    在至少一条所述目标停止线包括第一停止线和第二停止线、且所述车辆当前位置位于所述第一停止线和所述第二停止线之间区域的情况下，确定至少一个所述目标交通信号灯组中，第一灯组和第二灯组的优先级高于其他目标交通信号灯组的优先级，其中，所述第一停止线和所述第二停止线为：至少一条所述目标停止线中，所述车辆导航路径连续途经的两条停止线，所述第一灯组为与所述第一停止线绑定的交通信号灯组，所述第二灯组为与所述第二停止线绑定的交通信号灯组。
  4. 根据权利要求3所述的方法，其中，所述根据车辆当前位置确定至少一个所述目标交通信号灯组的优先级还包括：
    在至少一条所述目标停止线包括所述第一停止线和所述第二停止线、且所述车辆当前位置位于所述第一停止线和所述第二停止线之间区域的情况下，计算所述车辆当 前位置与所述第一停止线之间的第一距离，以及所述车辆当前位置与所述第二停止线之间的第二距离；
    根据所述第一距离和所述第二距离确定所述第一灯组和所述第二灯组的优先级。
  5. 根据权利要求4所述的方法，其中，所述根据所述第一距离和所述第二距离确定所述第一灯组和所述第二灯组的优先级包括：
    在所述第一距离小于等于所述第二距离的情况下，确定所述第一灯组的优先级大于所述第二灯组的优先级。
  6. 根据权利要求4所述的方法，其中，所述根据所述第一距离和所述第二距离确定所述第一灯组和所述第二灯组的优先级包括：
    在所述第一距离大于所述第二距离的情况下，确定所述第二灯组的优先级大于所述第一灯组的优先级。
  7. 根据权利要求2所述的方法，其中，所述根据车辆当前位置确定至少一个所述目标交通信号灯组的优先级包括：
    在所述车辆当前位置位于头部停止线的进入车道的情况下，确定至少一个所述目标交通信号灯组中，头部灯组的优先级高于其他目标交通信号灯组的优先级，其中，所述头部停止线为：至少一条所述目标停止线中，所述车辆导航路径途经的第一条停止线，所述头部灯组为与所述头部停止线绑定的交通信号灯组。
  8. 根据权利要求2所述的方法，其中，所述根据车辆当前位置确定至少一个所述目标交通信号灯组的优先级包括：
    在所述车辆当前位置位于尾部停止线的退出车道的情况下，确定至少一个所述目标交通信号灯组中，尾部灯组的优先级高于其他目标交通信号灯组的优先级，其中，所述尾部停止线为：至少一条所述目标停止线中，所述车辆导航路径途经的最后一条停止线，所述尾部灯组为与所述尾部停止线绑定的交通信号灯组。
  9. 一种交通信号灯运行状态确定装置，包括：
    第一确定模块，用于将车辆所在当前路口内的全量停止线中，车辆导航路径途经的至少一条停止线确定为目标停止线；
    读取模块，用于从高精地图中读取与至少一条所述目标停止线绑定的至少一个交通信号灯组，作为目标交通信号灯组，其中，一条所述目标停止线关联一个交通信号灯组，一个所述交通信号灯组中包括至少一个交通信号灯；
    第二确定模块，用于确定至少一个所述目标交通信号灯组的运行状态，以便将所述运行状态发送至决策系统后，所述决策系统根据所述目标交通信号灯组的运行状态指导车辆通行。
  10. 一种电子设备，包括：
    一个或多个处理器；
    存储装置，用于存储一个或多个程序，
    其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器执行根据权利要求1～8中任一项所述的方法。
  11. 一种计算机可读存储介质，其上存储有可执行指令，该指令被处理器执行时使处理器执行根据权利要求1～8中任一项所述的方法。
  12. 一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现根据权利要求1～8中任一项所述的方法。
PCT/CN2023/089926 2022-10-21 2023-04-21 交通信号灯运行状态确定方法及装置、电子设备 WO2024082588A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211299558.5 2022-10-21
CN202211299558.5A CN115662172A (zh) 2022-10-21 2022-10-21 交通信号灯运行状态确定方法及装置、电子设备

Publications (1)

Publication Number Publication Date
WO2024082588A1 true WO2024082588A1 (zh) 2024-04-25

Family

ID=84991528

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/089926 WO2024082588A1 (zh) 2022-10-21 2023-04-21 交通信号灯运行状态确定方法及装置、电子设备

Country Status (2)

Country Link
CN (1) CN115662172A (zh)
WO (1) WO2024082588A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115662172A (zh) * 2022-10-21 2023-01-31 北京京东乾石科技有限公司 交通信号灯运行状态确定方法及装置、电子设备

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019079941A1 (en) * 2017-10-23 2019-05-02 Bayerische Motoren Werke Aktiengesellschaft METHOD AND APPARATUS FOR DETERMINING A DRIVING STRATEGY OF A VEHICLE
CN110889965A (zh) * 2019-11-22 2020-03-17 北京京东乾石科技有限公司 无人车控制方法、装置和无人车
CN111785056A (zh) * 2020-07-07 2020-10-16 何世鸿 提示驾驶员到达交通信号灯关联停止线前时信号灯状态
CN112406876A (zh) * 2019-08-23 2021-02-26 比亚迪股份有限公司 车辆及其控制方法、控制装置
WO2021164018A1 (zh) * 2020-02-21 2021-08-26 华为技术有限公司 自动驾驶控制方法、信息处理方法、装置及系统
CN114170816A (zh) * 2021-12-10 2022-03-11 上海万位科技有限公司 一种车辆驾驶提示方法及装置
CN115083190A (zh) * 2022-06-17 2022-09-20 东风汽车集团股份有限公司 多车道交通路口的自动驾驶系统及方法
CN115662172A (zh) * 2022-10-21 2023-01-31 北京京东乾石科技有限公司 交通信号灯运行状态确定方法及装置、电子设备

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019079941A1 (en) * 2017-10-23 2019-05-02 Bayerische Motoren Werke Aktiengesellschaft METHOD AND APPARATUS FOR DETERMINING A DRIVING STRATEGY OF A VEHICLE
CN112406876A (zh) * 2019-08-23 2021-02-26 比亚迪股份有限公司 车辆及其控制方法、控制装置
CN110889965A (zh) * 2019-11-22 2020-03-17 北京京东乾石科技有限公司 无人车控制方法、装置和无人车
WO2021164018A1 (zh) * 2020-02-21 2021-08-26 华为技术有限公司 自动驾驶控制方法、信息处理方法、装置及系统
CN111785056A (zh) * 2020-07-07 2020-10-16 何世鸿 提示驾驶员到达交通信号灯关联停止线前时信号灯状态
CN114170816A (zh) * 2021-12-10 2022-03-11 上海万位科技有限公司 一种车辆驾驶提示方法及装置
CN115083190A (zh) * 2022-06-17 2022-09-20 东风汽车集团股份有限公司 多车道交通路口的自动驾驶系统及方法
CN115662172A (zh) * 2022-10-21 2023-01-31 北京京东乾石科技有限公司 交通信号灯运行状态确定方法及装置、电子设备

Also Published As

Publication number Publication date
CN115662172A (zh) 2023-01-31

Similar Documents

Publication Publication Date Title
US20200262448A1 (en) Decision method, device, equipment in a lane changing process and storage medium
CN110160552B (zh) 导航信息确定方法、装置、设备和存储介质
EP3709281A1 (en) Vehicle track prediction method and device, storage medium and terminal device
US11887479B2 (en) Parking management system, vehicle control device, and control center
RU2682151C1 (ru) Устройство определения окружения, аппаратура содействия при движении и способ определения окружения
RU2682092C1 (ru) Устройство планирования вождения, аппаратура содействия при движении и способ планирования вождения
JP2021536593A (ja) 道路の交差点の検証
WO2024060609A1 (zh) 信息交互方法及装置、电子设备和计算机可读存储介质
US20220163341A1 (en) Navigation system
WO2024082588A1 (zh) 交通信号灯运行状态确定方法及装置、电子设备
CN110426050A (zh) 地图匹配纠正方法、装置、设备和存储介质
CN109916414B (zh) 地图匹配方法、装置、设备和介质
CN112572424A (zh) 基于障碍物识别的车辆控制方法、装置、设备和介质
CN109782776B (zh) 无人车的车道选择方法、装置及存储介质
CN113747364B (zh) 一种基于5g网络的智能交通导航方法、设备及介质
US20150185020A1 (en) Compatibility based resource matching
CN114485706A (zh) 一种路线规划方法、装置、存储介质及电子设备
CN117253361A (zh) 车辆行驶轨迹信息的生成方法及装置
JP5918479B2 (ja) 経路案内装置
CN109934496A (zh) 区域间通行影响确定方法、装置、设备和介质
US20130060463A1 (en) Method, apparatus and computer program for selecting and displaying route favorable to driver
CN114608599A (zh) 导航路径生成方法、装置、电子设备及存储介质
CN114858176A (zh) 一种基于自动驾驶的路径导航方法及装置
CN115112138A (zh) 轨迹规划信息生成方法、装置、电子设备以及存储介质
CN114119951A (zh) 车信标注的方法、装置、设备以及存储介质