Lane selection method and device, equipment and storage medium

Abstract

The invention discloses a lane selection method, device and equipment and a storage medium, and relates to the technical field of intelligent driving, and the method comprises the steps: obtaining special lane information from the driving information of a target vehicle; a special lane corresponding to the special lane information is a special lane of a special vehicle, and the special lane is a lane provided with a stop station of the special vehicle; and generating a lane selection strategy according to the special lane information, and selecting a to-be-driven target lane for the target vehicle based on the lane selection strategy. In the lane selection strategy generation and lane selection process, the special lane information provided with the special vehicle parking station is fully considered, the predictability of the driving behavior of the special vehicle is improved, the problem that the vehicle is forced to brake or stop after the vehicle runs or changes the lane according to the selected lane can be avoided, and the driving safety of the vehicle is improved. And invalid lane changing is reduced, and the passing efficiency of the vehicle is improved, so that the driving experience of the user using the intelligent navigation auxiliary function is improved.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a lane selection method, device, equipment and storage medium. Background Technology

[0002] Navigated on Autopilot (NOA) is an intelligent driving assistance function that integrates adaptive cruise control and lane keeping assist. It can use connected maps to plan navigation and, under the driver's supervision, can automatically change lanes, enter and exit ramps, and select lanes according to the planned navigation route, significantly reducing the driver's workload.

[0003] Currently, NOA (Noise, Arrival, and Control) relies on the output of large models for key driving aspects such as perception, localization, decision-making, and planning. However, these decisions regarding vehicle behavior don't always align with the driver's optimal operating habits in real-world traffic scenarios. This is because large models lack the ability to anticipate the driving behavior of special vehicles, leading to inaccurate lane selection during lane changes and potentially resulting in ineffective lane changes that impact traffic efficiency. For example, in urban navigation scenarios, to improve efficiency, NOA may sometimes change lanes into lanes occupied by special vehicles like buses or their dedicated lanes. If a bus stop is ahead, the vehicle will be forced to brake or stop as the bus pulls in, resulting in an ineffective lane change. This not only affects traffic efficiency but also increases safety risks associated with lane changes, negatively impacting the user's driving experience.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a lane selection method, device, equipment, and storage medium, which aims to solve the technical problem that intelligent navigation assistance functions that rely on large model decisions lack foresight regarding the driving behavior of special vehicles, resulting in inaccurate lane selection. Furthermore, after the vehicle changes lanes based on the selected lane, it is prone to braking or stopping, thus leading to invalid lane changes.

[0006] To achieve the above objectives, this application proposes a lane selection method, which includes: Obtain special lane information from the driving information of the target vehicle; wherein, the special lane corresponding to the special lane information is a dedicated lane for special vehicles, and the special lane is a lane with a stop station for the special vehicle. A lane selection strategy is generated based on the specific lane information; The target lane to be driven in is selected for the target vehicle according to the lane selection strategy.

[0007] In an embodiment, the step of generating a lane selection strategy according to the special lane information comprises: determining a positional relationship between a current lane of the target vehicle and the special lane according to the special lane information; determining whether a current driving time of the target vehicle is within a time period of the special lane, and obtaining a determination result; determining a driving scenario in which the target vehicle is located based on the positional relationship and the determination result, and generating a lane selection strategy based on the driving scenario.

[0008] In an embodiment, the step of generating a lane selection strategy based on the driving scenario comprises: determining a selectable lane based on the driving scenario; obtaining determination conditions corresponding to the driving scenario, and determination logic of each of the determination conditions; combining the determination logic, the determination conditions, and the selectable lane to generate a lane selection strategy.

[0009] In an embodiment, the driving information comprises navigation information, the special lane information comprises station information of the stop station, and the driving scenario comprises a target driving scenario; the target driving scenario indicates that a current lane of the target vehicle is an adjacent lane of the special lane, and a current driving time of the target vehicle is not within a time period of the special lane; if the driving scenario in which the target vehicle is located is the target driving scenario, the lane selection method further comprises: determining a relative distance between the target vehicle and a front station according to the navigation information and the station information; a target determination condition corresponding to the target driving scenario comprises: whether there is a same-direction straight lane on a left side of the current lane of the target vehicle, whether there is a right-turn demand of the target vehicle in a target area in a case where the relative distance is less than or equal to a preset distance, and whether there is a slow vehicle or the special vehicle in the selectable lane; the slow vehicle has a vehicle speed less than or equal to a current vehicle speed of the target vehicle, the target area comprises a first area between a current position of the target vehicle and the front station, and the selectable lane comprises at least one of the current lane of the target vehicle, the special lane, and an adjacent lane of the special lane. The target determination condition corresponds to target determination logic, including: if there is no same-direction straight lane on the left side of the current lane of the target vehicle, and there is no right-turn demand of the target vehicle in the first area, in the case that there is a slow vehicle or a special vehicle in front of the right side of the target vehicle in the optional lane, the right side lane in the adjacent lane is not allowed to be selected, and in the case that there is a slow vehicle or a special vehicle in front of the target vehicle in the optional lane, and there is no slow vehicle or special vehicle in front of the right side of the target vehicle in the optional lane, the right side lane in the adjacent lane is allowed to be selected.

[0010] In an embodiment, the lane selection strategy includes a determination condition and determination logic; the step of selecting a target lane to be traveled by the target vehicle from the optional lanes according to the lane selection strategy includes: making a decision on each of the optional lanes according to the determination condition and the determination logic; selecting a target lane to be traveled by the target vehicle based on the decision results of each of the optional lanes.

[0011] In an embodiment, the driving information includes at least one of a networked map and a driving image; the step of obtaining special lane information from the driving information of the target vehicle includes: in the case that the driving information includes a networked map, obtaining attribute information of the networked map; the attribute information includes a lane type label; in the case that the driving information includes a driving image, identifying at least one of lane identification information and traffic sign information from the driving image; identifying special lane information according to at least one of the attribute information, the lane identification information and the traffic sign information.

[0012] In an embodiment, in the case that the driving information includes a driving image, after the step of identifying at least one of lane identification information and traffic sign information from the driving image, the method further includes: initializing a time threshold of the lane identification information and / or the traffic sign information; the time threshold is used to identify the validity period of the lane identification information and / or the traffic sign information.

[0013] In addition, to achieve the above-mentioned purpose, the application further provides a lane selection device, which includes: an information acquisition module, configured to obtain special lane information from driving information of a target vehicle; wherein the special lane corresponding to the special lane information is a special lane for a special vehicle, and the special lane is a lane provided with a stop site of the special vehicle; The strategy generation module is configured to generate a lane selection strategy according to the special lane information. The lane selection module is configured to select a target lane to be traveled by the target vehicle according to the lane selection strategy.

[0014] In addition, to achieve the above object, the present application further provides a lane selection device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the lane selection method as described above.

[0015] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the lane selection method as described above.

[0016] In addition, to achieve the above object, the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the lane selection method as described above.

[0017] The one or more technical solutions provided by the present application have at least the following technical effects: By obtaining the special lane information and the special vehicle information from the driving information of the target vehicle, generating the lane selection strategy according to the special lane information and the special vehicle information, and selecting the target lane to be traveled by the target vehicle from the selectable lanes according to the generated lane selection strategy, the special lane information of the special vehicle parking site is fully considered in the process of lane selection strategy generation and lane selection, the predictability of the driving behavior of the special vehicle is improved, the problem of forced braking or following stop after the vehicle travels or changes lanes according to the selected lane can be avoided, the generation of invalid lane changing is reduced, the traffic efficiency of the vehicle is improved, and the driving experience of the user using the intelligent navigation assistance function is improved. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application together with the specification.

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0020] Figure 1A flowchart provided by the first embodiment of the lane selection method of the present application; Figure 2 A module structure diagram of the lane selection device of the embodiment of the present application; Figure 3 A device structure diagram of the hardware running environment involved in the lane selection method of the embodiment of the present application.

[0021] The object implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0023] In order to better understand the technical solutions of the present application, the following will be described in detail in conjunction with the accompanying drawings and specific embodiments.

[0024] The main solution of the embodiment of the present application is: obtaining special lane information from the driving information of the target vehicle, determining the positional relationship between the target vehicle and the special lane such as the bus lane, thereby identifying the driving scene where the vehicle is located, determining the selectable lane and the lane selection strategy according to the driving scene where the target vehicle is located, selecting a target lane to be driven from the selectable lane according to the determined lane selection strategy, avoiding the problem of braking or following stop caused by the target vehicle after changing lane according to the selected lane, and reducing the generation of invalid lane change.

[0025] In the present embodiment, for the convenience of description, the intelligent navigation assistance (NOA) system is taken as the execution subject for description.

[0026] In the prior art, in order to improve response speed, optimize ability and cope with long-tail problem scenes that are difficult to cope with by traditional handwriting rules, the NOA system mostly relies on large models to complete perception, positioning, decision-making and planning tasks. For example, a large model is trained by relying on a large amount of driving scene training data, so that the large model has the ability to select a lane and make a decision on the timing of lane changing during piloting. The output relying on the large model has a black box characteristic that is difficult to explain, which is specifically manifested in that the decision on the vehicle behavior is not always in line with the optimal practice of the driver. For example, in the process of urban piloting, in order to improve the passing efficiency of the vehicle, the NOA will guide the vehicle to change lanes to the lane where the special vehicle such as a bus is located or the special lane thereof. At this time, if there is a bus stop in front, after the vehicle changes lanes, the vehicle will be forced to brake or stop following the bus when the bus stops at the stop, which is the logic of the optimal path or the highest passing time efficiency output by the large model. However, the subsequent braking or stopping of the vehicle after changing lanes to the lane where the bus is located causes the vehicle to have invalid lane changing, which not only affects the passing efficiency of the vehicle, but also increases the safety risk of lane changing and affects the driving experience of the user.

[0027] Therefore, the present application provides a solution. By identifying special lanes such as bus lanes or the rightmost lane where a bus stop is located, the driving situation of the vehicle is classified according to the positional relationship between the vehicle and the special lane, whether the current driving time of the vehicle is within the restricted time period of the special lane, etc. The lane selection strategy corresponding to the driving scene is comprehensively judged, so that the NOA system can select the best lane that is conducive to passing according to the driving scene of the vehicle, in order to avoid the braking or stopping problem after lane changing.

[0028] From the above embodiments, it can be seen that by obtaining special lane information, the present application classifies the scene of the vehicle equipped with the NOA system, generates different lane selection strategies for different scenes, and selects the best lane from the available lanes as the target lane to be driven, which can improve the braking or stopping problem caused by bus stopping when the vehicle changes lanes to the special lane such as the bus lane or the rightmost lane, thereby reducing the generation of invalid lane changing.

[0029] It should be noted that the execution subject of the present embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a lane selection device, a NOA system module, etc. that can realize the above functions. The present embodiment and each of the following embodiments will be described below taking the NOA system module as an example.

[0030] Based on this, the present application provides a lane selection method applied to an intelligent piloting assistance NOA system, which refers to Figure 1 , Figure 1A flowchart of a first embodiment of a lane selection method provided by the present application is shown.

[0031] In this embodiment, the lane selection method includes steps S10-S30: S10, obtaining special lane information from driving information of a target vehicle; wherein the special lane information corresponds to a special lane that is a special lane for a special vehicle, and the special lane is a lane where a stop site of the special vehicle is arranged; S20, generating a lane selection strategy according to the special lane information; S30, selecting a target lane to be driven by the target vehicle according to the lane selection strategy.

[0032] First, special lane information is obtained from the collected driving information of the target vehicle, wherein the target vehicle is a vehicle equipped with a NOA system, and the target vehicle can also be referred to as a self-vehicle or ego-vehicle.

[0033] The driving information of the target vehicle includes at least one of a networked map and a driving image, the networked map is a map for navigation of the target vehicle, and is a high-precision map for lane-level navigation. The driving image is image information collected by a visual sensor or an intelligent driving auxiliary camera in real time during driving of the target vehicle.

[0034] The driving information of the target vehicle includes special lane information, the special lane information is obtained from the collected driving information of the target vehicle, and the special lane information corresponds to a special lane, which is a special lane for a special vehicle, and the special lane is a lane where a stop site of the special vehicle is arranged. The special vehicle includes a bus, and the special lane includes a bus lane and a rightmost lane where a bus stop site is arranged.

[0035] Further, the special lane information includes identification information indicating whether the special lane exists, and in a case where the identification information indicates that the special lane exists, the special lane information further includes site information of the special vehicle arranged in the special lane.

[0036] A lane selection strategy is generated according to the special lane information, and a target lane to be driven by the target vehicle is selected according to the generated lane selection strategy, and the generated lane selection strategy is different according to different special lane information.

[0037] In an implementation, the driving information of the target vehicle further comprises traffic scene object information around the target vehicle, each traffic scene object in the traffic scene object information comprising a dynamic scene object and a static scene object. Further, the static scene object is a static traffic participant, including a road sign, a bus stop, a traffic signal, a building, etc., and the dynamic scene object is a dynamic traffic participant, including a pedestrian, a vehicle, a moving object, etc. According to the special lane information and the traffic scene object information around the target vehicle, a lane selection strategy of the target vehicle is generated.

[0038] In an embodiment, the lane selection strategy comprises at least a first selection strategy and a second selection strategy. Specifically, the first selection strategy is generated in the absence of a special lane, and the second selection strategy is generated according to the station information in the special lane in the presence of the special lane.

[0039] The lane selection strategy is used to select a target lane, and the target lane is used to ensure that the target vehicle will not be forced to brake or follow a stop after changing lanes due to a special vehicle entering a stop.

[0040] In the embodiment, by obtaining the special lane information from the driving information of the target vehicle, generating the lane selection strategy according to the special lane information, and selecting the target lane to be driven by the target vehicle from the selectable lanes based on the lane selection strategy, the problem of forced braking or following a stop after the vehicle drives or changes lanes according to the selected lane can be avoided, the generation of invalid lane changes is reduced, the traffic efficiency of the vehicle is improved, and the driving experience of the user using the NOA is improved.

[0041] In an implementation, the special lane is identified according to the collected driving information, so as to obtain the special lane information. Specifically, step S10 can comprise steps S11-S13: S11, in the case where the driving information comprises a networked map, attribute information of the networked map is obtained; the attribute information comprises a lane type label; S12, in the case where the driving information comprises a driving image, at least one of lane identification information and traffic sign information is identified from the driving image; S13, special lane information is identified according to at least one of the attribute information, the lane identification information and the traffic sign information.

[0042] It can be understood that the driving information of the target vehicle includes at least one of the connected map and the driving image, in the case that the collected driving information includes the connected map, attribute information of the connected map is acquired, the attribute information of the connected map includes lane type labels of each lane, and rule attributes related to the lanes corresponding to the lane type labels. Further, the lane type label is used to identify the lane type, and the rule attribute is mainly used to identify the related rules of the lane, such as the access rule and the access time, and the rule attribute specifically includes the time period of the lane restriction.

[0043] In the case that the driving information includes the driving image, at least one of the lane identification information and the traffic sign information is identified from the driving image.

[0044] According to the attribute information of the connected map, at least one of the identified lane identification information and the traffic sign information, the special lane information is identified.

[0045] In one embodiment, in the case that the connected map of the target vehicle is acquired, the special lane information is acquired according to the attribute information of the connected map; in the case that the connected map of the target vehicle is not acquired, at least one of the lane identification information and the traffic sign information is identified from the driving image of the target vehicle, and the special lane information is acquired according to the identified lane identification information and / or the traffic sign information.

[0046] Among them, for the identification of the special lane, including but not limited to the identification of the bus lane, through the connected map, the lane type label of each lane can be acquired, so as to determine whether there is a bus lane, and the positional relationship between the bus lane and the current lane of the target vehicle and the time period of the lane restriction.

[0047] If the connected map of the target vehicle is not acquired, or the special lane cannot be identified through the connected map, at least one of the lane identification information and the traffic identification information is identified from the driving image, so as to identify the special lane according to the identified lane identification information and / or the traffic identification information. For example, the text information sprayed in the lane is identified from the driving image, and the special lane such as the bus lane is identified through the keywords such as "bus" or "bus" identified.

[0048] Further, according to at least one of the attribute information, the lane identification information and the traffic sign information, the special lane, the station information in the special lane and the time period of the lane restriction are identified, and the special lane information is obtained.

[0049] In another possible implementation, after step S12, step S14 can also be included: S14, initialize a time threshold of the lane marking information and / or the traffic sign information; the time threshold is used to identify a validity period of the lane marking information and / or the traffic sign information.

[0050] After identifying at least one of the lane marking information and the traffic sign information from the driving image, a time threshold of the lane marking information and / or the traffic sign information is initialized, which is used to represent a validity period of the lane marking information and / or the traffic sign information. The reason is that in the actual traffic scene, the text information sprayed in the lane and the traffic sign are repeatedly arranged at a certain distance, therefore, by setting the time threshold to identify the validity period of the identified lane marking information and traffic sign information, and when the same lane marking information and / or traffic sign information is identified, the time threshold is initialized, thereby prolonging the data validity.

[0051] Exemplarily, in the case of identifying the bus lane according to the lane marking information and / or the traffic sign information, by setting the time threshold, the lane is marked as the bus lane within the period corresponding to the subsequent time threshold, until the next time the lane marking information and / or the traffic sign information is identified, the time threshold is updated to the initialization value, and the validity period is recalculated.

[0052] It should be noted that the time threshold is a configurable parameter, and exemplarily, the time threshold can be set to 180 seconds.

[0053] After obtaining the special lane information, a lane selection strategy is generated according to the special lane information, and a selectable lane is determined, and then based on the lane selection strategy, the best lane is selected from the selectable lane as the target lane to be driven for the target vehicle.

[0054] In a feasible implementation, the lane selection strategy is generated based on the scene classification of the target vehicle, therefore, step S20 can further include steps S21-S23: S21, determine the position relationship between the current driving lane of the target vehicle and the special lane according to the special lane information; S22, determine whether the current driving time of the target vehicle is within the restricted time period of the special lane, and obtain a determination result; S23, determine the driving scene of the target vehicle based on the position relationship and the determination result, and generate a lane selection strategy based on the driving scene.

[0055] The special lane information further includes a restricted driving time period of the special lane. When generating the lane selection strategy, first, a positional relationship between the current driving lane of the target vehicle and the special lane is determined according to the special lane information; then, it is determined whether the current driving time of the target vehicle is within the restricted driving time period of the special lane, and a determination result is obtained; the target vehicle is classified into a driving scene based on the positional relationship and the determination result, and the lane selection strategy is generated based on the driving scene.

[0056] The driving scene in which the target vehicle is located represents a positional relationship between the current lane of the target vehicle and the special lane, and whether the current driving time of the target vehicle is within the restricted driving time period of the special lane.

[0057] In one embodiment, a first positional relationship between the current driving lane of the target vehicle and the special lane is determined according to the special lane information, and a second positional relationship between the target vehicle and each traffic scene object is determined according to the driving information of the target vehicle. It is determined whether the current driving time of the target vehicle is within the restricted driving time period of the special lane, and a determination result is obtained. The target vehicle is classified into a driving scene based on the first positional relationship, the second positional relationship, and the obtained determination result, and the lane selection strategy is finally generated based on the driving scene.

[0058] The first positional relationship between the current driving lane of the target vehicle and the special lane represents a relative position and direction between the current driving lane of the target vehicle and the special lane, and the second positional relationship between the target vehicle and each traffic scene object represents a relative distance, a relative direction, and a change in the relative distance between the target vehicle and each traffic scene object.

[0059] In one embodiment, the special vehicle includes a bus, and the special lane includes a bus lane and a rightmost lane provided with a bus stop. The rightmost lane is a lane that has a possibility of being occupied by a bus for stopping. In another embodiment, in the presence of a bus lane, the special lane is the bus lane, and in the absence of a bus lane, the special lane is the rightmost lane that has a possibility of being occupied by a bus for stopping.

[0060] In some embodiments, while acquiring the special lane information, the traffic scene object around the target vehicle can also be identified according to the driving information of the target vehicle, and then the first positional relationship between the current driving lane of the target vehicle and the special lane, the determination of whether the current driving time of the target vehicle is within the restricted time period of the special lane, the determination result, and the second positional relationship between the target vehicle and each traffic scene object around the target vehicle are determined. Based on the first positional relationship, the second positional relationship, and the determination result of whether the current driving time of the target vehicle is within the restricted time period of the special lane, the target vehicle is classified into a scene, and the driving scene in which the target vehicle is located is identified.

[0061] That is, the identification of the driving scene in which the target vehicle is located is realized on the basis of the identification of the special lane and the traffic scene object, that is, the special lane and the traffic scene object around the target vehicle are identified according to the driving information of the target vehicle, and then based on the first positional relationship between the current driving lane of the target vehicle and the identified special lane, the determination result of whether the current driving time of the target vehicle is within the restricted time period of the special lane, and the second positional relationship between the target vehicle and each traffic scene object, the target vehicle is classified into a scene, and the driving scene in which the target vehicle is located is identified.

[0062] According to the identified driving scene in which the target vehicle is located, the selectable lane and the lane selection strategy are determined, and the target lane to be driven is selected for the target vehicle from the selectable lane based on the lane selection strategy.

[0063] Among them, the selectable lane includes at least one, the lane selection strategy corresponding to different driving scenes is different, the selectable lane corresponding to different driving scenes can be the same or different, in the case of multiple selectable lanes, the selectable lane corresponding to different driving scenes can be the same or different, and can also be partially the same.

[0064] In one embodiment, the selectable lane includes the current driving lane of the target vehicle and the same lane of the current lane of the target vehicle; in another embodiment, the selectable lane includes the current driving lane of the target vehicle and the same lane and adjacent lane of the current driving lane of the target vehicle.

[0065] The target lane is selected for the target vehicle from the optional lanes based on a lane selection strategy. Specifically, the optional lanes are comprehensively evaluated according to the lane selection strategy based on the driving scene in which the target vehicle is located, and the best lane is selected as the target lane to be driven by the target vehicle according to the evaluation result. For example, the traffic scene objects in the optional lanes are determined according to the lane selection strategy based on the driving scene in which the target vehicle is located, and the best lane is selected as the target lane according to the determination result. Alternatively, the traffic scene objects in the optional lanes are scored according to the lane selection strategy based on the driving scene in which the target vehicle is located, and the best lane is selected as the target lane according to the scoring result.

[0066] Optionally, the target lane is a lane that can ensure that the target vehicle continues to drive or changes lanes without braking or stopping.

[0067] The lane selection strategy includes a determination condition, a determination logic and an optional lane. Based on this, in step S23, the lane selection strategy is generated based on the driving scene, including steps S231-S233: S231, determining the optional lane based on the driving scene; S232, obtaining the determination condition corresponding to the driving scene, and the determination logic of each determination condition; S233, combining the determination logic, the determination condition and the optional lane to generate the lane selection strategy.

[0068] When generating the lane selection strategy, the optional lane is determined based on the driving scene, the determination condition corresponding to the driving scene is obtained, and the determination logic of each determination condition is obtained. The optional lane, the determination condition and the determination logic corresponding to the driving scene are combined to generate the lane selection strategy.

[0069] In one embodiment, the driving scene includes a first scene and a second scene, wherein the first scene represents that the target vehicle is currently driving in a special lane during a limited driving time period, and the second scene represents that the target vehicle is currently driving in a special lane but the current driving time of the target vehicle is not in the limited driving time period of the special lane.

[0070] Further, the determination condition corresponding to the driving scene includes a first determination condition corresponding to the first scene and a second determination condition corresponding to the second scene; and the lane selection strategy includes a first selection strategy corresponding to the first scene and a second selection strategy corresponding to the second scene.

[0071] In the case where the driving scene in which the target vehicle is located is the first scene, the lane selection strategy is generated based on the driving scene in step S23, including: determining a first optional lane based on the first scene; obtaining a first determination condition corresponding to the first driving scene, and a first determination logic of each of the first determination conditions; combining the first determination logic, the first determination condition and the first optional lane to generate a first selection strategy.

[0072] Correspondingly, in the case that the driving scene where the target vehicle is located is the second scene, the step S23 of generating the lane selection strategy based on the driving scene comprises: determining a second optional lane based on the second scene; obtaining a second determination condition corresponding to the second driving scene, and a second determination logic of each of the second determination conditions; combining the second determination logic, the second determination condition and the second optional lane to generate a second selection strategy.

[0073] In an available implementation, the driving information of the target vehicle comprises navigation information, the special lane information comprises station information of a station site of a special vehicle, the driving scene where the target vehicle is located comprises a target scene, the target scene represents that a current driving lane of the target vehicle is an adjacent lane of a special lane, and a current driving time of the target vehicle is not in a time period of limiting driving in the special lane.

[0074] If the driving scene where the target vehicle is located is the target driving scene, the lane selection method provided by the embodiment of the application further comprises the step S40: S40, determining a relative distance between the target vehicle and a front station according to the navigation information and the station information.

[0075] The target determination condition corresponding to the target driving scene comprises: whether there is a same-direction straight lane on the left side of the current driving lane of the target vehicle, whether there is a right-turn demand of the target vehicle in a target area in the case that the relative distance is less than or equal to a preset distance, and whether there is a slow vehicle or a special vehicle in the optional lane; wherein the speed of the slow vehicle is less than or equal to the current speed of the target vehicle, the target area comprises a first area between the current position of the target vehicle and the front station, and the optional lane comprises at least one of the current driving lane of the target vehicle, the special lane and the adjacent lane of the lane.

[0076] Correspondingly, the target determination logic corresponding to the target determination condition comprises: in the case that there is no same-direction straight lane on the left side of the current lane of the target vehicle, and there is no right-turn demand of the target vehicle in the first area, if there is a slow vehicle or a special vehicle in front of the right side of the target vehicle in the optional lane, the right side lane in the adjacent lane is not allowed to be selected, and in the case that there is a slow vehicle or a special vehicle in front of the target vehicle in the optional lane, and there is no slow vehicle or special vehicle in front of the right side of the target vehicle in the optional lane, the right side lane in the adjacent lane is allowed to be selected.

[0077] It should be noted that the adjacent lane of the special lane includes a left adjacent lane and a right adjacent lane of the special lane, and the target driving scene specifically represents that the current driving lane of the target vehicle is the left adjacent lane of the special lane, and the current driving time of the target vehicle is not in the restricted time period of the special lane.

[0078] In an available implementation, the lane selection strategy includes optional lanes, a judgment condition and a judgment logic, and step S30 can further include steps S31-S32: S31, determining each of the optional lanes according to the judgment condition and the judgment logic; S32, selecting a target lane to be driven by the target vehicle based on the determination results of each of the optional lanes.

[0079] According to the judgment condition and the judgment logic, each of the optional lanes is determined, and the target lane to be driven by the target vehicle is selected based on the determination results of each of the optional lanes.

[0080] It should be noted that the lane selection strategy is a set of judgment conditions, and contains the judgment logic and the judgment object of each judgment condition in the set of judgment conditions, wherein the judgment object is the optional lane. Therefore, according to the judgment logic in the lane selection strategy, it is determined whether each optional lane meets the lane-changing driving condition, so as to select the target lane to be driven by the target vehicle.

[0081] In one embodiment, the driving scene includes a first scene, the lane selection strategy includes a first selection strategy corresponding to the first scene, and the first scene represents that the current driving time of the target vehicle is in the restricted time period of the special lane. If the driving scene in which the target vehicle is located is the first scene, the special lane is excluded from the optional lanes, the other lanes except the special lane in the optional lanes are determined based on the first selection strategy, and the target lane to be driven by the target vehicle is selected according to the determination results of the first selection strategy.

[0082] It should be noted that, in the case that the driving scene where the target vehicle is located is the first scene, the optional lane is a lane in the same direction as the driving direction of the target vehicle, that is, the current driving lane of the target vehicle and the lane in the same direction thereof. In the case that the current driving time of the target vehicle is within the limited time period of the special lane, the driving scene where the target vehicle is located is classified as the first scene regardless of whether the current lane of the target vehicle is the special lane, and the special lane is excluded from the optional lane. Based on the first selection strategy, the remaining lanes except the special lane are determined, and the optimal lane is selected as the target lane to be driven by the target vehicle according to the determination result. If the current lane of the target vehicle is the special lane within the limited time period, the target vehicle can change lanes out of the special lane through the selected target lane. If the target vehicle is not driving in the special lane within the limited time period, the target vehicle can avoid driving into the limited lane through the selected target lane.

[0083] In another possible implementation, the driving scene includes a second scene, and the lane selection strategy includes a second selection strategy corresponding to the second scene. The second scene represents that the current driving lane of the target vehicle is a special lane, but the current driving time of the target vehicle is not within the limited time period of the special lane.

[0084] If the driving scene where the target vehicle is located is the second scene, the second selection strategy is used to determine each optional lane, and the target lane to be driven by the target vehicle is selected according to the determination result of each optional lane based on the second selection strategy.

[0085] It should be noted that the second determination condition in the second selection strategy includes whether there is a slow vehicle or a special vehicle in the left front of the target vehicle in the optional lane, and whether there is a right-turn demand of the target vehicle in the target area in the case that the relative distance between the target vehicle and the front station is less than or equal to a preset distance. In the second scene, the target area includes a first area between the current position of the target vehicle and the front station, and a second area between the front station and the target distance in front thereof. The front here refers to the front in the driving direction of the target vehicle. The optional lane includes the current driving lane of the target vehicle (that is, the special lane) and the adjacent lane of the special lane, and the adjacent lane includes the left adjacent lane.

[0086] In the second scene, first, the relative distance between the target vehicle and the front bus station is determined according to the navigation information in the driving information. In the case that the relative distance is less than or equal to a preset distance, whether there is a right-turn demand of the target vehicle within the preset distance range of the bus station is detected based on the navigation information of the target vehicle, and whether there is a slow vehicle in each optional lane is detected, wherein the slow vehicle is a vehicle with a speed less than or equal to the current speed of the target vehicle.

[0087] According to the second selection strategy, the target lane to be traveled by the target vehicle is selected from the optional lanes according to a decision result of the second selection strategy.

[0088] It should be noted that, in the case of the second scenario in which the driving scene of the target vehicle is the second scenario, the optional lanes include the current driving lane of the target vehicle and the left lane adjacent thereto. In an embodiment, the optional lanes are the current driving lane of the target vehicle and the same-lane lane adjacent thereto. In another embodiment, the optional lanes are the current driving lane of the target vehicle and the same-lane lane adjacent thereto.

[0089] For example, in the second scenario in which the current driving lane of the target vehicle is the special lane in the non-restricted time period, the left lane of the special lane is determined according to the decision logic of the second selection strategy shown in Table 1.

[0090] As shown in Table 1, the relative distance between the target vehicle and the front site is obtained according to the navigation information in the driving information, and the second determination condition of the second selection strategy includes: in the case that the relative distance is less than or equal to a preset distance X, it is determined according to the navigation information whether the target vehicle has a right-turn demand within a preset distance range of the front site. Specifically, it is determined whether the target vehicle has a right-turn demand in a first region between the target vehicle and the front site, and whether the target vehicle has a right-turn demand in a second region in front of the site.

[0091] Further, the speed information of each optional lane within the visual range of the target vehicle is obtained, or the speed information of the adjacent vehicles around the target vehicle is obtained, and the speed relationship between the target vehicle and other vehicles is determined. For a vehicle with a speed less than that of the target vehicle, it is determined as a slow vehicle, and for a vehicle with a speed greater than or equal to that of the target vehicle, it is determined as a non-slow vehicle. The second determination condition of the second selection strategy further includes whether there is a slow vehicle or a special vehicle in front of the target vehicle. For example, the preset distance X is 500 meters, and the second region is a region from the site to 300 meters in front of the site.

[0092] Table 1:

[0093] According to the second determination condition in the second selection strategy, it is determined whether there is a slow vehicle in front of the target vehicle according to the detection result of the slow vehicle, and whether the target vehicle has a right-turn demand within a short distance in front of and behind the bus site, and a comprehensive judgment is made, so as to determine whether the left lane can be selected as the target lane.

[0094] The determination logic of the second selection strategy includes: not allowing to select the left lane when there is no slow vehicle or special vehicle in front of the target vehicle and there is no right-turn demand in the first area of the target vehicle; allowing to select the left lane when there is no slow vehicle or special vehicle in front of the target vehicle and there is no right-turn demand in the target area of the target vehicle; not allowing to select the left lane when there is no slow vehicle or special vehicle in front of the target vehicle, there is no right-turn demand in the first area of the target vehicle, but there is a right-turn demand in the second area of the target vehicle; not allowing to select the left lane when there is a right-turn demand in the first area of the target vehicle, but there is no right-turn demand in the second area of the target vehicle.

[0095] Specifically, as shown in Table 1, in the case that there is no slow vehicle or special vehicle in the left lane and there is no right-turn demand of the target vehicle, the left lane is selected as the target lane, and the target vehicle can switch lanes in advance to avoid being hindered by a bus that needs to stop in the bus lane or the rightmost lane.

[0096] When there is a slow vehicle in the left lane of the target vehicle, the left lane cannot be selected as the target lane, and the current lane of the target vehicle is selected as the target lane. The target vehicle will continue to travel in the current lane and can select a target lane again after overtaking the slow vehicle according to the lane selection method provided in the embodiments of the present application.

[0097] When there are multiple slow vehicles in the left lane, it is usually a congested situation, and even if the target vehicle exits the bus lane or the rightmost lane, the traffic efficiency cannot be improved. Therefore, the current lane of the target vehicle is still selected as the target lane, and the target vehicle continues to travel in the current lane to avoid unnecessary lane changes in a congested situation.

[0098] For the case that the target vehicle has a right-turn demand within a preset distance range before and after the bus stop, there is no need to change lanes to avoid frequent lane changes. Therefore, the current lane of the target vehicle is also selected as the target lane.

[0099] In a feasible manner, the lanes are determined based on the lane selection strategy. Specifically, the current lane of the target vehicle and the selectable lanes are determined based on the determination conditions in the lane selection strategy, a better lane is determined as a candidate lane, and then the remaining selectable lanes and the candidate lane are determined, a better lane is determined as a candidate lane, until the selected candidate lane is the last selectable lane, and the candidate lane is the target lane.

[0100] In another possible implementation, the driving scene of the target vehicle further includes a third scene, i.e., a target driving scene, and the lane selection strategy includes a third selection strategy corresponding to the third scene, the third selection strategy including a third determination condition, a third determination logic, and third selectable lanes. The third scene represents that the lane currently occupied by the target vehicle is a left adjacent lane of a special lane, and the current driving time of the target vehicle is not within a time period for limiting driving in the special lane. If the driving scene in which the target vehicle is located is the third scene, the following applies: According to the third determination condition and the third determination logic, a decision is made on each of the third selectable lanes; Based on the decision results on each of the third selectable lanes, a target lane to be driven by the target vehicle is selected.

[0101] The third selection strategy is also a set of determination conditions, some of which are the same as those of the second selection strategy. Therefore, when the driving scene in which the target vehicle is located is the third scene, the left side of the current driving lane of the target vehicle is further detected according to the driving information to determine whether there is a straight lane in the target direction, where the target direction is the current driving direction of the target vehicle, or the target direction is the driving direction corresponding to the current driving lane of the target vehicle.

[0102] Based on the detection results on the straight lane, the right turn demand of the target vehicle, and the slow vehicle, a decision is made on each of the selectable lanes according to the third selection strategy, and a target lane to be driven by the target vehicle is selected from the selectable lanes according to the decision result of the third selection strategy.

[0103] Exemplarily, when the driving scene in which the target vehicle is located is the third scene, the right lane is decided according to the decision logic of the third selection strategy shown in Table 2.

[0104] According to the decision logic of the third selection strategy shown in Table 2, when there is a special vehicle stop site in front of the target vehicle, the target vehicle avoids selecting the special lane when there is a straight lane in the same direction on the left side of the target vehicle and no right turn demand.

[0105] When there is no straight lane in the same direction on the left side of the target vehicle, if the target vehicle has a right turn demand within a preset distance range of the front site, the right lane needs to be selected as the target lane in advance; if the target vehicle has no right turn demand and there is a slow vehicle or a special vehicle in front, the current driving lane of the target vehicle is selected as the target lane, so that the target vehicle continues to drive in the current driving lane.

[0106] Table 2:

[0107] As shown in Table 2, the point decision condition in the third selection strategy includes: whether there is a same-direction straight lane on the left side of the current driving lane of the target vehicle, whether there is a right-turn demand of the target vehicle in the target region in the case that the relative distance between the target vehicle and the front site is less than or equal to a preset distance, and whether there is a slow vehicle or the special vehicle in the optional lane.

[0108] The third decision logic of the third selection strategy includes: in the case that there is no same-direction straight lane on the left side of the current driving lane of the target vehicle, and there is no right-turn demand of the target vehicle in the first region, if there is a slow vehicle or a special vehicle in front right of the target vehicle in the optional lane, the right lane in the adjacent lane is not allowed to be selected; in the case that there is a slow vehicle or a special vehicle in front of the target vehicle in the optional lane, and there is no slow vehicle or special vehicle in front right of the target vehicle in the optional lane, the right lane in the adjacent lane is allowed to be selected; in the case that there is a right-turn demand of the target vehicle in the first region, the right lane is allowed to be selected; in the case that there is a same-direction straight lane on the left side of the target vehicle, and there is no right-turn demand of the target vehicle in the first region, the right lane is not allowed to be selected.

[0109] That is, in the case that there is no right-turn demand of the target vehicle, and there is a slow vehicle or a special vehicle in front of the target vehicle, and there is no slow vehicle or special vehicle in front right of the target vehicle, the target vehicle can select the right lane as the target lane. In particular, according to this case, if the target vehicle successfully drives into the right lane, the target vehicle will be in the second scenario, and the second selection strategy corresponding to the second scenario is used for decision-making, and the corresponding target lane is selected. That is, when the target vehicle drives into the right lane after overtaking the slow vehicle or the special vehicle, if it is detected that there is no slow vehicle or special vehicle in front left of the target vehicle, the target vehicle will still avoid the special lane, and when the target vehicle drives into the right lane after overtaking the slow vehicle or the special vehicle, if there is a slow vehicle or a special vehicle in front left of the target vehicle, it is a vehicle congestion situation, and it is difficult to improve the traffic efficiency by changing the driving lane. According to the decision logic of the second selection strategy, the target vehicle continues to drive in the current driving lane without unnecessary lane changing.

[0110] It should be noted that in the above decision conditions, whether there is a slow vehicle or a special vehicle in front left, front and front right of the target vehicle can also be whether there is at least one of a slow vehicle, a special vehicle and an obstacle in front left, front and front right of the target vehicle, wherein the obstacle can be a static obstacle (such as a parked vehicle and a set roadblock, etc.), or a dynamic obstacle (such as a pedestrian and a small-range moving road working equipment, etc.). The obstacle can be determined according to the identified traffic scene object, and the traffic scene object can be identified according to at least one of the networked map and the driving image. In an embodiment, the obstacle is identified at the same time as the slow vehicle.

[0111] In the embodiment, the driving scene of the vehicle is classified according to whether the vehicle is located in a special lane and whether the current driving time of the vehicle is within a restricted time period of the special lane, different lane selection strategies are generated for different driving scenes, and the target lane is selected according to the lane selection strategy, so that the traffic efficiency can be improved, the target lane after lane changing can be avoided to cause braking or following stop, the generation of invalid lane changing is reduced, and the traffic efficiency and user driving experience are improved.

[0112] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the lane selection method provided by the present application. More forms of simple transformation based on the technical concept are within the protection scope of the present application.

[0113] The present application also provides a lane selection device, please refer to Figure 2 The lane selection device comprises: An information acquisition module 10 is configured to acquire special lane information from driving information of a target vehicle, wherein the special lane information corresponds to a special lane which is a special lane for a special vehicle, and the special lane is a lane where a stop site of the special vehicle is arranged; A strategy generation module 20 is configured to generate a lane selection strategy according to the special lane information; A lane selection module 30 is configured to select a target lane to be driven for the target vehicle according to the lane selection strategy.

[0114] In an embodiment, the strategy generation module 20 is further configured to: determine a positional relationship between a current driving lane of the target vehicle and the special lane according to the special lane information; determine whether a current driving time of the target vehicle is within a restricted time period of the special lane to obtain a determination result; determine a driving scene in which the target vehicle is located based on the positional relationship and the determination result, and generate a lane selection strategy based on the driving scene.

[0115] In an embodiment, the strategy generation module 20 is further configured to: determine a selectable lane based on the driving scene; acquire a determination condition corresponding to the driving scene and determination logic of each determination condition; combine the determination logic, the determination condition and the selectable lane to generate a lane selection strategy.

[0116] In an embodiment, the driving information comprises navigation information, the special lane information comprises station information of a stop station of the special vehicle, and the driving scene comprises a target driving scene; the target driving scene indicates that a current driving lane of the target vehicle is an adjacent lane of the special lane, and a current driving time of the target vehicle is not within a time period of the special lane; if the driving scene in which the target vehicle is located is the target driving scene, the lane selection device further comprises: a distance detection module configured to determine a relative distance between the target vehicle and a front station according to the navigation information and the station information; a target determination condition corresponding to the target driving scene comprises: whether there is a same-direction straight lane on a left side of the current driving lane of the target vehicle, whether there is a right-turn demand of the target vehicle in a target area in a case that the relative distance is less than or equal to a preset distance, and whether there is a slow vehicle or the special vehicle in the selectable lane; wherein the slow vehicle has a speed less than or equal to a current speed of the target vehicle, the target area comprises a first area between a current position of the target vehicle and the front station, and the selectable lane comprises at least one of the current lane of the target vehicle, the special lane, and an adjacent lane of the special lane; a target determination logic corresponding to the target determination condition comprises: if there is no same-direction straight lane on the left side of the current driving lane of the target vehicle, and there is no right-turn demand of the target vehicle in the first area, in a case that there is a slow vehicle or a special vehicle in front right of the target vehicle in the selectable lane, the right side lane in the adjacent lane is not allowed to be selected, and in a case that there is a slow vehicle or the special vehicle in front of the target vehicle in the selectable lane, and there is no slow vehicle or the special vehicle in front right of the target vehicle in the selectable lane, the right side lane in the adjacent lane is allowed to be selected.

[0117] In an embodiment, the lane selection strategy comprises a determination condition, a determination logic, and a selectable lane; the lane selection module 30 is further configured to: make a decision for each of the selectable lanes according to the determination condition and the determination logic; select a target lane to be driven by the target vehicle based on a decision result for each of the selectable lanes.

[0118] In an embodiment, the driving information comprises at least one of a networked map and a driving image; the information acquisition module 10 is further configured to: in a case that the driving information comprises the networked map, acquire attribute information of the networked map; the attribute information comprises a lane type label; In a case where the driving information includes a driving image, at least one of lane marking information and traffic sign information is identified from the driving image. According to at least one of the attribute information, the lane marking information and the traffic sign information, special lane information is identified.

[0119] In a case where the driving information includes a driving image, the information acquisition module 10 is further configured to: initialize a time threshold of the lane marking information and / or the traffic sign information; the time threshold is used to identify a valid period of the lane marking information and / or the traffic sign information.

[0120] The lane selection device provided by the present application adopts the lane selection method in the above embodiments, and can solve the technical problem of inaccurate lane selection due to lack of predictability of driving behavior of special vehicles for intelligent piloting auxiliary functions relying on large model decision, which easily causes vehicle braking or following stop after the vehicle changes lane according to the selected lane, thereby causing invalid lane change. Compared with the prior art, the lane selection device provided by the present application has the same beneficial effects as the lane selection method provided by the above embodiments, and other technical features in the lane selection device are the same as the features disclosed in the above embodiments, which will not be repeated here.

[0121] The present application provides a lane selection device, which comprises at least one processor and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the lane selection method in Embodiment I.

[0122] Reference will now be made to the following description Figure 3 which illustrates a structural block diagram of a lane selection device suitable for implementing the embodiments of the present application. The lane selection device in the embodiments of the present application can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description), PMPs (Portable Media Player), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 3 The lane selection device shown is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0123] As Figure 3As shown, the lane selection device can include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for operation of the lane selection device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other by a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the lane selection device to communicate wirelessly or by wire with other devices to exchange data. Although the lane selection device with various systems is shown in the figure, it should be understood that all of the systems shown are not required to be implemented or possessed. More or fewer systems can be alternatively implemented or possessed.

[0124] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of embodiments of the present disclosure are performed.

[0125] The lane selection device provided by the present application adopts the lane selection method in the above-mentioned embodiments, which can solve the technical problem that the intelligent piloting auxiliary function relying on large model decision lacks predictability for the driving behavior of special vehicles, leading to inaccurate lane selection, and after the vehicle changes lanes according to the selected lane, the vehicle is prone to braking or stopping, thereby causing invalid lane change. Compared with the prior art, the lane selection device provided by the present application has the same beneficial effects as the lane selection method provided by the above-mentioned embodiments, and other technical features in the lane selection device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0126] It should be understood that various aspects of the disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the description of the embodiments above, specific features, structures, materials or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0127] The above description is merely illustrative of the application and is not intended to limit the scope of the application. Any modifications or equivalents of the technology disclosed herein should be construed as falling within the scope of the application. Therefore, the scope of the application should be determined by the scope of the claims.

[0128] The application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e., a computer program) for performing the lane selection method in the above-described embodiments.

[0129] The computer readable storage medium provided by the application may, for example, be a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system or device, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electric connection having one or more conductive wires, 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), an optical fiber, a portable compact disk read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the embodiments, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electric wire, an optical cable, an RF (Radio Frequency), etc., or any suitable combination thereof.

[0130] The above-described computer readable storage medium can be included in a lane selection device; or can exist separately without being assembled into the lane selection device.

[0131] The above-described computer readable storage medium carries one or more programs, which, when executed by the lane selection device, enable the lane selection device to perform the following steps: Obtain special lane information from the driving information of the target vehicle, wherein the special lane information corresponds to a special lane of the special vehicle, and the special lane is a lane in which a stop site of the special vehicle is arranged; Generate a lane selection strategy according to the special lane information; Select a target lane to be driven for the target vehicle according to the lane selection strategy.

[0132] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0133] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a procedure, or a part of code, which comprises one or more executable instructions for implementing the specified functions. It should also be noted that, in some alternative implementations, the functions noted in the blocks can occur in a different order than that noted in the figures. For example, two blocks noted in succession can in fact be executed substantially concurrently or in the opposite order, depending on the functionality involved. It should also be noted that each block in the block diagrams and / or flow diagrams, and combinations of blocks in the block diagrams and / or flow diagrams, can be implemented by dedicated hardware-based systems that perform the specified functions or operations, or can be implemented by a combination of dedicated hardware-based systems and computer instructions.

[0134] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0135] The readable storage medium provided by the application is a computer readable storage medium, which stores computer readable program instructions (i.e., a computer program) for executing the lane selection method described above, and can solve the technical problem of the intelligent pilot assistance function depending on the decision of a large model, the lack of predictability of the driving behavior of a special vehicle, inaccurate lane selection, and the easy triggering of vehicle braking or following after the vehicle changes lanes according to the selected lane, thereby causing invalid lane changes. Compared with the prior art, the computer readable storage medium provided by the application has the same beneficial effects as the lane selection method provided by the above-mentioned embodiments, and will not be described here.

[0136] The application also provides a computer program product comprising a computer program, which, when executed by a processor, implements the steps of the lane selection method as described above.

[0137] The computer program product provided by the application can solve the technical problem of the intelligent pilot assistance function depending on the decision of a large model, the lack of predictability of the driving behavior of a special vehicle, inaccurate lane selection, and the easy triggering of vehicle braking or following after the vehicle changes lanes according to the selected lane, thereby causing invalid lane changes. Compared with the prior art, the computer program product provided by the application has the same beneficial effects as the lane selection method provided by the above-mentioned embodiments, and will not be described here.

[0138] The above only describes some embodiments of the application, and does not limit the patent scope of the application, and any equivalent structural transformation made by using the content of the application specification and drawings, or direct / indirect application in other related technical fields is included in the patent protection scope of the application.

Claims

1. A lane selection method, characterized in that, The lane selection method includes: Obtain special lane information from the driving information of the target vehicle; wherein, the special lane corresponding to the special lane information is a dedicated lane for special vehicles, and the special lane is a lane with a stop station for the special vehicle. A lane selection strategy is generated based on the specific lane information; The target lane to be driven in is selected for the target vehicle according to the lane selection strategy.

2. The lane selection method as described in claim 1, characterized in that, The step of generating a lane selection strategy based on the special lane information includes: The positional relationship between the target vehicle's current driving lane and the special lane is determined based on the special lane information; Determine whether the current travel time of the target vehicle is within the restricted time period of the special lane, and obtain the determination result; Based on the positional relationship and the determination result, the driving scenario of the target vehicle is determined, and a lane selection strategy is generated based on the driving scenario.

3. The lane selection method as described in claim 2, characterized in that, The step of generating a lane selection strategy based on the driving scenario includes: Based on the driving scenario, selectable lanes are determined; Obtain the judgment conditions corresponding to the driving scenario, and the judgment logic for each judgment condition; The determination logic, the determination conditions, and the available lanes are combined to generate a lane selection strategy.

4. The lane selection method as described in claim 3, characterized in that, The driving information includes navigation information, the special lane information includes the stop information of the special vehicle, and the driving scenario includes a target driving scenario; the target driving scenario indicates that the current driving lane of the target vehicle is an adjacent lane of the special lane, and the current driving time of the target vehicle is not within the restricted time period of the special lane. If the driving scenario in which the target vehicle is located is the target driving scenario, the lane selection method further includes: The relative distance between the target vehicle and the station ahead is determined based on the navigation information and the station information; The target determination conditions corresponding to the target driving scenario include: whether there is a straight-ahead lane to the left of the target vehicle's current driving lane; whether the target vehicle needs to turn right within the target area when the relative distance is less than or equal to a preset distance; and whether there are slow-moving vehicles or special vehicles in the selectable lanes. The slow-moving vehicles are at a speed less than or equal to the target vehicle's current speed. The target area includes a first area between the target vehicle's current position and the next station. The selectable lanes include at least one of the target vehicle's current lane, the special lane, and the lane adjacent to the special lane. The target determination logic corresponding to the target determination conditions includes: if there is no straight-ahead lane to the left of the target vehicle's current driving lane, and the target vehicle does not need to turn right in the first area, and there is a slow-moving vehicle or a special vehicle in front of the target vehicle on the right in the selectable lane, then the right lane in the adjacent lane is not allowed to be selected; if there is a slow-moving vehicle or the special vehicle in front of the target vehicle in the selectable lane, and there is no slow-moving vehicle or the special vehicle in front of the target vehicle on the right in the selectable lane, then the right lane in the adjacent lane is allowed to be selected.

5. The lane selection method as described in any one of claims 1 to 4, characterized in that, The lane selection strategy includes determination criteria, determination logic, and available lanes; The step of selecting a target lane for the target vehicle according to the lane selection strategy includes: Decisions are made for each of the selectable lanes based on the determination conditions and the determination logic. Based on the decision results for each of the available lanes, a target lane is selected for the target vehicle to travel in.

6. The lane selection method as described in claim 1, characterized in that, The driving information includes at least one of the online map and driving images; The step of obtaining special lane information from the driving information of the target vehicle includes: If the driving information includes a connected map, obtain the attribute information of the connected map; the attribute information includes lane type labels; When the driving information includes driving images, at least one of lane marking information and traffic sign information is identified from the driving images; Identify special lane information based on at least one of the attribute information, the lane marking information, and the traffic sign information.

7. The lane selection method as described in claim 6, characterized in that, When the driving information includes driving images, after the step of identifying at least one of lane marking information and traffic sign information from the driving images, the method further includes: A time threshold is initialized for the lane marking information and / or the traffic sign information; the time threshold is used to identify the validity period of the lane marking information and / or the traffic sign information.

8. A lane selection device, characterized in that, The lane selection device includes: The information acquisition module is used to acquire special lane information from the driving information of the target vehicle; wherein, the special lane corresponding to the special lane information is a dedicated lane for special vehicles, and the special lane is a lane with a stop station for the special vehicle. The strategy generation module is used to generate a lane selection strategy based on the special lane information; The lane selection module is used to select a target lane for the target vehicle to travel in according to the lane selection strategy.

9. A lane selection device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the lane selection method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the lane selection method as described in any one of claims 1 to 7.

Images