Vehicle lane changing method, device, apparatus and storage medium

Abstract

The application relates to a vehicle lane changing method, device, equipment and storage medium. According to a lane changing suggestion behavior of an unmanned vehicle, a predicted driving path of other vehicles is acquired. The lane changing suggestion behavior includes a planning behavior of the unmanned vehicle invading the right of way of the other vehicles. Then, according to the predicted driving path, the driving path of the unmanned vehicle is updated. The predicted driving path includes a path planned by the other vehicles to avoid the unmanned vehicle or a path planned by the other vehicles not to avoid the unmanned vehicle. Therefore, before lane changing, the unmanned vehicle invades the right of way of the other vehicles to show the lane changing intention of the unmanned vehicle, and forces the other vehicles to avoid the unmanned vehicle, avoids the behavior of the other vehicles not avoiding the unmanned vehicle, and further avoids the problem that the unmanned vehicle cannot complete lane changing in time.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a vehicle lane-changing method, apparatus, device, and storage medium. Background Technology

[0002] During the operation of an autonomous vehicle, sensors installed on the vehicle acquire information about the surrounding environment (the driving paths of surrounding vehicles, obstacles, etc.), and based on this information, the vehicle's driving path is planned in advance to control its operation.

[0003] When an autonomous vehicle needs to change lanes, the system obtains the distance between it and other vehicles. If this distance is greater than a preset safe distance, the system controls the autonomous vehicle to change lanes. For example, if the autonomous vehicle needs to change lanes to the right, the system obtains environmental information about the right lane. If the distance between the autonomous vehicle and other vehicles in the right lane is greater than a preset safe distance, the system controls the autonomous vehicle to change lanes to the right.

[0004] However, on congested roads, other vehicles are close to the autonomous vehicle. When the autonomous vehicle changes lanes, the distance between it and other vehicles is less than the preset safe distance, causing the autonomous vehicle to be unable to complete the lane change in time. Summary of the Invention

[0005] Therefore, it is necessary to provide a vehicle lane-changing method, device, equipment, and storage medium to address the problem that autonomous vehicles cannot complete lane changes in a timely manner.

[0006] A first aspect includes a method for changing lanes by a vehicle, the method comprising:

[0007] Based on the lane change suggestion behavior of the autonomous vehicle, the predicted driving paths of other vehicles are obtained; the lane change suggestion behavior includes the planning behavior of the autonomous vehicle infringing on the right-of-way of other vehicles.

[0008] The driving path of the autonomous vehicle is updated based on the predicted driving path; the predicted driving path includes either a path planned by other vehicles to avoid the autonomous vehicle or a path planned by other vehicles not to avoid the autonomous vehicle.

[0009] In one embodiment, obtaining the predicted driving paths of other vehicles based on the lane-change suggestion behavior of the autonomous vehicle includes:

[0010] According to preset prediction rules, the predicted driving paths of other vehicles corresponding to the lane change suggestion behavior are predicted; the prediction rules are used to predict the driving trajectories of other vehicles based on the right-of-way violation behavior of the autonomous vehicle.

[0011] In one embodiment, the method further includes:

[0012] Acquire lane-changing behavior of multiple vehicles;

[0013] Obtain the driving trajectories of other vehicles corresponding to the lane-changing behaviors of the multiple vehicles;

[0014] The prediction rule is trained based on the lane-changing behaviors of the multiple vehicles and the driving trajectories of other vehicles corresponding to the lane-changing behaviors.

[0015] In one embodiment, after updating the driving path of the autonomous vehicle based on the predicted driving path, the method further includes:

[0016] A safety check is performed on the updated driving path of the autonomous vehicle to obtain the check results; the check results include the safety of the autonomous vehicle's driving path and the danger of the autonomous vehicle's driving path.

[0017] Based on the inspection results, control the autonomous vehicle to drive.

[0018] In one embodiment, the step of performing a safety check on the updated driving path of the autonomous vehicle to obtain the check results includes:

[0019] The distance between the autonomous vehicle and the other vehicles is obtained, including lateral distance and longitudinal distance;

[0020] The inspection results are obtained based on the distance between the autonomous vehicle and other vehicles.

[0021] In one embodiment, if the lateral distance is greater than a preset lateral safety distance and the longitudinal distance is greater than a preset longitudinal safety distance, then the inspection result is that the driving path of the autonomous vehicle is safe.

[0022] If the lateral distance is less than the preset lateral safety distance, and / or the longitudinal distance is less than the preset longitudinal safety distance, then the inspection result indicates that the autonomous vehicle's driving path is dangerous.

[0023] In one embodiment, controlling the autonomous vehicle to drive based on the inspection result includes:

[0024] If the inspection result indicates that the autonomous vehicle's driving path is dangerous, then the autonomous vehicle will be controlled to stop performing lane-changing actions.

[0025] In one embodiment, obtaining the predicted driving paths of other vehicles based on the lane-change suggestion behavior of the autonomous vehicle further includes:

[0026] Based on the driving path of the autonomous vehicle, obtain the lane change requirements of the autonomous vehicle.

[0027] Based on the lane change request, obtain the lane change suggestion behavior of the autonomous vehicle.

[0028] Secondly, a vehicle lane-changing device, the device comprising:

[0029] The acquisition module is used to acquire the predicted driving paths of other vehicles based on the lane change suggestion behavior of the autonomous vehicle; the lane change suggestion behavior includes the planning behavior of the autonomous vehicle infringing on the right-of-way of other vehicles.

[0030] An update module is used to update the driving path of the autonomous vehicle based on the predicted driving path; the predicted driving path includes paths planned by other vehicles to avoid the autonomous vehicle and paths planned by other vehicles not to avoid the autonomous vehicle.

[0031] Thirdly, a computer device includes a memory and a processor, the memory storing a computer program, the processor executing the steps of the method described above for the vehicle lane-changing method.

[0032] Fourthly, a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle lane-changing method described above.

[0033] The aforementioned lane-changing method, device, equipment, and storage medium obtain the predicted driving paths of other vehicles based on the lane-changing suggestion behavior of the autonomous vehicle. The lane-changing suggestion behavior includes the autonomous vehicle's planning behavior of infringing on the right-of-way of other vehicles. Then, based on the predicted driving paths, the autonomous vehicle's driving path is updated. The predicted driving paths include paths planned by other vehicles to avoid the autonomous vehicle or paths planned by other vehicles not to avoid it. This allows the autonomous vehicle to demonstrate its lane-changing intention by infringing on the right-of-way of other vehicles before changing lanes, simultaneously forcing other vehicles to avoid it, thus preventing other vehicles from failing to yield and avoiding the problem of the autonomous vehicle failing to complete the lane change in a timely manner. Attached Figure Description

[0034] Figure 1 This is a schematic diagram illustrating the application environment of a vehicle lane-changing method in one embodiment;

[0035] Figure 2 This is a flowchart illustrating a vehicle lane-changing method in one embodiment;

[0036] Figure 3 This is a flowchart illustrating the vehicle lane-changing method in another embodiment;

[0037] Figure 4 This is a flowchart illustrating the vehicle lane-changing method in another embodiment;

[0038] Figure 5 This is a flowchart illustrating the vehicle lane-changing method in another embodiment;

[0039] Figure 6 This is a flowchart illustrating the vehicle lane-changing method in another embodiment;

[0040] Figure 7 This is a schematic diagram of the vehicle lane changing device provided in one embodiment;

[0041] Figure 8 This is a schematic diagram of the vehicle lane-changing device provided in another embodiment;

[0042] Figure 9 This is a schematic diagram of the vehicle lane-changing device provided in another embodiment;

[0043] Figure 10 This is a schematic diagram of a vehicle lane-changing device provided in another embodiment;

[0044] Figure 11 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0045] The vehicle lane-changing method, apparatus, device, and storage medium provided in this application aim to solve the problem that autonomous vehicles cannot complete lane changes in a timely manner. The technical solutions of this application and how they solve the aforementioned technical problems will be described in detail below through embodiments and in conjunction with the accompanying drawings. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0046] The vehicle lane-changing method provided in this embodiment can be applied to, for example, Figure 1 In the application environment shown, the autonomous vehicle 110 travels in different lanes on the same road as other vehicles 120. When the autonomous vehicle 110 performs a lane change, it obtains the distance between itself and other vehicles 120 through sensors installed on the autonomous vehicle 110. If the distance is greater than a preset safe distance, the autonomous vehicle 110 is controlled to perform the lane change.

[0047] It should be noted that the vehicle lane changing method provided in this application embodiment can be executed by a vehicle lane changing device, which can be implemented as part or all of the vehicle lane changing terminal through software, hardware or a combination of software and hardware.

[0048] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of this application, but not all embodiments.

[0049] Figure 2 This is a flowchart illustrating a lane-changing method in one embodiment. This embodiment involves the specific process of updating the driving path of an autonomous vehicle by addressing its planning behavior of infringing on the right-of-way of other vehicles. Figure 2 As shown, the method includes the following steps:

[0050] S101. Based on the lane change suggestion behavior of the autonomous vehicle, obtain the predicted driving paths of other vehicles; the lane change suggestion behavior includes the planning behavior of the autonomous vehicle infringing on the right-of-way of other vehicles.

[0051] In this context, the autonomous vehicle can be an intelligent car that primarily relies on an in-vehicle computer system-based intelligent driving system to plan its driving path and achieve autonomous driving. Other vehicles can be vehicles traveling on the road, including manually driven vehicles and other autonomous vehicles; this application does not impose such limitations. Lane change suggestion behavior can be the planning behavior of the vehicle's lane change terminal, which can be the behavior of allowing sufficient safety time for other vehicles to infringe upon the right-of-way of the autonomous vehicle, giving other vehicles sufficient safety time to brake or swerve, thus ensuring road safety. Lane change planning behavior can include the specific distance at which the autonomous vehicle infringes upon the right-of-way; for example, lane change planning behavior could be the autonomous vehicle shifting 50cm to the right. Right-of-way can refer to the right of traffic participants to conduct road traffic activities within a certain space and time according to traffic regulations, and can be divided into the right to drive, the right of way, the right of precedence, and the right of occupation. The right-of-way of other vehicles can refer to the right of other vehicles to conduct traffic activities on the road. For example, when an autonomous vehicle and other vehicles are simultaneously traveling on a two-lane road, such as... Figure 1 As shown, autonomous vehicle 110 is traveling in the left lane, while other vehicles 120 are traveling in the right lane. According to relevant traffic regulations, vehicles traveling straight have the highest right-of-way. Therefore, other vehicles occupy the right-of-way in the right lane. In this case, the right-of-way for other vehicles is the right to continue traveling straight along the right lane. The driving path can refer to the route the vehicle travels, which may include routes the vehicle has already traveled and routes the vehicle plans to travel. The predicted driving path can be the terminal's prediction of the planned routes of other vehicles when the autonomous vehicle infringes on their right-of-way.

[0052] Specifically, after the terminal receives the lane-change suggestion behavior from the autonomous vehicle, it predicts the driving paths of other vehicles based on this suggestion behavior to obtain the predicted driving paths of the other vehicles. The terminal can obtain the predicted driving paths of other vehicles corresponding to the lane-change suggestion behavior based on the pre-stored correspondence between lane-change behaviors and the driving trajectories of other vehicles; alternatively, it can obtain a lane-change suggestion model through machine learning, input the lane-change suggestion behavior of the autonomous vehicle into the aforementioned lane-change suggestion model, and obtain the predicted driving paths of other vehicles; this application embodiment does not limit this. For example, continuing as... Figure 1 As shown, when the autonomous vehicle 110 is driving in the left lane and other vehicles 120 are driving in the right lane, the autonomous vehicle's lane change suggestion behavior is to shift 50cm to the right. Then, the terminal can determine the predicted driving path of other vehicles based on the correspondence between the autonomous vehicle's 50cm rightward shift and other vehicles' 30cm rightward avoidance.

[0053] S102. Update the driving path of the autonomous vehicle based on the predicted driving path; the predicted driving path includes paths planned by other vehicles to avoid the autonomous vehicle or paths planned by other vehicles not to avoid the autonomous vehicle.

[0054] Specifically, based on the above embodiments, the terminal obtains the predicted driving paths of other vehicles and can update the driving path of the autonomous vehicle according to these predicted driving paths. The predicted driving paths may include paths planned by other vehicles to avoid the autonomous vehicle, or paths planned by other vehicles not to avoid the autonomous vehicle. When the predicted driving path is a path planned by other vehicles to avoid the autonomous vehicle, and the distance between the autonomous vehicle and other vehicles meets the safety distance requirement, the autonomous vehicle's driving path is updated to the path for performing a lane change; when the distance between the autonomous vehicle and other vehicles does not meet the safety distance requirement, the autonomous vehicle's driving path remains the original driving path; when the predicted driving path is a path planned by other vehicles not to avoid the autonomous vehicle, the autonomous vehicle's path remains the original driving path.

[0055] The aforementioned lane-changing method involves the terminal obtaining the predicted driving paths of other vehicles based on the lane-changing suggestion behavior of the autonomous vehicle. The lane-changing suggestion behavior includes the autonomous vehicle's planning behavior of infringing on the right-of-way of other vehicles. Then, based on the predicted driving paths, the terminal updates the autonomous vehicle's driving path. The predicted driving paths include paths planned by other vehicles to avoid the autonomous vehicle or paths planned by other vehicles not to avoid it. This allows the autonomous vehicle to demonstrate its lane-changing intention by infringing on the right-of-way of other vehicles before changing lanes, simultaneously forcing other vehicles to avoid it. This prevents other vehicles from failing to avoid the autonomous vehicle, thus avoiding the problem of the autonomous vehicle failing to complete the lane change in a timely manner.

[0056] The above embodiments focus on describing the specific process by which the terminal obtains the predicted driving paths of other vehicles based on the lane change suggestion behavior of the autonomous vehicle, and then updates the driving path of the autonomous vehicle based on the predicted driving paths. The following embodiments will describe in detail how the terminal obtains the predicted driving paths of other vehicles based on the lane change suggestion behavior of the autonomous vehicle. Optionally, the predicted driving paths of other vehicles corresponding to the lane change suggestion behavior are predicted according to preset prediction rules; the prediction rules are used to predict the driving trajectories of other vehicles based on the autonomous vehicle's violation of right-of-way behavior.

[0057] Specifically, the prediction rule can be used to predict the driving trajectories of other vehicles based on the right-of-way violations of autonomous vehicles. The preset prediction rule can be a correspondence between lane-change suggestion behaviors and the predicted driving paths of other vehicles; it can also be a neural network model, obtained by machine learning through multiple lane-change suggestion behaviors and the predicted driving paths of other vehicles corresponding to those behaviors. This application embodiment does not impose any limitations on this. For example, when the preset prediction rule is a correspondence between lane-change suggestion behaviors and the predicted driving paths of other vehicles, when the terminal obtains the lane-change suggestion behavior of the autonomous vehicle, it predicts the driving path of other vehicles corresponding to the right-of-way violations of the autonomous vehicle based on the correspondence between the lane-change suggestion behavior and the predicted driving paths of other vehicles, which is the predicted driving path.

[0058] Furthermore, the terminal can train prediction rules by using multiple vehicle lane-changing behaviors and the corresponding trajectories of other vehicles.

[0059] Figure 3 This is a flowchart illustrating a vehicle lane-changing method in another embodiment. This embodiment involves the specific process of training a prediction rule using multiple vehicle lane-changing behaviors and the corresponding trajectories of other vehicles. Figure 3 As shown, one possible implementation method of the above-mentioned "predicting the predicted driving paths of other vehicles corresponding to lane change suggestion behavior according to preset prediction rules; the prediction rules are used to predict the driving trajectories of other vehicles based on the right-of-way violation behavior of autonomous vehicles" includes the following steps:

[0060] S201, Obtain lane change behavior of multiple vehicles.

[0061] Specifically, lane-changing behavior can refer to a vehicle changing its lane to the left or right. The terminal can determine lane-changing behavior by acquiring multiple frames of traffic image data and obtaining information about the vehicle's lane within those frames. The traffic image data can be point cloud data collected by LiDAR or image data captured by a camera; this embodiment does not impose any limitations on this. For example, the terminal can acquire multiple frames of image data captured by a camera to obtain the same vehicle's lane in different frames, and determine the lane-changing behavior based on the vehicle's lane in each frame. The terminal can acquire one lane-changing behavior at a time, and obtain multiple lane-changing behaviors by acquiring traffic image data multiple times; alternatively, it can acquire multiple lane-changing behaviors at once; this embodiment does not impose any limitations on this.

[0062] S202. Obtain the driving trajectories of other vehicles corresponding to multiple vehicle lane-changing behaviors.

[0063] Specifically, based on the above embodiments, when acquiring vehicle lane change information, data of other vehicles in each frame of traffic image data can be collected during the acquisition of vehicle lane change behavior to obtain the driving trajectories of other vehicles corresponding to the vehicle lane change behavior. Specifically, the process of acquiring the driving trajectories of other vehicles corresponding to multiple vehicle lane change behaviors can be as follows: the driving trajectory of other vehicles corresponding to one vehicle lane change behavior can be acquired at a time, and the driving trajectories of other vehicles corresponding to multiple vehicle lane change behaviors can be acquired by collecting traffic image data multiple times; alternatively, the driving trajectories of other vehicles corresponding to multiple vehicle lane change behaviors can be acquired at once. This application embodiment does not impose any limitations on this.

[0064] S203. Based on the lane-changing behaviors of multiple vehicles and the driving trajectories of other vehicles corresponding to the lane-changing behaviors of multiple vehicles, a prediction rule is trained.

[0065] Specifically, based on the above embodiments, multiple vehicle lane-changing behaviors and the corresponding trajectories of other vehicles are obtained. These multiple lane-changing behaviors can be input into a preset neural network model, which outputs the corresponding trajectories of other vehicles to train a prediction rule. In the specific training process of the prediction rule, a set of training parameters can be pre-set. Multiple vehicle lane-changing behaviors are input, and the corresponding trajectories of other vehicles are obtained through the neural network model with the pre-set training parameters. These trajectories are then compared with the actual trajectories of other vehicles corresponding to the aforementioned lane-changing behaviors. Based on the comparison result, the training parameters are adjusted until the trajectories of other vehicles obtained through the neural network model and the actual trajectories of other vehicles corresponding to the lane-changing behaviors meet preset requirements, thus obtaining target training parameters. Based on these target training parameters, the prediction rule is obtained.

[0066] The aforementioned vehicle lane-changing method involves the terminal acquiring multiple vehicle lane-changing behaviors and the corresponding trajectories of other vehicles. Based on these behaviors, a prediction rule is trained, enabling the terminal to more accurately predict the driving paths of other vehicles corresponding to lane-changing suggestions. This improves the accuracy of updating the autonomous vehicle's driving path based on the predicted path and enhances the safety of lane-changing behavior.

[0067] Based on the above embodiments, after updating the autonomous vehicle's driving path according to the predicted driving path, the terminal performs a safety check on the updated autonomous vehicle's driving path, and controls the autonomous vehicle's driving based on the safety check results. The following describes... Figure 4-5 The embodiments shown will be described in detail below.

[0068] Figure 4 This is a flowchart illustrating a vehicle lane-changing method in another embodiment. This embodiment involves performing a safety check on the updated autonomous vehicle's driving path and controlling the autonomous vehicle's movement based on the check results. For example... Figure 4 As shown, the method also includes the following steps:

[0069] S301. Conduct a safety check on the updated driving path of the autonomous vehicle and obtain the check results; the check results include whether the driving path of the autonomous vehicle is safe or dangerous.

[0070] Specifically, based on the above embodiments, after the terminal updates the driving path of the autonomous vehicle, a safety check can be performed on the updated driving path to obtain the check results. These results can include whether the autonomous vehicle's driving path is safe or dangerous. A safe driving path means that the updated autonomous vehicle's driving path does not overlap with the driving paths of other vehicles, or that the distance between the updated autonomous vehicle's driving path and the driving paths of other vehicles is greater than a preset safety range, thus preventing collisions between the autonomous vehicle and other vehicles during lane changes. A dangerous driving path means that the updated autonomous vehicle's driving path overlaps with the driving paths of other vehicles, or that the distance between the updated autonomous vehicle's driving path and the driving paths of other vehicles is less than a preset safety range. In this case, when the autonomous vehicle changes lanes based on the updated driving path, the risk of collision with other vehicles is relatively high, especially if other vehicles or the autonomous vehicle itself deviates slightly from their driving paths.

[0071] S302. Based on the inspection results, control the operation of the driverless vehicle.

[0072] Specifically, based on the above embodiments, after performing a safety check on the updated autonomous vehicle and obtaining the check results, the autonomous vehicle's driving can be controlled according to the check results. When the check result indicates that the autonomous vehicle's driving path is safe, the autonomous vehicle can be controlled to perform a lane change. Optionally, when the check result indicates that the autonomous vehicle's driving path is dangerous, the autonomous vehicle is controlled not to perform a lane change.

[0073] The aforementioned lane-changing method involves the terminal performing a safety check on the updated driving path of the autonomous vehicle to obtain the check results. These results include whether the autonomous vehicle's driving path is safe or dangerous. Based on the check results, the terminal controls the autonomous vehicle's driving, ensuring that the autonomous vehicle checks the safety of its driving path before performing a lane-changing action, thus improving the safety of lane-changing for autonomous vehicles.

[0074] Figure 5 This is a flowchart illustrating a vehicle lane-changing method in another embodiment. This embodiment details the process of performing a safety check on the updated driving path of the autonomous vehicle. Figure 5 As shown, one possible implementation of S301, "perform a safety check on the updated driving path of the autonomous vehicle and obtain the check results," includes the following steps:

[0075] S401. Obtain the distance between the autonomous vehicle and other vehicles, including lateral and longitudinal distances.

[0076] Specifically, based on the above embodiments, after obtaining the updated driving path of the autonomous vehicle and the predicted driving paths of other vehicles, the distance between the autonomous vehicle and other vehicles can be determined according to the updated driving path of the autonomous vehicle and the predicted driving paths of other vehicles. In the specific process of determining the distance between the autonomous vehicle and other vehicles based on the updated driving path of the autonomous vehicle and the predicted driving paths of other vehicles, the shortest distance between each point on the autonomous vehicle's driving path and each point on the predicted driving path of other vehicles at the same time can be selected as the distance between the autonomous vehicle and other vehicles. The distance includes a lateral distance and a longitudinal distance. The lateral distance can be the length along the lateral axis in a preset coordinate system. The longitudinal distance can be the length along the longitudinal axis in a preset coordinate system.

[0077] S402. Obtain the inspection results based on the distance between the autonomous vehicle and other vehicles.

[0078] Specifically, based on the above embodiments, the distance between the autonomous vehicle and other vehicles is obtained. A safety check is performed on the autonomous vehicle's driving path based on this distance, and the check result is obtained. Optionally, if the lateral distance is greater than a preset lateral safety distance, and the longitudinal distance is greater than a preset longitudinal safety distance, the check result is that the autonomous vehicle's driving path is safe. That is, when both the lateral and longitudinal distances are greater than their respective safety distances, the above check result is that the autonomous vehicle's driving path is safe. Optionally, if the lateral distance is less than a preset lateral safety distance, and / or the longitudinal distance is less than a preset longitudinal safety distance, the check result is that the autonomous vehicle's driving path is dangerous. That is, when either the lateral or longitudinal distance is less than its corresponding safety distance, the check result is that the autonomous vehicle's driving path is dangerous. For example, when the lateral distance is greater than a preset lateral safety distance, and the longitudinal distance is less than a preset longitudinal safety distance, the check result for the updated autonomous vehicle's driving path is that the autonomous vehicle's driving path is dangerous.

[0079] The aforementioned lane-changing method involves the terminal acquiring the distances between the autonomous vehicle and other vehicles, including lateral and longitudinal distances. Based on these distances, a check result is obtained. This makes the safety check of the updated autonomous vehicle's driving path more accurate, thereby making the control of the autonomous vehicle based on the check results safer.

[0080] Based on the above embodiments, the terminal can also obtain lane-changing suggestion behavior of the autonomous vehicle according to the driving path of the autonomous vehicle. The following is a demonstration... Figure 6 The embodiments shown will be described in detail below.

[0081] Figure 6 This is a flowchart illustrating a lane-changing method in another embodiment. This embodiment relates to the specific process by which the terminal obtains lane-changing suggestions from the autonomous vehicle based on its driving path. Figure 6 As shown, one possible implementation method of S101 "obtaining the driving path prediction results of other vehicles based on the lane change suggestion behavior of the autonomous vehicle" further includes the following steps:

[0082] S501. Based on the autonomous vehicle's driving path, obtain the autonomous vehicle's lane change requirements.

[0083] Specifically, as described in the above embodiments, the driving path can refer to the vehicle's travel route, which may include routes already traveled and routes planned for the vehicle. The driving path of the autonomous vehicle may include the planned travel route of the autonomous vehicle planned by the terminal. When the driving path of the autonomous vehicle includes a lane-changing route, the lane-changing requirement of the autonomous vehicle is obtained based on the driving path. For example, if the autonomous vehicle is traveling in the right lane, and based on the driving path, it is determined that the autonomous vehicle needs to turn left at the upcoming intersection, then the lane-changing requirement of the autonomous vehicle is to change lanes to the left. It should be noted that the lane-changing requirement of the autonomous vehicle can be adaptively changed according to changes in the autonomous vehicle's driving trajectory.

[0084] S502. Based on lane change requirements, obtain lane change suggestions for autonomous vehicles.

[0085] Specifically, based on the above embodiments, after obtaining the lane-change request of the autonomous vehicle, a suggested lane-change behavior for the autonomous vehicle is determined according to the lane-change request and the road conditions on which the autonomous vehicle is traveling. When the road on which the autonomous vehicle is traveling is a busy section with many vehicles and short distances between them, and the autonomous vehicle obtains the distance between itself and other vehicles through sensors, if this distance is less than a preset safe distance, making it impossible for the autonomous vehicle to complete the lane change in time, then the suggested lane-change behavior for the autonomous vehicle is obtained based on the lane-change request and the busy road conditions. For example, if the lane-change request of the autonomous vehicle is to change lanes to the right, and the road section on which the autonomous vehicle is traveling is congested, then the suggested lane-change behavior for the autonomous vehicle is determined to be a right-of-way violation of other vehicles.

[0086] The aforementioned lane-changing method involves the terminal obtaining the lane-changing request of the autonomous vehicle based on its driving path, obtaining lane-changing suggestion behavior based on the lane-changing request, obtaining the predicted driving paths of other vehicles based on the lane-changing suggestion behavior, and then updating the autonomous vehicle's driving path based on the predicted driving paths. This ensures that the updated driving path of the autonomous vehicle is determined by the lane-changing request, avoiding frequent lane changes by the autonomous vehicle and improving the safety and standardization of autonomous vehicle driving.

[0087] It should be understood that, although Figure 2-6 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated in this document, there is no strict order in which these steps are executed; they can be performed in other orders. Furthermore, Figure 2-6At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0088] Figure 7 This is a schematic diagram of the vehicle lane-changing device provided in one embodiment, such as... Figure 7 As shown, the vehicle lane-changing device includes: an acquisition module 10 and an update module 20, wherein:

[0089] The acquisition module 10 is used to acquire the predicted driving paths of other vehicles based on the lane change suggestion behavior of the autonomous vehicle; the lane change suggestion behavior includes the planning behavior of the autonomous vehicle infringing on the right-of-way of other vehicles.

[0090] The update module 20 is used to update the driving path of the autonomous vehicle based on the predicted driving path; the predicted driving path includes paths planned by other vehicles to avoid the autonomous vehicle and paths planned by other vehicles not to avoid the autonomous vehicle.

[0091] In one embodiment, the acquisition module 10 is specifically used to predict the predicted driving paths of other vehicles corresponding to the lane change suggestion behavior according to a preset prediction rule; the prediction rule is used to predict the driving trajectories of other vehicles based on the right-of-way violation behavior of the autonomous vehicle.

[0092] The vehicle lane-changing device provided in this embodiment of the invention can execute the above-described method embodiment, and its implementation principle and technical effect are similar, so they will not be described again here.

[0093] Figure 8 This is a schematic diagram of the vehicle lane-changing device provided in another embodiment. Figure 7 Based on the illustrated embodiments, as Figure 7 As shown, the vehicle lane-changing device also includes: a training module 30, wherein:

[0094] The training module 30 is specifically used to collect lane-changing behaviors of multiple vehicles; obtain the driving trajectories of other vehicles corresponding to the lane-changing behaviors of the multiple vehicles; and train the prediction rule based on the lane-changing behaviors of the multiple vehicles and the driving trajectories of other vehicles corresponding to the lane-changing behaviors of the multiple vehicles.

[0095] The vehicle lane-changing device provided in this embodiment of the invention can execute the above-described method embodiment, and its implementation principle and technical effect are similar, so they will not be described again here.

[0096] Figure 9This is a schematic diagram of the vehicle lane-changing device provided in another embodiment. Figure 7 or Figure 8 Based on the illustrated embodiments, as Figure 9 As shown, the vehicle lane-changing device also includes: an inspection module 40 and a control module 50, wherein:

[0097] The inspection module 40 is used to perform a safety check on the updated driving path of the autonomous vehicle and obtain the inspection results; the inspection results include the safety of the driving path of the autonomous vehicle and the danger of the driving path of the autonomous vehicle.

[0098] The control module 50 is used to control the driving of the unmanned vehicle based on the inspection results.

[0099] In one embodiment, the control module 50 is specifically used to control the autonomous vehicle to stop performing lane-changing behavior when the inspection result indicates that the autonomous vehicle's driving path is dangerous.

[0100] It should be noted that, Figure 9 Based on Figure 8 This is based on the above, of course Figure 9 It can also be based on Figure 7 The structure is shown here, but it is only one example.

[0101] The vehicle lane-changing device provided in this embodiment of the invention can execute the above-described method embodiment, and its implementation principle and technical effect are similar, so they will not be described again here.

[0102] Figure 10 This is a schematic diagram of the vehicle lane-changing device provided in another embodiment, such as... Figure 10 As shown, the inspection module 40 further includes: an acquisition unit 401 and an inspection unit 402, wherein:

[0103] Acquisition unit 401 is used to acquire the distance between the unmanned vehicle and the other vehicles, the distance including lateral distance and longitudinal distance;

[0104] The inspection unit 402 is used to obtain the inspection result based on the distance between the unmanned vehicle and other vehicles.

[0105] In one embodiment, if the lateral distance is greater than a preset lateral safety distance and the longitudinal distance is greater than a preset longitudinal safety distance, the inspection result is that the driving path of the autonomous vehicle is safe; if the lateral distance is less than the preset lateral safety distance and / or the longitudinal distance is less than the preset longitudinal safety distance, the inspection result is that the driving path of the autonomous vehicle is dangerous.

[0106] In one embodiment, the acquisition module 10 is further configured to acquire the lane change request of the autonomous vehicle based on the driving path of the autonomous vehicle; and acquire the lane change suggestion behavior of the autonomous vehicle based on the lane change request.

[0107] It should be noted that, Figure 10 Based on Figure 9 This is based on the above, of course Figure 10 It can also be based on Figure 7 or Figure 8 The structure is shown here, but it is only one example.

[0108] The vehicle lane-changing device provided in this embodiment of the invention can execute the above-described method embodiment, and its implementation principle and technical effect are similar, so they will not be described again here.

[0109] For specific limitations regarding a vehicle lane-changing device, please refer to the limitations on vehicle lane-changing methods above, which will not be repeated here. Each module in the aforementioned vehicle lane-changing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0110] In one embodiment, a computer device is provided, which may be a terminal device, and its internal structure diagram may be as follows: Figure 11 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a vehicle lane-changing method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0111] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0112] In one embodiment, a terminal device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to perform the following steps:

[0113] Based on the lane change suggestion behavior of the autonomous vehicle, the predicted driving paths of other vehicles are obtained; the lane change suggestion behavior includes the planning behavior of the autonomous vehicle infringing on the right-of-way of other vehicles.

[0114] The driving path of the autonomous vehicle is updated based on the predicted driving path; the predicted driving path includes either a path planned by other vehicles to avoid the autonomous vehicle or a path planned by other vehicles not to avoid the autonomous vehicle.

[0115] In one embodiment, when the processor executes the computer program, it further implements the following steps: predicting the predicted driving paths of other vehicles corresponding to the lane change suggestion behavior according to a preset prediction rule; the prediction rule is used to predict the driving trajectories of other vehicles based on the right-of-way violation behavior of the autonomous vehicle.

[0116] In one embodiment, when the processor executes the computer program, it further performs the following steps: collecting multiple vehicle lane-changing behaviors; obtaining the driving trajectories of other vehicles corresponding to the multiple vehicle lane-changing behaviors; and training the prediction rule based on the multiple vehicle lane-changing behaviors and the driving trajectories of other vehicles corresponding to the multiple vehicle lane-changing behaviors.

[0117] In one embodiment, when the processor executes the computer program, it further performs the following steps: performing a safety check on the updated driving path of the autonomous vehicle and obtaining a check result; the check result includes whether the driving path of the autonomous vehicle is safe and whether the driving path of the autonomous vehicle is dangerous; and controlling the autonomous vehicle to drive according to the check result.

[0118] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining the distance between the autonomous vehicle and the other vehicles, the distance including lateral distance and longitudinal distance; and obtaining the inspection result based on the distance between the autonomous vehicle and the other vehicles.

[0119] In one embodiment, if the lateral distance is greater than a preset lateral safety distance and the longitudinal distance is greater than a preset longitudinal safety distance, the inspection result is that the driving path of the autonomous vehicle is safe; if the lateral distance is less than the preset lateral safety distance and / or the longitudinal distance is less than the preset longitudinal safety distance, the inspection result is that the driving path of the autonomous vehicle is dangerous.

[0120] In one embodiment, when the processor executes the computer program, it further implements the following steps: when the inspection result indicates that the autonomous vehicle's driving path is dangerous, it controls the autonomous vehicle to stop performing lane-changing behavior.

[0121] In one embodiment, when the processor executes the computer program, it further implements the following steps: obtaining the lane-changing request of the autonomous vehicle based on the driving path of the autonomous vehicle; and obtaining the lane-changing suggestion behavior of the autonomous vehicle based on the lane-changing request.

[0122] The terminal device provided in this embodiment is similar in principle and technical effect to the method embodiment described above, and will not be repeated here.

[0123] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0124] Based on the lane change suggestion behavior of the autonomous vehicle, the predicted driving paths of other vehicles are obtained; the lane change suggestion behavior includes the planning behavior of the autonomous vehicle infringing on the right-of-way of other vehicles.

[0125] The driving path of the autonomous vehicle is updated based on the predicted driving path; the predicted driving path includes either a path planned by other vehicles to avoid the autonomous vehicle or a path planned by other vehicles not to avoid the autonomous vehicle.

[0126] In one embodiment, when the computer program is executed by a processor, it performs the following steps: predicting the predicted driving paths of other vehicles corresponding to the lane change suggestion behavior according to a preset prediction rule; the prediction rule is used to predict the driving trajectories of other vehicles based on the right-of-way violation behavior of the autonomous vehicle.

[0127] In one embodiment, when a computer program is executed by a processor, it performs the following steps: collecting lane-changing behaviors of multiple vehicles; obtaining the driving trajectories of other vehicles corresponding to the lane-changing behaviors of the multiple vehicles; and training the prediction rule based on the lane-changing behaviors of the multiple vehicles and the driving trajectories of other vehicles corresponding to the lane-changing behaviors of the multiple vehicles.

[0128] In one embodiment, when the computer program is executed by a processor, it performs the following steps: performing a safety check on the updated driving path of the autonomous vehicle and obtaining a check result; the check result includes whether the driving path of the autonomous vehicle is safe and whether the driving path of the autonomous vehicle is dangerous; and controlling the driving of the autonomous vehicle based on the check result.

[0129] In one embodiment, when the computer program is executed by a processor, it performs the following steps: obtaining the distance between the autonomous vehicle and the other vehicles, the distance including lateral distance and longitudinal distance; and obtaining the inspection result based on the distance between the autonomous vehicle and the other vehicles.

[0130] In one embodiment, if the lateral distance is greater than a preset lateral safety distance and the longitudinal distance is greater than a preset longitudinal safety distance, the inspection result is that the driving path of the autonomous vehicle is safe; if the lateral distance is less than the preset lateral safety distance and / or the longitudinal distance is less than the preset longitudinal safety distance, the inspection result is that the driving path of the autonomous vehicle is dangerous.

[0131] In one embodiment, when the computer program is executed by the processor, it performs the following steps: when the inspection result indicates that the autonomous vehicle's driving path is dangerous, it controls the autonomous vehicle to stop performing lane-changing behavior.

[0132] In one embodiment, when the computer program is executed by a processor, it performs the following steps: obtaining the lane-changing request of the autonomous vehicle based on the driving path of the autonomous vehicle; and obtaining the lane-changing suggestion behavior of the autonomous vehicle based on the lane-changing request.

[0133] The computer-readable storage medium provided in this embodiment is similar in principle and technical effect to the method embodiment described above, and will not be repeated here.

[0134] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0135] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for changing lanes for vehicles, characterized in that, The method includes: Based on the lane change suggestion behavior of the autonomous vehicle, the predicted driving paths of other vehicles are obtained; the lane change suggestion behavior includes the planning behavior of the autonomous vehicle infringing on the right-of-way of other vehicles, and the planning behavior includes the specific distance of the autonomous vehicle infringing on the right-of-way of other vehicles; the lane change suggestion behavior includes the autonomous vehicle deviating into the lane where the other vehicle is located. The driving path of the autonomous vehicle is updated based on the predicted driving path; the predicted driving path includes the path planned by other vehicles to avoid the autonomous vehicle or the path planned by other vehicles not to avoid the autonomous vehicle. A safety check is performed on the updated driving path of the autonomous vehicle to obtain the check results; the check results include whether the driving path of the autonomous vehicle is safe or dangerous. Based on the inspection results, control the autonomous vehicle to drive.

2. The method according to claim 1, characterized in that, The step of obtaining the predicted driving paths of other vehicles based on the lane-change suggestion behavior of the autonomous vehicle includes: According to preset prediction rules, the predicted driving paths of other vehicles corresponding to the lane change suggestion behavior are predicted; the prediction rules are used to predict the driving trajectories of other vehicles based on the right-of-way violation behavior of the autonomous vehicle.

3. The method according to claim 2, characterized in that, The method further includes: Collect data on lane-changing behavior of multiple vehicles; Obtain the driving trajectories of other vehicles corresponding to the lane-changing behaviors of the multiple vehicles; The prediction rule is trained based on the lane-changing behaviors of the multiple vehicles and the driving trajectories of other vehicles corresponding to the lane-changing behaviors.

4. The method according to claim 1, characterized in that, The updated driving path of the autonomous vehicle is subjected to a safety check, and the check results are obtained, including: The distance between the autonomous vehicle and the other vehicles is obtained, including lateral distance and longitudinal distance; The inspection results are obtained based on the distance between the autonomous vehicle and other vehicles.

5. The method according to claim 4, characterized in that, The process of obtaining the inspection result based on the distance between the autonomous vehicle and other vehicles includes: If the lateral distance is greater than a preset lateral safety distance, and the longitudinal distance is greater than a preset longitudinal safety distance, then the inspection result indicates that the autonomous vehicle's driving path is safe. If the lateral distance is less than the preset lateral safety distance, and / or the longitudinal distance is less than the preset longitudinal safety distance, then the inspection result indicates that the autonomous vehicle's driving path is dangerous.

6. The method according to claim 1, characterized in that, The updated driving path of the autonomous vehicle is subjected to a safety check, and the check results are obtained, including: When the updated autonomous vehicle's driving path does not overlap with the driving paths of other vehicles, or when the distance between the updated autonomous vehicle's driving path and the driving paths of other vehicles is greater than a preset safety range, the inspection result is determined to be that the autonomous vehicle's driving path is safe. When the updated autonomous vehicle's driving path overlaps with the driving paths of other vehicles, or when the distance between the updated autonomous vehicle's driving path and the driving paths of other vehicles is less than a preset safety range, the inspection result is determined to be that the autonomous vehicle's driving path is dangerous.

7. The method according to any one of claims 1-6, characterized in that, The step of controlling the autonomous vehicle to drive based on the inspection results includes: If the inspection result indicates that the autonomous vehicle's driving path is dangerous, then the autonomous vehicle will be controlled to stop performing lane-changing actions.

8. The method according to any one of claims 1-6, characterized in that, Before obtaining the predicted driving paths of other vehicles based on the lane-change suggestion behavior of the autonomous vehicle, the method further includes: Based on the driving path of the autonomous vehicle, obtain the lane change requirements of the autonomous vehicle. Based on the lane change request, obtain the lane change suggestion behavior of the autonomous vehicle.

9. A vehicle lane-changing device, characterized in that, The device includes: The acquisition module is used to acquire the predicted driving paths of other vehicles based on the lane change suggestion behavior of the autonomous vehicle; the lane change suggestion behavior includes the planning behavior of the autonomous vehicle infringing on the right-of-way of other vehicles, and the planning behavior includes the specific distance of the autonomous vehicle infringing on the right-of-way of other vehicles; the lane change suggestion behavior includes the autonomous vehicle deviating into the lane where the other vehicle is located. An update module is used to update the driving path of the autonomous vehicle based on the predicted driving path; the predicted driving path includes paths planned by other vehicles to avoid the autonomous vehicle and paths planned by other vehicles not to avoid the autonomous vehicle. The inspection module is used to perform a safety check on the updated driving path of the autonomous vehicle and obtain the inspection results; the inspection results include whether the driving path of the autonomous vehicle is safe or dangerous. The control module is used to control the driving of the driverless vehicle based on the inspection results.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-8.

Images