Automatic driving lane changing control method and device, computer equipment, readable storage medium and program product
By generating lane-changing driving trajectory and controlling the vehicle to change lanes, the problem that the autonomous driving system cannot complete lane changes in lane-changing scenarios is solved, and the lane-changing ability and scene applicability are improved.
Patent Information
- Application Number
- CN202411158295.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-11-12
AI Technical Summary
The existing autonomous driving system cannot complete lane change in road scenarios where lane change space is limited, resulting in low scenario applicability.
By receiving the lane change request, the target lane is determined, and the vehicle to be changed is determined based on the preset period. When the lane change is not completed, a lane change driving trajectory is generated, and the predicted motion trajectory of the target lane and obstacles that need to be avoided are controlled, the vehicle will change lanes, and the lane change is continuously judged whether the lane change is completed.
When lane change space is limited, ensure that the autonomous driving vehicle can safely complete lane change operations, improve lane change capabilities, avoid returning to the original lane, and enhance the scene applicability of the autonomous driving system.
Smart Images

Figure CN118928469A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of autonomous driving technology, and in particular to an autonomous driving lane change control method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art
[0002] At present, the autonomous driving system needs to ensure that the vehicle completes the lane change action in specific scenarios, that is, changing from the current lane to the adjacent lane on the left or right. The sources of lane change include but are not limited to the desire to enter a lane with a faster average speed, the desire to enter a lane leading to a specific direction (such as a ramp, a left turn lane), and the need to detour due to being blocked by a faulty vehicle.
[0003] Generally, the autonomous driving system needs to combine the surrounding traffic conditions to determine whether the lane change meets the safety requirements. If not, it will maintain the cruising state in the lane. Otherwise, it will generate the target lane change trajectory and execute the lane change action. However, due to the complexity of the road conditions, there will be limited lane change space during the vehicle driving (the term limited lane change space is a bit ambiguous, but I can't think of a better word to describe it). For example, it is necessary to enter the left turn lane from the straight lane before the intersection. At this time, when the autonomous driving vehicle determines that there is insufficient space for lane change safety, it cannot cruise and can only gradually slow down and eventually stop before the intersection, and cannot complete the lane change.
[0004] The current autonomous driving lane changing method has the problem of being unable to complete the lane change in road scenarios with limited lane changing space, and its scenario applicability is low. Summary of the invention
[0005] Based on this, it is necessary to provide an automatic driving lane change control method, device, computer equipment, computer readable storage medium and computer program product that can be applied to different scenarios in order to address the above technical problems.
[0006] In a first aspect, the present application provides an automatic driving lane change control method, comprising:
[0007] When a lane change request is received, determining a target lane according to the lane change request;
[0008] According to a preset cycle, determining whether the vehicle to be changed lanes has completed the lane change;
[0009] When the vehicle to be changed lanes has not completed the lane change, a lane change trajectory is generated according to the target lane and the predicted motion trajectory of the target obstacle to be avoided;
[0010] The vehicle is controlled to change lanes according to the lane-changing driving trajectory, and the process returns to the step of determining whether the vehicle to be changed lanes has completed the lane change according to a preset cycle.
[0011] In one embodiment, a lane change driving trajectory is generated according to a target lane and a predicted motion trajectory of a target obstacle to be avoided, including:
[0012] According to the target lane, the lane changing path of the vehicle to be changed is obtained;
[0013] According to the target lane, the predicted motion trajectory of the target obstacle to be avoided is obtained, and according to the lane change path and the predicted motion trajectory, the position points of the vehicle to be changed in the lane change path at each continuous moment in the future are determined to obtain the position time series of the vehicle to be changed;
[0014] The lane-changing driving trajectory is generated according to the lane-changing path and position time series.
[0015] In one embodiment, obtaining a lane change path of a vehicle to be changed lanes according to a target lane includes:
[0016] Identify environmental obstacles based on the location and width information of the target lane and the environmental information of the road where the vehicle to be changed is located;
[0017] Determine the lateral motion boundary of the vehicle to be changed lanes according to the obstacle information of the environmental obstacle, the target lane and the lane change direction of the vehicle to be changed lanes; the obstacle information is used to characterize the size and motion of the environmental obstacle;
[0018] The lane changing path is obtained according to the current position of the vehicle to be changed, the target lane and the lateral movement boundary.
[0019] In one embodiment, before determining the lateral motion boundary of the vehicle to be changed lanes according to the obstacle information of the environmental obstacle, the target lane and the lane change direction of the vehicle to be changed lanes, the method further includes:
[0020] According to the preset screening conditions, obstacles that have no interaction with the vehicle to be changed and the target lane are screened out from the environmental obstacles to obtain the screened environmental obstacles.
[0021] In one embodiment, according to the lane changing path and the predicted motion trajectory, the position points of the vehicle to be changed lanes in the lane changing path at each consecutive moment in the future are determined to obtain the position time series of the vehicle to be changed lanes, including:
[0022] Generate a virtual lane for the vehicle to change lanes according to the structural information and lane-changing path of the vehicle to change lanes;
[0023] According to the overlap between the virtual channel and the predicted motion trajectory, the position of the vehicle to be changed lanes in the lane change path at each successive moment in the future is determined;
[0024] According to the position-time correspondence between each future continuous moment and each position point in the lane change path, a position-time sequence is obtained.
[0025] In one embodiment, the method further comprises:
[0026] Identify the target obstacle in the target lane, and obtain the traffic density and average speed of the target lane based on the motion information of the target obstacle;
[0027] Generate a motion braking decision for controlling the vehicle to change lanes based on the traffic density and average vehicle speed of the target lane;
[0028] According to the lane changing path and the motion braking decision, the estimated arrival time corresponding to each position point in the lane changing path is determined, and the position time series of the vehicle to be changed lanes is obtained according to the estimated arrival time corresponding to each position point in the lane changing path.
[0029] In a second aspect, the present application also provides an automatic driving lane change control device, comprising:
[0030] a determination module, configured to determine a target lane according to the lane change request when a lane change request is received;
[0031] A judgment module, used to judge whether the vehicle to be changed lanes has completed the lane change according to a preset period;
[0032] A generation module, used for generating a lane-changing driving trajectory according to a target lane and a predicted motion trajectory of a target obstacle to be avoided when the vehicle to be changed lanes has not completed the lane change;
[0033] The control module is used to control the vehicle to change lanes according to the lane-changing driving trajectory, and return to execute the step of judging whether the vehicle to be changed lanes has completed the lane change according to a preset cycle.
[0034] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0035] When a lane change request is received, determining a target lane according to the lane change request;
[0036] According to a preset cycle, determining whether the vehicle to be changed lanes has completed the lane change;
[0037] When the vehicle to be changed lanes has not completed the lane change, a lane change trajectory is generated according to the target lane and the predicted motion trajectory of the target obstacle to be avoided;
[0038] The vehicle is controlled to change lanes according to the lane-changing driving trajectory, and the process returns to the step of determining whether the vehicle to be changed lanes has completed the lane change according to a preset cycle.
[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:
[0040] When a lane change request is received, determining a target lane according to the lane change request;
[0041] According to a preset cycle, determining whether the vehicle to be changed lanes has completed the lane change;
[0042] When the vehicle to be changed lanes has not completed the lane change, a lane change trajectory is generated according to the target lane and the predicted motion trajectory of the target obstacle to be avoided;
[0043] The vehicle is controlled to change lanes according to the lane-changing driving trajectory, and the process returns to the step of determining whether the vehicle to be changed lanes has completed the lane change according to a preset cycle.
[0044] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:
[0045] When a lane change request is received, determining a target lane according to the lane change request;
[0046] According to a preset cycle, determining whether the vehicle to be changed lanes has completed the lane change;
[0047] When the vehicle to be changed lanes has not completed the lane change, a lane change trajectory is generated according to the target lane and the predicted motion trajectory of the target obstacle to be avoided;
[0048] The vehicle is controlled to change lanes according to the lane-changing driving trajectory, and the process returns to the step of determining whether the vehicle to be changed lanes has completed the lane change according to a preset cycle.
[0049] The above-mentioned automatic driving lane change control method, device, computer equipment, computer readable storage medium and computer program product, when receiving a lane change request, determine the target lane according to the lane change request; judge whether the vehicle to be changed has completed the lane change according to a preset period; if the vehicle to be changed has not completed the lane change, generate a lane change driving trajectory according to the target lane and the predicted motion trajectory of the target obstacle to be avoided; control the vehicle to change lanes according to the lane change driving trajectory, and return to execute the step of judging whether the vehicle to be changed has completed the lane change according to the preset period. The pre-decision module for judging whether there is a safe lane change space in the lane change decision process is cancelled, and only the motion planning scheme is used to ensure the safety of the lane change process. When the lane change is necessary and the current lane has limited space for continued driving, it can be ensured that the cruise state can be immediately released after the lane change request is initiated, and the lane change action can be started. When the surrounding environment does not support safe lane change, the vehicle will continue to ensure safety through motion control means and continue to maintain the lane change state without returning to the original lane, which greatly improves the lane change ability of the automatic driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0051] FIG1 is a diagram showing an application environment of an automatic driving lane change control method according to an embodiment;
[0052] FIG2 is a schematic diagram of a flow chart of an automatic driving lane change control method in one embodiment;
[0053] FIG3 is a logic diagram of an automatic driving lane change control method according to an embodiment;
[0054] FIG4 is a schematic diagram of a lane change path in one embodiment;
[0055] FIG5 is a schematic diagram of a virtual channel in one embodiment;
[0056] FIG6 is a schematic diagram of a position time series in one embodiment;
[0057] FIG7 is a logic diagram of another automatic driving lane change control method according to an embodiment;
[0058] FIG8 is a structural block diagram of an automatic driving lane change control device in one embodiment;
[0059] FIG. 9 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0060] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0061] The automatic driving lane change control method provided in the embodiment of the present application can be applied in the application environment shown in FIG1. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.
[0062] In an exemplary embodiment, as shown in FIG2 , an automatic driving lane change control method is provided, which is described by taking the method applied to the terminal 102 in FIG1 as an example, and includes the following steps 202 to 206. Among them:
[0063] Step 202: upon receiving a lane change request, determining a target lane according to the lane change request.
[0064] Optionally, when the upstream decision module of the autonomous driving initiates a lane change request, the autonomous driving vehicle immediately enters the lane change mode, and the terminal identifies the target lane to change into from the lane change request.
[0065] Step 204: Determine whether the vehicle to be changed lanes has completed the lane change according to a preset period.
[0066] Optionally, after the autonomous driving vehicle enters the lane change mode, the terminal determines whether the vehicle has completed the lane change according to a preset period. As shown in FIG3 , if the vehicle has completed the lane change, the autonomous driving lane change control process ends and the autonomous driving vehicle exits the lane change mode.
[0067] Step 206, when the vehicle to be changed lanes has not completed the lane change, a lane change trajectory is generated according to the target lane and the predicted motion trajectory of the target obstacle to be avoided.
[0068] Among them, target obstacles include but are not limited to vehicles, pedestrians and warning signs.
[0069] Optionally, as shown in FIG3 , if the vehicle has not completed the lane change, the terminal identifies a target obstacle in the target lane that needs to be avoided, and predicts the predicted motion trajectory of the target obstacle, thereby changing the lane driving trajectory.
[0070] Step 208, controlling the vehicle to change lanes according to the lane-changing driving trajectory, and returning to execute the step of determining whether the vehicle to be changed lanes has completed the lane change according to a preset cycle.
[0071] Optionally, in the lane change mode, the autonomous driving vehicle controls the vehicle to change lanes according to the most recently generated lane change driving trajectory, and continues to determine whether the vehicle to be changed lanes has completed the lane change according to a preset cycle, as shown in FIG3 . If the lane change is not completed, a new lane change driving trajectory is generated, and the vehicle's lane change trajectory is adjusted in real time; if the lane change is completed, the autonomous driving vehicle exits the lane change mode.
[0072] When the autonomous driving needs to change lanes, there is no need to prejudge whether the lane change can be performed, but to directly generate the lane change trajectory. When the ego vehicle is in a cruising state and a lane change request is just initiated, the ego vehicle trajectory is ready to move to the target lane and will not continue to maintain the cruising state; when the ego vehicle is in a lane change state and the environmental conditions change and the lane change cannot be continued, the ego vehicle will brake to stop and will not return to the original lane until the environmental conditions allow the vehicle to continue to perform the lane change action, and the ego vehicle will start to complete the lane change. That is, the autonomous driving vehicle will definitely be able to complete the lane change and will not return to the original lane. In general, after receiving a lane change request, the ego vehicle will immediately start the lane change action. When the surrounding environment does not meet the safety conditions (that is, the lane change may cause a collision), the ego vehicle maintains a different path and only uses longitudinal behavior (that is, deceleration) to ensure safety.
[0073] In the above-mentioned automatic driving lane change control method, when a lane change request is received, the target lane is determined according to the lane change request; according to a preset period, it is determined whether the vehicle to be changed has completed the lane change; when the vehicle to be changed has not completed the lane change, a lane change driving trajectory is generated according to the target lane and the predicted motion trajectory of the target obstacle to be avoided; the vehicle is controlled to change lanes according to the lane change driving trajectory, and the step of returning to execute the step of determining whether the vehicle to be changed has completed the lane change according to the preset period is returned. The pre-decision module for determining whether there is a safe lane change space in the lane change decision process is cancelled, and only the motion planning scheme is used to ensure the safety of the lane change process. When the lane change is necessary and the current lane has limited space for continued driving, it can be ensured that the cruise state can be immediately released after the lane change request is initiated, and the lane change action can be started. When the surrounding environment does not support safe lane change, the vehicle will continue to ensure safety through motion control means, and continue to maintain the lane change state, and will not return to the original lane, which greatly improves the lane change ability of the automatic driving vehicle and can even achieve the effect of "squeezing in".
[0074] In one embodiment, a lane changing driving trajectory is generated according to a target lane and a predicted motion trajectory of a target obstacle to be avoided, including: obtaining a lane changing path of a vehicle to be changed according to the target lane; obtaining a predicted motion trajectory of a target obstacle to be avoided according to the target lane, determining the position points of the vehicle to be changed in the lane changing path at each continuous moment in the future according to the lane changing path and the predicted motion trajectory, and obtaining a position time series of the vehicle to be changed; and generating a lane changing driving trajectory according to the lane changing path and the position time series.
[0075] Optionally, the generated lane change driving trajectory contains two elements:
[0076] 1. Lane change path, that is, the route on the road plane that the autonomous driving vehicle needs to track for lateral movement, that is, the coordinates of the position.
[0077] 2. Position time series, the st sequence, determines how far the autonomous vehicle travels at a certain point in time. s refers to the distance the vehicle travels along the path, t refers to time, and the st sequence represents the distance the vehicle needs to travel at each time point starting from the current moment.
[0078] According to the path and st sequences, we can obtain the lane change trajectory planned by the autonomous driving vehicle, that is, where the autonomous driving vehicle will appear at a certain moment.
[0079] Specifically, it can be explained in combination with specific scenarios:
[0080] In the lane change scenario shown in FIG4 , the ego vehicle needs to change lanes to the left, and the stationary vehicle 3 is determined to be a vehicle that needs to be avoided laterally, and a lane change path is directly generated considering the vehicle 3. The lane change path is only the spatial position where the ego vehicle will travel in the future.
[0081] After the lane change path is generated, consider moving vehicles 1 and 2. Based on the lane change path and the width of the ego vehicle, generate a virtual driving channel for the ego vehicle. Combined with the predicted motion trajectories of vehicles 1 and 2, calculate when (t) and where (s) the two appear in the virtual channel, as shown in Figure 5, and plot them in the ST diagram, as shown in Figure 6. According to the movement ability boundaries of vehicles 1, 2 and the ego vehicle, make a decision to follow or overtake. Finally, combined with other requirements such as comfort, calculate the ST sequence of the ego vehicle. Each point in the ST sequence indicates the position of the ego vehicle along the lane change path at each time point, for example, after 1 second, the ego vehicle needs to travel 10 meters along the lane change path.
[0082] By combining the spatial coordinates of the lane-changing path and the time coordinates shown in the st sequence, the lane-changing driving trajectory can be obtained.
[0083] In this embodiment, there is no need to prejudge whether the lane change can be executed. Instead, the lane change driving trajectory is generated directly according to the target lane and the predicted motion trajectory of the target obstacle that needs to be avoided, thereby greatly improving the lane change capability of the autonomous driving vehicle.
[0084] In one embodiment, a lane changing path of a vehicle to be changed is obtained according to a target lane, including: identifying environmental obstacles according to position information and width information of the target lane and environmental information of the road on which the vehicle to be changed is located; determining a lateral motion boundary of the vehicle to be changed according to obstacle information of the environmental obstacles, the target lane and the lane changing direction of the vehicle to be changed; the obstacle information is used to characterize the size and motion of the environmental obstacles; and obtaining the lane changing path according to the current position of the vehicle to be changed, the target lane and the lateral motion boundary.
[0085] Optionally, the step of generating a lane change path, as shown in FIG3, includes: searching all surrounding targets, combining the position and width of the target lane, screening out the targets that need to be avoided by the vehicle laterally, and obtaining their position coordinates and geometric information. Combined with the information of the target to be avoided, as well as the direction of lane change and the target lane of lane change, generate the lateral motion boundary of the vehicle required to calculate the path. Use commonly used path planning schemes, such as 5th or 7th order polynomial curves, Bezier curves, clothoids, etc., to generate a path based on the lateral motion boundary generated in the previous step, with the starting point at the current position of the vehicle and the end point at the target lane.
[0086] In a feasible implementation manner, before determining the lateral movement boundary of the vehicle to be changed lanes according to the obstacle information of the environmental obstacles, the target lane and the lane changing direction of the vehicle to be changed lanes, it also includes: according to preset screening conditions, in the environmental obstacles, screening out obstacles that have no interaction with the vehicle to be changed lanes and the target lane to obtain screened environmental obstacles.
[0087] Specifically, in the link of generating the path, an obstacle screening module can be added to filter out obstacles that do not affect the path generation, such as obstacles that are not in the target lane of the lane change, or obstacles that are completely moving in the target lane, or obstacles that are completely unable to interact with the ego vehicle within the range of the ego vehicle's movement capability, and retain obstacles that affect the path generation, such as obstacles that are not in the target lane but slightly intrude into the target lane, and static obstacles that are in the target lane but can be avoided by the ego vehicle; the path boundary is generated based on the obstacles screened by the obstacle screening module, and the path is generated.
[0088] In this embodiment, there is no need to prejudge whether the lane change can be performed. Instead, the lane change path of the vehicle to be changed is obtained directly according to the target lane, thereby generating a lane change driving trajectory, which greatly improves the lane change ability of the autonomous driving vehicle.
[0089] In one embodiment, based on the lane changing path and the predicted motion trajectory, the position points of the vehicle to be lane-changed in the lane changing path at each continuous moment in the future are determined to obtain a position time series of the vehicle to be lane-changed, including: generating a virtual channel for the vehicle to be lane-changed to travel based on the structural information and the lane changing path of the vehicle to be lane-changed; determining the position points of the vehicle to be lane-changed in the lane changing path at each continuous moment in the future based on the overlap between the virtual channel and the predicted motion trajectory; and obtaining the position time series based on the position-time correspondence between each continuous moment in the future and each position point in the lane changing path.
[0090] Optionally, the step of generating a position time series ST sequence, as shown in FIG3, includes: generating a channel for the self-vehicle to travel based on the path (similar to a virtual lane), the channel width is centered on the path, and extends to the left and right by a certain distance half_width, half_width = half the width of the self-vehicle + safety width margin. Considering the predicted trajectories of all targets, when the predicted trajectory of a certain target will invade the driving channel of the self-vehicle, the intrusion time t and the intrusion position s are calculated by geometric overlap. According to the current position, speed and movement ability of the self-vehicle, it is judged whether the self-vehicle should follow the target at time t, or whether the self-vehicle can surpass the target at time t or surpass the target through game, and obtain the longitudinal decision for the target at time t. When the predicted trajectories of all targets are considered, the decision on surpassing and following all targets within the planning time can be combined to obtain the distance traveled by the self-vehicle within the entire planning time, and obtain the ST sequence.
[0091] In a feasible implementation, a target obstacle in a target lane is identified, and the traffic density and average speed of the target lane are obtained based on the motion information of the target obstacle; a motion braking decision for controlling the vehicle to be changed lanes is generated based on the traffic density and average speed of the target lane; an estimated arrival time corresponding to each position point in the lane changing path is determined based on the lane changing path and the motion braking decision, and a position time series of the vehicle to be changed lanes is obtained based on the estimated arrival time corresponding to each position point in the lane changing path.
[0092] Specifically, as shown in FIG7 , when generating an ST sequence, it is not necessary to make targeted decisions for each obstacle one by one. Other means can be used, such as the traffic density and average speed of the target lane to generate a general decision on movement or braking, and then generate an ST sequence that meets the requirements of the general decision. For example, if the general decision requires stopping before the lane line, then an ST sequence is generated that stops just before the lane line within the planning time domain. For example, if the general decision requires completing the lane change, then an ST sequence is generated that can complete the lane change within the planning time domain.
[0093] In this embodiment, there is no need to determine in advance whether the lane change can be executed. Instead, the predicted motion trajectory of the target obstacle to be avoided is directly obtained based on the target lane. The estimated arrival time corresponding to each position point in the lane change path is determined based on the lane change path and the predicted motion trajectory. Based on the estimated arrival time corresponding to each position point in the lane change path, the position time series of the vehicle to be changed is obtained, thereby generating a lane change driving trajectory, which greatly improves the lane change capability of the autonomous driving vehicle.
[0094] In an exemplary embodiment, an automatic driving lane change control method, as shown in FIG3 , includes:
[0095] When a lane change request is received, a target lane is determined according to the lane change request.
[0096] According to the preset cycle, it is determined whether the vehicle to be changed lanes has completed the lane change.
[0097] In the case that the vehicle to be changed lanes has not completed the lane change, environmental obstacles are identified according to the position information and width information of the target lane and the environmental information of the road where the vehicle to be changed lanes is located; according to the preset screening conditions, obstacles that have no interaction with the vehicle to be changed lanes and the target lane are screened out from the environmental obstacles to obtain screened environmental obstacles; according to the obstacle information of the environmental obstacles, the target lane and the lane change direction of the vehicle to be changed lanes, the lateral movement boundary of the vehicle to be changed lanes is determined; the obstacle information is used to characterize the size and movement of the environmental obstacles; according to the current position of the vehicle to be changed lanes, the target lane and the lateral movement boundary, the lane change path is obtained.
[0098] According to the target lane, the predicted motion trajectory of the target obstacle to be avoided is obtained; according to the structural information and lane changing path of the vehicle to be changed, a virtual channel for the vehicle to be changed is generated; according to the overlap between the virtual channel and the predicted motion trajectory, the position points of the vehicle to be changed in the lane changing path at each continuous moment in the future are determined; according to the position-time correspondence between each continuous moment in the future and each position point in the lane changing path, a position-time series is obtained.
[0099] The lane-changing driving trajectory is generated according to the lane-changing path and position time series.
[0100] The vehicle is controlled to change lanes according to the lane-changing driving trajectory, and the process returns to the step of determining whether the vehicle to be changed lanes has completed the lane change according to a preset cycle.
[0101] In an exemplary embodiment, an automatic driving lane change control method, as shown in FIG7 , includes:
[0102] When a lane change request is received, a target lane is determined according to the lane change request.
[0103] According to the preset cycle, it is determined whether the vehicle to be changed lanes has completed the lane change.
[0104] In the case that the vehicle to be changed lanes has not completed the lane change, environmental obstacles are identified according to the position information and width information of the target lane and the environmental information of the road where the vehicle to be changed lanes is located; according to the preset screening conditions, obstacles that have no interaction with the vehicle to be changed lanes and the target lane are screened out from the environmental obstacles to obtain screened environmental obstacles; according to the obstacle information of the environmental obstacles, the target lane and the lane change direction of the vehicle to be changed lanes, the lateral movement boundary of the vehicle to be changed lanes is determined; the obstacle information is used to characterize the size and movement of the environmental obstacles; according to the current position of the vehicle to be changed lanes, the target lane and the lateral movement boundary, the lane change path is obtained.
[0105] Identify the target obstacle in the target lane, and obtain the traffic density and average speed of the target lane based on the motion information of the target obstacle; generate a motion braking decision for controlling the vehicle to change lanes based on the traffic density and average speed of the target lane; determine the estimated arrival time corresponding to each position point in the lane changing path based on the lane changing path and the motion braking decision, and obtain the position time series of the vehicle to change lanes based on the estimated arrival time corresponding to each position point in the lane changing path.
[0106] The lane-changing driving trajectory is generated according to the lane-changing path and position time series.
[0107] The vehicle is controlled to change lanes according to the lane-changing driving trajectory, and the process returns to the step of determining whether the vehicle to be changed lanes has completed the lane change according to a preset cycle.
[0108] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0109] Based on the same inventive concept, the embodiment of the present application also provides an automatic driving lane change control device for implementing the automatic driving lane change control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more automatic driving lane change control device embodiments provided below can refer to the limitations of the automatic driving lane change control method above, and will not be repeated here.
[0110] In an exemplary embodiment, as shown in FIG8 , an automatic driving lane change control device 800 is provided, comprising: a determination module 801, a judgment module 802, a generation module 803 and a control module 804, wherein:
[0111] The determination module 801 is used to determine a target lane according to the lane change request when a lane change request is received.
[0112] The judgment module 802 is used to judge whether the vehicle to be changed lanes has completed the lane change according to a preset period.
[0113] The generation module 803 is used to generate a lane-changing driving trajectory according to the target lane and the predicted motion trajectory of the target obstacle to be avoided when the vehicle to be changed lanes has not completed the lane change.
[0114] The control module 804 is used to control the vehicle to change lanes according to the lane-changing driving trajectory, and return to execute the step of determining whether the vehicle to be changed lanes has completed the lane change according to a preset cycle.
[0115] In one embodiment, the generation module 803 is also used to obtain the lane changing path of the vehicle to be changed lanes according to the target lane; obtain the predicted motion trajectory of the target obstacle to be avoided according to the target lane, determine the position points of the vehicle to be changed lanes in the lane changing path at each continuous moment in the future according to the lane changing path and the predicted motion trajectory, and obtain the position time series of the vehicle to be changed lanes; generate the lane changing driving trajectory according to the lane changing path and the position time series.
[0116] In one embodiment, the generation module 803 is also used to identify environmental obstacles based on the position information and width information of the target lane and the environmental information of the road on which the vehicle to be changed is located; determine the lateral movement boundary of the vehicle to be changed according to the obstacle information of the environmental obstacles, the target lane and the lane changing direction of the vehicle to be changed; the obstacle information is used to characterize the size and movement of the environmental obstacles; and obtain the lane changing path according to the current position of the vehicle to be changed, the target lane and the lateral movement boundary.
[0117] In one embodiment, the generating module 803 is further used to filter out obstacles that have no interaction with the vehicle to be changed lanes and the target lane from the environmental obstacles according to preset screening conditions, so as to obtain screened environmental obstacles.
[0118] In one embodiment, the generation module 803 is further used to generate a virtual channel for the vehicle to change lanes based on the structural information and lane changing path of the vehicle to change lanes; determine the position points of the vehicle to change lanes in the lane changing path at each continuous moment in the future based on the overlap between the virtual channel and the predicted motion trajectory; and obtain a position-time series based on the position-time correspondence between each continuous moment in the future and each position point in the lane changing path.
[0119] In one embodiment, the generation module 803 is also used to identify the target obstacle in the target lane, and obtain the traffic density and average speed of the target lane based on the motion information of the target obstacle; generate a motion braking decision for controlling the vehicle to be changed lanes based on the traffic density and average speed of the target lane; determine the estimated arrival time corresponding to each position point in the lane changing path based on the lane changing path and the motion braking decision, and obtain the position time series of the vehicle to be changed lanes based on the estimated arrival time corresponding to each position point in the lane changing path.
[0120] Each module in the above-mentioned automatic driving lane change control device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.
[0121] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG9. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store automatic driving data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an automatic driving lane change control method is implemented.
[0122] Those skilled in the art will understand that the structure shown in FIG. 9 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
[0123] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: when a lane change request is received, determining a target lane according to the lane change request; judging whether a vehicle to be changed has completed the lane change according to a preset period; when the vehicle to be changed has not completed the lane change, generating a lane change driving trajectory according to the target lane and a predicted motion trajectory of a target obstacle to be avoided; controlling the vehicle to change lanes according to the lane change driving trajectory, and returning to execute the step of judging whether the vehicle to be changed has completed the lane change according to the preset period.
[0124] In one embodiment, when the processor executes the computer program, the following steps are also implemented: according to the target lane, a lane changing path of the vehicle to be changed is obtained; according to the target lane, a predicted motion trajectory of the target obstacle to be avoided is obtained; according to the lane changing path and the predicted motion trajectory, the position points of the vehicle to be changed in the lane changing path at each continuous moment in the future are determined, and a position time series of the vehicle to be changed is obtained; according to the lane changing path and the position time series, a lane changing driving trajectory is generated.
[0125] In one embodiment, when the processor executes the computer program, the following steps are also implemented: identifying environmental obstacles based on the position information and width information of the target lane and the environmental information of the road on which the vehicle to be changed is located; determining the lateral movement boundary of the vehicle to be changed according to the obstacle information of the environmental obstacles, the target lane and the lane changing direction of the vehicle to be changed; the obstacle information is used to characterize the size and movement of the environmental obstacles; and obtaining the lane changing path according to the current position of the vehicle to be changed, the target lane and the lateral movement boundary.
[0126] In one embodiment, when the processor executes the computer program, the following steps are further implemented: according to preset screening conditions, among the environmental obstacles, obstacles that have no interaction with the vehicle to be changed lanes and the target lane are screened out to obtain screened environmental obstacles.
[0127] In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the structural information and lane changing path of the vehicle to be changed, a virtual channel for the vehicle to be changed is generated; based on the overlap between the virtual channel and the predicted motion trajectory, the position point of the vehicle to be changed in the lane changing path at each continuous moment in the future is determined; based on the position-time correspondence between each continuous moment in the future and each position point in the lane changing path, a position-time series is obtained.
[0128] In one embodiment, the processor further implements the following steps when executing the computer program: identifying a target obstacle in a target lane, and acquiring the traffic density and average speed of the target lane based on the motion information of the target obstacle; generating a motion braking decision for controlling the vehicle to be changed lanes based on the traffic density and average speed of the target lane; determining an estimated arrival time corresponding to each position point in the lane changing path based on the lane changing path and the motion braking decision, and obtaining a position time series of the vehicle to be changed lanes based on the estimated arrival time corresponding to each position point in the lane changing path.
[0129] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: when a lane change request is received, a target lane is determined according to the lane change request; according to a preset period, whether a vehicle to be changed in lanes has completed the lane change; when the vehicle to be changed in lanes has not completed the lane change, a lane change driving trajectory is generated according to the target lane and a predicted motion trajectory of a target obstacle to be avoided; the vehicle is controlled to change lanes according to the lane change driving trajectory, and the step of returning to execute the step of determining whether the vehicle to be changed in lanes has completed the lane change according to the preset period.
[0130] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: according to the target lane, a lane changing path of the vehicle to be changed is obtained; according to the target lane, a predicted motion trajectory of the target obstacle to be avoided is obtained; according to the lane changing path and the predicted motion trajectory, the position points of the vehicle to be changed in the lane changing path at each continuous moment in the future are determined, and the position time series of the vehicle to be changed is obtained; according to the lane changing path and the position time series, a lane changing driving trajectory is generated.
[0131] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: identifying environmental obstacles based on the position information and width information of the target lane and the environmental information of the road on which the vehicle to be changed is located; determining the lateral movement boundary of the vehicle to be changed according to the obstacle information of the environmental obstacles, the target lane and the lane changing direction of the vehicle to be changed; the obstacle information is used to characterize the size and movement of the environmental obstacles; and obtaining the lane changing path according to the current position of the vehicle to be changed, the target lane and the lateral movement boundary.
[0132] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: according to preset screening conditions, among the environmental obstacles, obstacles that have no interaction with the vehicle to be changed and the target lane are screened out to obtain screened environmental obstacles.
[0133] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the structural information and lane changing path of the vehicle to be changed, a virtual channel for the vehicle to be changed lanes to travel is generated; based on the overlap between the virtual channel and the predicted motion trajectory, the position points of the vehicle to be changed lanes in the lane changing path at each continuous moment in the future are determined; based on the position-time correspondence between each continuous moment in the future and each position point in the lane changing path, a position-time series is obtained.
[0134] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: identifying a target obstacle in a target lane, and acquiring the traffic density and average speed of the target lane based on the motion information of the target obstacle; generating a motion braking decision for controlling the vehicle to be changed lanes based on the traffic density and average speed of the target lane; determining the estimated arrival time corresponding to each position point in the lane changing path based on the lane changing path and the motion braking decision, and obtaining a position time series of the vehicle to be changed lanes based on the estimated arrival time corresponding to each position point in the lane changing path.
[0135] In one embodiment, a computer program product is provided, including a computer program, which implements the following steps when executed by a processor: when a lane change request is received, determining a target lane according to the lane change request; judging whether a vehicle to be changed has completed the lane change according to a preset period; when the vehicle to be changed has not completed the lane change, generating a lane change driving trajectory according to the target lane and a predicted motion trajectory of a target obstacle to be avoided; controlling the vehicle to change lanes according to the lane change driving trajectory, and returning to execute the step of judging whether the vehicle to be changed has completed the lane change according to the preset period.
[0136] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: according to the target lane, a lane changing path of the vehicle to be changed is obtained; according to the target lane, a predicted motion trajectory of the target obstacle to be avoided is obtained; according to the lane changing path and the predicted motion trajectory, the position points of the vehicle to be changed in the lane changing path at each continuous moment in the future are determined, and the position time series of the vehicle to be changed is obtained; according to the lane changing path and the position time series, a lane changing driving trajectory is generated.
[0137] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: identifying environmental obstacles based on the position information and width information of the target lane and the environmental information of the road on which the vehicle to be changed is located; determining the lateral movement boundary of the vehicle to be changed according to the obstacle information of the environmental obstacles, the target lane and the lane changing direction of the vehicle to be changed; the obstacle information is used to characterize the size and movement of the environmental obstacles; and obtaining the lane changing path according to the current position of the vehicle to be changed, the target lane and the lateral movement boundary.
[0138] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: according to preset screening conditions, among the environmental obstacles, obstacles that have no interaction with the vehicle to be changed and the target lane are screened out to obtain screened environmental obstacles.
[0139] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the structural information and lane changing path of the vehicle to be changed, a virtual channel for the vehicle to be changed lanes to travel is generated; based on the overlap between the virtual channel and the predicted motion trajectory, the position points of the vehicle to be changed lanes in the lane changing path at each continuous moment in the future are determined; based on the position-time correspondence between each continuous moment in the future and each position point in the lane changing path, a position-time series is obtained.
[0140] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: identifying a target obstacle in a target lane, and acquiring the traffic density and average speed of the target lane based on the motion information of the target obstacle; generating a motion braking decision for controlling the vehicle to be changed lanes based on the traffic density and average speed of the target lane; determining the estimated arrival time corresponding to each position point in the lane changing path based on the lane changing path and the motion braking decision, and obtaining a position time series of the vehicle to be changed lanes based on the estimated arrival time corresponding to each position point in the lane changing path.
[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0142] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0143] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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 application.
[0144] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A lane change control method for automatic driving, It is characterized in that The method comprises: In case of receiving a lane change request, determining a target lane according to the lane change request; According to a preset cycle, determining whether the vehicle to be changed lanes has completed the lane change; In the case that the vehicle to be changed lanes has not completed the lane change, generating a lane change driving trajectory according to the target lane and the predicted motion trajectory of the target obstacle to be avoided; The vehicle is controlled to change lanes according to the lane-changing driving trajectory, and the step of returning to execute, according to a preset cycle, determining whether the vehicle to be changed lanes has completed the lane change.
2. The method according to claim 1, It is characterized in that The generating of a lane change driving trajectory according to the target lane and the predicted motion trajectory of the target obstacle to be avoided includes: According to the target lane, obtaining a lane changing path of the vehicle to be changed lanes; According to the target lane, a predicted motion trajectory of a target obstacle to be avoided is obtained, and according to the lane change path and the predicted motion trajectory, a position point of the vehicle to be changed lanes in the lane change path at each continuous moment in the future is determined to obtain a position time series of the vehicle to be changed lanes; The lane-changing driving trajectory is generated according to the lane-changing path and the position time series.
3. The method according to claim 2, It is characterized in that The acquiring, according to the target lane, a lane changing path of the vehicle to be lane-changed comprises: Identify environmental obstacles based on the position information and width information of the target lane and the environmental information of the road where the vehicle to change lanes is located; Determining the lateral motion boundary of the vehicle to be changed lanes according to the obstacle information of the environmental obstacle, the target lane, and the lane change direction of the vehicle to be changed lanes; the obstacle information is used to characterize the size and motion of the environmental obstacle; The lane changing path is acquired according to the current position of the vehicle to be lane-changed, the target lane, and the lateral movement boundary.
4. The method according to claim 3, It is characterized in that Before determining the lateral motion boundary of the vehicle to be changed lanes according to the obstacle information of the environmental obstacle, the target lane and the lane changing direction of the vehicle to be changed lanes, the method further includes: According to the preset screening conditions, obstacles that have no interaction with the vehicle to be changed lanes and the target lane are screened out from the environmental obstacles to obtain screened environmental obstacles.
5. The method according to claim 2, It is characterized in that The step of determining the position points of the vehicle to be lane-changed in the lane-changing path at each successive moment in the future according to the lane-changing path and the predicted motion trajectory to obtain the position time series of the vehicle to be lane-changed includes: generating a virtual lane for the vehicle to change lanes according to the structural information of the vehicle to change lanes and the lane changing path; Determining, according to the overlap between the virtual channel and the predicted motion trajectory, the position of the vehicle to be changed lanes in the lane changing path at each successive moment in the future; The position time sequence is obtained according to the position time correspondence between each future continuous moment and each position point in the lane change path.
6. The method according to claim 2, It is characterized in that The method further comprises: Identifying the target obstacle in the target lane, and acquiring the traffic density and average speed of the target lane according to the motion information of the target obstacle; generating a motion braking decision for controlling the vehicle to change lanes according to the traffic density and average vehicle speed of the target lane; According to the lane changing path and the motion braking decision, an estimated arrival time corresponding to each position point in the lane changing path is determined, and according to the estimated arrival time corresponding to each position point in the lane changing path, a position time series of the vehicle to be changed lanes is obtained.
7. An automatic driving lane change control device, It is characterized in that The device comprises: a determination module, configured to determine a target lane according to a lane change request when a lane change request is received; A judgment module, used to judge whether the vehicle to be changed lanes has completed the lane change according to a preset period; A generating module, configured to generate a lane-changing driving trajectory according to the target lane and a predicted motion trajectory of a target obstacle to be avoided, when the vehicle to be changed lanes has not completed the lane change; The control module is used to control the vehicle to change lanes according to the lane-changing driving trajectory, and return to execute the step of determining whether the vehicle to be changed lanes has completed the lane change according to a preset cycle.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
Citation Information
Cited By
Vehicle control method, vehicle and storage medium
CN120863641A
