Vehicle lane changing control method and vehicle

Abstract

The invention discloses a vehicle lane changing control method and a vehicle, and the method comprises the steps: responding to a received first vehicle lane changing instruction, obtaining the perception fusion data of the surrounding environment of the vehicle, carrying out the three-dimensional space-time search in an adjacent target lane based on the perception fusion data, and determining a feasible lane changing neutral position in the target lane; candidate lane changing neutral position information corresponding to the feasible lane changing neutral position is generated, and a neutral position identifier in the candidate lane changing neutral position information is displayed on a human-computer interaction interface of the vehicle; receiving a selection instruction for the neutral position identifier, and determining a target lane changing neutral position according to the selection instruction; and planning a lane changing track based on the target lane changing neutral position and the current driving state of the vehicle, and controlling the vehicle to execute a lane changing action according to the lane changing track. Through the technical scheme provided by the invention, the driving experience of the user in the lane changing process of the vehicle can be enhanced.

Description

Technical Field

[0001] This application belongs to the field of vehicle lane changing and control technology, and particularly relates to a vehicle lane changing control method and vehicle. Background Technology

[0002] With the rapid development of automotive intelligent technology, intelligent lane change assist has become an important component of the intelligent driving field. This function helps drivers automatically complete lane change operations, effectively reducing the driver's workload and improving driving convenience. However, most existing intelligent lane change assist functions rely on an autonomous decision-making mode, only defaulting to changing lanes to a fixed position in the adjacent lane. Drivers cannot perceive the lane change space and trajectory planned by the system, making it difficult to effectively control the lane change process. This significantly reduces the driver's sense of participation and control during lane changes, impacting the driving experience and sense of safety.

[0003] Therefore, how to enhance the user's driving experience during lane changes has become an urgent technical problem to be solved. Summary of the Invention

[0004] The embodiments of this application provide a vehicle lane change control method, apparatus, computer program product, computer-readable storage medium, and vehicle, which can at least to some extent enhance the user's driving experience during the vehicle lane change process.

[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0006] According to a first aspect of the embodiments of this application, a vehicle lane change control method is provided. The method includes: in response to receiving a first vehicle lane change command, acquiring perception fusion data of the vehicle's surrounding environment, and performing a three-dimensional spatiotemporal search in adjacent target lanes based on the perception fusion data to determine feasible lane change gaps within the target lanes; generating candidate lane change gap information corresponding to the feasible lane change gaps, and displaying a gap identifier in the candidate lane change gap information on the vehicle's human-machine interface; receiving a selection command for the gap identifier, and determining a target lane change gap according to the selection command; planning a lane change trajectory based on the target lane change gap and the vehicle's current driving state, and controlling the vehicle to perform a lane change action according to the lane change trajectory.

[0007] In some embodiments of this application, based on the foregoing scheme, the step of performing a three-dimensional spatiotemporal search in adjacent target lanes based on the perception fusion data to determine feasible lane-changing gaps within the target lanes includes: constructing a three-dimensional spatiotemporal search grid in the target lanes, wherein the dimensions of the three-dimensional spatiotemporal search grid include a longitudinal spatial dimension, a lateral spatial dimension, and a temporal dimension; identifying adjacent vehicles in front and behind within the target lanes based on the perception fusion data, and predicting the movement trajectories of the adjacent vehicles in front and behind within a preset time range; sliding a safety window within the three-dimensional spatiotemporal search grid, and performing conflict detection between the safety window and the movement trajectories of the adjacent vehicles in front and behind; and determining the safety window where no conflict is detected as the feasible lane-changing gap.

[0008] In some embodiments of this application, based on the aforementioned scheme, the conflict detection of the movement trajectory of the safety window and the adjacent vehicles in front and behind includes: determining whether the movement trajectory of the safety window and the adjacent vehicles in front and behind meet preset conditions. The preset conditions include that the longitudinal distance between the safety window and the vehicle in front is greater than a first safety distance, the longitudinal distance between the safety window and the vehicle behind is greater than a second safety distance, the vehicle does not intrude into the safety envelope of the adjacent vehicle during the lane change to the safety window, and the adjacent vehicle does not enter the safety window when the vehicle completes the lane change action; wherein, the first safety distance is dynamically calculated based on the relative speed between the vehicle and the vehicle in front, and the second safety distance is proportionally amplified when the vehicle is traveling at high speed; if the movement trajectory of the safety window and the adjacent vehicles in front and behind meet the preset conditions, it is determined that no conflict has been detected.

[0009] In some embodiments of this application, based on the aforementioned scheme, the step of performing a three-dimensional spatiotemporal search in adjacent target lanes based on the perception fusion data to determine feasible lane-changing gaps within the target lanes further includes: converting obstacle information in the perception fusion data into spatiotemporal point cloud data; constructing a three-dimensional KD tree index based on the spatiotemporal point cloud data; performing grid sampling within the three-dimensional spatiotemporal search grid to obtain candidate spatiotemporal points; performing nearest neighbor obstacle queries for each candidate spatiotemporal point using the three-dimensional KD tree index; and expanding the candidate spatiotemporal point into the safety window if the distance between the candidate spatiotemporal point and the nearest neighbor obstacle is greater than a third safety distance.

[0010] In some embodiments of this application, based on the foregoing scheme, displaying the gap indicator in the candidate lane change gap information on the vehicle's human-machine interface includes: converting the gap world coordinates in the candidate lane change gap information into pixel coordinates of the human-machine interface; drawing a gap indicator of a predetermined shape on the human-machine interface according to the pixel coordinates; setting the display style of the gap indicator according to the safety score in the candidate lane change gap information, setting the gap indicator with the highest safety score as the recommended style, and setting the gap indicator with a safety score lower than a preset score threshold as the unavailable style; rendering the corresponding safety score and estimated lane change time next to the gap indicator, and displaying a prompt text for the lane change action on the human-machine interface.

[0011] In some embodiments of this application, based on the foregoing scheme, receiving a selection instruction for the neutral gear indicator and determining a target lane change neutral gear according to the selection instruction includes: detecting the driver's selection operation on the neutral gear indicator within a preset waiting time, and determining the corresponding feasible lane change neutral gear as the target lane change neutral gear based on the selection operation; if the selection operation is not detected within the preset waiting time, then determining the feasible lane change neutral gear with the highest safety score as the target lane change neutral gear.

[0012] In some embodiments of this application, based on the aforementioned scheme, the current driving state includes the vehicle's current position, current speed, current heading angle, and current acceleration. The planning of the lane change trajectory based on the target lane change gap and the vehicle's current driving state includes: obtaining the position parameters of the target lane change gap and the lane information of the target lane, the lane information including lane curvature and lane line information; generating a lane change trajectory point series in a Frenner or Cartesian coordinate system using a polynomial trajectory optimization algorithm based on the position parameters and the lane information; wherein the lane change trajectory point series satisfies dynamic constraints during generation, does not intrude into the safety envelope of adjacent vehicles, and the target speed at the end of the lane change trajectory matches the vehicle's current speed; the dynamic constraints include the vehicle's lateral acceleration being less than a preset acceleration threshold and the vehicle's lateral jerk being less than a preset jerk threshold; and matching the corresponding target speed and target acceleration to the lane change trajectory point series to form a complete lane change trajectory.

[0013] In some embodiments of this application, based on the foregoing scheme, controlling the vehicle to perform a lane-changing action according to the lane-changing trajectory includes: sending the lane-changing trajectory to the vehicle's lateral and longitudinal controllers, and having the lateral and longitudinal controllers output steering wheel angle commands and accelerator and brake opening commands to control the vehicle to drive according to the lane-changing trajectory; during the process of the vehicle performing the lane-changing action, continuously acquiring updated perception fusion data and performing real-time verification of the lane-changing trajectory.

[0014] In some embodiments of this application, based on the foregoing scheme, the method further includes: in response to receiving a second vehicle lane change command for a multi-lane lane change, performing a three-dimensional spatiotemporal search in multiple adjacent target lanes respectively, determining feasible lane change gaps in each target lane and generating a continuous lane change gap sequence; planning a continuous lane change trajectory according to the lane change gap sequence, setting a preset buffer time between lane change actions in adjacent lanes, and controlling the vehicle to complete the multi-lane lane change action in sequence.

[0015] According to a second aspect of the embodiments of this application, a vehicle lane change control device is provided. The device includes: an acquisition unit, configured to, in response to receiving a first vehicle lane change command, acquire perception fusion data of the vehicle's surrounding environment, and perform a three-dimensional spatiotemporal search in adjacent target lanes based on the perception fusion data to determine feasible lane change gaps within the target lanes; a generation unit, configured to generate candidate lane change gap information corresponding to the feasible lane change gaps, and display a gap identifier in the candidate lane change gap information on the vehicle's human-machine interface; a determination unit, configured to receive a selection command for the gap identifier, and determine a target lane change gap according to the selection command; and a control unit, configured to plan a lane change trajectory based on the target lane change gap and the vehicle's current driving state, and control the vehicle to perform a lane change action according to the lane change trajectory.

[0016] According to a third aspect of the embodiments of this application, a computer program product is provided, the computer program product including computer instructions stored in a computer-readable storage medium and adapted to be read and executed by a processor to cause a computer device having the processor to perform an operation as described in any of the first aspects above.

[0017] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by a processor to perform the operation as described in any of the first aspects above.

[0018] According to a fifth aspect of the embodiments of this application, a vehicle is provided, the vehicle including one or more processors and one or more memories, the one or more memories storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by the one or more processors to perform the operation as described in any of the first aspects above.

[0019] Based on the technical solution proposed in this application, by responding to the driver's lane change command and acquiring perception fusion data, a three-dimensional spatiotemporal search is performed in the target lane to determine a feasible lane change gap. The gap is then displayed on the human-machine interface for the driver to select. Finally, the trajectory is planned and the lane change is controlled according to the selected target lane change gap. This allows the driver to participate in the lane change decision-making process and perceive the lane change space planned by the system, thereby effectively improving the driver's sense of participation and control during the lane change process. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0021] Figure 1 A flowchart of a vehicle lane change control method according to an embodiment of this application is shown; Figure 2 A schematic diagram of a feasible lane change gap according to an embodiment of this application is shown; Figure 3 A block diagram of a vehicle lane change control device according to an embodiment of this application is shown; Figure 4 A schematic diagram of the vehicle structure in an embodiment of this application is shown. Detailed Implementation

[0022] 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 only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0024] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices. It should also be noted that, for the sake of simplicity, certain components in the drawings that do not affect the interpretation of the technical solution of this application have been appropriately omitted.

[0025] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined. Therefore, the actual execution order may change depending on the actual situation.

[0026] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "multiple" means two or more.

[0027] This application proposes a vehicle lane change control scheme, aiming to solve the problems of poor interactivity and low driver control in existing intelligent lane change assistance functions, thereby enhancing the user's driving experience during the vehicle lane change process.

[0028] Next, this application will elaborate on the proposed vehicle lane change control scheme. (Refer to...) Figure 1 The flowchart of a vehicle lane change control method according to an embodiment of this application is shown. This method can be executed by a device with computational processing capabilities, such as... Figure 1 As shown, the method includes at least steps 110 to 140, which are described in detail below: In step 110, in response to receiving the first vehicle lane change command, the system acquires perception fusion data of the vehicle's surrounding environment and performs a three-dimensional spatiotemporal search in the adjacent target lane based on the perception fusion data to determine the feasible lane change gap in the target lane.

[0029] In this application, the first lane-change instruction can be triggered by the driver activating the vehicle's turn signal stalk, directly reflecting the driver's lane-change intention. Upon receiving the instruction, the vehicle's perception system can immediately activate, acquiring perception fusion data of the vehicle's surrounding environment through radar, cameras, high-precision maps, and other sensing devices. This data includes key information such as lane line information, obstacle positions, and the driving status of adjacent vehicles, forming the basis for subsequent lane-change decisions. Based on the aforementioned perception fusion data, the system can conduct a three-dimensional spatiotemporal search within the adjacent target lane where the driver intends to change lanes. Through this search process, feasible lane-change gaps within the target lane that do not involve driving conflicts and meet safe lane-change conditions are identified, allowing the target location for lane changes to no longer be limited to a fixed area within adjacent lanes.

[0030] Specifically, in one embodiment of this application, the step of performing a three-dimensional spatiotemporal search in adjacent target lanes based on the perception fusion data to determine feasible lane-changing gaps within the target lanes can be performed according to the following steps 111 to 114: Step 111: Construct a three-dimensional spatiotemporal search grid for the target lane. The dimensions of the three-dimensional spatiotemporal search grid include vertical spatial dimension, horizontal spatial dimension and time dimension.

[0031] Step 112: Identify the vehicles in front and behind in the target lane based on the perception fusion data, and predict the movement trajectory of the vehicles in front and behind within a preset time range.

[0032] Step 113: Slide a safe window within the three-dimensional spatiotemporal search grid and perform conflict detection between the safe window and the motion trajectories of the adjacent vehicles in front and behind.

[0033] Step 114: The safe window where no conflict was detected is identified as the feasible lane change gap.

[0034] In this application, a three-dimensional spatiotemporal search is performed on adjacent target lanes based on perception fusion data to determine feasible lane-changing gaps within the target lanes. A three-dimensional spatiotemporal search grid can be constructed in the target lanes first. This grid is the basic framework for conducting lane-changing gap searches and can contain three core dimensions: longitudinal spatial dimension, lateral spatial dimension, and temporal dimension. The longitudinal spatial dimension is based on the vehicle's driving direction and represents the front-to-back distance of the target lane. The lateral spatial dimension represents the left-to-right width range of the target lane. The temporal dimension covers the spatiotemporal range over a future period. The three dimensions are combined to form a three-dimensional search range, allowing the search for lane-changing gaps to no longer be limited to static spatial locations.

[0035] After constructing the three-dimensional spatiotemporal search grid, the vehicles in front and behind in the target lane can be accurately identified based on the perception fusion data. By using the vehicle position, speed, acceleration and other information contained in the perception fusion data, the real-time driving status of the vehicles in front and behind can be determined. At the same time, the trajectory of the vehicles in front and behind can be predicted within a preset time range using a constant speed model or acceleration model. This preset time range can be 0 to 8 seconds in the future, which can effectively cover the time required for a vehicle to complete a lane change, and provide a predictive basis for subsequent conflict detection.

[0036] After predicting the trajectories of adjacent vehicles, a safety window can be slid within the constructed 3D spatiotemporal search grid. The size of this safety window can be set according to the vehicle's size and safe lane-changing requirements. For example, a rectangular window with a length of 5 meters and a width of 2 meters can match the size of a typical passenger car, ensuring sufficient safety space after the vehicle enters the window. During the sliding of the safety window, conflict detection can be continuously performed on the movement trajectories of the safety window and adjacent vehicles to determine whether the position of the safety window overlaps or intersects with the predicted driving trajectories of the adjacent vehicles.

[0037] Finally, safe windows where no conflict is detected during the sliding process can be identified as feasible lane-changing gaps. The positions of these safe windows will not conflict with the driving trajectories of adjacent vehicles within a preset time range, thus meeting the spatial and temporal requirements for safe lane changing.

[0038] For example, in one specific embodiment, if a driver wants to change lanes to the right, the system constructs a three-dimensional spatiotemporal search grid in the adjacent target lane on the right. The vertical spatial dimension covers 20 to 100 meters in front of the target lane, the horizontal spatial dimension is 0.5 meters on each side of the lane center, and the time dimension is 0 to 8 seconds into the future. Through perception fusion data, the system identifies a vehicle in front and a vehicle behind in the target lane. The vehicle in front is currently traveling at a constant speed of 30 km / h, and the vehicle behind is traveling at a constant speed of 40 km / h. The system predicts that both vehicles will maintain this driving state for the next 8 seconds. The system then slides a safe window within the three-dimensional spatiotemporal search grid. When the safe window slides to a position 40 meters behind the vehicle in front and 35 meters in front of the vehicle behind, it detects that the window does not overlap with the predicted trajectories of the vehicles in front and behind, and the system then determines this safe window as a feasible lane-changing opportunity.

[0039] Based on the above scheme, by constructing a three-dimensional spatiotemporal search grid in the target lane, identifying and predicting the movement trajectories of adjacent vehicles in front and behind, and then sliding the safety window to perform conflict detection and determine feasible lane change gaps, the search for lane change gaps can cover both spatiotemporal dimensions, accurately filter out safe lane change positions without driving conflicts, thereby improving the comprehensiveness and accuracy of lane change gap search.

[0040] In one embodiment of step 113 above, the conflict detection between the safety window and the movement trajectories of the adjacent vehicles in front and behind can be performed according to the following steps 1131 to 1132: Step 1131: Determine whether the movement trajectories of the safety window and the adjacent vehicles in front and behind meet preset conditions. These preset conditions include: the longitudinal distance between the safety window and the preceding vehicle is greater than a first safety distance; the longitudinal distance between the safety window and the following vehicle is greater than a second safety distance; the vehicle does not intrude into the safety envelope of the adjacent vehicle during the lane change to the safety window; and the adjacent vehicle does not enter the safety window when the vehicle completes the lane change maneuver. The first safety distance is dynamically calculated based on the relative speed between the vehicle and the preceding vehicle, and the second safety distance is proportionally amplified when the vehicle is traveling at high speed.

[0041] Step 1132: If the movement trajectory of the safety window and the adjacent vehicles in front and behind meet the preset conditions, then it is determined that no conflict has been detected.

[0042] In this application, conflict detection is performed on the movement trajectory of the safety window and the adjacent vehicles in front and behind. The core of this method is to determine whether the movement trajectory of the safety window and the adjacent vehicles in front and behind meet the preset safety conditions. These preset conditions include four specific judgment requirements, which comprehensively ensure the safety of the lane changing process.

[0043] The first requirement is that the longitudinal distance between the safety window and the vehicle in front is greater than the first safety distance. This first safety distance is not a fixed value and can be dynamically calculated based on the relative speed between the vehicle and the vehicle in front. When the relative speed is high, the first safety distance increases accordingly, providing sufficient braking and reaction space for the vehicle. The second requirement is that the longitudinal distance between the safety window and the vehicle behind is greater than the second safety distance. Considering that the braking distance of the vehicle behind increases significantly at high speeds, the second safety distance can be proportionally increased at high speeds to avoid the risk of rear-end collisions. The safety distance at high speeds is much greater than at low speeds. The third requirement is that during the lane change to the safety window, no part of the vehicle body intrudes into the safety envelope of the adjacent vehicle. The safety envelope of the adjacent vehicle refers to the safe area extending outwards from the adjacent vehicle at a certain distance. This requirement effectively avoids collisions with adjacent vehicles during lane changes. The fourth requirement is that the adjacent vehicle does not enter the safety window when the vehicle completes the lane change. A lane change typically takes 3 to 5 seconds. This requirement ensures that when the vehicle completes the lane change and straightens its body, there are no other vehicles within the safety window, thus avoiding driving conflicts from a time perspective.

[0044] In the actual conflict detection process, the above four preset conditions can be judged one by one. Only when the movement trajectory of the safety window and the adjacent vehicles in front and behind simultaneously meet all the preset conditions will it be determined that the movement trajectory of the safety window and the adjacent vehicles in front and behind have not been detected to be in conflict, and the safety window will also have the basic conditions to become a feasible lane change gap.

[0045] For example, in one specific embodiment, a vehicle traveling at 60 km / h on an urban expressway wants to change lanes to the adjacent lane on the left. The system slides a safety window within that lane and then performs conflict detection. Calculations show that the longitudinal distance between the safety window and the vehicle in front is 35 meters. The first safety distance, dynamically calculated based on the relative speeds of the two vehicles, is 25 meters, satisfying the requirement that the longitudinal distance is greater than the first safety distance. The longitudinal distance between the safety window and the vehicle behind is 40 meters. Due to the high speed, the scaled-up second safety distance is 30 meters, satisfying the requirement that the longitudinal distance is greater than the second safety distance. The system simulates the process of the vehicle changing lanes to this safety window and finds that the vehicle does not enter the safety envelope of the adjacent vehicles in front or behind throughout the entire process. It also predicts that the vehicle will need 4 seconds to complete the lane change. After 4 seconds, the positions of the adjacent vehicles in front and behind have not entered the safety window, which meets all preset conditions. The system determines that no conflict has been detected.

[0046] Based on the above scheme, by judging whether the movement trajectory of the safety window and the adjacent vehicles in front and behind meet the preset conditions that include multiple dimensions, and only when all conditions are met is it determined that no conflict has been detected, lane change safety can be controlled from multiple dimensions of distance, space and time, so as to make the conflict detection results more accurate and ensure the safety of lane change gaps.

[0047] Specifically, in another embodiment of this application, the step of performing a three-dimensional spatiotemporal search in adjacent target lanes based on the perception fusion data to determine feasible lane-changing gaps within the target lanes can also be performed according to the following steps 115 to 117: Step 115: Convert the obstacle information in the perception fusion data into spatiotemporal point cloud data, and construct a three-dimensional KD tree index based on the spatiotemporal point cloud data.

[0048] Step 116: Perform grid sampling within the three-dimensional spatiotemporal search grid to obtain candidate spatiotemporal points, and use the three-dimensional KD tree index to perform nearest neighbor obstacle query for each candidate spatiotemporal point.

[0049] Step 117: If the distance between the candidate spatiotemporal point and the nearest neighbor obstacle is greater than the third safety distance, then the candidate spatiotemporal point is expanded into the safety window.

[0050] In this application, a three-dimensional spatiotemporal search is performed on adjacent target lanes based on perception fusion data to determine feasible lane-changing gaps within the target lanes. This can also be optimized by combining a three-dimensional KD-tree index to improve search efficiency and accuracy. First, the system can convert the obstacle information in the perception fusion data into spatiotemporal point cloud data. This data combines the obstacle's positional and temporal information, presenting it as three-dimensional spatiotemporal points. Each spatiotemporal point can contain longitudinal and lateral spatial coordinates and corresponding temporal coordinates, accurately representing the spatial position of the obstacle at different times. Based on the converted spatiotemporal point cloud data, the system can construct a three-dimensional KD-tree index. The three-dimensional KD-tree index is an efficient spatial data structure that can store the three-dimensional spatiotemporal point cloud data in an orderly manner, significantly improving the speed of subsequent nearest-neighbor obstacle queries.

[0051] After constructing the 3D KD-tree index, the system can perform grid sampling within the constructed 3D spatiotemporal search grid. Multiple candidate spatiotemporal points are obtained through equally spaced sampling, which form the basis for subsequent selection of the safety window. For each candidate spatiotemporal point, the system can perform a nearest neighbor obstacle query using the constructed 3D KD-tree index to quickly locate the nearest obstacle within the 3D spatiotemporal range and calculate the actual distance between them.

[0052] After completing the nearest neighbor obstacle query, the system can set a third safety distance as a judgment threshold. For example, the third safety distance can be set to 5 meters. If the actual distance between the candidate spatiotemporal point and the nearest neighbor obstacle is greater than the third safety distance, it means that the candidate spatiotemporal point is located without obstacle interference within the corresponding time range and has the basis for safe lane changing. The system can expand the candidate spatiotemporal point as the center to form a safe window that meets the needs of vehicle lane changing. The size of the safe window will be set according to the size of the vehicle body, generally covering a range of 5 meters longitudinally, 2 meters laterally, and 2 seconds in time.

[0053] For example, in a specific embodiment, after a vehicle is traveling on a regular road and triggers a lane change command, the system converts the obstacle information in the perception fusion data into spatiotemporal point cloud data containing multiple spatiotemporal points. Each spatiotemporal point contains three coordinates: x, y, and t. A three-dimensional KD-tree index is then constructed based on this data. The system samples within the three-dimensional spatiotemporal search grid of the target lane with a vertical step of 10 meters, a horizontal step of 3.5 meters, and a time step of 2 seconds, obtaining 20 candidate spatiotemporal points. The three-dimensional KD-tree index is used to perform a nearest neighbor obstacle query on one of the candidate spatiotemporal points. It is found that the distance to the nearest obstacle is 7 meters, which is greater than the third safety distance of 5 meters. Therefore, the system uses this candidate spatiotemporal point as the center, expanding vertically by 2.5 meters to each side and temporally by 1 second to each side, while keeping the horizontal distance fixed, forming a safety window.

[0054] Based on the above scheme, by converting obstacle information into spatiotemporal point cloud data and constructing a three-dimensional KD tree index, sampling within the search grid and querying the nearest neighbor obstacle through the index, and expanding the candidate spatiotemporal points into a safe window after the distance reaches the standard, the efficiency of obstacle query during lane change gap search can be greatly improved, while making the generation of safe windows more targeted, thereby improving the efficiency and accuracy of the entire three-dimensional spatiotemporal search.

[0055] Continue to refer to Figure 1 In step 120, candidate lane change gap information corresponding to the feasible lane change gap is generated, and the gap identifier in the candidate lane change gap information is displayed on the vehicle's human-machine interface.

[0056] In this application, after determining the feasible lane change gaps, the system can generate candidate lane change gap information corresponding to each feasible lane change gap. This information may also include the longitudinal start and end positions of the gap, the lateral target center, world coordinates, safety score, time window, lane identifier, and corresponding front and rear adjacent vehicle identifiers. Subsequently, the gap identifiers in this information are displayed on the vehicle's human-machine interface, allowing the driver to intuitively see all the possible lane change positions within the target lane, breaking the limitations of the original system's autonomous decision-making and the driver's inability to perceive lane change space.

[0057] In this application, the candidate lane change slot information can be refreshed according to a preset time period. If the feasible lane change slot is occupied, the corresponding candidate lane change slot information is marked as invalid.

[0058] In this application, a safety score can be calculated for each feasible lane change gap. The calculation process of the safety score includes obtaining the longitudinal clearance between the feasible lane change gap and the vehicle in front and the vehicle behind, processing the two longitudinal clearances through a nonlinear normalization algorithm and taking the average value, and clamping the average value within a preset numerical range to obtain the safety score.

[0059] In this application, the step of displaying the neutral gear indicator in the candidate lane change neutral gear information on the vehicle's human-machine interface can be performed according to the following steps 121 to 123: Step 121: Convert the world coordinates of the gap in the candidate lane change gap information into pixel coordinates of the human-computer interaction interface, and draw a gap mark of a set shape on the human-computer interaction interface according to the pixel coordinates.

[0060] Step 122: Set the display style of the gap identifier according to the safety score in the candidate lane change gap information, set the gap identifier with the highest safety score as the recommended style, and set the gap identifier with the safety score below the preset score threshold as the unavailable style.

[0061] Step 123: Render the corresponding safety score and estimated lane change time next to the gap indicator, and display the lane change prompt text on the human-computer interaction interface.

[0062] In this application, displaying the neutral gear indicator from candidate lane change information on the vehicle's human-machine interface requires a coordinate transformation. The system can extract the neutral gear world coordinates from the candidate lane change information. These coordinates are the three-dimensional spatial coordinates of the neutral gear on the actual road. Then, through a coordinate transformation algorithm, the world coordinates are converted into pixel coordinates on the human-machine interface. The pixel coordinates directly correspond to the display position on the human-machine interface. After the transformation, the system can draw a neutral gear indicator of a set shape on the human-machine interface based on the pixel coordinates. This indicator can be square, which can intuitively and clearly show the position and range of the lane change neutral gear, making it convenient for the driver to identify.

[0063] After drawing the neutral gear indicators, the system can set corresponding display styles for different indicators based on the safety scores in the candidate lane change neutral gear information. The safety score is a value between 0 and 1, calculated by the system based on factors such as the distance between the neutral gear and the vehicles in front and behind, and the risk of conflict. The higher the score, the safer the neutral gear. The system can set the neutral gear indicator with the highest safety score as the recommended style. This style is generally highlighted with a faint light animation, making it more prominent in the human-machine interface and providing the driver with a clear lane change reference. At the same time, neutral gear indicators with safety scores below a preset threshold are set to an unavailable style. This style is generally displayed as a gray semi-transparent image and cannot be clicked by the driver, visually and operationally preventing the driver from selecting low-safety neutral gears.

[0064] In addition, the system can display the corresponding safety score and estimated lane change time next to each selectable lane change slot. The safety score is presented in numerical form, and the estimated lane change time is the time required to complete the lane change calculated by the system based on the vehicle's current driving status, allowing the driver to fully understand the information for each lane change slot. Simultaneously, prompts for the lane change action can be displayed in a fixed location on the human-machine interface, such as "Click to select lane change location" or "Planning lane change trajectory," providing real-time feedback to the driver on the progress of the lane change process and enhancing the intuitiveness of the interaction.

[0065] For example, in one specific embodiment, the system identifies three feasible lane-change gaps within the target lane, with safety scores of 0.95, 0.82, and 0.35, respectively. After converting the world coordinates of these three gaps to pixel coordinates on the central control screen, the system draws three square gap markers on the screen. Since 0.95 is the highest safety score, the corresponding gap marker is set to a recommended style with a bright green highlight and a faint animation. 0.35 is below the preset score threshold of 0.6, so the corresponding gap marker is set to a gray, semi-transparent, unavailable style. The gap marker for 0.82 is a regular green, semi-transparent style. Simultaneously, the numbers 0.953 seconds and 0.824 seconds are displayed next to the 0.95 and 0.82 gap markers, respectively. A prompt to select a lane-change position is displayed at the bottom of the central control screen, allowing the driver to clearly understand all lane-change gap information.

[0066] Based on the above solution, by converting the neutral gear world coordinates into pixel coordinates and drawing a mark, setting different display styles according to the safety score, and rendering the score and time next to the mark and displaying prompt text, drivers can intuitively and comprehensively grasp the position, safety and lane change information of the neutral gear in the human-machine interface, thereby improving the convenience and intuitiveness of human-machine interaction.

[0067] In this application, the step of displaying the neutral gear indicator corresponding to the candidate lane change neutral gear information on the vehicle's human-machine interface can also include the following steps 124 to 125: Step 124: Simultaneously render the neutral marker and the trajectory marker on the vehicle's augmented reality head-up display device, and merge the neutral marker and the trajectory marker with the real lane scene for display.

[0068] Step 125: Output voice prompts based on the vehicle's driving status. The voice prompts include lane change neutral prompts, selection confirmation prompts, and lane change status prompts.

[0069] Continue to refer to Figure 1 In step 130, a selection instruction for the neutral gap identifier is received, and a target lane change neutral gap is determined according to the selection instruction.

[0070] After the neutral gear indicator in the candidate lane change information is displayed on the vehicle's human-machine interface, the system can enter a waiting state and receive the driver's selection instruction for the neutral gear indicator on the human-machine interface. The driver can select any neutral gear indicator according to his own driving judgment and needs, and the system will determine the corresponding feasible lane change neutral gear as the target lane change neutral gear according to the selection instruction.

[0071] Specifically, in this application, receiving the selection instruction for the neutral gap identifier and determining the target lane change neutral gap according to the selection instruction can be performed according to the following steps 131 to 132: Step 131: Detect the driver's selection operation on the neutral gear indicator within a preset waiting time, and determine the corresponding feasible lane change neutral gear as the target lane change neutral gear based on the selection operation.

[0072] Step 132: If the selection operation is not detected within the preset waiting time, the feasible lane change gap with the highest safety score is determined as the target lane change gap.

[0073] In this application, the system receives a selection instruction for a neutral gear indicator and determines the target lane change neutral gear based on the selection instruction. A preset waiting time, which can be 5 seconds, can be set. This is the operation time reserved by the system for the driver to select a lane change neutral gear. Within this preset waiting time, the system can continuously detect the driver's selection operation of the neutral gear indicator on the human-machine interface. This operation can be the driver clicking the neutral gear indicator on the touch screen. When the selection operation is detected, the system will immediately identify the feasible lane change neutral gear corresponding to the clicked neutral gear indicator and determine the feasible lane change neutral gear as the target lane change neutral gear, and then proceed to the next stage of lane change trajectory planning.

[0074] If the system does not detect any selection of the neutral gear indicator by the driver within the preset waiting time, it means that the driver has not actively selected a neutral gear for lane changing. At this time, the system can automatically activate the default selection mechanism, filter out the feasible lane changing gear with the highest safety score from all feasible lane changing gears, and determine the gear as the target lane changing gear. This avoids the lane changing process from being interrupted due to the driver's failure to operate in time, and ensures the continuity and usability of the lane changing function.

[0075] For example, in a specific embodiment, refer to Figure 2 The diagram illustrates a feasible lane change gap according to an embodiment of this application.

[0076] like Figure 2 As shown, the system displays three feasible lane change slots on the human-machine interface, with a preset waiting time of 5 seconds. After the driver activates the turn signal stalk, the system starts timing and detects the driver's selection. If the driver touches or clicks one of the slots, "Target Area 2," with a safety score of 0.9, within 3 seconds of the timer starting, the system immediately identifies the slot corresponding to that slot as the target lane change slot. If the driver does not click on any slot slot within the preset 5-second waiting time, the system compares the safety scores of the three slots and automatically identifies the slot with the highest score of 0.9 as the target lane change slot.

[0077] Based on the above scheme, by detecting the driver's selection operation within a preset waiting time and determining the corresponding target lane change slot, and automatically selecting the slot with the highest safety score when no operation is detected, the driver's right to choose and the continuity of the lane change function can be taken into account, thereby improving the flexibility and practicality of the lane change control method.

[0078] In this application, receiving the selection instruction for the empty slot identifier can be achieved through the following step 133: Step 133: Receive selection commands from the driver via touch operation of the human-machine interface, shortcut key operation of the steering wheel, or voice command operation, and determine the corresponding target lane change neutral position after parsing the selection commands.

[0079] Continue to refer to Figure 1 In step 140, a lane change trajectory is planned based on the target lane change gap and the vehicle's current driving state, and the vehicle is controlled to perform a lane change action according to the lane change trajectory.

[0080] In this application, after determining the target lane change gap, the system can combine the determined target lane change gap with the vehicle's current driving status to perform professional lane change trajectory planning. After planning a smooth and safe lane change route, the lane change trajectory is transmitted to the vehicle's control execution module, which then controls the vehicle to complete the entire lane change action according to the lane change trajectory.

[0081] In this application, the current driving state includes the vehicle's current position, current speed, current heading angle, and current acceleration.

[0082] In this application, the planning of the lane-changing trajectory based on the target lane-changing gap and the vehicle's current driving state can be performed according to the following steps 141 to 143: Step 141: Obtain the position parameters of the target lane change gap and the lane information of the target lane, wherein the lane information includes lane curvature and lane line information.

[0083] Step 142: Based on the position parameters and lane information, a polynomial trajectory optimization algorithm is used to generate a lane change trajectory point sequence in the Frenner or Cartesian coordinate system. The lane change trajectory point sequence satisfies dynamic constraints during generation, does not intrude into the safety envelope of adjacent vehicles, and the target speed at the end of the lane change trajectory matches the current speed of the vehicle. The dynamic constraints include the vehicle's lateral acceleration being less than a preset acceleration threshold and the vehicle's lateral abruptness being less than a preset abruptness threshold.

[0084] Step 143: Match the target velocity and target acceleration to the lane change trajectory point series to form a complete lane change trajectory.

[0085] In this application, the vehicle's current position, current speed, current heading angle, and current acceleration comprehensively characterize the vehicle's real-time driving situation and form the core foundation for planning lane-change trajectories. Planning a lane-change trajectory based on the target lane change gap and the vehicle's current driving state involves first obtaining the position parameters of the target lane change gap, including its longitudinal start position, longitudinal end position, and lateral center position. Simultaneously, lane information for the target lane is obtained, primarily including lane curvature and lane line information. Lane curvature characterizes the degree of road bending in the target lane, while lane line information determines the driving boundaries of the target lane. This information serves as crucial constraints for trajectory planning.

[0086] After acquiring all the above information, the system can generate a series of lane change trajectory points using a polynomial trajectory optimization algorithm, based on the position parameters of the target lane change gap and the lane information of the target lane. The generation process can be performed in either the Frenner coordinate system or the Cartesian coordinate system. The Frenner coordinate system, based on the road, is better suited to changes in road curvature, while the Cartesian coordinate system, being a Cartesian coordinate system, offers more intuitive calculations. Several constraints must be strictly met during the generation of the lane change trajectory point series: Firstly, the constraints are dynamic constraints, which require that the vehicle's lateral acceleration be less than a preset acceleration threshold. This preset acceleration threshold can be 2.5 meters per second squared. Simultaneously, the vehicle's lateral jerkiness must be less than a preset jerkiness threshold, which can be 3 meters per second cubic. These constraints ensure the smoothness of lane changes and prevent excessive body roll or sudden steering wheel movements.

[0087] The second constraint is a spatial constraint, which requires that the driving path corresponding to the generated trajectory point sequence does not intrude into the safety envelope of neighboring vehicles, thus avoiding collisions with neighboring vehicles.

[0088] The third constraint is the speed constraint, which requires that the target speed at the end of the lane change trajectory match the vehicle's current speed, generally keeping them the same or slightly higher, to avoid sudden deceleration during the lane change process, which would affect driving stability.

[0089] After generating the lane change trajectory points, the system can match the corresponding target speed and target acceleration for each trajectory point, so that the trajectory points not only contain spatial location information, but also driving speed and acceleration information. By connecting these trajectory points with speed and acceleration in sequence, a complete lane change trajectory is formed, which can directly guide the vehicle's lane change actions.

[0090] For example, in a specific embodiment, the vehicle's current position is point A on the road, its current speed is 40 km / h, its current heading angle is 0 degrees, and its current acceleration is 0 m / s². The selected target lane change gap has its lateral center position 3.5 meters to the left of the current lane and its longitudinal starting position 20 meters in front of point A. The system simultaneously obtains that the target lane has a curvature of 0 and a straight lane line. Then, in the Frenner coordinate system, a fifth-order polynomial trajectory optimization algorithm is used to generate a sequence of trajectory points. During the generation process, it ensures that the lateral acceleration is always less than 2.5 m / s², the lateral jerk is less than 3 m / s³, the trajectory path does not intrude into the safety envelope of adjacent vehicles, and the trajectory endpoint speed remains consistent with the current speed of 40 km / h. Finally, each trajectory point is matched with the corresponding constant-speed target speed and the target acceleration of 0 to form a complete lane change trajectory.

[0091] Based on the above scheme, by obtaining the position parameters of the target lane change gap and the lane information of the target lane, and combining the current driving state of the vehicle, a polynomial trajectory optimization algorithm is used in a specified coordinate system to generate a trajectory point series that satisfies multiple constraints. The speed and acceleration of the point series are matched to form a complete trajectory, which can make the planned lane change trajectory fit the actual driving state of the vehicle and the road conditions, while ensuring the smoothness and safety of the lane change process, thereby improving the rationality and safety of the lane change trajectory.

[0092] In this application, the step of controlling the vehicle to perform a lane-changing action based on the lane-changing trajectory can be executed according to the following steps 144 to 145: Step 144: The lane change trajectory is sent to the vehicle's lateral and longitudinal controllers, which then output steering wheel angle commands and accelerator and brake opening commands to control the vehicle to travel according to the lane change trajectory.

[0093] Step 145: During the process of the vehicle performing a lane change, continuously acquire updated perception fusion data and perform real-time verification of the lane change trajectory.

[0094] In this application, the vehicle is controlled to perform a lane-changing maneuver based on the lane-changing trajectory. First, the planned complete lane-changing trajectory is sent to the vehicle's lateral and longitudinal controllers. The lateral controller is primarily responsible for steering control, while the longitudinal controller is primarily responsible for throttle and brake control. The two controllers cooperate to jointly control the vehicle's movement. The lateral controller can calculate the steering wheel angle corresponding to each driving stage based on the lateral position changes of the lane-changing trajectory and output steering wheel angle commands to control the vehicle's steering action. The longitudinal controller can calculate the throttle or brake opening based on the target speed and acceleration matched to the lane-changing trajectory and output throttle or brake opening commands to control the vehicle's acceleration and deceleration. Through the coordinated work of the two controllers, the vehicle is controlled to travel according to the planned lane-changing trajectory.

[0095] After the vehicle initiates a lane change maneuver, the system does not cease operation. Instead, it continuously acquires updated perception fusion data through sensing devices. This data represents real-time feedback on the surrounding environment during the vehicle's movement, including information such as changes in the driving status of nearby vehicles and changes in the position of obstacles. The system compares the updated perception fusion data with the original lane change trajectory, performing real-time verification to determine whether the current trajectory still meets the requirements for a safe lane change. If the surrounding environment changes and the original trajectory poses a risk of driving conflict, the system can immediately adjust the lane change trajectory or directly abort the lane change maneuver, ensuring the safety of the lane change process.

[0096] For example, in one specific embodiment, the system sends the planned lane-changing trajectory to the vehicle's lateral and longitudinal controllers. The lateral controller, based on the trajectory requirements, outputs a steering wheel angle command to gradually turn 15 degrees to the left. The longitudinal controller, based on the speed requirements of the trajectory, outputs a command to maintain throttle opening and constant speed. The vehicle then begins the lane change according to these commands. During the lane change, the system continuously acquires perception fusion data. If it detects a sudden acceleration of a vehicle behind in the target lane, indicating a rear-end collision risk with the original lane-changing trajectory, the system immediately adjusts the trajectory, outputting commands to increase the steering wheel angle and accelerate the lane-changing speed, allowing the vehicle to quickly complete the lane change and avoid the driving risk.

[0097] Based on the above scheme, by sending the lane-changing trajectory to the lateral and longitudinal controllers, which then output corresponding instructions to control the vehicle's movement, and continuously acquiring perception fusion data and verifying the trajectory in real time during the lane-changing process, the vehicle can accurately complete the lane-changing action according to the planned trajectory, while responding to environmental changes in a timely manner during the lane-changing process, thereby improving the accuracy and safety of the lane-changing action.

[0098] In this application, steps 151 to 152 may also be performed: Step 151: Render the trajectory marker corresponding to the lane change trajectory in the human-computer interaction interface. During the process of the vehicle performing the lane change action, render the progress marker and status prompt text of the lane change action in real time.

[0099] Step 152: After the lane change is completed, clear the gap indicator and the trajectory indicator on the human-computer interaction interface, and display a lane change completion prompt.

[0100] In this application, steps 153 to 154 may also be performed: Step 153: If a new obstacle is detected during the real-time verification process, the target lane change gap is occupied, or the safety score is lower than the preset score threshold, the lane change action is immediately stopped, the vehicle is controlled to return to the original lane and maintain stable driving.

[0101] Step 154: If a driver's manual takeover operation is detected during the vehicle's lane change maneuver, the output of lane change control commands shall be stopped immediately, and control of the vehicle shall be transferred to the driver.

[0102] Based on the technical solution proposed in this application, by responding to the driver's lane change command and acquiring perception fusion data, a three-dimensional spatiotemporal search is performed in the target lane to determine a feasible lane change gap. The gap is then displayed on the human-machine interface for the driver to select. Finally, the trajectory is planned and the lane change is controlled according to the selected target lane change gap. This allows the driver to participate in the lane change decision-making process and perceive the lane change space planned by the system, thereby effectively improving the driver's sense of participation and control during the lane change process.

[0103] In addition, the vehicle lane change control method described in this application may also perform the following steps 161 to 162: Step 161: In response to receiving a second vehicle lane change command that crosses multiple lanes, perform a three-dimensional spatiotemporal search in multiple adjacent target lanes to determine the feasible lane change gaps in each target lane and generate a continuous lane change gap sequence.

[0104] Step 162: Plan a continuous lane change trajectory according to the lane change gap sequence, set a preset buffer time between lane change actions in adjacent lanes, and control the vehicle to complete the lane change action across multiple lanes in sequence.

[0105] In this application, the proposed vehicle lane change control method can also support lane change operations across multiple lanes, meeting the complex lane change needs of drivers. When a driver needs to change lanes across multiple lanes, a second vehicle lane change command can be issued. This command can be triggered by the driver continuously or repeatedly flicking the turn signal stalk, representing the driver's intention to change lanes across multiple lanes. After receiving the second vehicle lane change command, the system can search for lane change gaps in multiple adjacent target lanes. Within each target lane, the feasible lane change gaps are determined sequentially according to the aforementioned three-dimensional spatiotemporal search method. Then, based on the vehicle's driving direction and the lane order, the feasible lane change gaps in multiple target lanes are arranged in an orderly manner to generate a continuous lane change gap sequence. Each lane change gap in this sequence corresponds to each adjacent target lane, forming a continuous lane change path across multiple lanes.

[0106] After generating a continuous sequence of lane change gaps, the system can plan a continuous lane change trajectory based on the overall position information of the sequence and the vehicle's current driving state. This trajectory is not a single lane change line, but rather consists of multiple sequentially connected lane change trajectories, each corresponding to a lane change operation. Simultaneously, the system can set a preset buffer time between lane change actions in adjacent lanes, for example, 1 to 2 seconds. This buffer time represents the period of stable driving within the lane after the vehicle completes a lane change, allowing the driver time to observe the surrounding environment and ensuring a smoother driving experience. Finally, following the planned continuous lane change trajectory, the system can control the vehicle to execute the next lane change action only after completing the previous lane change action and waiting for the preset buffer time, sequentially completing all lane change actions across multiple lanes.

[0107] For example, in one specific embodiment, a driver on a highway wants to change lanes from the rightmost lane to the leftmost lane, requiring crossing two adjacent lanes. The driver continuously activates the left turn signal stalk, issuing a second lane change command. Upon receiving the command, the system performs a three-dimensional spatiotemporal search in both the middle and leftmost lanes, identifying a feasible lane change opportunity in both lanes and arranging them into a continuous lane change sequence according to driving order. The system then plans a continuous lane change trajectory from the rightmost lane to the middle lane, and then from the middle lane to the leftmost lane based on this sequence, while setting a preset buffer time of 1.5 seconds between each lane change action. The system first controls the vehicle to complete the lane change from the rightmost lane to the middle lane, and after the vehicle travels smoothly in the middle lane for 1.5 seconds, it then controls the vehicle to complete the lane change from the middle lane to the leftmost lane, ultimately completing the multi-lane lane change operation.

[0108] Based on the above scheme, by responding to the second command for lane changing across multiple lanes, searching and generating a continuous sequence of lane change gaps in multiple target lanes, planning a continuous lane change trajectory and setting a buffer time between adjacent lane changes, and controlling the vehicle to complete the lane change in sequence, the vehicle can achieve continuous lane change operations across multiple lanes, meet the complex lane change needs of drivers, and thus improve the applicability of the lane change control method.

[0109] The following describes an embodiment of the apparatus described in this application, which can be used to execute the vehicle lane change control method described in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the vehicle lane change control method described in the above applications.

[0110] See Figure 3 The diagram shows a block diagram of a vehicle lane change control device according to an embodiment of this application.

[0111] like Figure 3As shown, the vehicle lane change control device 300 according to an embodiment of this application includes: an acquisition unit 301, a generation unit 302, a determination unit 303, and a control unit 304.

[0112] The acquisition unit 301 is configured to, in response to receiving a lane change command from a first vehicle, acquire perception fusion data of the surrounding environment of the vehicle, and perform a three-dimensional spatiotemporal search in adjacent target lanes based on the perception fusion data to determine feasible lane change gaps within the target lanes; the generation unit 302 is configured to generate candidate lane change gap information corresponding to the feasible lane change gaps, and display the gap identifier in the candidate lane change gap information on the vehicle's human-machine interface; the determination unit 303 is configured to receive a selection command for the gap identifier, and determine the target lane change gap according to the selection command; and the control unit 304 is configured to plan a lane change trajectory based on the target lane change gap and the vehicle's current driving state, and control the vehicle to perform a lane change action according to the lane change trajectory.

[0113] In some embodiments of this application, based on the foregoing scheme, the acquisition unit 301 is configured to: construct a three-dimensional spatiotemporal search grid in the target lane, wherein the dimensions of the three-dimensional spatiotemporal search grid include a longitudinal spatial dimension, a lateral spatial dimension, and a time dimension; identify adjacent vehicles in front and behind in the target lane based on the perception fusion data, and predict the movement trajectories of the adjacent vehicles in front and behind within a preset time range; slide a safety window in the three-dimensional spatiotemporal search grid, and perform conflict detection between the safety window and the movement trajectories of the adjacent vehicles in front and behind; and determine the safety window where no conflict is detected as the feasible lane change gap.

[0114] In some embodiments of this application, based on the aforementioned scheme, the acquisition unit 301 is configured to: determine whether the movement trajectories of the safety window and the adjacent vehicles in front and behind meet preset conditions, the preset conditions including that the longitudinal distance between the safety window and the vehicle in front is greater than a first safety distance, the longitudinal distance between the safety window and the vehicle behind is greater than a second safety distance, the vehicle does not intrude into the safety envelope of the adjacent vehicle during the lane change to the safety window, and the adjacent vehicle does not enter the safety window when the vehicle completes the lane change action; wherein, the first safety distance is dynamically calculated based on the relative speed between the vehicle and the vehicle in front, and the second safety distance is proportionally amplified when the vehicle is traveling at high speed; if the movement trajectories of the safety window and the adjacent vehicles in front and behind meet the preset conditions, it is determined that no conflict was detected.

[0115] In some embodiments of this application, based on the foregoing scheme, the acquisition unit 301 is further configured to: convert obstacle information in the perception fusion data into spatiotemporal point cloud data, construct a three-dimensional KD tree index based on the spatiotemporal point cloud data; perform grid sampling within the three-dimensional spatiotemporal search grid to obtain candidate spatiotemporal points, and perform nearest neighbor obstacle query for each candidate spatiotemporal point through the three-dimensional KD tree index; if the distance between the candidate spatiotemporal point and the nearest neighbor obstacle is greater than the third safety distance, then expand the candidate spatiotemporal point into the safety window.

[0116] In some embodiments of this application, based on the foregoing scheme, the generation unit 302 is configured to: convert the world coordinates of the gaps in the candidate lane change gap information into pixel coordinates of the human-computer interaction interface; draw a gap marker of a predetermined shape on the human-computer interaction interface according to the pixel coordinates; set the display style of the gap marker according to the safety score in the candidate lane change gap information, set the gap marker with the highest safety score as the recommended style, and set the gap marker with the safety score below a preset score threshold as the unavailable style; render the corresponding safety score and estimated lane change time next to the gap marker, and display a prompt text for the lane change action on the human-computer interaction interface.

[0117] In some embodiments of this application, based on the aforementioned scheme, the determining unit 303 is configured to: detect the driver's selection operation on the neutral gear indicator within a preset waiting time, and determine the corresponding feasible lane change neutral gear as the target lane change neutral gear based on the selection operation; if the selection operation is not detected within the preset waiting time, then determine the feasible lane change neutral gear with the highest safety score as the target lane change neutral gear.

[0118] In some embodiments of this application, based on the aforementioned scheme, the current driving state includes the vehicle's current position, current speed, current heading angle, and current acceleration. The control unit 304 is configured to: acquire the position parameters of the target lane change gap and the lane information of the target lane, the lane information including lane curvature and lane line information; generate a lane change trajectory point series in a Frenner or Cartesian coordinate system using a polynomial trajectory optimization algorithm based on the position parameters and the lane information; wherein, the lane change trajectory point series satisfies dynamic constraints during generation, does not intrude into the safety envelope of adjacent vehicles, and the target speed at the end of the lane change trajectory matches the vehicle's current speed, the dynamic constraints including the vehicle's lateral acceleration being less than a preset acceleration threshold and the vehicle's lateral jerk being less than a preset jerk threshold; and match the corresponding target speed and target acceleration for the lane change trajectory point series to form a complete lane change trajectory.

[0119] In some embodiments of this application, based on the foregoing scheme, the control unit 304 is further configured to: send the lane change trajectory to the vehicle's lateral and longitudinal controllers, and have the lateral and longitudinal controllers output steering wheel angle commands and accelerator and brake opening commands to control the vehicle to drive according to the lane change trajectory; during the process of the vehicle performing the lane change action, continuously acquire updated perception fusion data and perform real-time verification of the lane change trajectory.

[0120] In some embodiments of this application, based on the foregoing scheme, the control unit 304 is further configured to: in response to receiving a second vehicle lane change command for cross-lane lane change, perform a three-dimensional spatiotemporal search in multiple adjacent target lanes respectively, determine feasible lane change gaps in each target lane and generate a continuous lane change gap sequence; plan a continuous lane change trajectory according to the lane change gap sequence, set a preset buffer time between lane change actions in adjacent lanes, and control the vehicle to complete the cross-lane lane change action in sequence.

[0121] Based on the same inventive concept, embodiments of this application provide a computer program product, the computer program product including computer instructions stored in a computer-readable storage medium and adapted to be read and executed by a processor so as to cause a computer device having the processor to perform the operations performed by the vehicle lane change control method as described above.

[0122] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to implement the operations performed by the vehicle lane change control method described above.

[0123] Based on the same inventive concept, this application also provides a vehicle, see reference. Figure 4 The diagram shows a structural schematic of a vehicle in an embodiment of this application. The vehicle includes one or more memories 404, one or more processors 402, and at least one computer program (computer program instruction) stored in the memory 404 and executable on the processor 402. When the processor 402 executes the computer program, it implements the vehicle lane change control method as described above.

[0124] Among them, Figure 4In this document, a bus architecture (represented by bus 400) is used. Bus 400 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 402 and memory represented by memory 404. Bus 400 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 405 provides an interface between bus 400 and receiver 401 and transmitter 403. Receiver 401 and transmitter 403 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 402 is responsible for managing bus 400 and general processing, while memory 404 can be used to store data used by processor 402 during operation.

[0125] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. When implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this application and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.

[0126] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0127] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0128] When the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing computer program instructions, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0129] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A vehicle lane change control method, characterized in that, The method includes: In response to receiving a lane change command from a first vehicle, the system acquires perception fusion data of the surrounding environment of the vehicle, and performs a three-dimensional spatiotemporal search in the adjacent target lane based on the perception fusion data to determine the feasible lane change gap in the target lane. Generate candidate lane change gap information corresponding to the feasible lane change gap, and display the gap identifier in the candidate lane change gap information on the vehicle's human-machine interface. Receive a selection instruction for the neutral gap identifier, and determine the target lane change neutral gap based on the selection instruction; The system plans a lane-changing trajectory based on the target lane-changing gap and the vehicle's current driving state, and controls the vehicle to perform the lane-changing action according to the lane-changing trajectory.

2. The method according to claim 1, characterized in that, The step of performing a three-dimensional spatiotemporal search in adjacent target lanes based on the perception fusion data to determine feasible lane-changing gaps within the target lanes includes: A three-dimensional spatiotemporal search grid is constructed in the target lane, and the dimensions of the three-dimensional spatiotemporal search grid include vertical spatial dimension, horizontal spatial dimension and time dimension; Based on the perception fusion data, identify the vehicles in front and behind in the target lane, and predict the movement trajectory of the vehicles in front and behind within a preset time range; Slide a safe window within the three-dimensional spatiotemporal search grid and perform conflict detection between the safe window and the movement trajectories of the adjacent vehicles in front and behind; The safe window where no conflict was detected is identified as the feasible lane change gap.

3. The method according to claim 2, characterized in that, The collision detection between the safety window and the movement trajectories of the adjacent vehicles in front and behind includes: The system determines whether the movement trajectories of the safety window and the adjacent vehicles in front and behind meet preset conditions. These preset conditions include: the longitudinal distance between the safety window and the vehicle in front is greater than a first safety distance; the longitudinal distance between the safety window and the vehicle behind is greater than a second safety distance; the vehicle does not intrude into the safety envelope of the adjacent vehicle during the lane change to the safety window; and the adjacent vehicle does not enter the safety window when the vehicle completes the lane change. The first safety distance is dynamically calculated based on the relative speed between the vehicle and the vehicle in front, and the second safety distance is proportionally amplified when the vehicle is traveling at high speed. If the movement trajectory of the safety window and the adjacent vehicles in front and behind meet the preset conditions, it is determined that no conflict has been detected.

4. The method according to claim 2, characterized in that, The step of performing a three-dimensional spatiotemporal search in adjacent target lanes based on the perception fusion data to determine feasible lane-changing gaps within the target lanes further includes: The obstacle information in the perception fusion data is converted into spatiotemporal point cloud data, and a three-dimensional KD tree index is constructed based on the spatiotemporal point cloud data. Candidate spatiotemporal points are obtained by grid sampling within the three-dimensional spatiotemporal search grid, and nearest neighbor obstacle queries are performed on each candidate spatiotemporal point through the three-dimensional KD tree index. If the distance between the candidate spatiotemporal point and its nearest neighbor obstacle is greater than the third safety distance, then the candidate spatiotemporal point is expanded into the safety window.

5. The method according to claim 1, characterized in that, The step of displaying the neutral gear indicator in the candidate lane change neutral gear information on the vehicle's human-machine interface includes: The world coordinates of the lane change gap information in the candidate lane change gap information are converted into pixel coordinates of the human-computer interaction interface, and a gap mark of a set shape is drawn on the human-computer interaction interface according to the pixel coordinates. The display style of the gap identifier is set according to the safety score in the candidate lane change gap information. The gap identifier with the highest safety score is set as the recommended style, and the gap identifier with the safety score below the preset score threshold is set as the unavailable style. Next to the gap indicator, render the corresponding safety score and estimated lane change time, and display a prompt text for the lane change action on the human-computer interaction interface.

6. The method according to claim 1, characterized in that, The step of receiving a selection instruction for the gap identifier and determining the target lane change gap according to the selection instruction includes: Within a preset waiting time, the driver's selection operation on the neutral gear indicator is detected, and the corresponding feasible lane change neutral gear is determined as the target lane change neutral gear based on the selection operation. If the selection operation is not detected within the preset waiting time, the feasible lane change gap with the highest safety score is determined as the target lane change gap.

7. The method according to claim 1, characterized in that, The current driving state includes the vehicle's current position, current speed, current heading angle, and current acceleration. The planning of the lane-change trajectory based on the target lane-change gap and the vehicle's current driving state includes: Obtain the position parameters of the target lane change gap and the lane information of the target lane, wherein the lane information includes lane curvature and lane line information; Based on the location parameters and lane information, a polynomial trajectory optimization algorithm is used to generate a lane change trajectory point series in the Frenner or Cartesian coordinate system. The lane change trajectory point series satisfies dynamic constraints during the generation process, does not intrude into the safety envelope of adjacent vehicles, and the target speed at the end of the lane change trajectory matches the current speed of the vehicle. The dynamic constraints include the vehicle's lateral acceleration being less than a preset acceleration threshold and the vehicle's lateral jerk being less than a preset jerk threshold. Match the target velocity and target acceleration to the lane change trajectory points to form a complete lane change trajectory.

8. The method according to claim 1, characterized in that, The step of controlling the vehicle to perform a lane-changing action according to the lane-changing trajectory includes: The lane change trajectory is sent to the vehicle's lateral and longitudinal controllers, which then output steering wheel angle commands and accelerator and brake opening commands to control the vehicle to travel according to the lane change trajectory. During the lane change maneuver, the vehicle continuously acquires updated perception fusion data and verifies the lane change trajectory in real time.

9. The method according to claim 1, characterized in that, The method further includes: In response to receiving a second vehicle lane change command that crosses multiple lanes, a three-dimensional spatiotemporal search is performed in multiple adjacent target lanes to determine the feasible lane change gaps in each target lane and generate a continuous lane change gap sequence. Based on the lane change gap sequence, a continuous lane change trajectory is planned, and a preset buffer time is set between lane change actions in adjacent lanes to control the vehicle to complete the lane change action across multiple lanes in sequence.

10. A vehicle, characterized in that, The vehicle includes one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to implement the method as described in any one of claims 1 to 9.

Images