Vehicle control method, vehicle and storage medium

Abstract

The embodiment of the invention relates to a vehicle control method, a vehicle and a storage medium, and relates to the technical field of vehicle driving control, and the method comprises the steps: determining a target lane corresponding to a target vehicle under the condition that a lane changing state machine of the target vehicle obtains that a current lane changing state is a lane changing unlocked state, acquiring environment sensing data of the target vehicle; generating constraint conditions based on the target lane, the environment sensing data and a preset driving track, and determining a target driving track; and controlling the target vehicle to drive to the target lane based on the target driving track. According to the method, the target lane is determined before the current lane changing state of the lane changing state machine is the lane changing unlocked state and the driving track is searched, so that the feasibility of the target driving track is ensured, the situations of back-and-forth lane changing, continuous multi-lane changing and the like are avoided, and the stability of the vehicle driving track is improved.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle driving control technology, and in particular to a vehicle control method, a vehicle, and a storage medium. Background Technology

[0002] With the development of artificial intelligence technology, it is possible to plan the driving trajectory for a vehicle and control the vehicle to drive along the planned trajectory.

[0003] In related technologies, there are discrepancies between lane-changing decision results and planned driving trajectories, which may lead to repeated lane changes or situations where lane-changing decisions cannot be executed. Summary of the Invention

[0004] To solve the above-mentioned technical problems, or at least partially solve them, this disclosure provides a vehicle control method, a vehicle, and a storage medium.

[0005] This disclosure provides a vehicle control method, the method comprising: determining the target lane corresponding to the target vehicle based on the current lane-changing state machine of the target vehicle being in a lane-changing unlocked state, and acquiring environmental perception data of the target vehicle; determining a target driving trajectory based on the target lane, the environmental perception data, and preset driving trajectory constraints; and controlling the target vehicle to drive to the target lane based on the target driving trajectory.

[0006] Therefore, when the current lane-changing state of the lane-changing state machine is an unlocked lane-changing state and the target lane is determined before searching the driving trajectory, the feasibility of the target driving trajectory is guaranteed, thereby avoiding back-and-forth lane changes and continuous multi-lane lane changes, and improving the stability of the vehicle driving trajectory.

[0007] Optionally, determining the target lane corresponding to the target vehicle includes: when a turning intention signal of the target vehicle is detected, determining the lane corresponding to the turning intention direction based on the turning intention signal, and verifying that the lane corresponding to the turning intention direction exists and is reachable, and then using the lane corresponding to the turning intention direction as the target lane; when the turning intention signal is not detected, and a lane change is detected in the navigation route, obtaining multiple candidate lanes based on the navigation route, and determining the target vehicle from the multiple candidate lanes; when a lane change is detected in the navigation route, determining the lane change trajectory of the target vehicle based on a preset trajectory search algorithm, and determining the target lane based on the lane change trajectory.

[0008] This solves the arbitration problem in the event of multi-source target lane conflicts, dynamically adapts to various lane-changing needs, and ensures the certainty and stability of the target lane during the lane-changing process through multi-level judgment logic, avoiding frequent or uncertain target lane switching.

[0009] Optionally, determining the target lane from the plurality of candidate lanes includes: obtaining the lane type, number of lanes, and traffic rules of each candidate lane to determine the priority of the plurality of candidate lanes; and determining the candidate lane with the highest priority as the target lane.

[0010] Therefore, when the lane pointed to by the navigation route is different from the current lane, the priority of the navigation suggested lane is evaluated based on factors such as road type and number of lanes, and the lane with the highest priority is selected as the target lane, thereby further improving the stability of the target lane.

[0011] Optionally, determining the target driving trajectory based on the target lane, the environmental perception data, and the preset driving trajectory generation constraints includes: processing the target lane, the environmental perception data, and the preset driving trajectory generation constraints based on a preset driving trajectory search algorithm to obtain multiple candidate driving trajectories; wherein each candidate driving trajectory has a corresponding trajectory cost; and selecting the candidate driving trajectory with the minimum trajectory cost as the target driving trajectory.

[0012] Therefore, by calculating and determining the target driving trajectory with the minimum trajectory cost through the target lane, environmental perception data and preset driving trajectory generation constraints, the weights can be dynamically adjusted according to different target lanes to adjust the candidate driving trajectories to have corresponding trajectory costs, thereby ensuring the feasibility of the target driving trajectory, thus avoiding situations such as back-and-forth lane changes and continuous multi-lane lane changes, and improving the stability of vehicle driving trajectory.

[0013] Optionally, in the process of generating the candidate driving trajectory, the method further includes: obtaining the previous frame driving trajectory of the target vehicle; transforming the previous frame driving trajectory based on a preset coordinate transformation matrix to obtain the driving trajectory to be compared; calculating the distance deviation between the driving trajectory to be compared and the candidate driving trajectory; and adjusting the trajectory cost of the candidate driving trajectory based on the distance deviation.

[0014] Therefore, during the generation of candidate driving trajectories, the trajectory cost of the candidate driving trajectory is adjusted by comparing the deviation with the driving trajectory of the previous frame, which further ensures the feasibility of the target driving trajectory, thereby avoiding situations such as back-and-forth lane changes and continuous multi-lane lane changes, and improving the stability of the vehicle driving trajectory.

[0015] Optionally, controlling the target vehicle to travel to the target lane based on the target driving trajectory includes: obtaining the target trajectory points of the target driving trajectory according to a preset search order; calculating the lateral displacement value between the current position point of the target vehicle and the target trajectory points; and determining that the target vehicle travels to the target lane when there is a target trajectory point whose lateral displacement value is less than a preset lateral displacement threshold.

[0016] Therefore, by calculating the lateral displacement between the vehicle's current position and the target trajectory point in real time during the vehicle's movement, it can be determined whether the target vehicle has entered the target lane, thereby improving the accuracy of vehicle control and thus enhancing vehicle driving stability.

[0017] Optionally, after determining the target lane, the method further includes: controlling the lane-changing state machine to a locked state for traveling to the target lane.

[0018] Therefore, by setting the target lane to a locked state through the lane-changing state machine, and maintaining this locked state until the lane change is completed or a cancellation condition is met, the target lane is usually adjusted first rather than switched when environmental conditions change, thus ensuring behavioral consistency and avoiding frequent switching of the target lane.

[0019] Optionally, the method further includes: detecting the driving information of the target vehicle; and updating the state of the lane-changing state machine based on the driving information.

[0020] Therefore, the state of the lane-changing state machine is updated in real time according to the vehicle's driving status. By managing the lane-changing state machine, chaotic state transitions during lane changing can be avoided, and situations such as lane changing cancellation, interruption, or completion can be accurately identified, thereby further improving the stability of vehicle driving.

[0021] This disclosure also provides a vehicle control device, comprising: a first determining module, configured to determine the target lane corresponding to the target vehicle based on the target vehicle's lane-changing state machine obtaining that the current lane-changing state is an unlocked lane-changing state; an acquiring module, configured to acquire environmental perception data of the target vehicle; a second determining module, configured to generate constraint conditions based on the target lane, the environmental perception data, and a preset driving trajectory, and determine a target driving trajectory; and a control module, configured to control the target vehicle to drive to the target lane based on the target driving trajectory.

[0022] This disclosure also provides a vehicle, the vehicle including: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the vehicle control method provided in this disclosure.

[0023] This disclosure also provides a computer-readable storage medium storing a computer program for performing the vehicle control method provided in this disclosure.

[0024] This disclosure also provides a computer program product, including a computer program, wherein the computer program is executed by a processor as described in this disclosure embodiment of the vehicle control method.

[0025] The technical solution provided in this disclosure has the following advantages compared with the prior art: The vehicle control scheme provided in this disclosure includes: determining the target lane corresponding to the target vehicle when the current lane-changing state machine of the target vehicle obtains that the current lane-changing state is an unlocked lane-changing state, and obtaining the environmental perception data of the target vehicle; generating constraint conditions based on the target lane, environmental perception data, and preset driving trajectory to determine the target driving trajectory; and controlling the target vehicle to drive to the target lane based on the target driving trajectory. This method determines the target lane when the current lane-changing state machine is an unlocked lane-changing state and before searching for a driving trajectory, ensuring the feasibility of the target driving trajectory, thereby avoiding back-and-forth lane changes and continuous multi-lane lane changes, and improving the stability of the vehicle driving trajectory.

[0026] The above description is merely an overview of the technical solution disclosed herein. In order to better understand the technical means of this disclosure and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this disclosure more apparent and understandable, specific embodiments of this disclosure are described below. Attached Figure Description

[0027] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0028] Figure 1 A schematic flowchart of a vehicle control method provided in an embodiment of this disclosure; Figure 2 A schematic flowchart of another vehicle control method provided in an embodiment of this disclosure; Figure 3 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of the present disclosure; Figure 4 This is a schematic diagram of the structure of a vehicle provided in an embodiment of the present disclosure. Detailed Implementation

[0029] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0030] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0031] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0032] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0033] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0034] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0035] In real-world vehicle control scenarios, lane-changing decisions are separated from driving trajectory planning, leading to inconsistencies between the lane-changing decision results and the planned driving trajectory. This can result in repeated lane changes or decisions that cannot be executed. Furthermore, the lack of a lane-changing state machine for management leads to chaotic state transitions during lane changes, making it impossible to accurately identify situations such as lane-changing cancellation, interruption, or completion. Additionally, frequent trajectory replanning due to environmental changes during lane changes results in a lack of an effective trajectory persistence mechanism to ensure driving comfort.

[0036] To address the aforementioned technical problems, this disclosure proposes a vehicle control scheme. Based on the target vehicle's lane-changing state machine, if the current lane-changing state is "locked," the scheme determines the target lane corresponding to the target vehicle and acquires the target vehicle's environmental perception data. Based on the target lane, environmental perception data, and a preset driving trajectory, constraints are generated to determine the target driving trajectory. The scheme then controls the target vehicle to move to the target lane based on the target driving trajectory. This method ensures the feasibility of the target driving trajectory by determining the target lane before searching for a driving trajectory, even when the current lane-changing state of the lane-changing state machine is "locked" and before the driving trajectory is searched. This avoids back-and-forth lane changes and continuous multi-lane lane changes, thus improving the stability of the vehicle's driving trajectory.

[0037] Figure 1 This is a flowchart illustrating a vehicle control method provided in an embodiment of the present disclosure. The vehicle control method can be executed by a vehicle control device, which can be implemented using software and / or hardware and is generally integrated into a vehicle. Figure 1 As shown, this vehicle control method is applied to a vehicle and includes: Step 101: Based on the target vehicle's lane-changing state machine, if the current lane-changing state is unlocked, determine the target lane corresponding to the target vehicle and obtain the target vehicle's environmental perception data.

[0038] The target vehicle refers to any vehicle that is in motion, and this disclosure does not impose specific restrictions on the type of vehicle.

[0039] Among them, the lane-changing state machine refers to the component or device that records the lane-changing state, which includes a variety of different lane-changing states, such as attempting a lane change, lane-changing in progress, and lane-changing canceled.

[0040] Specifically, the following states can be categorized as follows: Current Lane Forward Status: This indicates driving in the current lane with default driving information and no lane change action triggered. Left Lane Change Attempt Status: This indicates an attempt to change lanes to the left, detecting a left lane change request (e.g., the driver shifts the lever to the left, and the navigation suggests a left lane change) but no valid trajectory is generated. Right Lane Change Attempt Status: This indicates an attempt to change lanes to the right, detecting a right lane change request (e.g., the driver shifts the lever to the right, and the navigation suggests a right lane change) but no valid trajectory is generated. Left Lane Change Status: This indicates a left lane change in progress, with a left lane change trajectory generated and executed. Right Lane Change Status: This indicates a right lane change in progress, with a right lane change trajectory generated and executed. Cancelled Lane Change Status: This indicates a lane change has been cancelled; the driver reverses the lever, actively terminating the lane change. Lane Change Interrupted Status: This indicates a lane change has been interrupted due to external conditions. Lane Change Failed Status: This indicates a failed lane change, and the planner cannot generate a valid trajectory. Lane Change Completed Status: This indicates a successful lane change and transition to the target lane.

[0041] In this embodiment of the disclosure, during the driving of the target vehicle, the current lane-changing state is obtained based on the lane-changing state machine of the target vehicle. The target lane corresponding to the target vehicle is determined only if the current lane-changing state is locked or unlocked. For example, if the state indication of the lane-changing state machine is "lane-changing in progress, medium lane-changing locked state", it means that no new target lane confirmation operation will be performed when the target vehicle is in the process of changing lanes to avoid back-and-forth lane changes. Or, if the state indication of the lane-changing state machine is "lane-changing completed, medium lane-changing unlocked state", it means that the target vehicle has completed the previous lane change. In such cases, a new target lane can be determined to improve the effectiveness of vehicle control.

[0042] Furthermore, when the current lane-changing state in the lane-changing state machine of the target vehicle is an unlocked lane-changing state, the target lane corresponding to the target vehicle is determined. In this embodiment of the disclosure, there are many ways to determine the target lane corresponding to the target vehicle. In some embodiments, when the steering intention signal of the target vehicle is detected, the lane corresponding to the steering intention direction is determined based on the steering intention signal, and when it is verified that the lane corresponding to the steering intention direction exists and is reachable, the lane corresponding to the steering intention direction is taken as the target lane.

[0043] In other embodiments, when no steering intention signal is detected, but a lane change is detected in the navigation route, multiple candidate lanes are obtained based on the navigation route, and the target vehicle is determined from the multiple candidate lanes.

[0044] In some other embodiments, when a lane change is detected as not occurring on the navigation route, a preset trajectory search algorithm is used to determine the target vehicle's lane-changing trajectory, and the target lane is then determined based on this trajectory. This allows for the determination of the final target lane based on a certain priority for target lanes determined in different ways, further improving the flexibility and stability of control.

[0045] Furthermore, environmental perception data of the target vehicle is acquired; where environmental perception data refers to all data corresponding to the environment of the target vehicle. This can be achieved by using one or more preset sensors to perceive the environment of the target vehicle and acquire environmental perception data, such as road structure and obstacle information corresponding to the target vehicle.

[0046] Step 102: Generate constraints based on the target lane, environmental perception data, and preset driving trajectory to determine the target driving trajectory.

[0047] Among them, the preset driving trajectory generation constraints refer to the constraints in the driving trajectory generation process, including kinematic constraints, safety constraints, and comfort constraints. Kinematic constraints include the maximum lateral acceleration limit and the minimum turning radius limit. Safety constraints include the minimum distance to obstacles and the minimum distance to lane boundaries. Comfort constraints include acceleration limits and curvature change rate limits.

[0048] The target driving trajectory refers to the optimal driving trajectory selected or generated during the planning stage, and the target vehicle will drive according to the target driving trajectory.

[0049] In this embodiment of the disclosure, after determining the target lane and acquiring environmental perception data, there are many ways to determine the target driving trajectory based on the target lane, environmental perception data and preset driving trajectory generation constraints. In some embodiments, the target lane, environmental perception data and preset driving trajectory generation constraints are processed based on a preset driving trajectory search algorithm to obtain multiple candidate driving trajectories; wherein, each candidate driving trajectory has a corresponding trajectory cost, and the candidate driving trajectory corresponding to the minimum trajectory cost is taken as the target driving trajectory.

[0050] In other embodiments, the target lane, environmental perception data, and preset driving trajectory generation constraints are input into a preset driving trajectory generation model for processing to obtain the target driving trajectory. The above two methods are only examples, and different methods can be selected for processing according to different actual application scenarios. This disclosure does not impose specific restrictions on the method of determining the target driving trajectory based on the target lane, environmental perception data, and preset driving trajectory generation constraints.

[0051] Step 103: Control the target vehicle to drive to the target lane based on the target driving trajectory.

[0052] In this embodiment of the disclosure, after determining the target driving trajectory, the target vehicle is controlled to drive to the target lane so as to drive according to the target driving trajectory. Specifically, the target vehicle is controlled to drive according to the target driving trajectory, and the lateral displacement value between the current position point of the target vehicle and the target trajectory point in the target driving trajectory is calculated. When there is a target trajectory point with a lateral displacement value less than a preset lateral displacement threshold, it is determined that the target vehicle has driven to the target lane.

[0053] The vehicle control scheme provided in this disclosure determines the target lane corresponding to the target vehicle when the current lane-changing state machine of the target vehicle is in an unlocked lane-changing state, and acquires the environmental perception data of the target vehicle; it then generates constraints based on the target lane, the environmental perception data, and a preset driving trajectory to determine the target driving trajectory; and finally, it controls the target vehicle to drive to the target lane based on the target driving trajectory. This method determines the target lane before searching for a driving trajectory, ensuring the feasibility of the target driving trajectory by determining the target lane when the current lane-changing state machine is in an unlocked lane-changing state. This avoids back-and-forth lane changes and continuous multi-lane lane changes, thereby improving the stability of the vehicle's driving trajectory.

[0054] In some embodiments, determining the target lane corresponding to the target vehicle includes: when a steering intention signal of the target vehicle is detected, determining the lane corresponding to the steering intention direction based on the steering intention signal, and if it is verified that the lane corresponding to the steering intention direction exists and is reachable, taking the lane corresponding to the steering intention direction as the target lane; when no steering intention signal is detected, and a lane change is detected in the navigation route, obtaining multiple candidate lanes based on the navigation route, and determining the target vehicle from the multiple candidate lanes; when no lane change is detected in the navigation route, determining the lane change trajectory of the target vehicle based on a preset trajectory search algorithm, and determining the target lane based on the lane change trajectory.

[0055] Among them, the steering intention signal refers to the lever signal for steering control of the target vehicle.

[0056] In this disclosed embodiment, the arbitration problem in the event of conflict between multiple target lanes (pole, navigation, efficiency) is resolved. That is, the pole instruction, navigation route and efficiency requirement may point to different target lanes, and the final target lane can be determined. This application takes into account the target lane provided by the navigation, as well as the dynamic adaptation to the driver's pole instruction or efficiency lane change requirement.

[0057] Specifically, priority is set for the source of the target lane, with lever commands taking precedence. When a valid lever signal is detected, the lane in the direction of the lever is used as the target lane. The validity criteria include a stable lever state, the existence and reachability of the target lane, and the lane change not being completed. The navigation route is the next best option; if there is no lever, the lane with the highest priority in the navigation path is used as the target lane. When neither of the above two conditions is met, the trajectory search algorithm autonomously optimizes and selects the target lane.

[0058] Understandably, target lane locking can ensure the stability and consistency of lane-changing behavior. Therefore, through multi-level judgment logic, the certainty and stability of the target lane during the lane-changing process can be ensured, avoiding frequent or uncertain target lane switching.

[0059] Specifically, when a valid stalk signal (left turn or right turn) is detected, the system first verifies whether the adjacent lane in the direction of the stalk exists and is reachable; if the verification is successful, the lane in that direction is immediately locked as the target lane, and the system enters the lane change attempt state.

[0060] In some embodiments, determining a target lane from multiple candidate lanes includes: obtaining the lane type, number of lanes, and traffic rules for each candidate lane; determining the priority of the multiple candidate lanes; and determining the candidate lane with the highest priority as the target lane.

[0061] Specifically, in the absence of a lever signal, check if there is a need to change the navigation route. When it is detected that the lane pointed to by the navigation route is different from the current lane, evaluate the priority of the navigation suggested lane (based on factors such as road type and number of lanes) and select the lane with the highest priority as the target lane.

[0062] The priority evaluation of candidate lanes adopts a multi-factor weighted algorithm, which considers one or more factors, including but not limited to lane type (such as main road or auxiliary road), number of lanes, and traffic rule restrictions.

[0063] Therefore, when the lane pointed to by the navigation route is different from the current lane, the priority of the navigation suggested lane is evaluated based on factors such as road type and number of lanes, and the lane with the highest priority is selected as the target lane, thereby further improving the stability of the target lane.

[0064] Specifically, when there is neither a lever signal nor a need to change navigation, the trajectory search algorithm autonomously calculates the optimal trajectory and the corresponding lane as the target lane based on the current traffic conditions (such as the speed of vehicles in adjacent lanes, traffic density, etc.).

[0065] It should be noted that after the target lane is determined, the target lane is set to a locked state and maintained until the lane change is completed or the cancellation condition is met. In the locked state, even if the environmental conditions change (such as an obstacle suddenly appearing in the adjacent lane), the system will prioritize adjusting the trajectory rather than switching the target lane to ensure consistent behavior. The lock release conditions include lane change completion (the vehicle is fully in the target lane), driver active cancellation (counter-steering the steering lever), and determination that lane change is not feasible (such as the target lane being suddenly closed).

[0066] This solves the arbitration problem in the event of multi-source target lane conflicts, dynamically adapts to various lane-changing needs, and ensures the certainty and stability of the target lane during the lane-changing process through multi-level judgment logic, avoiding frequent or uncertain target lane switching.

[0067] In some embodiments, determining a target driving trajectory based on the target lane, environmental perception data, and preset driving trajectory generation constraints includes: processing the target lane, environmental perception data, and preset driving trajectory generation constraints based on a preset driving trajectory search algorithm to obtain multiple candidate driving trajectories; wherein each candidate driving trajectory has a corresponding trajectory cost; and selecting the candidate driving trajectory with the minimum trajectory cost as the target driving trajectory.

[0068] Among them, the preset driving trajectory search algorithm can be Particle Swarm Optimization (PSO), the particle swarm algorithm, or Monte Carlo Tree Search (MCTS), which is a decision algorithm that combines stochastic simulation and tree search, approximating the optimal solution through a finite number of random samplings. The specific algorithm can be selected and set according to the actual application needs.

[0069] Specifically, trajectory cost is a core indicator used to evaluate the quality of a trajectory. It is usually quantified by a cost function in terms of safety, comfort, efficiency, etc. For example, safety cost includes distance from obstacles and collision risk; comfort cost includes centripetal acceleration and lateral deviation; efficiency cost includes distance to the target point and speed matching degree; and intention and interaction cost includes the need to consider the intentions and interaction risks of other traffic participants in long-term trajectory prediction.

[0070] Specifically, when there is a lane change requirement triggered by the driver's lever or a change in the navigation route, the target lane deviation weight can be increased during the trajectory search. The trajectory search algorithm prioritizes the target lane deviation weight, and the searched trajectory tries to reach the target lane as much as possible. When there is no lane change requirement triggered by the driver's lever or a change in the navigation route, the only possible lane change is an autonomous decision based on efficiency optimization. In this case, the target lane deviation weight is reduced to enhance efficiency factors.

[0071] It should be noted that, in addition to adjusting the weights based on the reasons for lane changes, dynamic optimization can also be combined with real-time traffic conditions (such as congestion levels) to further improve efficiency.

[0072] Therefore, by calculating and determining the target driving trajectory with the minimum trajectory cost through the target lane, environmental perception data and preset driving trajectory generation constraints, the weights can be dynamically adjusted according to different target lanes to adjust the candidate driving trajectories to have corresponding trajectory costs, thereby ensuring the feasibility of the target driving trajectory, avoiding situations such as back-and-forth lane changes and continuous multi-lane lane changes, and improving the stability of the vehicle driving trajectory.

[0073] In some embodiments, during the generation of candidate driving trajectories, the driving trajectory of the target vehicle in the previous frame is obtained; the driving trajectory in the previous frame is transformed based on a preset coordinate transformation matrix to obtain the driving trajectory to be compared; the distance deviation between the driving trajectory to be compared and the candidate driving trajectory is calculated; and the trajectory cost of the candidate driving trajectory is adjusted based on the distance deviation.

[0074] Specifically, in order to ensure the continuity and smoothness of the trajectory during the lane change process, the key trajectory point information planned in the previous frame is saved and converted to the current frame coordinate system for use, which effectively solves the problem of trajectory jump between frames.

[0075] Specifically, key trajectory points are extracted and saved from the previous frame's driving trajectory at fixed time intervals. These key trajectory points contain complete motion state information such as the vehicle's position coordinates, heading angle, speed, acceleration, and yaw rate. When sparse sampling, a balance between computational efficiency and accuracy is considered. Typically, key trajectory points are retained at intervals of, for example, 1 second, to ensure sufficient information without causing excessive computational burden.

[0076] Specifically, since each frame's planning is performed in the current vehicle coordinate system, while the saved driving trajectory of the previous frame is expressed in the vehicle coordinate system of the previous frame, a coordinate system transformation must be performed to ensure continuity. The transformation process is based on the relative pose changes between two frames and is achieved through a three-dimensional transformation matrix. This three-dimensional transformation matrix contains the translation and rotation changes of the vehicle between two consecutive frames, which can accurately describe the spatial relationship between the two coordinate systems.

[0077] In the specific conversion process, the time difference between two frames is first obtained, then the transformation matrix is ​​calculated using the pose change information provided by the positioning system, and finally the saved trajectory points are subjected to batch coordinate transformation.

[0078] Therefore, the trajectory search algorithm introduces the cost of trajectory change between two frames. After the coordinate transformation, the trajectory search algorithm will penalize the planned trajectory that differs greatly from the trajectory of the previous frame, so that the deviation between the planned trajectory and the planned trajectory of the previous frame is not too large. This solves the technical problem of frequent trajectory replanning caused by environmental changes during lane changing and the lack of an effective trajectory persistence mechanism to ensure driving comfort.

[0079] Therefore, during the generation of candidate driving trajectories, the trajectory cost of the candidate driving trajectory is adjusted by comparing the deviation with the driving trajectory of the previous frame, which further ensures the feasibility of the target driving trajectory, thereby avoiding situations such as back-and-forth lane changes and continuous multi-lane lane changes, and improving the stability of the vehicle driving trajectory.

[0080] In some embodiments, controlling a target vehicle to travel to a target lane based on a target driving trajectory includes: obtaining target trajectory points of the target driving trajectory according to a preset search order; calculating the lateral displacement value between the current position point of the target vehicle and the target trajectory point; and determining that the target vehicle is traveling to the target lane when there is a target trajectory point with a lateral displacement value less than a preset lateral displacement threshold.

[0081] Among them, a lateral displacement threshold is preset, such as 0.3 meters. This setting can be selected according to the actual application scenario. When the actual lateral displacement value between the vehicle and the target lane is less than the preset lateral displacement threshold, it is considered that the center area of ​​the target lane has been reached.

[0082] Specifically, following a preset search order, such as a back-to-foreign search order, the system searches backward from the end of the trajectory to find the first point that does not meet the threshold condition. The next target trajectory point is the landing point of the vehicle. This search method can quickly locate the section of the target trajectory that meets the condition, avoiding unnecessary full trajectory scanning and further improving data processing efficiency.

[0083] Therefore, by calculating the lateral displacement between the vehicle's current position and the target trajectory point in real time during the vehicle's movement, it can be determined whether the target vehicle has entered the target lane, thereby improving the accuracy of vehicle control and thus enhancing the stability of vehicle movement.

[0084] Optionally, after determining the target lane, the lane-changing state machine is locked to drive into the target lane.

[0085] Specifically, after determining the target lane, the target lane is set to a locked state and maintained until the lane change is completed or a cancellation condition is met. In the locked state, even if environmental conditions change (such as an obstacle suddenly appearing in an adjacent lane), the system will prioritize adjusting the trajectory rather than switching the target lane to ensure consistent behavior. The lock release conditions include lane change completion (the vehicle is fully in the target lane), driver active cancellation (counter-steering the steering lever), and determination that lane change is not feasible (such as the target lane being suddenly closed).

[0086] Therefore, by setting the target lane to a locked state through the lane-changing state machine, and maintaining this locked state until the lane change is completed or a cancellation condition is met, the target lane is usually adjusted first rather than switched when environmental conditions change, thus ensuring behavioral consistency and avoiding frequent switching of the target lane.

[0087] In some embodiments, the driving information of the target vehicle is detected; the state of the lane-changing state machine is updated based on the driving information.

[0088] The driving information includes driving trajectory type (such as left shift, right lane change, etc.) and driving lane information.

[0089] Specifically, once the target vehicle's driving trajectory changes to straight, the lane markings of the target vehicle have changed, meaning it has moved to another lane. If the lateral displacement of the trajectory points relative to the lane centerline is less than a threshold, the lane change is considered complete, and the lane change state machine is updated to the lane change end state.

[0090] Specifically, if the target vehicle's driving trajectory changes to straight ahead and the lane markings remain unchanged, meaning the target vehicle is still in its original lane and has not completed the lane change, the lane change state machine is updated to a lane change interruption state.

[0091] Specifically, if the driver cancels or reverses the lever, and the lane markings of the target vehicle do not change, it means that the target vehicle is still in its original lane and has not completed the lane change. The state of the lane change state machine is then updated to the lane change cancel state.

[0092] For example, firstly, in the current lane ahead, if a left lever is detected and the system switches to a left lane change attempt state with a left lane change trajectory, the system switches to a left lane change state. After receiving a cancel or reverse lever input, the system switches to a lane change cancellation state and returns to the current lane ahead. If a cancel or reverse lever input is received in the current lane ahead, the system also switches to a lane change cancellation state. After the left lane change, the trajectory changes to straight and the lane markings remain unchanged, so the system switches to a lane change interruption state and returns to the current lane ahead. After the left lane change, the trajectory changes to straight and the lane markings change, so the system switches to a lane change end state. Then, if a right lever is detected and the system switches to a right lane change attempt state with a right lane change trajectory, the system switches to a right lane change state. After receiving a cancel or reverse lever input, the system switches to a lane change cancellation state and returns to the current lane ahead. After the right lane change, the trajectory changes to straight and the lane markings change, so the system switches to a lane change end state.

[0093] Therefore, the state of the lane-changing state machine is updated in real time according to the vehicle's driving status. By managing the lane-changing state machine, chaotic state transitions during lane changing can be avoided, and situations such as lane changing cancellation, interruption, or completion can be accurately identified, thereby further improving the stability of vehicle driving.

[0094] Based on the foregoing embodiments, this disclosure addresses the problems of repeated lane changes caused by inconsistencies between lane-changing decisions and trajectory planning, arbitration issues arising from conflicts between multiple target lanes (pole, navigation, efficiency), human-machine co-driving conflicts caused by inaccurate lane-changing state determination, and ride comfort issues caused by discontinuous trajectories during lane changes. By constructing a deep collaborative mechanism between the trajectory search algorithm and the lane-changing state machine, and employing dynamic weight allocation for multiple target lanes, dual state determination based on lane marking changes and lateral displacement, and trajectory persistence, this disclosure achieves a smooth, safe, and expected lane-changing process for intelligent vehicles. The following section further elaborates on this. Figure 2Provide a detailed description.

[0095] Figure 2 This is a flowchart illustrating another vehicle control method provided in this embodiment of the present disclosure. This embodiment further optimizes the above-described vehicle control method based on the previous embodiment. Figure 2 As shown, the method includes: Step 201: Based on the target vehicle's lane change state machine, if the current lane change state is unlocked, when the target vehicle's steering intention signal is detected, determine the lane corresponding to the steering intention direction based on the steering intention signal, and if it is verified that the lane corresponding to the steering intention direction exists and is reachable, take the lane corresponding to the steering intention direction as the target lane.

[0096] Step 202: When no turning intention signal is detected, if a lane change is detected in the navigation route, multiple candidate lanes are obtained based on the navigation route, and the target vehicle is determined from the multiple candidate lanes. When no lane change is detected in the navigation route, the lane change trajectory of the target vehicle is determined based on a preset trajectory search algorithm, and the target lane is determined based on the lane change trajectory.

[0097] Step 203: Obtain the environmental perception data of the target vehicle, process the target lane, environmental perception data and preset driving trajectory generation constraints based on the preset driving trajectory search algorithm to obtain multiple candidate driving trajectories, and take the candidate driving trajectory with the minimum trajectory cost as the target driving trajectory.

[0098] Step 204: Obtain the target trajectory points of the target driving trajectory according to the preset search order, calculate the lateral displacement value between the current position point of the target vehicle and the target trajectory points, and determine that the target vehicle has driven to the target lane when there is a target trajectory point with a lateral displacement value less than the preset lateral displacement threshold.

[0099] Step 205: Control the lane-changing state machine to the locked state of driving to the target lane, detect the driving information of the target vehicle, and update the state of the lane-changing state machine based on the driving information.

[0100] Specifically, during the target vehicle's journey, if the current lane-changing state obtained from the lane-changing state machine is an unlocked lane-changing state, the target lane is determined based on the priority of the target lane's source. The lever instruction takes priority; when a valid lever signal is detected, the lane in the lever direction is prioritized as the target lane. The validity criteria include a continuously stable lever state, the existence and reachability of the target lane, and the lane not yet in a completed lane-changing state. The navigation route is considered second-best; if no lever is available, the highest priority lane in the navigation path is used as the target lane. If neither of the above conditions applies, the trajectory search algorithm autonomously optimizes and selects the target lane.

[0101] Specifically, based on a preset driving trajectory search algorithm, the target lane, environmental perception data, and preset driving trajectory generation constraints are processed to obtain multiple candidate driving trajectories, and the candidate driving trajectory with the minimum trajectory cost is taken as the target driving trajectory.

[0102] It should be noted that in the process of generating candidate driving trajectories, the driving trajectory of the target vehicle in the previous frame is obtained; the driving trajectory of the previous frame is transformed based on a preset coordinate transformation matrix to obtain the driving trajectory to be compared; the distance deviation between the driving trajectory to be compared and the candidate driving trajectory is calculated; the trajectory cost of the candidate driving trajectory is adjusted based on the distance deviation. In other words, the trajectory search algorithm introduces the trajectory change cost between two frames. After the coordinate transformation is completed, the trajectory search algorithm will penalize the planned trajectory that differs greatly from the trajectory of the previous frame, so that the deviation between the planned trajectory and the planned trajectory of the previous frame is not too large.

[0103] Specifically, following a preset search order, such as a back-to-foreign search order, the system searches backward from the end of the trajectory to find the first point that does not meet the threshold condition. The next target trajectory point is the landing point of the vehicle. This search method can quickly locate the section of the target trajectory that meets the condition, avoiding unnecessary full trajectory scanning and further improving data processing efficiency.

[0104] Specifically, after determining the target lane, the target lane is set to a locked state and maintained until the lane change is completed or the cancellation condition is met. In the locked state, even if the environmental conditions change, the system will prioritize adjusting the trajectory rather than switching the target lane to ensure consistent behavior.

[0105] Specifically, once the target vehicle's driving trajectory changes to straight, the lane markings of the target vehicle have changed, meaning it has moved to another lane. If the lateral displacement of the trajectory points relative to the lane centerline is less than a threshold, the lane change is considered complete, and the lane change state machine is updated to the lane change end state.

[0106] Specifically, a closed-loop control design is adopted to achieve organic coordination of environmental perception, decision-making and planning, and execution output. More specifically, firstly, multi-source data such as road structure, obstacle information, and driver input (e.g., lever input) are acquired in real time through environmental perception; then, the target lane is determined by multi-source target lane arbitration, that is, the target lane is dynamically determined by comprehensively considering lever input commands, navigation routes, and efficiency requirements; the trajectory search algorithm generates a target driving trajectory that meets the requirements of vehicle dynamics and comfort based on the target lane of the arbitration result, environmental perception data, and driving trajectory generation constraints; the lane-changing state machine continuously monitors the matching degree between the planning result and the actual driving state, and dynamically adjusts the lane-changing state to ensure the consistency of the entire link from environmental perception to trajectory output. The closed-loop data flow effectively solves the problem of the disconnect between decision-making and execution in traditional open-loop systems, and shows stronger robustness, especially in complex lane-changing scenarios.

[0107] Therefore, the lane-changing state machine and the trajectory search algorithm work together. The lane-changing state machine constrains the target lane before the search and verifies the feasibility of the trajectory during the search, fundamentally avoiding back-and-forth lane changes and continuous multi-lane lane changes, thus improving trajectory stability. Refined lane-changing state management deeply couples the lane-changing state with the cause and failure scenario, and the output can accurately guide downstream control. Scenario-based dynamic weight adjustment designs differentiated trajectory search algorithm weight strategies for levers, automatic efficiency, and navigation lane changes, improving adaptability to multiple scenarios.

[0108] The vehicle control scheme provided in this disclosure, based on the target vehicle's lane-changing state machine, determines the lane corresponding to the direction of the turning intention when a turning intention signal of the target vehicle is detected, and if the lane corresponding to the direction of the turning intention exists and is reachable, it is designated as the target lane. When no turning intention signal is detected, and a lane change is detected in the navigation route, multiple candidate lanes are obtained based on the navigation route, and the target vehicle is determined from these candidate lanes. When no lane change is detected in the navigation route, the target vehicle's lane-changing trajectory is determined based on a preset trajectory search algorithm, and the target vehicle is determined based on the lane-changing trajectory. The system acquires environmental perception data of the target vehicle and processes the target lane, environmental perception data, and preset driving trajectory generation constraints based on a preset driving trajectory search algorithm to obtain multiple candidate driving trajectories. The candidate driving trajectory with the lowest trajectory cost is selected as the target driving trajectory. The target trajectory points are obtained according to a preset search order. The lateral displacement value between the target vehicle's current position and the target trajectory point is calculated. If a target trajectory point exists with a lateral displacement value less than a preset lateral displacement threshold, the target vehicle is determined to have entered the target lane, and the lane-changing state machine is locked to the target lane. The driving information of the target vehicle is detected, and the state of the lane-changing state machine is updated based on the driving information. Therefore, by ensuring the current lane-changing state machine is in an unlocked state and the target lane is determined before searching for a driving trajectory, the feasibility of the target driving trajectory is guaranteed, thus avoiding back-and-forth lane changes and continuous multi-lane lane changes, improving the stability of the vehicle's driving trajectory.

[0109] Figure 3 This is a schematic diagram of a vehicle control device provided in an embodiment of the present disclosure. The device can be implemented by software and / or hardware and is generally integrated into a vehicle. Figure 3 As shown, the device, applied to a vehicle, includes: The first determining module 310 is used to determine the target lane corresponding to the target vehicle when the current lane changing state is obtained from the lane changing state machine of the target vehicle and the current lane changing state is an unlocked lane changing state. The acquisition module 320 is used to acquire environmental perception data of the target vehicle; The second determining module 330 is used to generate constraint conditions based on the target lane, the environmental perception data and the preset driving trajectory to determine the target driving trajectory; The control module 340 is used to control the target vehicle to drive to the target lane based on the target driving trajectory.

[0110] Therefore, when the current lane-changing state of the lane-changing state machine is an unlocked lane-changing state and the target lane is determined before searching the driving trajectory, the feasibility of the target driving trajectory is guaranteed, thereby avoiding back-and-forth lane changes and continuous multi-lane lane changes, and improving the stability of the vehicle driving trajectory.

[0111] Optionally, determining the target lane corresponding to the target vehicle includes: when a turning intention signal of the target vehicle is detected, determining the lane corresponding to the turning intention direction based on the turning intention signal, and verifying that the lane corresponding to the turning intention direction exists and is reachable, and then using the lane corresponding to the turning intention direction as the target lane; when the turning intention signal is not detected, and a lane change is detected in the navigation route, obtaining multiple candidate lanes based on the navigation route, and determining the target vehicle from the multiple candidate lanes; when a lane change is detected in the navigation route, determining the lane change trajectory of the target vehicle based on a preset trajectory search algorithm, and determining the target lane based on the lane change trajectory.

[0112] This solves the arbitration problem in the event of multi-source target lane conflicts, dynamically adapts to various lane-changing needs, and ensures the certainty and stability of the target lane during the lane-changing process through multi-level judgment logic, avoiding frequent or uncertain target lane switching.

[0113] Optionally, determining the target lane from the plurality of candidate lanes includes: obtaining the lane type, number of lanes, and traffic rules of each candidate lane to determine the priority of the plurality of candidate lanes; and determining the candidate lane with the highest priority as the target lane.

[0114] Therefore, when the lane pointed to by the navigation route is different from the current lane, the priority of the navigation suggested lane is evaluated based on factors such as road type and number of lanes, and the lane with the highest priority is selected as the target lane, thereby further improving the stability of the target lane.

[0115] Optionally, determining the target driving trajectory based on the target lane, the environmental perception data, and the preset driving trajectory generation constraints includes: processing the target lane, the environmental perception data, and the preset driving trajectory generation constraints based on a preset driving trajectory search algorithm to obtain multiple candidate driving trajectories; wherein each candidate driving trajectory has a corresponding trajectory cost; and selecting the candidate driving trajectory with the minimum trajectory cost as the target driving trajectory.

[0116] Therefore, by calculating and determining the target driving trajectory with the minimum trajectory cost through the target lane, environmental perception data and preset driving trajectory generation constraints, the weights can be dynamically adjusted according to different target lanes to adjust the candidate driving trajectories to have corresponding trajectory costs, thereby ensuring the feasibility of the target driving trajectory, thus avoiding situations such as back-and-forth lane changes and continuous multi-lane lane changes, and improving the stability of vehicle driving trajectory.

[0117] Optionally, in the process of generating the candidate driving trajectory, the method further includes: obtaining the previous frame driving trajectory of the target vehicle; transforming the previous frame driving trajectory based on a preset coordinate transformation matrix to obtain the driving trajectory to be compared; calculating the distance deviation between the driving trajectory to be compared and the candidate driving trajectory; and adjusting the trajectory cost of the candidate driving trajectory based on the distance deviation.

[0118] Therefore, during the generation of candidate driving trajectories, the trajectory cost of the candidate driving trajectory is adjusted by comparing the deviation with the driving trajectory of the previous frame, which further ensures the feasibility of the target driving trajectory, thereby avoiding situations such as back-and-forth lane changes and continuous multi-lane lane changes, and improving the stability of the vehicle driving trajectory.

[0119] Optionally, controlling the target vehicle to travel to the target lane based on the target driving trajectory includes: obtaining the target trajectory points of the target driving trajectory according to a preset search order; calculating the lateral displacement value between the current position point of the target vehicle and the target trajectory points; and determining that the target vehicle travels to the target lane when there is a target trajectory point whose lateral displacement value is less than a preset lateral displacement threshold.

[0120] Therefore, by calculating the lateral displacement between the vehicle's current position and the target trajectory point in real time during the vehicle's movement, it can be determined whether the target vehicle has entered the target lane, thereby improving the accuracy of vehicle control and thus enhancing vehicle driving stability.

[0121] Optionally, after determining the target lane, the method further includes: controlling the lane-changing state machine to a locked state for traveling to the target lane.

[0122] Therefore, by setting the target lane to a locked state through the lane-changing state machine, and maintaining this locked state until the lane change is completed or a cancellation condition is met, the target lane is usually adjusted first rather than switched when environmental conditions change, thus ensuring behavioral consistency and avoiding frequent switching of the target lane.

[0123] Optionally, the method further includes: detecting the driving information of the target vehicle; and updating the state of the lane-changing state machine based on the driving information.

[0124] Therefore, the state of the lane-changing state machine is updated in real time according to the vehicle's driving status. By managing the lane-changing state machine, chaotic state transitions during lane changing can be avoided, and situations such as lane changing cancellation, interruption, or completion can be accurately identified, thereby further improving the stability of vehicle driving.

[0125] The vehicle control device provided in this disclosure can execute the vehicle control method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of executing the method.

[0126] This disclosure also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the vehicle control method provided in any embodiment of this disclosure.

[0127] Figure 4 is a structural schematic diagram of a vehicle provided in an embodiment of this disclosure.

[0128] For example, such as Figure 4 As shown, the vehicle includes a memory 401 and a processor 402. The memory 401 stores executable program code 4011, and the processor 402 is used to call and execute the executable program code 4011 to perform a vehicle control method.

[0129] This embodiment can divide the vehicle into functional modules according to the above method example. For example, each function can be assigned to a separate module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0130] When each functional module is divided according to its corresponding function, the vehicle may include: a receiving and acquisition module, a calculation module, and a warning module, etc. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0131] The vehicle provided in this embodiment is used to execute the vehicle control method described above, and therefore can achieve the same effect as the above implementation method.

[0132] When using integrated units, the vehicle may include a processing module and a storage module. The processing module is used to control and manage the vehicle's actions. The storage module supports the vehicle in executing program code and data.

[0133] The processing module may be a processor or a controller that can implement or execute various exemplary logic blocks, modules, and circuits as described herein. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0134] This embodiment also provides a computer-readable storage medium (including but not limited to disk storage, CD-ROM, optical storage, etc.) storing computer program code. When the computer program code is run on a computer, the computer executes the above-mentioned related method steps to implement a vehicle control method provided in the above embodiment.

[0135] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement a vehicle control method provided in the above embodiment.

[0136] The beneficial effects of the above embodiments can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0137] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0138] In the embodiments provided in this disclosure, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms. In the description of this disclosure, it should be understood that if the terms "upper", "lower", "front", "rear", "left" and "right" are used to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the position or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this disclosure.

[0139] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element. The above are merely embodiments of this disclosure and are not intended to limit the scope of this disclosure. Various modifications and variations can be made to this disclosure by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of the claims of this disclosure.

Claims

1. A vehicle control method, characterized in that, The method includes: If the current lane change state is determined to be an unlocked lane change state based on the lane change state machine of the target vehicle, the target lane corresponding to the target vehicle is determined, and the environmental perception data of the target vehicle is obtained. Based on the target lane, the environmental perception data, and the preset driving trajectory, constraints are generated to determine the target driving trajectory. Based on the target driving trajectory, the target vehicle is controlled to drive to the target lane.

2. The method according to claim 1, characterized in that, Determining the target lane corresponding to the target vehicle includes: When the steering intention signal of the target vehicle is detected, the lane corresponding to the steering intention direction is determined based on the steering intention signal, and if it is verified that the lane corresponding to the steering intention direction exists and is reachable, the lane corresponding to the steering intention direction is taken as the target lane. When no steering intention signal is detected, but a lane change is detected in the navigation route, multiple candidate lanes are obtained based on the navigation route, and the target vehicle is determined from the multiple candidate lanes; When the navigation route does not have a lane change, the lane change trajectory of the target vehicle is determined based on a preset trajectory search algorithm, and the target lane is determined based on the lane change trajectory.

3. The method according to claim 2, characterized in that, Determining the target lane from the plurality of candidate lanes includes: The priority of the multiple candidate lanes is determined by obtaining the lane type, number of lanes, and traffic rules for each candidate lane; The highest priority candidate lane is determined as the target lane.

4. The method according to claim 1, characterized in that, The step of generating constraints based on the target lane, the environmental perception data, and the preset driving trajectory to determine the target driving trajectory includes: The target lane, the environmental perception data, and the preset driving trajectory generation constraints are processed based on a preset driving trajectory search algorithm to obtain multiple candidate driving trajectories; wherein each candidate driving trajectory has a corresponding trajectory cost. The candidate driving trajectory corresponding to the minimum trajectory cost is taken as the target driving trajectory.

5. The method according to claim 4, characterized in that, In the process of generating the candidate driving trajectory, the method further includes: Obtain the previous frame's driving trajectory of the target vehicle; The driving trajectory of the previous frame is transformed based on a preset coordinate transformation matrix to obtain the driving trajectory to be compared. Calculate the distance deviation between the driving trajectory to be compared and the candidate driving trajectory; The trajectory cost of adjusting the candidate driving trajectory based on the distance deviation.

6. The method according to claim 1, characterized in that, The step of controlling the target vehicle to travel to the target lane based on the target driving trajectory includes: The target trajectory points of the target driving trajectory are obtained according to a preset search order; Calculate the lateral displacement between the current position of the target vehicle and the target trajectory point; When there is a target trajectory point where the lateral displacement value is less than a preset lateral displacement threshold, the target vehicle is determined to have traveled to the target lane.

7. The method according to claim 1, characterized in that, After determining the target lane, the method further includes: The lane-changing state machine is controlled to be in a locked state to travel to the target lane.

8. The method according to claim 7, characterized in that, The method further includes: Detect the driving information of the target vehicle; The state of the lane-changing state machine is updated based on the driving information.

9. A vehicle, characterized in that, The vehicles include: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for performing the method described in any one of claims 1-8.

Images