Vehicle lane change control method and electronic device

Abstract

The application provides a vehicle lane changing control method and electronic equipment. The method comprises the following steps: in the case that it is determined that the vehicle has a target lane changing intention, controlling the vehicle to travel along the target lane line corresponding to the target lane, and determining whether the corresponding lane changing condition is met; if the corresponding lane changing condition is met, controlling the vehicle to complete lane changing; if the corresponding lane changing condition is not met, controlling the vehicle to travel along the target vehicle corresponding to the target lane, and re-determining whether the corresponding lane changing condition is met; if the corresponding lane changing condition is met, controlling the vehicle to complete lane changing; if the corresponding lane changing condition is not met, determining whether the target lane changing node corresponding to the vehicle is reached, if the target lane changing node is not reached, continuing to control the vehicle to travel along the target vehicle, continuing to determine whether the corresponding lane changing condition is met, if the target lane changing node is reached, controlling the vehicle to travel along the target vehicle, and again determining whether the corresponding lane changing condition is met, until the corresponding lane changing condition is met, and then controlling the vehicle to complete lane changing. In this way, the vehicle lane changing process is safer, more reliable and more effective.

Description

Technical Field

[0001] This application relates to the field of decision-making and control technology for assisted driving vehicles, and in particular to a vehicle lane change control method and electronic equipment. Background Technology

[0002] In scenarios such as heavily congested urban traffic, vehicles in assisted driving modes often need to "create" lane-changing space by interacting with vehicles in the target lane (i.e., adjacent lanes) when other vehicles in the target lane have no sufficient legal obligation to yield. Traditional assisted driving lane-changing control systems typically rely on a fixed-rule gap-acceptance model, making their decision-making logic binary ("variable" or "immutable"). This leads to a dilemma in dynamic game scenarios: if too conservative, the necessary lane change may never be completed; if too aggressive, it can easily cause sudden braking or even collisions, resulting in safety risks and driving discomfort. Therefore, achieving safer, more reliable, and more efficient lane-changing is crucial for improving the safety and user experience of assisted driving. Summary of the Invention

[0003] This application provides a vehicle lane change control method and electronic device for achieving safer, more reliable, and more efficient vehicle lane change processing.

[0004] Firstly, this application provides a vehicle lane change control method, which includes: when it is determined that a vehicle intends to change lanes to a target lane, controlling the vehicle to move close to the target lane line corresponding to the target lane, so that the vehicle is in a lane-keeping driving state, and determining whether the corresponding lane change conditions are met, wherein the target lane is the adjacent lane to the lane where the vehicle is located, and the target lane line is the adjacent lane line between the lane where the vehicle is located and the target lane; if it is determined that the corresponding lane change conditions are met, controlling the vehicle to perform a lane change to complete the lane change from the current lane to the target lane; if the corresponding lane change conditions are not met, controlling the vehicle to move close to the target vehicle corresponding to the target vehicle in the target lane, so that the vehicle is in a lane-keeping driving state, and then restarting the lane change process. Determine if the corresponding lane change conditions are met. The target vehicle is the vehicle in the target lane that is attempting to change lanes and overtake. If the corresponding lane change conditions are met, control the vehicle to perform a lane change to complete the lane change from the current lane to the target lane. If the corresponding lane change conditions are not met, determine if the vehicle has reached the target lane change node. If the target lane change node has not been reached, keep the vehicle in a close following state and continue to determine if the corresponding lane change conditions are met. If the target lane change node has been reached, control the vehicle to forcefully cut into the target vehicle to keep the vehicle in a forced-cutting state and determine if the corresponding lane change conditions are met again. This process continues until the corresponding lane change conditions are met, at which point the vehicle is controlled to perform a lane change to complete the lane change from the current lane to the target lane.

[0005] By employing the aforementioned technical solution, during lane-changing, the vehicle is first controlled to move close to the target lane line to determine if the corresponding lane change conditions are met. If the conditions are met, the vehicle completes the lane change. If not, the vehicle continues to move close to the target vehicle in front and re-determines whether the conditions are met. If the conditions are still not met, the vehicle performs a forced lane change and re-determines whether the conditions are met to complete the lane change. In this way, through a multi-stage, progressive collaborative game strategy, a more accurate identification of the target vehicle's intention to yield to the changing vehicle is achieved, resulting in a safer, smoother, and more efficient forced lane change. Furthermore, by gradually adjusting the distance between the vehicle and the target vehicle through line-hugging, close-to-the-car, and forced lane-changing maneuvers, the driving risks caused by blind lane changes are effectively avoided. This also allows the target vehicle driver to quickly understand the vehicle's lane-changing intention, significantly shortening the "guessing" time in the game, thereby improving the efficiency and safety of lane changes. Furthermore, through dynamic game theory, the defensive posture of the target vehicle can be effectively softened, creating lane-changing opportunities that cannot be provided by real-world legal models, significantly improving the success rate in scenarios where lane changes are necessary. This enables safer, more reliable, and more effective lane-changing handling, allowing vehicles to complete lane changes and thus enhancing the safety and user experience of assisted driving.

[0006] Optionally, in one implementation of this application, determining whether the corresponding lane conditions are met includes: determining the type of yielding intention of the target vehicle in the target lane, wherein the yielding intention type includes explicit intention and implicit intention, and explicit intention includes explicit yielding intention and explicit refusal to yield intention; and determining whether the corresponding lane conditions are met based on the yielding intention type, wherein if the yielding intention type is explicit yielding intention, the corresponding lane conditions are met; and if the yielding intention type is implicit intention or explicit refusal to yield intention, the corresponding lane conditions are not met.

[0007] Using the above technical solution, the yielding intention type of target vehicles in the target lane is calculated, and the yielding intention type is divided into explicit yielding, explicit refusal to yield, and implicit yielding. Figure 3 Furthermore, based on different types of yielding intentions, the system differentiates whether lane change conditions are met. Lane change conditions are only confirmed when the target vehicle has a clear yielding intention. This effectively improves the accuracy and logical rigor of lane change condition determination, avoids lane change operations triggered by ambiguous yielding intentions or clear refusal to yield by the target vehicle, significantly reduces safety hazards during lane change processes of autonomous vehicles, and optimizes the reliability of vehicle lane change decisions and driving safety.

[0008] Optionally, in one implementation of this application, controlling a vehicle to travel along the target lane line corresponding to the target lane includes: determining first driving strategy information for the vehicle to travel along the target lane line corresponding to the target lane; the first driving strategy information includes first lateral motion trajectory planning strategy information and first longitudinal motion control strategy information; the first lateral motion trajectory planning strategy information includes a first lateral distance, which is a safe distance relative to the target lane when the vehicle is traveling along the lane line; the first longitudinal motion control strategy information includes a first longitudinal acceleration, which is an acceleration that causes the vehicle to decelerate; and controlling the vehicle to travel along the target lane line corresponding to the target lane according to the first driving strategy information.

[0009] By adopting the above technical solution, the vehicle is controlled to move towards the target lane by using the first lateral movement trajectory planning strategy information, including the first lateral distance, and the first longitudinal movement control strategy information, including the first longitudinal acceleration. The first lateral distance is the safe distance for the vehicle to move towards the target lane, and the first longitudinal acceleration is the acceleration that decelerates the vehicle. This ensures both the accuracy of the vehicle's lane-keeping and the lateral safety distance, while also improving the driving stability during the lane-keeping process through longitudinal deceleration. This enhances the safety and stability of the vehicle when moving towards the target lane, and allows for safer, more reliable, and more effective control of the vehicle to complete lane changes.

[0010] Optionally, in one implementation of this application, controlling a vehicle to travel close to the target vehicle in front of the target vehicle in the target lane includes: determining second driving strategy information for the vehicle to travel close to the target vehicle in front of the target vehicle; the second driving strategy information includes second lateral motion trajectory planning strategy information and second longitudinal motion control strategy information; the second lateral motion trajectory planning strategy information includes a second lateral distance, which is a safe distance between the vehicle and the target vehicle, and the second lateral distance is less than a first lateral distance; the second longitudinal motion control strategy information includes a second longitudinal acceleration, which is an acceleration that makes the vehicle's speed lower than the reference speed of the traffic flow corresponding to the target lane; and controlling the vehicle to travel close to the target vehicle in front of the target vehicle according to the second driving strategy information.

[0011] By adopting the above technical solution, the vehicle is controlled to move close to the target vehicle corresponding to the target vehicle by using the second lateral movement trajectory planning strategy information, including the second lateral distance, and the second longitudinal movement control strategy information, including the second longitudinal acceleration. The second lateral distance is the safe distance between the vehicle and the target vehicle corresponding to the target vehicle, and the second longitudinal acceleration is the acceleration that makes the vehicle's speed lower than the reference speed of the traffic flow corresponding to the target lane. This ensures the accuracy of the vehicle's close-to-the-target vehicle movement and the lateral safety distance, thereby improving the safety and stability of the vehicle when moving close to the target vehicle corresponding to the target vehicle. As a result, the vehicle can be controlled to complete lane changes more safely, reliably, and effectively.

[0012] Optionally, in one implementation of this application, the method further includes: when the reference speed of the traffic flow is less than a speed threshold, re-controlling the vehicle to travel along the target lane line.

[0013] By adopting the above technical solution, when the traffic flow speed is less than the speed threshold, the vehicle is controlled to return to the lane-hugging driving state, preventing safety accidents caused by congestion in the target lane during the lane change process, ensuring the safety of the lane change process, thereby improving the safety and stability of the vehicle when driving close to the target lane line, and thus enabling safer, more reliable and more effective control of the vehicle to complete the lane change.

[0014] Optionally, in one implementation of this application, the target lane-changing node can be understood as a node that needs to be forced to change lanes, or it can be called a forced lane-changing node.

[0015] Optionally, in one implementation of this application, controlling the vehicle to forcibly approach the target vehicle includes: reducing the vehicle's speed and reducing the safe distance between the vehicle and the target vehicle, so that the vehicle continues to approach the target vehicle.

[0016] By adopting the above technical solution, by actively reducing the vehicle's own speed and shortening the safe distance between the vehicle and the target vehicle, the vehicle continuously moves closer to the target vehicle. This allows the driver of the target vehicle to quickly understand the vehicle's lane-changing intention, shortens the "game" time between the vehicle and the target vehicle during the lane-changing process, and thus enables safer, more reliable, and more effective control of the vehicle to complete the lane change.

[0017] Optionally, in one implementation of this application, when the yielding intention type is an explicit refusal to yield, a new target vehicle is re-determined, and the yielding intention type of the new target vehicle is determined for the vehicle, so as to perform corresponding vehicle lane change control processing.

[0018] By adopting the above technical solution, when the system determines that the target vehicle clearly intends to refuse to yield, it can automatically select a new target vehicle and identify the type of yielding intention of the new target vehicle to the vehicle. Then, it can execute the corresponding lane change control according to the type of yielding intention of the new target vehicle, so as to ensure the rationality and safety of the lane change decision.

[0019] Optionally, in one implementation of this application, determining the yielding intention type of a target vehicle in a target lane includes: determining the yielding feedback information of the target vehicle, the yielding feedback information including the driving status information of the target vehicle and the spatial situational change information of the target vehicle and the target preceding vehicle corresponding to the target vehicle; and determining the yielding intention type of the target vehicle based on the yielding feedback information.

[0020] By adopting the above technical solution, the target vehicle's driving status information and spatial situation change information can be used to obtain a more accurate type of yielding intention from the target vehicle. Based on the more accurate yielding intention type, it can be more accurate to determine whether the lane change conditions are met, thereby selecting a more accurate lane change strategy and controlling the vehicle to complete the lane change more effectively, safely and reliably.

[0021] Optionally, in one implementation of this application, determining the type of yielding intention of the target vehicle towards the vehicle based on the yielding feedback information includes: determining the probability of the target vehicle's yielding intention towards the vehicle based on the yielding feedback information; determining the yielding intention type based on the yielding intention probability, wherein if the yielding intention probability is less than or equal to a first yielding threshold, the yielding intention type is determined to be an explicit refusal to yield; if the yielding intention probability is greater than the first yielding threshold and less than a second yielding threshold, the yielding intention type is determined to be an indefinite intention; and if the yielding intention probability is greater than or equal to the second yielding threshold, the yielding intention type is determined to be an explicit yielding intention.

[0022] By employing the above technical solution, the yielding intention of a target vehicle in the target lane is quantified. First, the corresponding yielding intention probability is calculated. Then, this yielding intention probability is compared with a preset first yielding threshold and a second yielding threshold to obtain the range of the yielding intention probability of the target vehicle in relation to the target vehicle. Based on the range of the yielding intention probability, a more accurate yielding intention type of the target vehicle can be obtained. Based on the more accurate yielding intention type, it can be more accurately determined whether the corresponding lane change conditions are met, thereby selecting a more accurate lane change strategy and controlling the vehicle to complete the lane change more safely, reliably, and effectively.

[0023] Optionally, in one implementation of this application, determining the probability of a target vehicle's yielding intention to another vehicle based on yielding feedback information includes: determining multiple yielding evaluation information corresponding to the target vehicle based on the yielding feedback information, wherein the multiple yielding evaluation information includes a spatial assessment score, a spatial change trend assessment score, a spatial change trend cause assessment score, and a collision assessment score between the target vehicle and the target vehicle behind it; and determining the yielding intention probability based on each yielding evaluation information and the weight corresponding to each yielding evaluation information.

[0024] By adopting the above technical solution, based on the obtained yield feedback information, multiple yield evaluation information corresponding to the target vehicle is extracted and determined. Specifically, these include spatial assessment score, spatial change trend assessment score, spatial change trend cause assessment score, and collision assessment score between the vehicle and the vehicle behind it. Then, the preset weights of each yield evaluation information are combined for weighted calculation, and the probability of the target vehicle's yield intention to the vehicle in the target lane is accurately determined. This achieves a multi-dimensional comprehensive assessment of the yield intention probability, effectively improving the comprehensiveness, rationality, and accuracy of the yield intention probability determination. As a result, a more accurate yield intention type of the target vehicle can be obtained. Based on the more accurate yield intention type, it can be more accurately determined whether the lane change conditions are met, thus allowing for the selection of a more accurate lane change strategy and enabling safer, more reliable, and more effective control of the vehicle to complete the lane change.

[0025] Optionally, in one implementation of this application, the method further includes: during the process of the vehicle performing a lane change, if it is determined that the current lane change environment meets the corresponding lane change conditions, then the vehicle is controlled to continue performing the lane change; if it is determined that the lane change environment does not meet the corresponding lane change conditions, then according to the current lane change environment, the vehicle is controlled to re-execute any one of the following driving processes: driving close to the lane, driving close to other vehicles, or forcibly cutting in, in order to re-determine whether the corresponding lane change conditions are met and thus perform a new lane change.

[0026] By adopting the above technical solution, during the process of a vehicle changing lanes, it is possible to determine in real time whether the current lane-changing environment meets the corresponding lane-changing conditions. If the corresponding lane-changing conditions are met, the lane-changing process is maintained and continues. If the corresponding lane-changing conditions are not met, the vehicle is controlled to re-execute any one of the following processing operations: lane-hugging, vehicle-hugging, or forced lane-cutting, based on the current real-time lane-changing environment. This allows for a re-determination of whether the vehicle meets the lane-changing conditions, achieving dynamic monitoring, condition verification, and strategy rollback adjustment during the lane-changing process, ensuring the continuity of lane-changing control and the reliability of decision-making.

[0027] Secondly, this application provides an electronic device, including a vehicle lane change control system for controlling lane changes of a vehicle, used to implement the aforementioned vehicle lane change control method.

[0028] Optionally, in one implementation of this application, the electronic device may be a vehicle, and the system is deployed in the vehicle's central decision controller to implement the aforementioned vehicle lane change control method.

[0029] In summary, the vehicle lane change control scheme provided in this application, during the lane change process, firstly, determines the first driving strategy information for the vehicle to travel close to the target lane line corresponding to the target lane. Based on the first driving strategy information, the vehicle is controlled to travel close to the target lane line corresponding to the target lane, so that the vehicle is in a close-to-the-lane driving state. Secondly, it determines the yielding feedback information from the target vehicle regarding the vehicle in the close-to-the-lane driving state. Based on the yielding feedback information, it determines the type of yielding intention of the target vehicle. If the yielding intention type is a clear yielding intention, it is determined that the corresponding lane change conditions are met, and the vehicle is controlled to execute lane change processing to complete the lane change; if the yielding intention type is an unclear yielding intention or a clear refusal to yield, it is determined that the corresponding lane change conditions are not met, and a second driving strategy information for the vehicle to travel close to the target preceding vehicle corresponding to the target vehicle is determined. Based on the second driving strategy information, the vehicle is controlled to travel close to the target preceding vehicle corresponding to the target vehicle, so that the vehicle is in a close-to-the-lane driving state, and then... If the vehicle is in a close-to-the-car state, the system checks whether the corresponding lane change conditions are met. If the conditions are met, the system controls the vehicle to perform a lane change. If the conditions are not met, the system checks whether the vehicle has reached the target lane change node. If the target lane change node has not been reached, the vehicle continues to be in a close-to-the-car state, and the system checks whether the corresponding lane change conditions are met. If the target lane change node has been reached, the system controls the vehicle to forcibly cut into the target vehicle, and checks again whether the corresponding lane change conditions are met in the forcible cutting state. This process continues until the corresponding lane change conditions are met, at which point the system controls the vehicle to perform a lane change.

[0030] Thus, by first controlling the vehicle to drive close to the target lane line, it is determined whether the corresponding lane change conditions are met. If the conditions are met, the vehicle completes the lane change. If the conditions are not met, the vehicle continues to drive close to the target vehicle in front, and the conditions are re-evaluated. If the conditions are still not met, a forced lane change is executed. Through a multi-stage, progressive collaborative game strategy, the system accurately identifies the target vehicle's intention to yield and achieves safe, smooth, and efficient forced lane changes. Furthermore, by gradually adjusting the distance between the vehicle and the target vehicle through lane-hugging, close-to-the-car, and forced lane-cutting, the system effectively avoids the driving risks caused by blind lane changes and allows the target vehicle driver to quickly understand the vehicle's lane change intention, significantly shortening the "guessing" time in the game and thus improving the efficiency and safety of lane changes. In addition, through dynamic game theory, the system effectively "softens" the target vehicle's defensive posture, creating lane change opportunities that cannot be provided by real-world legal models, significantly improving the success rate in mandatory lane change scenarios. This allows for safer, more reliable, and more effective control of the vehicle to complete lane changes, thereby improving the safety and user experience of assisted driving. Attached Figure Description

[0031] Figure 1 This is a flowchart illustrating a vehicle lane change control method provided in this application.

[0032] Figure 2 This is a schematic diagram illustrating the principle of lateral safety distance in the vehicle lane change control method provided in this application.

[0033] Figure 3 This is a schematic diagram illustrating the principle of a vehicle traveling close to the target lane line in the vehicle lane change control method provided in this application.

[0034] Figure 4 This is a schematic diagram illustrating the principle of a vehicle driving close to the target vehicle in the lane change control method provided in this application.

[0035] Figure 5 This is a schematic diagram illustrating the principle of a vehicle forcibly cutting into a target vehicle in the vehicle lane change control method provided in this application.

[0036] Figure 6 This is a schematic diagram illustrating the principle of the vehicle lane change control method provided in this application.

[0037] Figure 7 This is a structural schematic diagram of a vehicle provided in the implementation of this application. Detailed Implementation

[0038] As mentioned earlier, achieving safer, more reliable, and more efficient lane change handling is crucial for improving the safety and user experience of assisted driving.

[0039] Currently, while cutting-edge research has begun to incorporate intention prediction technology, two major bottlenecks remain: First, after the lane change intention prediction module predicts the lane change intention and transmits it to the decision-making module, the decision-making module makes a lane change decision based on the prediction result. However, after the decision is made, subsequent lane change behavior of the vehicle will affect the deceleration and yielding behavior of surrounding vehicles, thus changing the intention prediction result and generating prediction errors. In other words, in existing solutions, prediction and decision-making are separated, failing to form a closed-loop action strategy based on interactive feedback. This leads to biased decision results and ultimately reduces the accuracy of the overall lane change decision and driving control of the vehicle. Second, the high-level game decision-making in existing lane change control technologies directly generates vehicle control commands based on the lane change decision result, only achieving mechanical lane change actions. That is, existing solutions lack a method to transform high-level game decision-making into a low-level, refined, smooth vehicle control sequence with clear interactive semantics. This results in rigid vehicle lane change behavior, making it difficult for surrounding human drivers to recognize the lane change intention, failing to form effective driving coordination, and ultimately failing to guarantee the safety and effectiveness of lane change operations, making it impossible to smoothly complete lane change actions.

[0040] Based on this, this application provides a vehicle lane change control method, which includes: when it is determined that the vehicle has a target lane change intention, controlling the vehicle to drive close to the target lane line corresponding to the target lane, so that the vehicle is in a close-to-the-lane driving state, and determining whether the corresponding lane change conditions are met, wherein the target lane is the adjacent lane of the lane where the vehicle with the lane change intention is located, and the target lane line is the adjacent lane line between the lane where the vehicle is located and the target lane; if it is determined that the corresponding lane change conditions are met, controlling the vehicle to perform a lane change process to complete the lane change from the current lane to the target lane; if the corresponding lane change conditions are not met, controlling the vehicle to drive close to the target vehicle corresponding to the target vehicle in the target lane, so that the vehicle is in a close-to-the-lane driving state, and re-determining whether the lane change conditions are met. If the lane change conditions are not met, the target vehicle is the vehicle in the target lane that is attempting to change lanes and overtake. If the lane change conditions are met, the vehicle is controlled to perform a lane change to complete the lane change from its current lane to the target lane. If the lane change conditions are not met, it is determined whether the target lane change node corresponding to the vehicle has been reached. If the target lane change node has not been reached, the vehicle continues to be in a close-to-the-vehicle driving state, and the lane change conditions are determined again. If the target lane change node has been reached, the vehicle is controlled to forcibly cut into the target vehicle to put the vehicle in a forced-cutting driving state, and the lane change conditions are determined again until the lane change conditions are met. Then, the vehicle is controlled to perform a lane change to complete the lane change from its current lane to the target lane.

[0041] Thus, during lane-changing, the system first controls the vehicle to move close to the target lane line to determine if the lane change conditions are met. If they are, the vehicle completes the lane change. If not, the vehicle continues to move close to the target vehicle in front and reassess whether the lane change conditions are met. If they are still not met, the vehicle performs a forced lane change. Based on a multi-stage, progressive collaborative game strategy, the system accurately identifies the target vehicle's yielding intention and achieves safe, smooth, and efficient forced lane changes. Furthermore, by gradually adjusting the distance between the vehicle and the target vehicle, the system effectively avoids the driving risks caused by blind lane changes and allows the target vehicle driver to quickly understand the lane-changing intention, significantly shortening the "guessing" time in the game and thus improving the efficiency and safety of lane changes. In addition, through dynamic game theory, the system effectively "softens" the target vehicle's defensive posture, creating lane-changing opportunities that cannot be provided by real-world legal models, significantly improving the success rate in mandatory lane-changing scenarios. This allows for safer, more reliable, and more effective control of the vehicle to complete lane changes, thereby improving the safety and user experience of assisted driving.

[0042] The technical solution provided by the implementation method of this application will be described in further detail below with reference to the accompanying drawings.

[0043] One implementation of this application provides a vehicle lane change control method, such as... Figure 1 As shown, the method includes the following steps.

[0044] S100: Determine whether the vehicle has a target lane change intention. If it is determined that the vehicle has a target lane change intention, proceed to step S200; if it is determined that the vehicle has not a target lane change intention, continue to proceed to step S100 to determine whether a target lane change intention has been generated again in real time or periodically.

[0045] Optionally, in one implementation of this application, the target lane-changing intention can be understood as a strong lane-changing intention generated by a pre-specified vehicle. For example, determining a strong lane-changing intention can be achieved by: the driver actively sending a lane-changing command, i.e., the driver directly issuing a lane-changing operation command, such as activating the turn signal, which confirms a strong lane-changing intention. Alternatively, it can be achieved through navigation route planning in assisted driving mode, where the vehicle, based on route planning information such as approaching an exit / entrance, needing to turn left / right, or needing to switch to the target lane, pre-determines a lane-changing need and thus confirms a strong lane-changing intention.

[0046] Of course, the methods for determining that a vehicle has a strong intention to change lanes are not limited to the examples mentioned above; other methods can also be used to determine that a vehicle has a strong intention to change lanes.

[0047] S200: Controls the vehicle to travel along the target lane line corresponding to the target lane, so that the vehicle is in a lane-keeping driving state.

[0048] Controlling a vehicle to travel close to the target lane line can be achieved by controlling the vehicle to travel close to the target lane line and positioning the vehicle in front of the target vehicle in the target lane.

[0049] For example, controlling a vehicle to travel along the target lane line corresponding to the target lane may include: determining first driving strategy information for the vehicle to travel along the target lane line corresponding to the target lane, the first driving strategy information including first lateral motion trajectory planning strategy information and first longitudinal motion control strategy information, the first lateral motion trajectory planning strategy information including first lateral distance, which is a safe distance relative to the target lane when the vehicle is traveling along the line, and the first longitudinal motion control strategy information including first longitudinal acceleration, which is the acceleration that causes the vehicle to decelerate; and controlling the vehicle to travel along the target lane line corresponding to the target lane according to the first driving strategy information.

[0050] Optionally, in one implementation of this application, the target lane is the adjacent lane to the lane where the vehicle is located, corresponding to the lane change intention. The target lane can be determined, for example, based on the driver's intention to change lanes, such as sending a lane change command or navigation route instructions, to determine the lane to which the vehicle needs to change lanes. Furthermore, the target lane line is the adjacent lane line between the vehicle's current lane and the target lane.

[0051] The target vehicle is the vehicle in the target lane that is attempting to overtake another vehicle in accordance with the lane change intention. It is typically a vehicle adjacent to the vehicle in the target lane, especially a vehicle located behind the vehicle in the target lane. For example, the target vehicle could be the first vehicle behind the vehicle in front, or the vehicle in the target lane that is closest to the vehicle in front.

[0052] Furthermore, the methods for determining the target lane and target vehicle are not limited to the examples mentioned above; they can be set as needed.

[0053] Optionally, in one implementation of this application, the first lateral distance can be either the lateral safety distance between the vehicle and the target lane line, or the lateral safety distance between the vehicle and the lane centerline of the target lane. For example, as shown... Figure 2 As shown, Figure 2Examples of the first lateral distance are shown for both straight and curved target lane lines. When the target lane line is straight, the first lateral distance is relatively intuitive; it is the straight-line distance between the left side of the vehicle and the target lane line, ensuring sufficient lateral clearance between the vehicle and other vehicles in the target lane to avoid collisions. When the target lane line is curved, the trajectory of driving close to the line becomes more complex due to the changing curvature. The vehicle needs to dynamically adjust the lateral distance according to the lane line curvature while also maintaining longitudinal safety distances from vehicles in front and behind, ensuring smooth driving while improving the safety and controllability of lane changes.

[0054] Optionally, in one implementation of this application, controlling the vehicle to travel close to the target lane line can include: initiating lateral trajectory planning for the vehicle towards the target lane, i.e., controlling the vehicle to smoothly approach the target lane line at a low lateral speed according to a first lateral motion trajectory planning strategy. Simultaneously, longitudinal coordinated control is initiated, employing a slight negative acceleration (e.g., -0.3 to -0.6 m / s²) for coordinated deceleration, i.e., controlling the vehicle to decelerate collaboratively according to the first longitudinal motion control strategy, thereby providing a safety margin for potential lane cut-ins and conveying a "polite request" rather than a "forced cut-in" interactive signal to following vehicles. Finally, the vehicle's lateral position is stabilized at a certain distance offset from the original lane centerline, and it travels parallel to the target lane line, forming a "lane-hugging" state.

[0055] For example, such as Figure 3 As shown, Figure 3 This is a schematic diagram illustrating the principle of controlling a vehicle to move along the target lane line. Assume vehicle A wants to change lanes from lane M to target lane N. During the process of controlling vehicle A to move along the target lane line corresponding to target lane N, a first driving strategy is determined. This first driving strategy includes a first lateral movement trajectory planning strategy and a first longitudinal movement control strategy. Then, the vehicle is controlled to move along the target lane line according to this first driving strategy. Vehicle B is the target vehicle that vehicle A wants to enter in lane N.

[0056] Furthermore, the first lateral motion trajectory planning strategy information may also include other information such as the first lateral travel trajectory and the first lateral travel speed, and the first longitudinal motion control strategy information may also include other information such as the first longitudinal travel trajectory. Of course, the first driving strategy information may also include other information. Additionally, the first lateral distance can be determined based on reference information such as lane width or set as needed, and the first longitudinal acceleration can be determined based on reference information such as the vehicle's own speed, the target vehicle's speed, and the traffic flow speed or set as needed.

[0057] S300: Determine whether the strain gauge condition is met. If the strain gauge condition is not met, proceed to step S400; if the strain gauge condition is met, proceed to step S900.

[0058] For example, determining whether the corresponding lane conditions are met includes: determining the type of yielding intention of the target vehicle in the target lane, the yielding intention type including explicit intention and implicit intention, explicit intention including explicit yielding intention and explicit refusal to yield intention; determining whether the corresponding lane conditions are met based on the yielding intention type, wherein if the yielding intention type is explicit yielding intention, the corresponding lane conditions are met; if the yielding intention type is implicit intention or explicit refusal to yield intention, the corresponding lane conditions are not met.

[0059] For example, determining the type of yielding intention of a target vehicle may include: First, determining the yielding feedback information of the target vehicle, which includes the target vehicle's driving status information and spatial situational change information between the target vehicle and the target preceding vehicle. Second, based on the yielding feedback information, determining multiple yielding evaluation information corresponding to the target vehicle, including a spatial assessment score, a spatial change trend assessment score, a spatial change trend cause assessment score, and a collision assessment score between the target vehicle and the target following vehicle. Next, determining the yielding intention probability based on each yielding evaluation information and its corresponding weight. Finally, determining the yielding intention type based on the yielding intention probability.

[0060] Optionally, in one implementation of this application, the driving state information may include the speed and acceleration of the target vehicle, and the spatial situation change information of the target vehicle corresponding to the target vehicle may include the distance information of the target vehicle corresponding to the vehicle in front, the acceleration of the target vehicle corresponding to the vehicle in front, and the acceleration of the target vehicle corresponding to the vehicle behind.

[0061] Optionally, in one implementation of this application, the spatial evaluation score can reflect the distance information between the target vehicle and the target vehicle in front of it. For example, the formula for calculating the spatial evaluation score is: d_score = d_rel * (1 / 10), where d_rel is the distance between the target vehicle and the target vehicle in front of it, with the distance unit being, for example, meters (m). Furthermore, the spatial evaluation score is a calibrated value, and its numerical range is from 0 to 1 (inclusive).

[0062] Optionally, in one implementation of this application, the spatial change trend assessment score can reflect the speed information of the target vehicle and the vehicle in front of it. For example, the formula for calculating the spatial change trend assessment score is: trend_score = 0.5 + v_rel * (1 / 6), where v_rel is the speed of the vehicle in front of it relative to the target vehicle, with the speed unit being, for example, m / s. Furthermore, the spatial change trend assessment score is a calibrated value, and its numerical range is from 0 to 1 (inclusive).

[0063] Optionally, in one implementation of this application, the spatial change trend cause assessment score can reflect the acceleration information of the target vehicle and the target vehicle in front of it. For example, the calculation formula for the spatial change trend cause assessment score is as follows: when the relative acceleration a_rel_front_rear of the target vehicle and the target vehicle is less than 0, the calculation formula for the spatial change trend cause assessment score is: w_score = 0; when the relative acceleration a_rel_front_rear of the target vehicle and the target vehicle is greater than or equal to 0, the calculation formula for the spatial change trend cause assessment score is: w_score = a_rel_front_rear * (1 / 3) * (1 - |a_rear| / (a_rear + a_front)), where a_rear is the absolute acceleration of the target vehicle, a_front is the absolute acceleration of the target vehicle in front of it, and the numerical range of the spatial change trend cause assessment score is 0 to 1 (inclusive).

[0064] Optionally, in one implementation of this application, the collision assessment score between a vehicle and its corresponding target following vehicle can reflect the speed and distance information between the two vehicles. For example, the collision assessment score is calculated using the formula: s_score = (time_gap / 5), where time_gap is the relative collision time between the vehicle and its corresponding following vehicle, and time_gap = d_rel_rear_self / max(v_rel_rear_self, 0.1), where d_rel_rear_self is the relative distance between the vehicle and its corresponding target following vehicle, and v_rel_rear_self is the relative speed between the vehicle and its corresponding target following vehicle. Furthermore, the numerical range of the collision assessment score between the two vehicles is 0 to 1 (inclusive).

[0065] Optionally, in one implementation of this application, the probability of yielding intention is determined based on each yielding evaluation information and its corresponding weight. For example, it can be: yielding intention probability score = W1*d_score + W2*trend_score + W3*w_score + W4*s_score, where W1, W2, W3, and W4 are the weights corresponding to the spatial assessment score, the spatial change trend assessment score, the spatial change trend cause assessment score, and the collision assessment score between the vehicle and its corresponding target following vehicle, respectively. These weights can be set according to actual needs. For example, W1 can be 0.3, W2 can be 0.2, W3 can be 0.2, and W4 can be 0.3.

[0066] Thus, the probability of the target vehicle's intention to yield to other vehicles was obtained through the above method.

[0067] Finally, the yielding intention type is determined based on the yielding intention probability. If the yielding intention probability is less than or equal to the first yielding threshold, the yielding intention type is determined to be an explicit refusal to yield. If the yielding intention probability is greater than the first yielding threshold and less than the second yielding threshold, the yielding intention type is determined to be an indefinite intention. If the yielding intention probability is greater than or equal to the second yielding threshold, the yielding intention type is determined to be an explicit yielding intention.

[0068] Optionally, in one implementation of this application, the first yielding threshold may be, for example, 0.3, and the second yielding threshold may be, for example, 0.7. That is, when the yielding intention probability is less than or equal to 0.3, the yielding intention type is determined to be an explicit refusal to yield; when the yielding intention probability is greater than 0.3 and less than 0.7, the yielding intention type is determined to be an indefinite intention; and when the yielding intention probability is greater than or equal to 0.7, the yielding intention type is determined to be an explicit yielding intention.

[0069] Of course, the first and second yielding thresholds are not limited to the examples above, and can be set as needed. Furthermore, the methods for calculating the probability of yielding intent and determining the type of yielding intent are also not limited to the examples above, and can be set as needed.

[0070] That is, the probability of the target vehicle's yielding intention to other vehicles is first determined by the above method, then the yielding intention type is determined by the yielding intention probability and the preset yielding threshold, and finally, the corresponding lane conditions are determined based on the yielding intention type.

[0071] S400: Controls the vehicle to drive close to the target vehicle in the target lane, so that the vehicle is in a close-to-the-car driving state.

[0072] For example, controlling a vehicle to travel close to the target vehicle in a target lane includes: determining second driving strategy information for the vehicle to travel close to the target vehicle in a target lane; the second driving strategy information includes second lateral motion trajectory planning strategy information and second longitudinal motion control strategy information; the second lateral motion trajectory planning strategy information includes a second lateral distance, which is a safe distance between the vehicle and the target vehicle in a target lane, and the second lateral distance is less than a first lateral distance; the second longitudinal motion control strategy information includes a second longitudinal acceleration, which is an acceleration that makes the vehicle's speed lower than the reference speed of the traffic flow in the target lane; and controlling the vehicle to travel close to the target vehicle in a target lane according to the second driving strategy information.

[0073] Optionally, in one implementation of this application, controlling the vehicle to follow the target vehicle ahead of the target vehicle may include: controlling the vehicle to follow the target vehicle ahead of the target vehicle according to the second lateral motion trajectory planning strategy information, while maintaining a safe lateral distance; simultaneously, the second longitudinal motion control strategy information is switched to "adaptive following," with the following speed slightly lower than the reference speed of traffic flow in the target lane, and employing a "forward only" tailgating strategy. Furthermore, during this process, the direct reactions of the target vehicle (such as deceleration magnitude) and the spatial situational changes of the target vehicle and the vehicle ahead of it are continuously integrated to dynamically update the yielding intention probability. And, if the yielding intention probability is greater than the second yielding threshold, the vehicle is controlled to perform a lane change, completing the lane change.

[0074] Furthermore, the reference speed for traffic flow in the target lane can be determined by detecting the average speed of vehicles passing through the target lane while the vehicle is traveling close to the lane line. The method for determining the reference speed for traffic flow in the target lane is not limited here; it can be set as needed.

[0075] Optionally, in one implementation of this application, if the reference speed of the traffic flow in the target lane is detected to be very low or directly 0 (i.e. below a certain speed threshold, such as when the target lane is in a traffic jam) during the process of controlling the vehicle to drive close to the target lane line, the vehicle can be controlled to return to the state of driving close to the target lane line and the type of yielding intention of the target vehicle can be re-determined.

[0076] For example, such as Figure 4 As shown, Figure 4This is a schematic diagram illustrating the principle of controlling a vehicle to closely follow the target vehicle. Assume vehicle A wants to change lanes from lane M to target lane N, and the target vehicle is identified as vehicle B, with vehicle C being the target vehicle preceding it. During the process of controlling vehicle A to closely follow vehicle C, a second driving strategy is determined. This second driving strategy includes a second lateral trajectory planning strategy and a second longitudinal motion control strategy. The second lateral trajectory planning strategy specifies the lateral trajectory of vehicle A to closely follow vehicle C and the safe distance maintained between vehicle A and target vehicle B. Since vehicle A needs to achieve this closely following state, the second longitudinal motion control strategy specifies a positive acceleration for the vehicle, for example, 1.2 m / s². 2 Then, based on the second driving strategy information, vehicle A is controlled to drive close to the target vehicle C, which corresponds to the target vehicle B.

[0077] In other words, if the target vehicle does not show a clear refusal to yield, the goal of this stage is to prompt the target vehicle to make a clear decision through continuous and gentle pressure.

[0078] Furthermore, the second lateral motion trajectory planning strategy information may also include other information such as the second lateral travel trajectory and the second lateral travel speed, and the second longitudinal motion control strategy information may also include other information such as the second longitudinal travel trajectory. Of course, the second driving strategy information may also include other information. Additionally, the second lateral distance can be determined based on reference information such as lane width or set as needed, and the second longitudinal acceleration can be determined based on reference information such as the vehicle's own speed, the target vehicle's speed, and the traffic flow speed or set as needed.

[0079] S500: Determine whether the strain gauge condition is met. If the strain gauge condition is not met, proceed to step S600; if the strain gauge condition is met, proceed to step S900.

[0080] For example, the lane change conditions in this step can be the same as those in step S300 above, and the probability of the target vehicle's yielding intention to the vehicle can be recalculated in the manner described in step S300 above, thereby determining whether the corresponding lane change conditions are met.

[0081] Of course, the lane-changing conditions in this step can be different from those in step S300. For example, the values ​​of the first and second yield thresholds corresponding to the lane-changing conditions in this step are different from the values ​​of the first and second yield thresholds corresponding to the lane-changing conditions in step S300. Other differences are also possible. The lane-changing conditions in this step can be set as needed.

[0082] S600: Determine whether the vehicle has reached the target lane change node. If the target lane change node has not been reached, return to step S400 to keep the vehicle in close proximity and further determine whether the corresponding lane change conditions are met; if the target lane change node has been reached, proceed to step S700.

[0083] For example, the target lane change node is the lane change node that determines that the vehicle must perform a lane change. In other words, the target lane change node can be understood as the node that requires a forced lane change, or it can be called a forced lane change node.

[0084] The target lane change node can be a location node, for example. When the target lane change node is a location node, it can be a node where the distance between the vehicle's current location and the maximum drivable distance in its lane is insufficient to support a slow lane change. For instance, the distance between the vehicle's current location and a certain location in its lane is less than or equal to a certain distance threshold (e.g., 50 meters, the specific value can be set as needed). The method for determining whether the vehicle has reached the target lane change node can be, for example: when the drivable distance in the target lane is insufficient, i.e., the distance between the vehicle and the end of the target lane is less than the distance threshold (e.g., 50 meters), then the vehicle has reached the target lane change node. Alternatively, it can be: when the vehicle is about to reach a fork in the road, and the vehicle's travel path information indicates that a lane change is required, then the vehicle has also reached the target lane change node.

[0085] The target lane change node can also be a time node. When the target lane change node is a time node, it can refer to a time frame from when the vehicle first determined the intention to change lanes and initiated the lane change assessment until the current time, which has exceeded a certain time threshold (e.g., 10 minutes, the specific value of which can be set as needed). In other words, a lane change attempt has been made for a considerable period of time, but the lane change has not yet been completed.

[0086] Of course, the target lane change node is not limited to a location node, and the method of determining the arrival of a vehicle at the target lane change node is not limited to the examples mentioned above; it can be set as needed.

[0087] S700: Controls the vehicle to forcibly drive towards the target vehicle, so that the vehicle is in a forced driving state.

[0088] For example, controlling a vehicle to forcibly approach a target vehicle includes: reducing the vehicle's speed and reducing the safe distance between the vehicle and the target vehicle, so that the vehicle continues to move close to the target vehicle.

[0089] Optionally, in one implementation of this application, during the process of a vehicle forcibly cutting into a target vehicle, the vehicle's speed is very low, and the safe distance between the vehicle and the target vehicle is dynamically reduced, resulting in a more aggressive lateral intrusion distance. Furthermore, the direct reactions of the target vehicle (such as the magnitude of deceleration) and the spatial situational changes between the target vehicle and the vehicle in front of it are continuously integrated to continuously update the probability of the target vehicle's yielding intention.

[0090] For example, such as Figure 5 As shown, Figure 5 This is a schematic diagram illustrating the principle of controlling a vehicle to forcibly cut into a target vehicle. Assume vehicle A wants to change lanes from lane M to target lane N, and the target vehicle is identified as vehicle B. During the process of controlling vehicle A to forcibly cut into target vehicle B, vehicle A's speed will decrease, and it will continuously approach target vehicle B. Throughout this process, the probability of target vehicle B's willingness to yield is continuously updated.

[0091] Reducing the vehicle's speed, for example, by gradually reducing the vehicle's speed according to a certain reduction ratio or value. Also, reducing the safe distance between the vehicle and the target vehicle, for example, by reducing the safe distance between the vehicle and the target vehicle according to a certain reduction ratio or value.

[0092] Of course, the method of controlling vehicle A to forcibly drive into target vehicle B is not limited to the example above, and can be set as needed.

[0093] S800: Determine whether the strain gauge condition is met. If the strain gauge condition is not met, continue to step S700; if the strain gauge condition is met, proceed to step S900.

[0094] For example, the lane change conditions in this step can be the same as those in the aforementioned steps S300 or S500, and the probability of the target vehicle's yielding intention to the vehicle can be recalculated in the manner described in the aforementioned steps S300 or S500, thereby determining whether the corresponding lane change conditions are met.

[0095] Of course, the lane-changing conditions in this step can be different from those in steps S300 or S500. For example, the values ​​of the first and second yield thresholds corresponding to the lane-changing conditions in this step may be different from those in steps S300 or S500. Alternatively, they can be different in other ways. The lane-changing conditions in this step can be set as needed.

[0096] Optionally, in one implementation of this application, if the lane change conditions are not met after the vehicle enters the forced lane-changing state, step S700 is executed again. This can involve controlling the vehicle to continue braking slowly or stopping and waiting, so that step S800 can be executed again to determine whether the lane change conditions are met, until the lane change is completed when the lane change conditions are met. In this way, it can be ensured that the vehicle will not collide with other vehicles and that an opportunity can be found to complete the lane change.

[0097] In addition, if the corresponding lane change conditions are still not met after a vehicle forcibly cuts in, a new target vehicle can be identified to perform the aforementioned vehicle lane change control process.

[0098] S900: Controls the vehicle to perform lane change processing and completes the lane change.

[0099] For example, based on information such as the speed and distance between the target vehicle and the target vehicle in front of it, a third driving strategy information including the vehicle's speed and trajectory can be generated. Based on the third driving strategy information, the vehicle can drive into the gap between the target vehicle and the target vehicle in front of it, so as to be between the target vehicle and the target vehicle in front of it, and complete the lane change from the original lane to the adjacent target lane.

[0100] Optionally, in one implementation of this application, during the process of controlling the vehicle to perform a lane change, it can be continuously determined whether the corresponding lane change conditions are still met during the lane change process. If the corresponding lane change conditions are met, the vehicle is controlled to continue to complete the lane change. If the corresponding lane change conditions are not met, the vehicle can be controlled to return to the corresponding driving state before the lane change process, such as returning to the state of forcibly cutting into the target vehicle, driving close to the vehicle in front of the target vehicle, or driving close to the line of the target lane, so as to re-control the vehicle to change lanes.

[0101] Optionally, in one implementation of this application, during any lane change process such as the vehicle driving close to the target lane line corresponding to the target lane, the vehicle driving close to the target vehicle in front of the target vehicle, or the vehicle forcibly cutting into the target vehicle, if the yielding intention type is a clear refusal to yield, the target vehicle can be re-determined. For example, when the target vehicle is the vehicle with the closest lateral distance to the vehicle and clearly refuses to yield, the target vehicle in front of or behind the target vehicle can be selected as the new target vehicle, and the yielding intention type of the new target vehicle can be further determined, thereby controlling the vehicle to complete the lane change.

[0102] Optionally, in one implementation of this application, the control commands are smoothed and optimized during the processes of controlling the vehicle to drive close to the target lane line corresponding to the target lane, controlling the vehicle to drive close to the target vehicle in front of the target vehicle, controlling the vehicle to cut into the target vehicle, controlling the vehicle to return to driving close to the line, driving close to the target vehicle, and controlling the vehicle to change lanes.

[0103] That is, such as Figure 6 As shown, the vehicle lane change control method provided in this application may include the following steps: During the lane change process, firstly, it is determined whether the vehicle has a strong intention to change lanes, and the target lane and target vehicle are identified. Then, the vehicle is controlled to drive close to the target lane line corresponding to the target lane. After the vehicle is in the close-to-the-lane driving state, the type of yielding intention of the target vehicle in the target lane is determined to determine whether the corresponding lane change condition is met (i.e., whether the yielding condition of the following vehicle is met). If the corresponding lane change condition is met, the vehicle is controlled to perform the lane change process and complete the lane change; if the corresponding lane change condition is not met, the vehicle is controlled to drive close to the target vehicle corresponding to the target vehicle, and the type of yielding intention of the target vehicle in the target lane is re-determined to determine whether the corresponding lane change condition is met. If the corresponding lane change condition is met, the vehicle is controlled to perform the lane change process and complete the lane change; if the corresponding lane change condition is not met, the vehicle is controlled to forcibly cut into the target vehicle, and during the forced cutting process, it is continuously determined whether the corresponding lane change condition is met until the corresponding lane change condition is met, and the vehicle is controlled to complete the lane change process. Furthermore, during the process of controlling the vehicle to perform a lane change, it will further determine whether the corresponding lane change conditions are met. If the corresponding lane change conditions are met, the vehicle will continue to be controlled to complete the lane change. If the corresponding lane change conditions are not met, the vehicle can be controlled to return to the corresponding driving state before the lane change was performed, such as switching from the lane change to the corresponding forced entry driving state, so as to re-determine the corresponding lane change conditions and control the vehicle to perform the lane change.

[0104] Corresponding to the aforementioned method, this application also provides an electronic device, including a vehicle lane change control system for controlling lane changes of a vehicle, used to implement the aforementioned vehicle lane change control method. This electronic device may be, for example, a vehicle, a server, or other similar equipment.

[0105] Optionally, in one implementation of this application, the electronic device may be a vehicle, such as... Figure 7As shown, the vehicle includes a lane change control system, which is deployed in the vehicle's central decision controller. This system includes a motion planning module, a perception fusion module, and an intent calculation module. The motion planning module comprises a lateral planning module and a longitudinal planning module. Specifically, the lateral planning module determines vehicle lateral motion trajectory planning strategy information, such as first lateral motion trajectory planning strategy information and second lateral motion trajectory planning strategy information; the longitudinal planning module determines vehicle longitudinal motion control strategy information, such as first longitudinal motion control strategy information and second longitudinal motion control strategy information; the perception fusion module determines the yielding feedback information from the target vehicle; and the intent calculation module determines the yielding intent type.

[0106] Optionally, in one implementation of this application, the vehicle lane change control system further includes a lane change decision state machine. The lane change decision state machine is used to determine the state of the vehicle, receive information from the motion planning module, the perception fusion module, and the intent calculation module, fuse and process this information to obtain a lane change decision result, and send instructions to the motion planning module, the perception fusion module, and the intent calculation module according to the lane change decision result, so that these modules can perform corresponding lane change actions according to the lane change decision result.

[0107] Optionally, in one implementation of this application, the vehicle lane change control system can also be deployed on the vehicle cloud to implement the aforementioned vehicle lane change control method.

[0108] For example, in an implementable case, suppose a vehicle needs to change lanes to the right in congested traffic due to navigation route planning, specifically including the following steps.

[0109] Step 1: Initialization of the vehicle lane change control system and confirmation of the target vehicle. First, the perception fusion module confirms the following vehicle (Vehicle_Target, i.e., the target vehicle) and the preceding vehicle (Vehicle_Lead, i.e., the target vehicle in front of the target vehicle) in the target lane as key interaction objects. That is, it identifies the target vehicle and its corresponding target vehicle in the target lane. At this point, the lane change decision state machine in the system is in the initial "Approach" state. For example, if it is determined that the vehicle has a strong intention to change lanes, the system controls the vehicle to gradually decelerate. Once the speed reaches a safe level, the system enters the first stage and executes Step 2.

[0110] Step Two: Execute "Line-Following Probe," which involves controlling the vehicle to travel close to the target lane line to maintain a lane-keeping state. Upon receiving the "Probe" command, the motion planning module in the vehicle lane change control system calls the lateral planning module to dynamically generate a smooth trajectory (Traj_Lat) with a lateral offset of 3 meters within 3 seconds. This trajectory, based on the width of the target lane, controls the vehicle to maintain a distance of 0-5 cm between the outer edge of the tires and the target lane line, achieving vehicle driving control based on the first lateral motion trajectory planning strategy information. Simultaneously, the longitudinal planning module is called to synchronously generate a longitudinal speed planning curve (Traj_Lon), with a dynamic speed limit. This dynamic value is the reference speed of the traffic flow in the target lane, for example, -2 m / s, achieving vehicle driving control based on the first longitudinal motion control strategy information.

[0111] Furthermore, during this first phase, the intent calculation module continuously receives perception data from the target vehicle and calculates the probability of yielding intent. If the yielding intent probability is greater than the first yielding threshold and less than the second yielding threshold, the process proceeds to the second phase, executing step three. If the yielding intent probability is greater than or equal to the second yielding threshold, a lane change is executed. For example, if the calculated yielding intent probability is 0.45, and the first yielding threshold (i.e., the close-to-the-car threshold) is 0.3 and the second yielding threshold (i.e., the lane change threshold) is 0.7, then the yielding intent probability is greater than the close-to-the-car threshold and less than the lane change threshold, meaning the corresponding lane change condition is not met, and step three is executed.

[0112] Step 3: Execute "Follow-up Driving", which means controlling the vehicle to follow the target vehicle in front of it so that the vehicle is in the following driving state.

[0113] In other words, the vehicle lane change control system enters a "negotiation" state with the target vehicle. At this time, the behavior of the vehicle lane change control system changes. The motion planning module in the vehicle lane change control system receives the "negotiation" instruction, that is, it receives the instruction that "when the lateral distance between the vehicle and the target vehicle is greater than the set safe distance, then the vehicle will laterally intrude until it reaches the safe distance," and calls the lateral planning module to generate a trajectory that satisfies the above instruction. In addition, during this process, the intent calculation module continuously receives the target vehicle's perception data and calculates the yielding intent probability. For example, if the calculated yielding intent probability is still 0.45, it still does not meet the lane change conditions, so it continues to determine whether the vehicle has reached the target lane change node. If it has not reached the aforementioned target lane change node, the vehicle continues to maintain a close following state and further determines whether the corresponding lane change conditions are met. If it has reached the aforementioned target lane change node, for example, if the vehicle perceives that the driving distance in the lane is insufficient, that is, it has reached the end of the lane, then the vehicle must change lanes and enter the third stage, executing step four. If, before reaching the aforementioned target lane-changing node, the vehicle continues to drive close to the vehicle and determines whether the corresponding lane-changing conditions are met, and if the calculated probability of yielding intention is greater than 0.7, then a lane change is executed.

[0114] Step Four: Execute "Forced Lane Cut," which involves controlling the vehicle to forcefully cut into the target vehicle. When the vehicle lane change control system receives the vehicle's status change to "Forced Lane Cut," the system instruction becomes "If the lateral distance between the vehicle and the target vehicle is greater than the set safe distance, then laterally intrude until it equals the safe distance." Furthermore, the safe distance at this point is less than the safe distance in the "Negotiation" state. In addition, during this process, the intent calculation module continuously receives the target vehicle's perception data and calculates the probability of yielding intent. For example, if the yielding intent probability is 0.73, meeting the lane change conditions, the vehicle is controlled to execute the lane change process, completing the lane change.

[0115] Optionally, in one implementation of this application, after the vehicle enters the forced lane-changing state, the driver can be prompted by voice to take over the vehicle. Additionally, the vehicle can be controlled to continue braking and waiting close to the target vehicle, and during the waiting process, the yielding intention type of the target vehicle is continuously calculated to determine whether the corresponding lane change conditions are met. If the corresponding lane change conditions are met, the vehicle is controlled to complete the lane change.

[0116] In summary, the vehicle lane change control scheme provided in this application firstly determines the first driving strategy information for the vehicle to travel close to the target lane line corresponding to the target lane. Based on the first driving strategy information, the vehicle is controlled to travel close to the target lane line corresponding to the target lane, so that the vehicle is in a lane-keeping state. Secondly, the yielding feedback information of the target vehicle is determined. Based on the yielding feedback information, the probability of the target vehicle's yielding intention is calculated. Based on the yielding intention probability and a preset threshold, the range of the yielding intention probability is determined. Based on the range of the yielding intention probability, the yielding intention type is determined. Finally, based on the yielding intention type, it is determined whether the corresponding lane change conditions are met. If the corresponding lane change conditions are met, the vehicle is controlled to perform a lane change. If the corresponding lane change conditions are not met, a second driving strategy is determined, in which the vehicle moves close to the target vehicle ahead of the target vehicle. Based on this strategy, the vehicle is controlled to move close to the target vehicle ahead of the target vehicle, maintaining a close-to-the-car state. The corresponding lane change conditions are then re-evaluated. If the conditions are still not met, the target lane change node is checked. If the target lane change node is not reached, the vehicle continues to move close to the target vehicle, and the corresponding lane change conditions are checked again. If the target lane change node is reached, the vehicle is controlled to forcibly cut into the target vehicle, maintaining a forcibly-cutting-in state. The corresponding lane change conditions are checked again until they are met, at which point the vehicle performs a lane change. Furthermore, if the yielding intention type is a clear refusal to yield, the target vehicle can be re-identified. Additionally, if a vehicle encounters an emergency while driving close to another vehicle or cutting into another lane, causing the reference speed of traffic in the target lane to be very slow or even zero, the vehicle can be controlled to return to the close-to-the-car / close-to-the-line / cutting-in driving state.

[0117] In other words, the vehicle lane change control scheme provided in this application is specifically a method and system for achieving safe, smooth, and efficient forced lane changes (commonly known as "cutting in") in highly interactive scenarios with congestion, low speed, and minimal safety gaps, through a multi-stage, progressive collaborative game strategy. It can also be understood as a closed-loop collaborative game control system of "perception-prediction-decision-execution-re-perception," which is particularly suitable for collaborative game decision-making and control of lane changes in highly interactive scenarios with congestion. The core is to decouple a single lane change decision into a multi-stage, progressive interactive process that includes "probing," "negotiation," and "execution." At each stage, specific lateral and longitudinal collaborative control strategies are designed to clearly and safely convey the vehicle's lane change intention to the following vehicle (i.e., the target vehicle) through dynamic behavior. The game strategy is adjusted in real time based on the feedback from the following vehicle (i.e., the probability of the target vehicle's yielding intention is calculated in real time), ultimately inducing lane change space while ensuring safety. The process mainly consists of three stages: Stage 1, lane-keeping probing and intention broadcasting - lane-keeping driving stage: In this stage, the vehicle aims to clearly and non-threateningly convey its lane-changing intention and initially probe the reaction of the vehicle behind it; Stage 2, gradual approach and dynamic game - vehicle-keeping driving stage: If the vehicle behind does not show clear rejection, continuous and gentle pressure is used to prompt the vehicle behind to make a clear decision; Stage 3, forced lane-cutting stage: If the previous lane-keeping and vehicle-keeping driving cannot create lane-changing space for the vehicle and the vehicle has reached the latest lane-changing point, the vehicle triggers the forced lane-cutting state, which is the final game stage.

[0118] Thus, by designing a multi-stage closed-loop game control process, the abstract "intention prediction" is transformed into a concrete and executable sequence of vehicle behaviors. Specifically, the yielding intention of the target vehicle is quantified by probability, ensuring the accuracy of this intention. Furthermore, the probing behavior of "line-hugging + deceleration" is an internationally recognized language of driver intention, easily understood by human drivers, significantly reducing the "guessing" time in the game and improving the interpretability and high interaction efficiency of the lane-changing scheme. In addition, the gradual lane-changing strategy avoids abrupt forced entry; each stage has clear safety monitoring and exit paths, and all control commands are smoothly optimized, ensuring driving comfort and improving the safety and smoothness of the lane-changing process. Moreover, through dynamic game theory, the defensive posture of following vehicles can be effectively "softened," creating lane-changing opportunities that cannot be provided by real-world legal models, significantly improving the success rate in mandatory lane-changing scenarios. Furthermore, the system parameters can be calibrated according to different regional driving cultures, exhibiting strong adaptability and ensuring a high success rate and strong adaptability in lane-changing.

[0119] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0120] It should be noted that, in addition to the specific implementations described above, those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Although the description of this application is presented in conjunction with preferred implementations, this does not mean that the features of this invention are limited to that implementation. On the contrary, the purpose of describing the invention in conjunction with implementations is to cover other options or modifications that may be derived from the claims of this application. To provide a thorough understanding of this application, many specific details are included in the above description, and this application may also be implemented without using these details. Furthermore, to avoid confusion or obscuring the focus of this application, some specific details will be omitted in the description. It should be noted that, unless otherwise specified, the implementations and features of the implementations in this application can be combined with each other.

[0121] Although this application has been illustrated and described with reference to certain preferred embodiments, those skilled in the art should understand that the above description is a further detailed explanation of the application in conjunction with specific implementations, and should not be construed as limiting the specific implementation of the application to these descriptions. Those skilled in the art can make various changes in form and detail, including some simple deductions or substitutions, without departing from the spirit and scope of this application.

Claims

1. A vehicle lane change control method, characterized in that, A vehicle lane change control system applied to control lane changes for vehicles, the method comprising: If it is determined that the vehicle has the intention to change lanes, the vehicle is controlled to drive close to the target lane line corresponding to the target lane, so that the vehicle is in the lane-keeping driving state, and it is determined whether the corresponding lane change conditions are met. The target lane is the adjacent lane to the lane where the vehicle is located, which corresponds to the lane with the lane change intention, and the target lane line is the adjacent lane line between the lane where the vehicle is located and the target lane. If the lane change conditions are met, the vehicle is controlled to perform a lane change to complete the lane change from the current lane to the target lane. If the lane change conditions are not met, the vehicle is controlled to drive close to the target vehicle in the target lane, so that the vehicle is in a close-driving state, and the corresponding lane change conditions are re-determined. The target vehicle is the vehicle in the target lane that is overtaking the vehicle corresponding to the lane change intention. If the lane change conditions are met, the vehicle is controlled to perform a lane change to complete the lane change from the current lane to the target lane. If the lane-changing conditions are not met, determine whether the target lane-changing node corresponding to the vehicle has been reached. If the target lane-changing node has not been reached, keep the vehicle in the close-to-the-vehicle driving state and continue to determine whether the corresponding lane-changing conditions are met. If the target lane-changing node has been reached, control the vehicle to forcibly cut into the target vehicle so that the vehicle is in the forcibly cutting-in driving state, and determine again whether the corresponding lane-changing conditions are met, until the lane-changing conditions are met, control the vehicle to perform lane-changing processing to complete the lane change from the current lane to the target lane.

2. The method according to claim 1, characterized in that, Determine whether the strain gauge conditions are met, including: Determine the type of yielding intention of the target vehicle in the target lane, wherein the yielding intention type includes explicit intention and implicit intention, and the explicit intention includes explicit yielding intention and explicit refusal to yield intention; Based on the type of yielding intention, determine whether the corresponding lane condition is met. If the type of yielding intention is the explicit yielding intention, the corresponding lane condition is met. If the type of yielding intention is the inexplicable intention or the explicit refusal to yield, the corresponding lane condition is not met.

3. The method according to claim 2, characterized in that, Controlling the vehicle to travel close to the target lane line corresponding to the target lane includes: The system determines first driving strategy information for the vehicle to travel along the target lane line corresponding to the target lane. The first driving strategy information includes first lateral motion trajectory planning strategy information and first longitudinal motion control strategy information. The first lateral motion trajectory planning strategy information includes a first lateral distance, which is the safe distance of the vehicle relative to the target lane when traveling along the line. The first longitudinal motion control strategy information includes a first longitudinal acceleration, which is the acceleration that causes the vehicle to decelerate. Based on the first driving strategy information, the vehicle is controlled to drive along the target lane line corresponding to the target lane.

4. The method according to claim 3, characterized in that, Controlling the vehicle to drive close to the target vehicle in the target lane includes: The system determines second driving strategy information for the vehicle to travel close to the target vehicle corresponding to the target vehicle. The second driving strategy information includes second lateral motion trajectory planning strategy information and second longitudinal motion control strategy information. The second lateral motion trajectory planning strategy information includes a second lateral distance, which is a safe distance between the vehicle and the target vehicle corresponding to the target vehicle. The second lateral distance is less than the first lateral distance. The second longitudinal motion control strategy information includes a second longitudinal acceleration, which is an acceleration that makes the vehicle's speed lower than the reference speed of the traffic flow corresponding to the target lane. Based on the second driving strategy information, the vehicle is controlled to drive close to the target vehicle in front of the target vehicle. The method further includes: If the reference speed of the traffic flow is less than the speed threshold, the vehicle is recontrolled to move closer to the target lane line.

5. The method according to claim 4, characterized in that, Controlling the vehicle to forcibly drive towards the target vehicle includes: The vehicle's speed is reduced, and the safe distance between the vehicle and the target vehicle is decreased, so that the vehicle continues to move closer to the target vehicle.

6. The method according to claim 5, characterized in that, The method further includes: If the yielding intention type is the explicit refusal to yield intention, a new target vehicle is determined, and the yielding intention type of the new target vehicle for the vehicle is determined, so as to perform corresponding vehicle lane change control processing.

7. The method according to claim 6, characterized in that, Determining the type of yielding intention of the target vehicle in the target lane includes: Determine the yielding feedback information of the target vehicle in relation to the vehicle, wherein the yielding feedback information includes the driving status information of the target vehicle and the spatial situation change information of the target vehicle and the target vehicle in front of the target vehicle; Based on the yielding feedback information, the type of yielding intention of the target vehicle towards the vehicle is determined.

8. The method according to claim 7, characterized in that, Based on the yielding feedback information, the type of yielding intention of the target vehicle towards the vehicle is determined, including: Based on the yielding feedback information, determine the probability of the target vehicle's yielding intention towards the vehicle; Based on the probability of yielding intention, the type of yielding intention is determined, wherein if the probability of yielding intention is less than or equal to a first yielding threshold, the type of yielding intention is determined to be an explicit refusal to yield; if the probability of yielding intention is greater than the first yielding threshold and less than a second yielding threshold, the type of yielding intention is determined to be an indefinite intention; and if the probability of yielding intention is greater than or equal to the second yielding threshold, the type of yielding intention is determined to be an explicit yielding intention.

9. The method according to claim 8, characterized in that, Based on the yielding feedback information, the probability of the target vehicle's yielding intention towards the vehicle is determined, including: Based on the yielding feedback information, multiple yielding evaluation information corresponding to the target vehicle is determined. The multiple yielding evaluation information includes the space assessment score, space change trend assessment score, space change trend cause assessment score, and collision assessment score between the target vehicle and the target vehicle in front of the target vehicle. The probability of yielding intention is determined based on each yielding evaluation information and the weight corresponding to each yielding evaluation information.

10. An electronic device, characterized in that, The vehicle lane change control system includes a vehicle lane change control system for implementing the vehicle lane change control method as described in any one of claims 1-9.

Images