Vehicle lane changing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a vehicle lane changing method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring navigation information and sensing data of a vehicle, and determining position information of the vehicle at the current moment based on the navigation information and the sensing data; predicting an obstacle area on the current road based on the position information, and collecting image information corresponding to the obstacle area; determining boundary information of the obstacle based on the image information, and determining a lane where the obstacle is located based on the boundary information; and determining a relative position relationship between the lane where the obstacle is located and the vehicle, and determining a lane changing strategy of the vehicle based on the relative position relationship. According to the embodiment of the invention, the obstacle area on the current road can be predicted, potential dangers can be found in time, collision accidents can be avoided, a driver can better master road condition and obstacle information, and the driving comfort and convenience are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a vehicle lane changing method, device, electronic device, and computer-readable storage medium. Background Art

[0002] With the development of intelligent driving technology, intelligent driving of vehicles on a single lane can no longer meet the needs of intelligent driving, nor can it solve the complex road section problems faced. When there is an obstacle in the current lane, it is necessary to implement an avoidance lane change strategy. For example, when an obstacle on the road is identified, it will be used as a sign of road construction or traffic control, and the driving path will be adjusted accordingly. However, based on the current technical perception, the recognition of obstacles is not stable, and there is a high probability that detection jumps will occur. Therefore, how to implement lane change strategies when encountering obstacles during vehicle driving and improve vehicle traffic efficiency and driving safety is a problem that needs to be solved urgently. Summary of the invention

[0003] To solve the above technical problems, the embodiments of the present application provide a vehicle lane changing method and device, an electronic device, a computer-readable storage medium, and a computer program product.

[0004] According to one aspect of an embodiment of the present application, a vehicle lane changing method is provided, comprising: acquiring navigation information and sensor data of the vehicle, and determining the position information of the vehicle at a current moment based on the navigation information and the sensor data; predicting an obstacle area on the current road based on the position information, and collecting image information corresponding to the obstacle area; determining boundary information of the obstacle based on the image information, and determining the lane where the obstacle is located based on the boundary information; determining the relative position relationship between the lane where the obstacle is located and the vehicle, and determining the lane changing strategy of the vehicle based on the relative position relationship.

[0005] According to one aspect of an embodiment of the present application, determining the lane changing strategy of the vehicle based on the relative position relationship includes: if the relative position relationship indicates that the obstacle and the vehicle are in adjacent lanes, obtaining status information of the vehicle, the lane line of the adjacent lane, and the distance between the obstacle and the lane line, the status information including the vehicle speed and steering wheel angle of the vehicle, and the lane line is the lane line on the adjacent lane close to the vehicle on one side; determining a first path offset of the vehicle based on the status information, the vehicle speed, the steering wheel angle, the lane line, and the distance between the obstacle and the lane line, so that the vehicle avoids the obstacle in the current lane based on the first offset.

[0006] According to one aspect of an embodiment of the present application, the method also includes: if the relative position relationship indicates that the obstacle and the vehicle are in the same lane, obtaining the vehicle body information and the lane width of the current lane; obtaining the road condition information of the adjacent lane, the road condition information including the traffic status information and road information of the adjacent lane; determining the preset boundary safety threshold of the vehicle based on the traffic status information and the road information; determining the second path offset of the vehicle based on the preset boundary safety threshold, the vehicle body information and the lane width, so that the vehicle leaves the current lane based on the second path offset.

[0007] According to one aspect of an embodiment of the present application, the method also includes: after the vehicle leaves the current lane, if the distance value between the obstacle and the vehicle is not greater than a preset distance threshold, obtaining real-time status information of the vehicle, the real-time status information including real-time vehicle speed and real-time steering wheel angle; determining a third path offset of the vehicle based on the real-time vehicle speed, real-time steering wheel angle and the distance value, so that the vehicle avoids the obstacle based on the third path offset; determining the lane changing strategy of the vehicle and the path offset corresponding to the lane changing path based on the second path offset and the third path offset.

[0008] According to one aspect of an embodiment of the present application, the method also includes: determining the operating status of the target vehicle in the adjacent lane based on the road condition information, the target vehicle including the vehicle to be overtaken in the adjacent lane; determining the collision probability between the vehicle and the target vehicle based on the operating status and the operating status of the vehicle; and correcting the lane changing strategy of the vehicle based on the collision probability.

[0009] According to one aspect of an embodiment of the present application, the method also includes: determining a target image recognition model and configuration parameters corresponding to the target image recognition model based on scene information corresponding to the obstacle area; performing image recognition on the image information through the target image recognition model based on the configuration parameters corresponding to the target image recognition model to determine the boundary information of the obstacle.

[0010] According to one aspect of an embodiment of the present application, the method also includes: determining a target edge detection algorithm based on configuration parameters corresponding to the target image recognition model; performing edge strength identification on each pixel point in the image information based on the target edge detection algorithm to determine the edge strength value of each pixel point relative to adjacent pixels in the image information; removing non-maximum points in the image information based on the edge strength value of each pixel point to obtain boundary information of obstacles in the image information.

[0011] According to one aspect of an embodiment of the present application, a vehicle lane changing device is provided, including: an acquisition module, used to acquire navigation information and sensor data of the vehicle, and determine the position information of the vehicle at the current moment based on the navigation information and the sensor data; an acquisition module, used to predict the obstacle area on the current road based on the position information, and collect image information corresponding to the obstacle area; a determination module, used to determine the boundary information of the obstacle based on the image information, and determine the lane where the obstacle is located based on the boundary information; a lane changing module, used to determine the relative position relationship between the lane where the obstacle is located and the vehicle, and determine the lane changing strategy of the vehicle based on the relative position relationship.

[0012] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements the vehicle lane changing method as described above.

[0013] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer executes the vehicle lane changing method as described above.

[0014] According to one aspect of an embodiment of the present application, a computer program product is also provided, including a computer program, which implements the steps in the vehicle lane changing method as described above when executed by a processor.

[0015] In the technical solution provided in the embodiments of the present application, the position of the vehicle can be determined in real time by acquiring the navigation information and sensor data of the vehicle, and the obstacle area on the current road can be predicted based on the actual position of the vehicle, so that potential dangers can be discovered in time and collision accidents can be avoided. The boundary information of the obstacle can be determined based on the image information, and the lane where the obstacle is located can be judged. The relative position between the obstacle and the vehicle can be accurately calculated, and then a suitable lane changing strategy can be specified for the vehicle to avoid collisions between the vehicle and obstacles or other vehicles, providing the driver with more accurate and real-time driving assistance information, helping the driver to better understand the road conditions and obstacle information, and improving driving comfort and convenience.

[0016] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0018] Figure 1 is a schematic diagram of an implementation environment for changing lanes of a vehicle during vehicle driving, shown in an exemplary embodiment of the present application;

[0019] Figure 2 is a flow chart of a vehicle lane changing method shown in an exemplary embodiment of the present application;

[0020] Figure 3 is a flow chart of a vehicle lane changing method shown in another exemplary embodiment of the present application;

[0021] Figure 4 is a flow chart of a vehicle lane changing method shown in another exemplary embodiment of the present application;

[0022] Figure 5 is a flow chart of a vehicle lane changing method shown in another exemplary embodiment of the present application;

[0023] Figure 6 is a flow chart of a vehicle lane changing method shown in another exemplary embodiment of the present application;

[0024] Figure 7 is a flow chart of a vehicle lane changing method shown in another exemplary embodiment of the present application;

[0025] Figure 8 is a flow chart of a vehicle lane changing method shown in another exemplary embodiment of the present application;

[0026] Fig. 9 is a schematic diagram of a simplified process of changing vehicle lanes in an exemplary application scenario;

[0027] Fig.10 is a block diagram of a vehicle lane changing device shown in an exemplary embodiment of the present application;

[0028] Fig.11 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0029] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0030] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0031] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0032] The term "multiple" as used in this application refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0033] First of all, it should be noted that navigation is a technology that points to the critical path of the destination. It is the process of monitoring and controlling the movement of objects such as processes, vehicles, and pedestrians from one location to another. Intelligent driving systems are usually equipped with a variety of high-precision sensors, such as radar, LiDAR, and cameras. These sensors can perceive the environment around the vehicle in real time, including road conditions, pedestrians, other vehicles and other obstacles. Through AI algorithms such as deep learning, intelligent driving systems can identify and understand complex traffic scenes and issue warnings for potential collision risks. High-precision maps provide key data such as road information, obstacle locations, and traffic rules for intelligent driving systems. Combined with real-time sensor data, intelligent driving systems can more accurately determine the location and type of obstacles.

[0034] In the intelligent driving system, sensor fusion technology can be used to perceive the environment around the vehicle in real time and detect potential obstacles. When an obstacle is detected, the system will immediately identify it, including the type, size, and location of the obstacle. Based on the obstacle detection results, the intelligent driving system will evaluate the potential collision risk. The evaluation results include the possibility of collision, the severity of collision, etc. Based on the results of risk assessment, the intelligent driving system will formulate an avoidance strategy, which includes parameters such as the lane to change to, the direction of avoidance, speed, acceleration, etc.

[0035] Figure 1 FIG. 1 is a schematic diagram showing an implementation environment of a vehicle lane change during vehicle driving, shown in an exemplary embodiment of the present application. Figure 1 As shown, during the driving process of the vehicle, the navigation information of the vehicle and the sensor data sent back by the sensor device can be obtained through the smart terminal 110, and then the smart terminal 110 can determine the location information of the vehicle at the current moment according to the navigation information and sensor data of the vehicle, and then predict the obstacle area on the current road according to the location information of the vehicle, and then the smart terminal 110 collects the image information corresponding to the obstacle area, and then determines the boundary information of the obstacle according to the image information, and then determines the lane where the obstacle is located according to the boundary information. Then, the relative position relationship between the lane where the obstacle is located and the vehicle can be determined to determine the lane change strategy of the vehicle, and then the vehicle can avoid obstacles during driving.

[0036] in, Figure 1 The smart terminal 110 shown can be any terminal device that supports data processing, such as a smart phone, a car computer, a tablet computer, a laptop computer, or a wearable device.

[0037] With the development of intelligent driving technology, intelligent driving of vehicles on a single lane can no longer meet the needs of intelligent driving, nor can it solve the complex road section problems faced. When there is an obstacle in the current lane, it is necessary to implement an avoidance lane change strategy. For example, when an obstacle on the road is identified, it will be used as a sign of road construction or traffic control, and the driving path will be adjusted accordingly. However, based on the current technical perception, the recognition of obstacles is not stable, and there is a high probability that detection jumps will occur. Therefore, how to implement lane change strategies when encountering obstacles during vehicle driving and improve vehicle traffic efficiency and driving safety is a problem that needs to be solved urgently.

[0038] The problems pointed out above are generally applicable in general travel scenarios. In order to solve these problems, the embodiments of the present application respectively propose a vehicle lane changing method, a vehicle lane changing device, an electronic device, a computer-readable storage medium and a computer program product. These embodiments will be described in detail below.

[0039] See also Figure 2 , Figure 2 FIG. 1 is a flow chart of a vehicle lane changing method shown in an exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown is specifically executed by the smart terminal 110 in the implementation environment. It should be understood that the method can also be applied to other exemplary implementation environments and be specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment to which the method is applicable.

[0040] like Figure 2 As shown, in an exemplary embodiment, the vehicle lane changing method only includes steps S210 to S240, which are described in detail as follows:

[0041] Step S210, obtaining navigation information and sensor data of the vehicle, and determining the current position information of the vehicle based on the navigation information and sensor data.

[0042] Specifically, the navigation information of the vehicle and the data sensed by the on-board sensor can be fused and processed, and then the recognition strategy of the navigation information can be used to understand the scene and the scene with the vehicle. The navigation information includes the road type, the vehicle's driving direction, the expected driving path, etc. The on-board sensor processes the data of obstacles, and uses the image data and radar data captured by the on-board camera to prepare for recognition through pre-processing such as denoising and contrast enhancement. The current vehicle's location information is determined based on the navigation information.

[0043] Exemplarily, navigation information usually includes map data, route planning data, GPS signals, etc. This information is generally provided by the vehicle navigation system or the navigation application on the smartphone. Among them, GPS data: obtains the vehicle's latitude and longitude, speed, direction and other basic information through the vehicle's GPS receiver; map data: uses digital maps (such as OpenStreetMap, GoogleMaps, etc.) to provide detailed road information, points of interest (POI), etc.; route planning: based on the destination and current location, the navigation system provides the optimal route. Sensor data mainly comes from various sensors installed on the vehicle, including but not limited to: radar sensor: used to detect obstacles and other vehicles around the vehicle; laser radar (LiDAR): provides high-precision three-dimensional environmental information; camera: used for image recognition, such as traffic sign recognition, lane keeping, etc.; inertial navigation system (INS): combined with accelerometer and gyroscope, provides vehicle acceleration, angular velocity and other data for calculating position; wheel speed sensor: measures the rotation speed of the wheel, used to calculate speed and distance.

[0044] Afterwards, the raw data can be cleaned, denoised and calibrated, and algorithms such as Kalman filtering and particle filtering can be used to integrate GPS data, INS data, radar and LiDAR data to improve the accuracy and reliability of location information. Finally, the fused location information can be matched with the digital map to correct deviations and ensure that the vehicle is on the correct road.

[0045] Step S220: predicting the obstacle area on the current road based on the position information, and collecting image information corresponding to the obstacle area.

[0046] Specifically, the area where obstacles exist on the current road can be predicted based on the current position information of the vehicle. For example, if the current position information of the vehicle is in a highway construction area, a city road maintenance area, etc., the obstacle area on the current road can be predicted, and then the image information of the obstacle area can be obtained through the vehicle-mounted image acquisition device.

[0047] For example, real-time traffic data can be integrated, including vehicle location, speed, acceleration, etc. Collect historical traffic data and analyze the patterns of road congestion and accident-prone areas. Combine geographic information system (GIS) data to understand road layout, obstacle types, etc. Then, use big data analysis and artificial intelligence algorithms (such as machine learning, deep learning, etc.) to build an obstacle prediction model. The model should be able to predict potential obstacle areas on the road based on real-time traffic data, historical data and GIS data. Improve the accuracy of prediction by continuously training and optimizing the model. According to the current location information and real-time traffic data of the vehicle, use the trained model to predict obstacles, and the prediction results should include information such as the location, size, and type of the obstacle area. Configure high-definition cameras, laser radar (LiDAR), radar sensors, etc. on the vehicle to collect road images and obstacle information. Then ensure that the sensor can cover the predicted obstacle area and provide sufficient resolution and accuracy. When the vehicle drives to the predicted obstacle area, trigger the sensor to collect images. Preprocess the collected images, including denoising, contrast enhancement, etc., to improve image quality.

[0048] Step S230: determining the boundary information of the obstacle based on the image information, and determining the lane where the obstacle is located based on the boundary information.

[0049] Specifically, image processing algorithms (such as edge detection, target recognition, etc.) can be used to extract feature information of the obstacle area, and then the lane corresponding to the obstacle can be determined according to the boundary information of the obstacle.

[0050] Exemplarily, the collected image is subjected to preprocessing operations such as denoising and contrast enhancement to improve the image quality. If the image is in color, it can be converted to a grayscale image to simplify processing. Obstacles are detected in the image using computer vision algorithms (such as convolutional neural networks CNN, YOLO, Faster R-CNN, etc.). These algorithms are usually able to identify and locate multiple obstacles in the image, such as vehicles, pedestrians, bicycles, etc., and the detected obstacles are contour extracted. Usually, edge detection algorithms (such as Canny edge detection) or shape analysis algorithms are used. After contour extraction, the boundary information of the obstacle can be obtained, including the coordinates and shape of the boundary. Then, in the same image, a lane line detection algorithm (such as Hough transform, lane line detection based on machine learning, etc.) is used to identify the lane line. The lane line detection algorithm is usually able to identify the lane line in the image and give the position and slope of the lane line. Finally, the boundary information of the obstacle is associated with the lane line information. By comparing the position of the obstacle and the position of the lane line, it can be determined whether the obstacle is located in a certain lane. If the obstacle has a clear overlap with the lane line or the obstacle is located between the lane lines, the lane where the obstacle is located can be determined. It should be noted that sometimes obstacles may span multiple lanes, and more complex algorithms are needed to make accurate judgments.

[0051] Step S240, determining the relative position relationship between the lane where the obstacle is located and the vehicle, and determining the lane changing strategy of the vehicle based on the relative position relationship.

[0052] Specifically, the precise location information of obstacles is obtained by using on-board sensors (such as radar, camera, lidar, etc.), including their lateral and longitudinal positions in the lane. At the same time, the position of the vehicle itself is determined by GPS and vehicle dynamic parameters (such as speed, direction, etc.), and image processing technology (such as edge detection, Hough transform, etc.) or a special lane recognition algorithm is used to identify the lane line. Determine the lane where the obstacle is located and the lane where the vehicle is currently located. Target lane condition: Check whether the target lane has enough space for the vehicle to change lanes safely, including whether there are other vehicles approaching or parallel. Obstacle impact: Assess the potential impact of obstacles on the lane changing process, such as the size, speed, and direction of movement of the obstacles. Use prediction algorithms (such as prediction models based on machine learning or deep learning) to predict the future trajectories of obstacles and other vehicles to determine the safety of lane changing, and ensure that the vehicle's speed matches the average speed of the target lane to reduce the speed difference during the lane changing process, maintain a safe distance from the front and rear vehicles in the target lane, and avoid collisions during lane changing. Then, the steering angle and steering speed can be determined based on the relative position relationship to achieve a smooth lane changing process. After all lane-changing conditions are met, the lane-changing operation is performed while maintaining continuous monitoring of the surrounding environment. During the lane-changing process, the vehicle status and environmental changes are constantly monitored. If an emergency occurs, the lane-changing strategy is adjusted in time or the lane-changing is terminated.

[0053] In this embodiment, the vehicle's position can be determined in real time by acquiring the vehicle's navigation information and sensor data, and the obstacle area on the current road can be predicted based on the vehicle's actual position, so that potential dangers can be discovered in time and collision accidents can be avoided. The boundary information of the obstacle can be determined based on the image information, and the lane it is in can be judged. The relative position between the obstacle and the vehicle can be accurately calculated, and then a suitable lane changing strategy can be specified for the vehicle to avoid collisions between the vehicle and obstacles or other vehicles, providing the driver with more accurate and real-time driving assistance information, helping the driver to better understand road conditions and obstacle information, and improving driving comfort and convenience.

[0054] Further, based on the above embodiments, please refer to Figure 3 In one of the exemplary embodiments provided in the present application, the specific implementation process of determining the lane change strategy of the vehicle based on the relative position relationship may also include steps S310 to S330, which are described in detail as follows:

[0055] Step S310: if the relative position relationship indicates that the obstacle and the vehicle are in an adjacent lane, then the vehicle status information, the lane line of the adjacent lane, and the distance between the obstacle and the lane line are obtained, wherein the status information includes the vehicle speed and the steering wheel angle, and the lane line is the lane line on the adjacent lane close to the vehicle side;

[0056] Step S320, determining a first path offset of the vehicle based on the vehicle speed, the steering wheel angle, the lane line, and the distance between the obstacle and the lane line, so that the vehicle avoids the obstacle in the current lane based on the first offset.

[0057] Specifically, the location of the obstacle may limit the driving path of the vehicle. Whether the vehicle can safely bypass the obstacle can be determined based on the relative position relationship between the lane where the obstacle is located and the vehicle. Therefore, if the relationship between the vehicle and the lane where the obstacle is located is changed, and the obstacle is located in the adjacent lane of the vehicle, the state information of the vehicle, the lane line of the lane where the obstacle is located, and the distance between the obstacle and the lane line can be obtained. The state information of the vehicle includes the location information of the vehicle, the body length, body width, vehicle speed, steering wheel angle, etc. of the vehicle, and then the first path deviation of the vehicle is calculated by the distance between the obstacle and the lane line on the side of the vehicle close to the adjacent lane. If the distance between the obstacle and the lane line on the side of the vehicle close to the adjacent lane is greater than the preset safety distance threshold, it indicates that the obstacle does not affect the normal driving of the vehicle, and the vehicle can directly drive normally in the current lane without calculating the first path deviation. If the distance between the obstacle and the lane line on the side of the vehicle close to the adjacent lane is not greater than the preset safety distance threshold, the first path deviation of the vehicle can be calculated based on the state information of the vehicle, the position of the lane line on the adjacent lane, and the distance between the obstacle and the lane line, and the vehicle is controlled to determine the vehicle's avoidance or lane change strategy based on the first path deviation.

[0058] Exemplarily, the state information of the vehicle may include the speed, acceleration, direction, current position, etc. of the vehicle. The lane line of the adjacent lane specifically refers to the lane line information on the adjacent lane close to the vehicle side, which generally includes the position, direction, curvature, etc. of the lane line. The distance between the obstacle and the lane line refers to the horizontal or vertical distance from the obstacle to the above-mentioned specified lane line, depending on the direction of the lane and the position of the obstacle. Using the state information of the vehicle (such as speed, direction) and the information of the lane line (such as position, direction), it is possible to calculate how the vehicle will move relative to the lane line if it continues to drive in the current state. Combined with the distance between the obstacle and the lane line, the potential degree of proximity between the vehicle and the obstacle can be evaluated if the current path is continued. Among them, the "first path offset" refers to the degree to which the vehicle is expected to deviate from its current lane (or remain in its lane) without any maneuvering changes, while also taking into account the relative position to the obstacles in the adjacent lane.

[0059] Among them, if the first path deviation indicates that the vehicle has enough space to safely change to the adjacent lane without colliding with the obstacle, the vehicle may be advised or a lane change may be performed. Delayed lane change: If the first path deviation indicates that it may not be safe to change lanes immediately (for example, because the obstacle is too close), the vehicle may be advised to wait for a better opportunity, or gradually adjust the vehicle's speed and direction to create safer lane change conditions. No lane change: If the obstacle is very close to the lane line, or the current state of the vehicle (such as too fast or too slow) is not suitable for lane change, it may be decided to stay in the current lane.

[0060] In this embodiment, by acquiring the relative position relationship between the obstacle and the vehicle in the adjacent lane, as well as the distance between the obstacle and the lane line, the specific position of the obstacle can be accurately sensed, thereby avoiding collision with the obstacle, and based on the vehicle's status information (such as speed, acceleration, etc.) and lane line information, the vehicle's first path offset can be calculated in real time, and then the driving trajectory can be adjusted to ensure that the vehicle maintains a safe distance during the lane change process.

[0061] Further, based on the above embodiments, please refer to Figure 4 In one of the exemplary embodiments provided in the present application, the specific implementation process of the above-mentioned vehicle lane changing method may also include steps S410 to S440, which are described in detail as follows:

[0062] Step S410, if the relative position relationship indicates that the obstacle and the vehicle are in the same lane, then obtaining the vehicle body information and the lane width of the current lane;

[0063] Step S420, obtaining the traffic condition information of the adjacent lane, where the traffic condition information includes the traffic state information and road information of the adjacent lane;

[0064] Step S430, determining a preset boundary safety threshold of the vehicle based on the traffic status information and the road information;

[0065] Step S440, based on the preset boundary safety threshold, vehicle body information and lane width, the second path offset of the vehicle is determined so that the vehicle leaves the current lane based on the second path offset. Specifically, if the relative position relationship between the lane where the obstacle is located and the vehicle indicates that the obstacle and the vehicle are in the same lane, it indicates that the vehicle needs to change lanes, and then the road condition information on the adjacent lane of the lane where the vehicle is located can be obtained, wherein the road condition information of the adjacent lane includes the traffic conditions on the adjacent lane, such as traffic volume, average speed of the vehicle, lane width, etc. And the preset boundary safety threshold of the vehicle can be determined based on the road condition information on the adjacent lane, wherein the setting of the preset boundary safety threshold can be determined based on the road type and the traffic volume on the road, the average speed of the vehicle, lane width, etc. This preset boundary safety threshold is the minimum safety distance or space required for the vehicle to safely leave the current lane and be included in the adjacent lane. Finally, the system uses the preset boundary safety threshold, the vehicle's body information, and the width of the current lane to calculate the vehicle's second path offset. The second path offset is an accurate calculation value designed to ensure that the vehicle can safely leave the current lane while avoiding collisions with vehicles or obstacles in adjacent lanes.

[0066] For example, when an obstacle is detected in the same lane as the vehicle, the vehicle will look for an opportunity to safely change lanes to other open lanes. Before changing lanes, the vehicle needs to check the traffic conditions in the adjacent lanes to ensure that the vehicle's lane change will not interfere with other vehicles. Generally speaking, when determining the lane keeping path and the lane change path, the second path offset of the vehicle can be determined based on the vehicle's body information and the width of the current lane. Based on the path offset, the driving area can be adjusted and the lane change path of the vehicle can be determined. Therefore, the second path offset of the vehicle can be calculated as:

[0067] offset2=0.5*(lane width -ego width )-safe buffer

[0068] Among them, lane width Indicates the width of the current lane; ego width Indicates the width of the vehicle, which can be obtained based on the vehicle's body information; safe buffer The second path offset is the amount by which the vehicle deviates to the adjacent lane when preparing to change lanes. When planning a lane keeping path, the vehicle's offset needs to be considered for planning to obtain a more accurate lane keeping path.

[0069] Exemplarily, when it is determined that the obstacle is in the same lane as the vehicle, the first task is to understand the condition of the adjacent lane, which usually involves using sensors (such as radar, lidar, camera, etc.) to scan and collect information about the adjacent lane, including the vehicle's position, speed, direction, and whether there are other obstacles (such as construction areas, parked vehicles, etc.). The purpose of this step is to ensure that the adjacent lane is safe and feasible before changing lanes. With the road condition information of the adjacent lane, the vehicle needs to calculate and determine an optimal lane change path. The choice of lane change path should take into account multiple factors, such as the distance of the lane change, the required steering angle, the speed and direction of the vehicle in the adjacent lane, etc. The goal is to find a safe and efficient path that allows the vehicle to smoothly transition to the adjacent lane. Path offset refers to the lateral offset of the vehicle relative to the current driving path when it moves from the current lane to the adjacent lane. Determining the path offset requires considering factors such as the size of the vehicle, steering ability, the width of the adjacent lane, and the curvature of the lane change path. Accurate path offset calculation helps the vehicle maintain stability and safety when performing lane change operations.

[0070] In this embodiment, when the obstacle and the vehicle are in the same lane, by obtaining the road condition information of the adjacent lane and determining the lane change path and its corresponding path offset based on the information, driving safety can be significantly improved, the driving experience can be optimized, traffic efficiency can be improved, the adaptability of the intelligent driving system can be enhanced, and the development of autonomous driving technology can be promoted.

[0071] Further, based on the above embodiments, please refer to Figure 5 In one of the exemplary embodiments provided in the present application, the specific implementation process of determining the lane change path of the vehicle and the path offset corresponding to the lane change path based on the road condition information may also include steps S510 to S530, which are described in detail as follows:

[0072] Step S510, after the vehicle leaves the current lane, if the distance between the obstacle and the vehicle is not greater than a preset distance threshold, real-time status information of the vehicle is obtained, the real-time status information including real-time vehicle speed and real-time steering wheel angle;

[0073] Step S520, determining a third path offset of the vehicle based on the real-time vehicle speed, the real-time steering wheel angle, and the distance value, so that the vehicle performs obstacle avoidance processing on the obstacle based on the third path offset;

[0074] Step S530, based on the second path offset and the third path offset, the lane change strategy of the vehicle and the path offset corresponding to the lane change path are determined. Specifically, after the vehicle successfully leaves the current lane, that is, after the vehicle leaves the lane where the obstacle is located, the current speed of the vehicle needs to be obtained. The vehicle speed is an important factor in determining the obstacle avoidance strategy, because different vehicle speeds may require different obstacle avoidance actions. At the same time, the system obtains the current steering wheel angle. This helps the system understand the current driving direction and posture of the vehicle, so as to more accurately predict and plan the obstacle avoidance path. The system uses the real-time vehicle speed, the real-time steering wheel angle, and the distance value between the obstacle and the vehicle to calculate the third path offset through a complex algorithm or model. This third path offset is intended to enable the vehicle to safely avoid obstacles while maintaining driving stability and controllability, and because the vehicle speed and steering wheel angle may change at any time, the third path offset needs to be continuously updated and adjusted to ensure the effectiveness and accuracy of the obstacle avoidance strategy.

[0075] Exemplarily, after the vehicle leaves the current lane, the distance value between the obstacle and the vehicle is further detected. If the distance value is not greater than the preset safety distance, it is necessary to further obtain the real-time status information of the vehicle, wherein the real-time status information includes the real-time speed and real-time steering wheel angle of the vehicle, etc. Then, the third path offset of the vehicle can be determined based on the real-time speed and real-time steering wheel angle of the vehicle through a corresponding algorithm or model, so that the vehicle can avoid the obstacle according to the third path offset.

[0076] That is to say, after the vehicle leaves the current lane, if it is detected that the obstacle still poses an obstacle to the vehicle's driving, the lane changing path corresponding to when the vehicle and the obstacle are in the same lane and the path offset corresponding to the lane changing path can be determined by the second path offset corresponding to when the vehicle leaves the same lane as the obstacle and the third path offset when the vehicle avoids the obstacle.

[0077] Optionally, in some feasible embodiments, the third path offset and the first path offset in the above embodiment are essentially the same, that is, when the vehicle leaves the same lane as the obstacle, the vehicle and the obstacle are in different lanes, and if the obstacle appears near the adjacent lane, the vehicle will continue to drive in its own lane, but if the distance between the obstacle and the vehicle is too close, the vehicle will further use the first path offset to avoid the obstacle in the adjacent lane.

[0078] Moreover, after the vehicle changes lanes to the adjacent lane, the relative position relationship between the vehicle and the obstacle becomes that the obstacle is located in the adjacent lane of the vehicle, so it is necessary to calculate the safe driving path of the vehicle after avoiding the obstacle, so it is necessary to calculate the third path offset between the vehicle and the obstacle. The detailed process is as described in the above embodiment, and will not be repeated here. Then, the path offset of the vehicle can be determined based on the third path offset and the second path offset.

[0079] In this embodiment, the safe distance between the vehicle and the lane boundary or other vehicles can be calculated in combination with the vehicle body information and lane width, thereby avoiding collisions during lane changes, avoiding collisions between the vehicle and obstacles or other vehicles, and providing the driver with more accurate and real-time driving assistance information, helping the driver to better understand road conditions and obstacle information, and improving driving comfort and convenience.

[0080] Further, based on the above embodiments, please refer to Figure 6 In one of the exemplary embodiments provided in the present application, the specific implementation process of the above vehicle lane changing method may also include steps S610 to S630, which are described in detail as follows:

[0081] Step S610, determining the running state of a target vehicle in an adjacent lane based on the road condition information, the target vehicle including a vehicle to be overtaken in the adjacent lane;

[0082] Step S620, determining a collision probability between the vehicle and a target vehicle based on the running state and the running state of the vehicle;

[0083] Step S630: modifying the vehicle's lane-changing strategy based on the collision probability.

[0084] Specifically, it should be noted that the operating status of the target garage and the operating status of the vehicle include multiple motion parameters of the vehicle, wherein the motion parameters may include direction, speed, posture, etc., and then the collision probability between the two vehicles can be calculated based on the operating status of the vehicle and the motion status of the target vehicle, and then the lane changing strategy of the vehicle can be corrected based on the collision probability, for example: changing the target vehicle, slowing down the acceleration of the vehicle, or correcting the path offset, etc.

[0085] Exemplarily, the system first needs to collect road condition information through sensors (such as radar, camera, laser radar, etc.), including but not limited to the position, speed, acceleration, driving direction, etc. of vehicles in adjacent lanes. Based on this information, the system identifies the "target vehicles" in adjacent lanes that may become the objects of overtaking. These target vehicles need special attention during the lane change process, because their operating status will directly affect the safety of the lane change. The system needs to comprehensively consider the current operating status of the host vehicle (i.e., the vehicle performing the lane change operation) and the target vehicle, including but not limited to the relative position, speed difference, acceleration, change in driving direction, etc. of the two. Through complex algorithms or models, the system can calculate the probability of collision between the host vehicle and the target vehicle in the future. This probability value reflects the safety risk level of the lane change operation. This step is the key to strategy adjustment. According to the evaluation results of the collision probability, the original lane change strategy can be modified. If the collision probability is low, it means that the lane change operation is relatively safe, and the original lane change strategy may be maintained or executed. If the collision probability is high, it means that there is a greater safety risk in the lane change operation, and a series of measures may be taken to reduce the risk, such as delaying the lane change, slowing down, adjusting the lane change direction, etc. In some extreme cases, if the probability of a collision is extremely high, the system may even completely cancel the lane change operation to ensure driving safety.

[0086] In this embodiment, by real-time monitoring of the operating status of the target vehicle (such as speed, acceleration, direction, etc.) and the operating status of the own vehicle, the collision probability between the two can be accurately calculated, so as to timely identify potential collision risks. According to the real-time changes in the collision probability, the system can intelligently adjust the timing of lane changing to ensure that the lane changing operation is performed under safe conditions.

[0087] Further, based on the above embodiments, please refer to Figure 7 In one of the exemplary embodiments provided in the present application, the specific implementation process of the above vehicle lane changing method may further include step S710 and step S720, which are described in detail as follows:

[0088] Step S710, determining a target image recognition model and configuration parameters corresponding to the target image recognition model based on scene information corresponding to the obstacle area;

[0089] Step S720: performing image recognition on the image information through the target image recognition model based on the configuration parameters corresponding to the target image recognition model to determine the boundary information of the obstacle.

[0090] Specifically, the target image recognition model and the configuration parameters corresponding to the target image recognition model can be determined according to the complexity of the scene information corresponding to the obstacle. Then, the target image recognition model can be used to perform image recognition on the image information of the obstacle area according to its corresponding configuration parameters, and then the boundary information of the obstacle can be determined according to the result of image recognition.

[0091] For example, first, scene information related to the obstacle area is collected. This information may include the type of scene (such as indoor, outdoor, traffic scene, etc.), lighting conditions, possible types of obstacles (such as pedestrians, vehicles, buildings, etc.), and other environmental factors that may affect image recognition.

[0092] Based on the collected scene information, select a model from the available image recognition models that best suits the current scenario. For example, for traffic scenarios, a model specialized for vehicle and pedestrian detection may be selected; whereas for indoor scenarios, a model more suitable for detecting furniture and other indoor objects may be selected. After selecting the target image recognition model, its configuration parameters need to be determined based on the model's characteristics and scenario requirements. These parameters may include recognition accuracy, processing speed, recognition range, etc. For example, in scenarios that require a fast response, some accuracy may be sacrificed to increase processing speed. The image information is processed using the configured target image recognition model. This typically involves inputting an image into the model, which identifies obstacles in the image based on the learned features. During the image recognition process, the model outputs boundary information of the obstacle, which may be expressed in pixel coordinates, bounding boxes, or other forms to accurately describe the location and shape of the obstacle.

[0093] Then, based on the obstacle model of deep learning, the model is optimized in combination with navigation information, and reinforcement learning is used to let obstacles learn more effective recognition and detection strategies in specific navigation scenarios. Based on the modeling of obstacles in different scenarios, the algorithm of recognition parameters is adjusted, and a specific recognition type is selected to design the reward function. The reward function is the standard for evaluating the behavior of the intelligent agent. In obstacle recognition, the correct recognition of obstacles and thus safe navigation will receive positive rewards, while the misidentification of obstacles or the behavior that causes potential danger will receive negative rewards. During the training process, a balance is constantly struck between exploring new strategies and using the best known strategies, and finally the optimal recognition strategy is achieved. By selecting appropriate image recognition models and configuration parameters, this method can support the recognition of various types of obstacles, such as vehicles, pedestrians, animals, roadblocks, etc.

[0094] In this embodiment, the appropriate target image recognition model is selected according to the scene information corresponding to the obstacle area, which can ensure that the model has higher recognition accuracy for obstacles in specific scenes. It can adapt to the obstacle recognition needs in different scenes, such as urban roads, highways, rural roads, etc., and has strong versatility and adaptability. By optimizing the target image recognition model and configuration parameters, the processing time of image recognition can be shortened and the recognition efficiency can be improved.

[0095] Further, based on the above embodiments, please refer to Figure 8 In one of the exemplary embodiments provided in the present application, the specific implementation process of the above-mentioned vehicle lane changing method may also include steps S810 to S830, which are described in detail as follows:

[0096] Step S810, determining a target edge detection algorithm based on configuration parameters corresponding to the target image recognition model;

[0097] Step S820, performing edge strength recognition on each pixel in the image information based on the target edge detection algorithm to determine the edge strength value of each pixel relative to adjacent pixels in the image information;

[0098] Step S830: removing non-maximum points in the image information based on the edge strength value of each pixel point to obtain boundary information of obstacles in the image information.

[0099] Specifically, after the obstacle is identified by the target image recognition model, it is necessary to confirm the placement boundary of the obstacle on the lane. However, due to the uncertainty of the placement of the obstacle, such as irregular placement, the boundary of the obstacle needs to be confirmed. In some feasible embodiments, the non-maximum suppression method can be used to enhance the performance of the edge detection algorithm. Among them, non-maximum suppression (NMS) is an image processing technology that is used to enhance the performance of the edge detection algorithm. In edge detection, an edge image is usually generated, which contains all the edges in the image. However, these edges are discontinuous or contain some noise. The role of NMS is to identify and retain the maximum value points in the edge image, while suppressing the non-maximum points, and enhancing the continuity and clarity of the edge by removing the non-maximum points in the edge image. This can reduce noise and make the edge detection results more accurate.

[0100] Exemplarily, an edge detection algorithm is first applied, such as the Canny edge detector. The Canny algorithm applies a Gaussian filter to smooth the image and reduce the impact of noise. Then, NMS is applied to increase the edge in order to generate an edge image of the obstacle. Then, the corresponding edge strength of each pixel in the edge image of the obstacle is detected within its domain. If the edge strength of the current pixel is less than that of any pixel in its neighborhood, the edge strength of the pixel is set to 0 and marked as a non-maximum point. This continues until all pixels are processed. The final edge image only contains non-maximum points. By removing the non-maximum points in these edge images, the maximum points are retained. Therefore, the boundary of the obstacle can be determined based on the remaining maximum points.

[0101] Optionally, in some achievable embodiments, the most suitable edge detection algorithm is selected according to the configuration parameters of the target image recognition model and the characteristics of the image information. These parameters may include the resolution, noise level, contrast, etc. of the image, wherein there are multiple edge detection algorithms, such as Canny edge detection, Sobel operator, Prewitt operator, Roberts operator, etc. Each algorithm has its specific application scenario and advantages and disadvantages. The edge intensity of each pixel in the image information is identified using the selected edge detection algorithm, with the purpose of calculating the edge intensity value of each pixel relative to its adjacent pixel. The edge intensity value reflects the sharpness of the edge at the pixel point, that is, the speed of the change of the pixel values ​​on both sides of the edge. After obtaining the edge intensity value of each pixel point, the purpose of removing the non-maximum point is to retain the local maximum point on the edge, that is, those points that are most likely to be the true position of the edge. By removing the non-maximum point, the redundancy and blur of the edge can be reduced, making the edge clearer and more accurate. The removal of the non-maximum point usually involves gradient calculation of the edge intensity value and retaining the local maximum point in the gradient direction. Then, after the non-maximum point is removed, the remaining pixel points constitute the boundary of the obstacle. These boundary points can be further optimized through subsequent processing steps such as connection and smoothing to obtain more complete and accurate obstacle boundary information.

[0102] In this embodiment, by selecting or adjusting the edge detection algorithm according to the configuration parameters of the target image recognition model, it can be ensured that the algorithm has a higher detection accuracy for the edges of obstacles in specific image information. This targeted edge detection helps to reduce false detections and missed detections and improve the accuracy of edge recognition. By performing edge strength recognition on each pixel in the image information, more detailed edge information can be obtained. This detailed edge strength value helps to more accurately determine the boundaries of obstacles in subsequent processing.

[0103] Fig. 9It is a simplified flowchart of vehicle lane change in an exemplary application scenario. In the application scenario shown in 9, the navigation information and sensor data of the vehicle are obtained, and the current position information of the vehicle is determined based on the navigation information and sensor data; the obstacle area on the current road is predicted based on the position information, and the image information corresponding to the obstacle area is collected; the target image recognition model and the configuration parameters corresponding to the target image recognition model are determined based on the scene information corresponding to the obstacle area; the target edge detection algorithm is determined based on the configuration parameters corresponding to the target image recognition model; the edge strength of each pixel in the image information is identified based on the target edge detection algorithm to determine the edge strength value of each pixel relative to the adjacent pixel in the image information; the non-maximum points in the image information are removed based on the edge strength value of each pixel to obtain the boundary information of the obstacle in the image information. Determine the boundary information of the obstacle based on the image information, and determine the lane where the obstacle is located based on the boundary information; determine the relative position relationship between the lane where the obstacle is located and the vehicle, and if the relative position relationship indicates that the obstacle and the vehicle are in adjacent lanes, obtain the vehicle's state information, the lane line of the adjacent lane, and the distance between the obstacle and the lane line, where the lane line is the lane line on the adjacent lane close to the vehicle; determine the first path offset of the vehicle based on the state information, the lane line, and the distance between the obstacle and the lane line; so that the vehicle can avoid the obstacle in the current lane based on the first offset. If the relative position relationship indicates that the obstacle and the vehicle are in the same lane, obtain the road condition information of the adjacent lane of the vehicle; obtain the vehicle's body information and the lane width of the current lane; determine the second path offset corresponding to the vehicle based on the body information and the lane width; after the vehicle leaves the current lane, if the distance value between the obstacle and the vehicle is not greater than the preset distance threshold, determine the path offset corresponding to the lane change path based on the second path offset and the first path offset. Determine the running state of the target vehicle in the adjacent lane based on the road condition information, the target vehicle includes the vehicle to be overtaken in the adjacent lane; determine the collision probability between the vehicle and the target vehicle based on the running state and the running state of the vehicle; and modify the lane change strategy of the vehicle based on the collision probability. For the detailed implementation process, please refer to the records in the above embodiments, which will not be repeated here.

[0104] Fig.10 is a block diagram of a vehicle lane changing device shown in an exemplary embodiment of the present application. The device can be applied to Figure 1 The implementation environment shown is specifically configured in the intelligent terminal 110. The device may also be applicable to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment applicable to the device.

[0105] like Fig.10As shown, the exemplary vehicle lane changing device 1000 includes: an acquisition module 1010, which is used to acquire navigation information and sensor data of the vehicle, and determine the current position information of the vehicle based on the navigation information and the sensor data; an acquisition module 1020, which is used to predict the obstacle area on the current road based on the position information, and collect image information corresponding to the obstacle area; a determination module 1030, which is used to determine the boundary information of the obstacle based on the image information, and determine the lane where the obstacle is located based on the boundary information; a lane changing module 1040, which is used to determine the relative position relationship between the lane where the obstacle is located and the vehicle, and determine the lane changing strategy of the vehicle based on the relative position relationship.

[0106] According to one aspect of the embodiment of the present application, the lane changing module 1040 is further used to obtain the vehicle status information, the lane line of the adjacent lane, and the distance between the obstacle and the lane line if the relative position relationship indicates that the obstacle and the vehicle are in an adjacent lane, the status information includes the vehicle speed and steering wheel angle, and the lane line is the lane line on the adjacent lane close to the vehicle side; determine the first path offset of the vehicle based on the vehicle speed, steering wheel angle, lane line, and the distance between the obstacle and the lane line, so that the vehicle avoids the obstacle in the current lane based on the first offset. .

[0107] According to one aspect of an embodiment of the present application, the lane changing module 1040 is also used to obtain the vehicle body information and the lane width of the current lane if the relative position relationship indicates that the obstacle and the vehicle are in the same lane; obtain the road condition information of the adjacent lane, the road condition information including the traffic status information and road information of the adjacent lane; determine the preset boundary safety threshold of the vehicle based on the traffic status information and the road information; determine the second path offset of the vehicle based on the preset boundary safety threshold, the vehicle body information and the lane width, so that the vehicle leaves the current lane based on the second path offset.

[0108] According to one aspect of an embodiment of the present application, the lane changing module 1040 is also used to obtain real-time status information of the vehicle after the vehicle leaves the current lane, if the distance value between the obstacle and the vehicle is not greater than a preset distance threshold, the real-time status information includes the real-time vehicle speed and the real-time steering wheel angle; determine a third path offset of the vehicle based on the real-time vehicle speed, the real-time steering wheel angle and the distance value, so that the vehicle avoids the obstacle based on the third path offset; determine the lane changing strategy of the vehicle and the path offset corresponding to the lane changing path based on the second path offset and the third path offset.

[0109] According to one aspect of an embodiment of the present application, the lane changing module 1040 is also used to determine the operating status of a target vehicle in an adjacent lane based on road condition information, the target vehicle including a vehicle to be overtaken in an adjacent lane; determine the collision probability between the vehicle and the target vehicle based on the operating status and the operating status of the vehicle; and correct the lane changing strategy of the vehicle based on the collision probability.

[0110] According to one aspect of an embodiment of the present application, the above-mentioned determination module 1030 is also used to determine the target image recognition model and the configuration parameters corresponding to the target image recognition model based on the scene information corresponding to the obstacle area; and perform image recognition on the image information through the target image recognition model based on the configuration parameters corresponding to the target image recognition model to determine the boundary information of the obstacle.

[0111] According to one aspect of an embodiment of the present application, the above-mentioned determination module 1030 is also used to determine the target edge detection algorithm based on the configuration parameters corresponding to the target image recognition model; perform edge strength recognition on each pixel point in the image information based on the target edge detection algorithm to determine the edge strength value of each pixel point relative to the adjacent pixel points in the image information; remove non-maximum points in the image information based on the edge strength value of each pixel point to obtain the boundary information of the obstacle in the image information.

[0112] It should be noted that the vehicle lane changing device provided in the above embodiment and the vehicle lane changing method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, and will not be repeated here. In actual application, the vehicle lane changing device provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0113] An embodiment of the present application also provides an electronic device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by one or more processors, the electronic device implements the vehicle lane changing method provided in the above-mentioned embodiments.

[0114] Fig.11 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Fig.11 The computer system 1100 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0115] like Fig.11As shown, the computer system 1100 includes a central processing unit (CPU) 1101, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1102 or the program loaded from the storage part 1108 to the random access memory (RAM) 1103, such as executing the method described in the above embodiment. In the RAM 1103, various programs and data required for system operation are also stored. The CPU 1101, the ROM 1102 and the RAM 1103 are connected to each other through the bus 1104. The input / output (I / O) interface 1105 is also connected to the bus 1104.

[0116] The following components are connected to the I / O interface 1105: an input section 1106 including a keyboard, a mouse, etc.; an output section 1107 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. A removable medium 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1110 as needed so that a computer program read therefrom is installed into the storage section 1108 as needed.

[0117] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 1109, and / or installed from a removable medium 1111. When the computer program is executed by a central processing unit (CPU) 1101, various functions defined in the system of the present application are executed.

[0118] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0119] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0120] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0121] Another aspect of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the vehicle lane changing method as described above is implemented. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0122] Another aspect of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the vehicle lane changing method provided in each of the above embodiments.

[0123] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. A person skilled in the art can easily make corresponding changes or modifications based on the main concept and spirit of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection required by the claims.

Claims

1. A vehicle lane changing method, characterized in that: include: Acquire navigation information and sensor data of the vehicle, and determine the location information of the vehicle at the current moment based on the navigation information and the sensor data; Predicting an obstacle area on the current road based on the position information, and collecting image information corresponding to the obstacle area; Determining boundary information of the obstacle based on the image information, and determining a lane where the obstacle is located based on the boundary information; The relative position relationship between the lane where the obstacle is located and the vehicle is determined, and a lane changing strategy of the vehicle is determined based on the relative position relationship.

2. The method according to claim 1, characterized in that The determining the lane changing strategy of the vehicle based on the relative position relationship includes: If the relative position relationship indicates that the obstacle and the vehicle are in adjacent lanes, then obtaining status information of the vehicle, a lane line of the adjacent lane, and a distance between the obstacle and the lane line, wherein the status information includes a speed and a steering wheel angle of the vehicle, and the lane line is a lane line on the adjacent lane close to the vehicle; A first path offset of the vehicle is determined based on the vehicle speed, the steering wheel angle, the lane line, and the distance between the obstacle and the lane line, so that the vehicle avoids the obstacle in the current lane based on the first offset.

3. The method according to claim 1, characterized in that The method further comprises: If the relative position relationship indicates that the obstacle and the vehicle are in the same lane, obtaining body information of the vehicle and a lane width of the current lane; Acquiring traffic condition information of adjacent lanes, wherein the traffic condition information includes traffic status information and road information of adjacent lanes; A preset boundary safety threshold of the vehicle is determined based on the traffic state information and the road information; A second path offset of the vehicle is determined based on the preset boundary safety threshold, the vehicle body information, and the lane width, so that the vehicle leaves the current lane based on the second path offset.

4. The method according to claim 3, characterized in that The method further comprises: After the vehicle leaves the current lane, if the distance between the obstacle and the vehicle is not greater than a preset distance threshold, obtaining real-time status information of the vehicle, the real-time status information including real-time vehicle speed and real-time steering wheel angle; determining a third path offset of the vehicle based on the real-time vehicle speed, the real-time steering wheel angle, and the distance value, so that the vehicle performs obstacle avoidance processing on the obstacle based on the third path offset; A lane changing strategy of the vehicle and a path offset corresponding to the lane changing path are determined based on the second path offset and the third path offset.

5. The method according to claim 3, characterized in that The method further comprises: Determine the running state of the target vehicle on the adjacent lane based on the road condition information, the target vehicle includes a vehicle to be overtaken on the adjacent lane; determining a probability of collision between the vehicle and a target vehicle based on the operating state and the operating state of the vehicle; A lane changing strategy of the vehicle is modified based on the collision probability.

6. The method according to claim 1, characterized in that The method further comprises: Determine a target image recognition model and configuration parameters corresponding to the target image recognition model based on scene information corresponding to the obstacle area; The target image recognition model performs image recognition on the image information based on configuration parameters corresponding to the target image recognition model to determine boundary information of the obstacle.

7. The method according to claim 6, characterized in that The method further comprises: Determining a target edge detection algorithm based on configuration parameters corresponding to the target image recognition model; Performing edge strength identification on each pixel in the image information based on the target edge detection algorithm to determine an edge strength value of each pixel relative to adjacent pixels in the image information; Based on the edge strength value of each pixel point, non-maximum points in the image information are removed to obtain boundary information of obstacles in the image information.

8. A vehicle lane changing device, characterized in that: The device comprises: An acquisition module, used to acquire navigation information and sensor data of the vehicle, and determine the location information of the vehicle at the current moment based on the navigation information and the sensor data; A collection module, used to predict the obstacle area on the current road based on the position information, and collect image information corresponding to the obstacle area; a determination module, configured to determine boundary information of the obstacle based on the image information, and determine a lane where the obstacle is located based on the boundary information; The lane changing module is used to determine the relative position relationship between the lane where the obstacle is located and the vehicle, and determine the lane changing strategy of the vehicle based on the relative position relationship.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the electronic device to implement the vehicle lane changing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Computer-readable instructions are stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the vehicle lane changing method according to any one of claims 1 to 7.

Images