Automatic driving vehicle lane changing method and device, computer device and storage medium

Abstract

The application relates to a lane changing method and device of an autonomous vehicle, a computer device and a storage medium. The method comprises the following steps: acquiring surrounding environment information of the autonomous vehicle, obtaining a safety value of the autonomous vehicle according to the surrounding environment information; acquiring first driving information of the autonomous vehicle at a first time, obtaining a first comfort degree value of passengers according to the first driving information; guiding the autonomous vehicle to drive according to the safety value and a preset driving route, obtaining second driving information at a second time, updating the first comfort degree value according to the second driving information, obtaining a second comfort degree value, and guiding the autonomous vehicle to change lanes. The method can solve the problems of poor passenger comfort degree and untimely lane changing in the lane changing process of the vehicle.

Description

Technical Field

[0001] This invention relates to the field of autonomous vehicle technology, and in particular to an autonomous vehicle lane-changing method, apparatus, computer equipment, and storage medium. Background Technology

[0002] Autonomous vehicles typically change lanes when encountering congestion ahead, referring to pre-planned routes, or in case of emergencies in the lane ahead. However, during lane changes, obstacles such as other vehicles or pedestrians may suddenly appear in the target lane, and different lanes also have different environmental factors such as direction and protection measures. Therefore, with the development of intelligent driving technology, more and more vehicles are equipped with intelligent driving assistance systems to provide environmental information around the vehicle and assist the driver in changing lanes. However, in actual lane changes, the vehicle may suddenly decelerate or stop. Existing intelligent driving assistance systems do not fully consider lane changes and the sudden appearance of obstacles, nor do they adequately consider passenger comfort, which may lead to problems such as poor passenger comfort and untimely lane changes during lane changes. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, device, computer equipment, and storage medium for lane changing of autonomous vehicles to address the aforementioned technical problems and improve the poor lane changing performance of autonomous vehicles.

[0004] On the one hand, a lane-changing method for an autonomous vehicle is provided, the lane-changing method for an autonomous vehicle includes:

[0005] Obtain information about the surrounding environment of the autonomous vehicle, and obtain safety values ​​for the autonomous vehicle based on the surrounding environment information;

[0006] Obtain the first driving information of the autonomous vehicle at a first moment, and obtain the first comfort value of the passenger based on the first driving information;

[0007] The autonomous vehicle is guided to drive according to the safety value and the preset driving route, and the second driving information at the second moment is obtained. The first comfort value is updated according to the second driving information to obtain a second comfort value, so as to guide the autonomous vehicle to change lanes.

[0008] In one embodiment, the step of acquiring surrounding environmental information of the autonomous vehicle and obtaining a safety value of the autonomous vehicle based on the surrounding environmental information includes:

[0009] Obtain the surrounding environment information, including information about the lane ahead and information about surrounding obstacles;

[0010] The safety value is obtained by fusing the information of the lane ahead with the information of the surrounding obstacles.

[0011] In one embodiment, the step of fusing the forward lane information with the surrounding obstacle information to obtain the safety value includes:

[0012] Obtain the information about the lane ahead, including the lane guardrail, and obtain the information about surrounding obstacles, including surrounding vehicles and pedestrians;

[0013] Determine whether there is a lane protection barrier in front of the lane in which the autonomous vehicle is traveling. If yes, obtain the first lane protection value; otherwise, obtain the second lane protection value.

[0014] Based on the surrounding obstacle information, the moving speed and current position of the surrounding vehicles and pedestrians are obtained, and obstacle avoidance values ​​are obtained based on the moving speed and current position;

[0015] The first lane protection value, the second lane protection value, and the obstacle avoidance value are weighted and processed to obtain the safety value.

[0016] In one embodiment, the step of obtaining the first driving information of the autonomous vehicle at a first moment and obtaining the first comfort value of the passenger based on the first driving information includes:

[0017] Acquire the first driving information, including the first driving speed, first acceleration, and first driving direction of the autonomous vehicle at the first moment;

[0018] The first comfort value is obtained by fusing the first driving speed, the first acceleration, the first driving direction, and the safety value.

[0019] In one embodiment, the step of guiding the autonomous vehicle to drive according to the safety value and a preset driving route, and obtaining second driving information at a second moment, includes:

[0020] Determine whether the safety value is greater than the safety threshold; if so, perform lane change or deceleration on the autonomous vehicle; if not, the autonomous vehicle continues to drive normally.

[0021] The autonomous vehicle performs lane-changing processing based on the corresponding position coordinates of the driving route.

[0022] Obtain the second driving information of the autonomous vehicle at the second time point.

[0023] In one embodiment, the step of updating the first comfort value based on the second driving information to obtain a second comfort value, in order to guide the autonomous vehicle to change lanes, includes:

[0024] The second driving speed, second acceleration, and second driving direction of the autonomous vehicle are obtained based on the second driving information.

[0025] The second driving speed, the second acceleration, the second driving direction, and the safety value are fused together to update the first comfort value and obtain the second comfort value.

[0026] Determine whether the second comfort value is greater than the comfort threshold; if so, the autonomous vehicle performs a lane change; if not, the autonomous vehicle continues to drive normally.

[0027] In one embodiment, the step of obtaining the safety values ​​of the autonomous vehicle further includes:

[0028] Obtain the surrounding environment information, including lane type and violation type;

[0029] Determine whether the lane in which the autonomous vehicle is permitted to drive is consistent with the lane type. If yes, obtain first permitted driving information; otherwise, obtain first prohibited driving information.

[0030] Determine whether the driving status of the autonomous vehicle is consistent with the type of violation. If yes, obtain the second prohibition driving information; if no, obtain the second permission driving information.

[0031] The first permitted driving information, the first prohibited driving information, the second permitted driving information, and the second prohibited driving information are fused together to obtain the safety value.

[0032] On the other hand, an autonomous vehicle lane-changing device is provided, the autonomous vehicle lane-changing device comprising:

[0033] The first acquisition module is used to acquire the surrounding environment information of the autonomous vehicle and obtain the safety value of the autonomous vehicle based on the surrounding environment information.

[0034] The second acquisition module is used to acquire the first driving information of the autonomous vehicle at a first moment, and to obtain the first comfort value of the passenger based on the first driving information.

[0035] The lane change guidance module is used to guide the autonomous vehicle to drive according to the safety value and the preset driving route, and to obtain the second driving information at the second moment. The first comfort value is updated according to the second driving information to obtain the second comfort value, so as to guide the autonomous vehicle to change lanes.

[0036] In another aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0037] Obtain information about the surrounding environment of the autonomous vehicle, and obtain safety values ​​for the autonomous vehicle based on the surrounding environment information;

[0038] Obtain the first driving information of the autonomous vehicle at a first moment, and obtain the first comfort value of the passenger based on the first driving information;

[0039] The autonomous vehicle is guided to drive according to the safety value and the preset driving route, and the second driving information at the second moment is obtained. The first comfort value is updated according to the second driving information to obtain a second comfort value, so as to guide the autonomous vehicle to change lanes.

[0040] In another aspect, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0041] Obtain information about the surrounding environment of the autonomous vehicle, and obtain safety values ​​for the autonomous vehicle based on the surrounding environment information;

[0042] Obtain the first driving information of the autonomous vehicle at a first moment, and obtain the first comfort value of the passenger based on the first driving information;

[0043] The autonomous vehicle is guided to drive according to the safety value and the preset driving route, and the second driving information at the second moment is obtained. The first comfort value is updated according to the second driving information to obtain a second comfort value, so as to guide the autonomous vehicle to change lanes.

[0044] The aforementioned method, apparatus, computer equipment, and storage medium for lane changing of an autonomous vehicle acquires information about the surrounding environment of the autonomous vehicle and obtains a safety value for the autonomous vehicle based on the surrounding environment information; acquires first driving information of the autonomous vehicle at a first moment and obtains a first comfort value for the passenger based on the first driving information; guides the autonomous vehicle to drive according to the safety value and a preset driving route, and obtains second driving information at a second moment, updates the first comfort value based on the second driving information, and obtains a second comfort value to guide the autonomous vehicle to change lanes. This can solve problems such as poor passenger comfort and untimely lane changing during vehicle lane changing. Attached Figure Description

[0045] Figure 1 This is an application environment diagram of an autonomous vehicle lane-changing method in one embodiment;

[0046] Figure 2 This is a flowchart illustrating a lane-changing method for an autonomous vehicle in one embodiment.

[0047] Figure 3 This is a schematic diagram of the process for obtaining safety values ​​for an autonomous vehicle in one embodiment;

[0048] Figure 4 This is a schematic diagram of the process of fusing information about the lane ahead with information about surrounding obstacles in one embodiment;

[0049] Figure 5 This is a schematic diagram of the process for obtaining a first comfort level value in one embodiment;

[0050] Figure 6 This is a schematic diagram of the process for obtaining second driving information in one embodiment;

[0051] Figure 7 This is a schematic diagram of the process of guiding an autonomous vehicle to change lanes in one embodiment;

[0052] Figure 8 This is a flowchart illustrating the process of obtaining a safety value in one embodiment;

[0053] Figure 9 This is a structural block diagram of the lane-changing device for an autonomous vehicle in another embodiment;

[0054] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] This application provides a vehicle lane change planning method that can be applied to, for example... Figure 1 The application environment shown is illustrated. Terminal 102 communicates with server 104 via a network. For example, the lane-changing method for autonomous vehicles provided in this application can be applied to scenarios where autonomous vehicles are performing lane-changing operations during operation. Autonomous vehicles typically change lanes when the lane ahead is congested, when referring to a pre-planned route, or when an emergency occurs in the lane ahead. However, during lane changes, obstacles such as other vehicles or pedestrians may suddenly appear in the target lane, and each lane also has different environmental factors such as direction and protection measures. Therefore, with the development of intelligent driving technology, more and more vehicles are equipped with intelligent driving assistance systems to provide environmental information around the vehicle to assist the driver in lane changes. However, in actual lane-changing processes, vehicles may suddenly decelerate or stop. Existing intelligent driving assistance systems do not fully consider lane changes and the sudden appearance of obstacles, nor do they fully consider passenger comfort, which may lead to problems such as poor passenger comfort and untimely lane changes during lane changes. Therefore, this application obtains the surrounding environment information of the autonomous vehicle, and obtains the safety value of the autonomous vehicle based on the surrounding environment information; obtains the first driving information of the autonomous vehicle at a first moment, and obtains the first comfort value of the passenger based on the first driving information; guides the autonomous vehicle to drive according to the safety value and a preset driving route, and obtains the second driving information at a second moment, updates the first comfort value based on the second driving information, and obtains the second comfort value to guide the autonomous vehicle to change lanes, which can solve problems such as poor passenger comfort and untimely lane changes. In some implementation processes, the surrounding environment information of the autonomous vehicle can be collected by the terminal 102, and the surrounding environment information can be uploaded to the server 104 for data analysis and calculation to obtain a lane change guidance strategy. Then, the server 104 sends the lane change guidance strategy to the terminal 102. The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, portable wearable devices, or sub-servers, and the server 104 can be implemented using a separate server, a server cluster composed of multiple servers, or a cloud computing platform.

[0057] In one embodiment, such as Figure 2 As shown, a lane-changing method for an autonomous vehicle is provided, including the following steps:

[0058] S1: Obtain the surrounding environment information of the autonomous vehicle, and obtain the safety value of the autonomous vehicle based on the surrounding environment information;

[0059] S2: Obtain the first driving information of the autonomous vehicle at the first moment, and obtain the first comfort value of the passenger based on the first driving information;

[0060] S3: Guide the autonomous vehicle to drive according to the safety value and the preset driving route, and obtain the second driving information at the second moment. Update the first comfort value according to the second driving information to obtain the second comfort value, so as to guide the autonomous vehicle to change lanes.

[0061] The above steps can improve problems such as unreasonable lane-changing timing and high time costs for autonomous vehicles.

[0062] In step S1, for example, the surrounding environment information of the autonomous vehicle is obtained, and the safety value of the autonomous vehicle is obtained based on the surrounding environment information. For example, the surrounding environment information can be obtained by acquiring information about other vehicles, lanes, and obstacles at any angle around the vehicle through the vehicle-mounted camera. For example, video information from the front, rear, left, and right of the autonomous vehicle (current vehicle) can be acquired. Then, the video is segmented and analyzed according to a preset period. In some implementations, the preset period can be 300 milliseconds or 500 milliseconds. The specific value is not limited here. The implementer can adjust the value of the period according to the real-time requirements of image analysis. In some implementations, the surrounding environment information of the current vehicle can also be photographed and stored directly according to the preset period. After acquiring information about the surrounding environment, the vehicle can obtain information about the front and rear of its current lane, as well as information about the front and rear of nearby lanes. This information includes whether there are other vehicles, pedestrians, or construction obstacles in the lane, as well as the number of vehicles, lane type, and lane shape. By fusing this information, the safety value of the autonomous vehicle is obtained, which serves as the data basis for subsequent lane-changing guidance. For example, when there are many other vehicles and pedestrians around the autonomous vehicle, the safety value can be considered low. In other implementations, when there are many curves in the lane, the safety value of the autonomous vehicle can also be considered low.

[0063] After obtaining the safety values, to further evaluate the comfort of passengers in the autonomous vehicle, step S2, exemplarily, involves obtaining the first driving information of the autonomous vehicle at a first moment, and obtaining the first comfort value of the passengers based on the first driving information. For example, the driving speed of the autonomous vehicle at the current moment (the first moment) can be obtained. In some implementations, this can be directly read from the current driving information of the vehicle (e.g., the dashboard), or the current driving speed of the autonomous vehicle can be obtained through a positioning system or positioning software. It should be noted that when the autonomous vehicle is traveling at a high speed, the comfort of the passengers may be affected to some extent. Therefore, in this implementation, a threshold can be set for the driving speed. For example, if the driving speed threshold is T1 and the current driving speed is V1, then the mathematical expression of the first comfort value S1 can be:

[0064]

[0065] It can be observed that when V1 is less than T1, S1 is less than 0, while when V1 is greater than T1, S1 is greater than 0, and the value of S1 increases with the increase of V1. Therefore, in some implementations, passenger comfort can be evaluated based on the value of S1. The larger the first comfort value S1, the lower the passenger comfort. In some implementations, the driving speed threshold T1 can be set to 40 km / h or 70 km / h, where km / h represents the speed unit: kilometers per hour. In specific implementations, implementers can modify and set the speed threshold according to factors such as lane type and travel time; the specific value of the speed threshold is not limited here.

[0066] After obtaining the safety value and the first comfort value, the first comfort value can be updated to obtain the second comfort value. In step S3, for example, the autonomous vehicle is guided to drive according to the safety value and the preset driving route, and the second driving information at the second moment is obtained. The first comfort value is updated according to the second driving information to obtain the second comfort value, so as to guide the autonomous vehicle to change lanes. For example, since the autonomous vehicle usually sets the destination position in advance before driving and obtains the drivable route from the current starting position to the destination position, there may be multiple preset driving routes. However, these driving routes are mainly generated based on static information and do not fully consider the safety hazards that may occur during driving, that is, they do not consider the safety value of the autonomous vehicle. Therefore, in this implementation process, the autonomous vehicle can be guided according to a preset driving route, and can also be guided according to safety values. That is, when the safety value is low, the autonomous vehicle may need to change lanes to avoid dangerous factors ahead. Then, the second driving information at the second moment is obtained. That is, after guiding the autonomous vehicle according to the safety value and driving route, the autonomous vehicle will travel a distance to reach another position at another moment (the second moment), which corresponds to the second driving information: such as the driving speed at the second moment. Then, the first comfort level is updated according to the driving speed at the second moment to obtain the second comfort level. Finally, the autonomous vehicle is guided to change lanes based on the value of the second comfort level.

[0067] In some embodiments, such as Figure 3 As shown, the steps for obtaining information about the surrounding environment of an autonomous vehicle and obtaining a safety value for the autonomous vehicle based on the surrounding environment information include:

[0068] S11: Obtain the surrounding environment information, including information about the lane ahead and information about surrounding obstacles;

[0069] S12: The safety value is obtained by fusing the information of the lane ahead with the information of the surrounding obstacles.

[0070] like Figure 3As shown, in steps S11 to S12, the surrounding environment information includes the information of the lane ahead and the information of surrounding obstacles. A safety value is obtained based on the information of the lane ahead and the information of surrounding obstacles. For example, the information of the lane where the autonomous vehicle is located and the adjacent lane is obtained, such as the type of the lane and the shape of the lane. Specifically, if the current autonomous vehicle is a large truck or van, and the lane ahead prohibits this type of vehicle from passing, it is identified that the type of the lane ahead is inconsistent with the type of the autonomous vehicle. At this time, the value C1 corresponding to the lane type can be set to 0. When the type of the lane ahead is consistent with the type of the autonomous vehicle, the value C1 corresponding to the lane type can be set to 1. Furthermore, the shape of the lane can also be identified. When the lane ahead is a straight lane within a certain distance (e.g., 100 meters), it can be considered that the autonomous vehicle will have relatively high safety if it drives in the straight lane. When there is a turning situation within a certain distance ahead, it can be considered that the autonomous vehicle has relatively low safety. Therefore, the curvature coefficient C2 of the lane within a certain distance can be obtained. The larger the value of C2, the lower the safety is considered, that is, the lower the safety value. Furthermore, the surrounding obstacle information can include other vehicles around the autonomous vehicle. When other vehicles are identified around the autonomous vehicle, the autonomous vehicle is considered to have a low safety value and needs to change lanes, slow down, or stop. Therefore, the safety value can be obtained by fusing the information of the lane ahead with the surrounding obstacle information. For the fusion method, in some implementation processes, weights W1 and W2 can be set for the lane type value and the lane curvature coefficient respectively. The value of C1 can be a discrete value of 0 or 1. When the type of the lane ahead is consistent with the type of the current autonomous vehicle, the value of C1 can be set to 1. If the type of the lane ahead is inconsistent with the type of the current autonomous vehicle, the value of C1 can be set to 0. The value of C2 can be a continuous value between [0, 1]. When C2 equals 0, it means that the lane ahead is a straight lane. When C2 equals 1, it means that there are multiple lanes with large turning angles ahead. For values ​​between 0 and 1, they can be evaluated based on the turning angle and the number of turns. For example, when the turning angle is less than 30 degrees and there is only 1 turn, the value of C2 can be set to 0.3. When the turning angle is between 30 degrees and 60 degrees and there are 2 turns, the value of C2 can be set to 0.7. In the specific implementation process, the mapping relationship between the value of C2 and the number and angle of turning lanes can be adjusted according to the autonomous vehicle's ability to handle turning lanes. No specific numerical limitation is made here.

[0071] like Figure 4 As shown, in some embodiments, the step of fusing the forward lane information with the surrounding obstacle information to obtain the safety value includes:

[0072] S21: Obtain the information of the lane ahead, including the lane protection barrier, and obtain the information of surrounding obstacles, including surrounding vehicles and surrounding pedestrians;

[0073] S22: Determine whether there is a lane protection barrier in front of the lane in which the autonomous vehicle is traveling. If yes, obtain the first lane protection value; if no, obtain the second lane protection value.

[0074] S23: Based on the surrounding obstacle information, obtain the moving speed and current position of the surrounding vehicles and pedestrians, and obtain the obstacle avoidance value based on the moving speed and current position;

[0075] S24: The first lane protection value, the second lane protection value, and the obstacle avoidance value are weighted and processed to obtain the safety value.

[0076] like Figure 4 As shown, in steps S21 to S24, the information on the lane ahead includes a lane guardrail, and the information on surrounding obstacles includes surrounding vehicles and pedestrians. A safety value is obtained based on the lane protection value and the obstacle avoidance value. For example, it can be determined whether there is a guardrail in the lane ahead. If there is a guardrail, the autonomous vehicle is considered to be in a relatively safe environment, and a first lane protection value can be obtained. If there is no guardrail, the autonomous vehicle is considered to be in a relatively dangerous environment, and a second protection value can be obtained. Furthermore, surrounding obstacle information can include: other vehicles, pedestrians, maintenance obstacles, potholes, and other obstacles around the autonomous vehicle. When relevant obstacle information is identified around the autonomous vehicle, its safety score is considered low, requiring lane changing, deceleration, or stopping. Therefore, by obtaining the movement speed and current position of surrounding vehicles and pedestrians, their trajectories can be estimated, and obstacle avoidance scores can be evaluated based on these trajectories. Specifically, when the trajectories of surrounding vehicles and pedestrians highly overlap with the autonomous vehicle's trajectory, and their speed is high or they are prone to sudden changes in direction, the obstacle avoidance score of the autonomous vehicle is considered low, requiring advance lane change guidance to prevent subsequent collisions with obstacles. Preferably, different weights can be assigned to the first lane protection score, the second lane protection score, and the obstacle avoidance score. A weighted sum of these scores yields a safety score, providing a data basis for subsequent assessments of scenario safety.

[0077] To obtain the first comfort level value, such as Figure 5As shown, the steps of obtaining the first driving information of the autonomous vehicle at a first moment and obtaining the first comfort value of the passenger based on the first driving information include:

[0078] S31: Obtain the first driving information including the first driving speed, first acceleration, and first driving direction of the autonomous vehicle at the first moment;

[0079] S32: The first driving speed, the first acceleration, the first driving direction, and the safety value are fused together to obtain the first comfort value.

[0080] like Figure 5 As shown, in steps S31 to S32, it is exemplarily explained that the first driving speed, first acceleration, and first driving direction are obtained and fused to obtain the first comfort value. For example, assuming the current time is the first time, the first driving speed, first acceleration, and first driving direction of the autonomous vehicle are obtained through the driving information of the autonomous vehicle. When the values ​​of the first driving speed and first acceleration are large, and the deviation of the first driving direction from the lane is large, it is considered that the passenger's comfort will be affected to a certain extent. Therefore, in this implementation, thresholds can be set for the driving speed, driving acceleration, and deviation of the direction. For example, let the driving speed threshold be T1, the driving acceleration threshold be T2, and the deviation threshold be T3. Let the first driving speed be V1, the first driving acceleration be V2, and the deviation of the direction be V3, and set different weights for the driving speed, driving acceleration, and deviation of the direction: w1, w2, and w3, where w1, w2, and w3 are all continuous values ​​in the interval [0, 1]. Then the mathematical expression of the first comfort value S1 can be:

[0081]

[0082] It can be observed that different values ​​of V1, V2, and V3 will change the value of S1. Therefore, in some implementation processes, passenger comfort can be assessed based on the value of S1. The larger the initial comfort value S1, the lower the passenger comfort. In some implementation processes, the driving speed threshold T1 can be set to 30 km / h or 80 km / h, where km / h represents the speed unit: kilometers per hour; the acceleration threshold T2 can be set to 2 m / s². 2 The directional deviation threshold T3 can be set to 30 degrees. In practice, the implementer can modify and set the driving speed threshold, acceleration threshold, and directional deviation threshold according to factors such as lane type and driving time; specific values ​​are not limited here. Preferably, a first comfort value can also be obtained based on a safety value. For example, the mathematical expression of the first comfort value S1 can be:

[0083]

[0084] Where Safe represents the safety value, and g(·) represents the safety value evaluation function. When the safety value is low, the output of the safety value evaluation function is 1, and when the safety value is high, the output of the safety value evaluation function is 0. In this way, the safety value can be given priority. When an autonomous vehicle is in a dangerous scenario, it will seriously affect the comfort of passengers.

[0085] like Figure 6 As shown, the steps of guiding the autonomous vehicle to drive according to the safety value and the preset driving route, and obtaining the second driving information at the second moment, include:

[0086] S41: Determine whether the safety value is greater than the safety threshold; if yes, then change lanes or decelerate the autonomous vehicle; if no, then the autonomous vehicle continues to drive normally.

[0087] S42: Perform lane change processing on the autonomous vehicle according to the corresponding position coordinates of the driving route;

[0088] S43: Obtain the second driving information of the autonomous vehicle at the second moment.

[0089] like Figure 6 As shown, in steps S41 to S43, it is exemplarily illustrated that the lane change of the autonomous vehicle is guided based on the comparison result of the safety value and the safety threshold, as well as the driving route. For example, the mathematical expression of the safety value evaluation function can be:

[0090]

[0091] Here, Safe represents the safety value, and T0 represents the safety threshold. When the safety value is greater than or equal to the safety threshold, the vehicle needs to change lanes or slow down. When the safety value is less than the safety threshold, the autonomous vehicle can continue to drive normally according to its current lane and direction. Preferably, the vehicle changes lanes at the locations where lane changes are required according to the pre-set driving route, and after changing lanes or driving for a period of time, it enters a second moment. At this time, the second driving information of the second moment is obtained to provide a data basis for further evaluation of passenger comfort.

[0092] like Figure 7 As shown, the step of updating the first comfort value based on the second driving information to obtain a second comfort value, in order to guide the autonomous vehicle to change lanes, includes:

[0093] S51: Obtain the second driving speed, second acceleration, and second driving direction of the autonomous vehicle based on the second driving information;

[0094] S52: The second driving speed, the second acceleration, the second driving direction and the safety value are fused together to update the first comfort value and obtain the second comfort value;

[0095] S53: Determine whether the second comfort value is greater than the comfort threshold; if yes, then the autonomous vehicle performs a lane change; if no, the autonomous vehicle drives normally.

[0096] like Figure 7 As shown, in steps S51 to S53, for example, a second driving speed, a second acceleration, and a second driving direction are acquired and fused with a safety value to obtain a second comfort value. This second comfort value is then compared with a comfort threshold to guide the autonomous vehicle's lane-changing. For instance, at a second moment, the second driving speed, second acceleration, and second driving direction of the autonomous vehicle are acquired, along with obstacle information and lane protection information around the autonomous vehicle to obtain a safety value at that moment. Then, the second driving speed, second acceleration, second driving direction, and the safety value are weighted and summed to obtain an updated second comfort value. When the second comfort value is greater than or equal to the comfort threshold, the autonomous vehicle performs a lane-changing operation; when the second comfort value is less than the comfort threshold, the autonomous vehicle proceeds with the driving.

[0097] like Figure 8 As shown, the steps for obtaining the safety values ​​of the autonomous vehicle further include:

[0098] S61: Obtain the surrounding environment information, including lane type and violation type;

[0099] S62: Determine whether the lane that the autonomous vehicle is allowed to drive in is consistent with the lane type. If yes, obtain the first permitted driving information; if no, obtain the first prohibited driving information.

[0100] S63: Determine whether the driving status of the autonomous vehicle is consistent with the type of violation. If yes, obtain the second prohibition driving information; if no, obtain the second permission driving information.

[0101] S64: The first permitted driving information, the first prohibited driving information, the second permitted driving information, and the second prohibited driving information are fused together to obtain the safety value.

[0102] like Figure 8As shown, in steps S61 to S64, it is exemplarily explained that the system determines whether the lane in which the autonomous vehicle is traveling is consistent with the type of the lane that the autonomous vehicle is allowed to travel in. Based on the determination result, for example, the surrounding environment information may include: lane type and violation type. It should be noted that the lane type includes small vehicles and large vehicles, and the violation type includes: being in a prohibited passage time, one-way street, prohibited turning, etc. Then, it determines whether the lane that the autonomous vehicle is allowed to travel in is consistent with the lane type. For example, when the autonomous vehicle is a small vehicle, the selected driving lane allows small vehicles to pass, and the first permitted driving information is obtained; when the autonomous vehicle is a large vehicle, and the selected driving lane prohibits large vehicles from passing, the first prohibited driving information is obtained; furthermore, if the autonomous vehicle is in a prohibited passage time, or mistakenly enters a one-way street, or turns in a prohibited turning place, the second prohibited driving information is obtained; otherwise, the second permitted driving information is obtained. Preferably, the first permitted driving information A1, the first prohibited driving information F1, the second permitted driving information A2, and the second prohibited driving information F2 are fused to obtain a safety value Safe. The fusion method may include setting A1, F1, A2, and F2 to discrete values ​​of 0 or 1. Only when A1 and A2 are 1 and F1 and F2 are 0 can a higher safety value Safe be obtained.

[0103] It should be understood that, although Figures 2 to 8 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figures 2 to 8 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0104] In one embodiment, such as Figure 9 As shown, an autonomous vehicle lane-changing device is provided, the autonomous vehicle lane-changing device comprising:

[0105] The first acquisition module is used to acquire the surrounding environment information of the autonomous vehicle and obtain the safety value of the autonomous vehicle based on the surrounding environment information.

[0106] The second acquisition module is used to acquire the first driving information of the autonomous vehicle at a first moment, and to obtain the first comfort value of the passenger based on the first driving information.

[0107] The lane change guidance module is used to guide the autonomous vehicle to drive according to the safety value and the preset driving route, and to obtain the second driving information at the second moment. The first comfort value is updated according to the second driving information to obtain the second comfort value, so as to guide the autonomous vehicle to change lanes.

[0108] In the first acquisition module, it is exemplarily described that the surrounding environment information of the autonomous vehicle is acquired, and the safety value of the autonomous vehicle is obtained based on the surrounding environment information. For example, the surrounding environment information can be obtained by acquiring information about other vehicles, lanes, and obstacles at any angle around the vehicle through the vehicle-mounted camera. For example, video information from the front, rear, left, and right of the autonomous vehicle (current vehicle) can be acquired. Then, the video is segmented and analyzed according to a preset period. In some implementations, the preset period can be 200 milliseconds or 600 milliseconds. No specific value is limited here. The implementer can adjust the period value according to the real-time requirements of image analysis. In some implementations, the surrounding environment information of the current vehicle can also be photographed and stored directly according to the preset period. After acquiring information about the surrounding environment, the vehicle can obtain information about the front and rear of its current lane, as well as information about the front and rear of nearby lanes. This information includes whether there are other vehicles, pedestrians, or construction obstacles in the lane, as well as the number of vehicles, lane type, and lane shape. By fusing this information, the safety value of the autonomous vehicle is obtained, which serves as the data basis for subsequent lane-changing guidance. For example, when there are many other vehicles and pedestrians around the autonomous vehicle, the safety value can be considered low. In other implementations, when there are many curves in the lane, the safety value of the autonomous vehicle can also be considered low.

[0109] In the second acquisition module, it is exemplarily explained that the first driving information of the autonomous vehicle at a first moment is acquired, and the first comfort value of the passengers is obtained based on the first driving information. For example, the driving speed of the autonomous vehicle at the current moment (first moment) can be acquired. In some implementations, this can be directly read from the current driving information of the vehicle (e.g., the dashboard), or the current driving speed of the autonomous vehicle can be acquired through a positioning system or positioning software. It should be noted that when the autonomous vehicle is traveling at a high speed, the comfort of the passengers on board may be affected to a certain extent. Therefore, in this implementation, a threshold can be set for the driving speed. For example, if the driving speed threshold is T1 and the current driving speed is V1, then the mathematical expression of the first comfort value S1 can be:

[0110]

[0111] It can be observed that when V1 is less than T1, S1 is less than 0, while when V1 is greater than T1, S1 is greater than 0, and the value of S1 increases with the increase of V1. Therefore, in some implementations, passenger comfort can be evaluated based on the value of S1. The larger the first comfort value S1, the lower the passenger comfort. In some implementations, the driving speed threshold T1 can be set to 30 km / h or 50 km / h, where km / h represents the speed unit: kilometers per hour. In specific implementations, implementers can modify and set the speed threshold according to factors such as lane type and travel time; the specific value of the speed threshold is not limited here.

[0112] In the lane change guidance module, it is exemplarily described that the autonomous vehicle is guided to drive according to a safety value and a preset driving route, and second driving information at a second moment is obtained. The first comfort value is updated according to the second driving information to obtain a second comfort value, so as to guide the autonomous vehicle to change lanes. For example, since the autonomous vehicle usually sets the destination position in advance and obtains the drivable route from the current starting position to the destination position before driving, there may be multiple preset driving routes. However, these driving routes are mainly generated based on static information and do not fully consider the safety hazards that may occur during driving, that is, they do not consider the safety value of the autonomous vehicle. Therefore, in this implementation, the autonomous vehicle can be guided to change lanes according to the preset driving route. The driving route guides the autonomous vehicle's movement and can also be guided based on safety values. That is, when the safety value is low, the autonomous vehicle may need to change lanes to avoid potential hazards ahead. Then, second driving information is obtained at the second moment. After guiding the autonomous vehicle's movement based on the safety value and the driving route, the autonomous vehicle will travel a certain distance to reach a different position at another moment (the second moment), which corresponds to the second driving information: such as the driving speed at the second moment. Then, the first comfort level is updated based on the driving speed at the second moment to obtain the second comfort level. Finally, the autonomous vehicle is guided on whether to change lanes based on the value of the second comfort level.

[0113] The aforementioned device can be applied to scenarios where autonomous vehicles are changing lanes during operation. A first acquisition module acquires information about the surrounding environment of the autonomous vehicle and obtains a safety value based on this information. A second acquisition module acquires first driving information of the autonomous vehicle at a first moment and obtains a first passenger comfort value based on this information. A lane-change guidance module guides the autonomous vehicle based on the safety value and a preset driving route, and obtains second driving information at a second moment. The first comfort value is updated based on the second driving information to obtain a second comfort value, thus guiding the autonomous vehicle to change lanes. This addresses issues such as poor passenger comfort and untimely lane changes.

[0114] Specific limitations regarding lane-changing devices for autonomous vehicles can be found in the limitations on lane-changing methods for autonomous vehicles described above, and will not be repeated here. Each module in the aforementioned lane-changing device for autonomous vehicles can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0115] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores data acquired and calculated during lane-changing by the autonomous vehicle. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements an autonomous vehicle lane-changing method.

[0116] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0117] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0118] Obtain information about the surrounding environment of the autonomous vehicle, and obtain safety values ​​for the autonomous vehicle based on the surrounding environment information;

[0119] Obtain the first driving information of the autonomous vehicle at a first moment, and obtain the first comfort value of the passenger based on the first driving information;

[0120] The autonomous vehicle is guided to drive according to the safety value and the preset driving route, and the second driving information at the second moment is obtained. The first comfort value is updated according to the second driving information to obtain a second comfort value, so as to guide the autonomous vehicle to change lanes.

[0121] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0122] Obtain information about the surrounding environment of the autonomous vehicle, and obtain safety values ​​for the autonomous vehicle based on the surrounding environment information;

[0123] Obtain the first driving information of the autonomous vehicle at a first moment, and obtain the first comfort value of the passenger based on the first driving information;

[0124] The autonomous vehicle is guided to drive according to the safety value and the preset driving route, and the second driving information at the second moment is obtained. The first comfort value is updated according to the second driving information to obtain a second comfort value, so as to guide the autonomous vehicle to change lanes.

[0125] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0126] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0127] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A lane-changing method for an autonomous vehicle, characterized in that, include: Obtain information about the surrounding environment of the autonomous vehicle, and obtain safety values ​​for the autonomous vehicle based on the surrounding environment information; Obtain the first driving information of the autonomous vehicle at a first moment, and obtain the first comfort value of the passenger based on the first driving information; The autonomous vehicle is guided to drive according to the safety value and the preset driving route, and second driving information at a second moment is obtained. The second driving speed, second acceleration, and second driving direction of the autonomous vehicle are obtained according to the second driving information. The second driving speed, second acceleration, and second driving direction are fused with the safety value to update the first comfort value and obtain a second comfort value. It is determined whether the second comfort value is greater than the comfort threshold. If it is, the autonomous vehicle performs a lane change. If not, the autonomous vehicle drives normally.

2. The lane-changing method for an automated vehicle according to claim 1, characterized in that, The steps of acquiring information about the surrounding environment of an autonomous vehicle and obtaining a safety value for the autonomous vehicle based on the surrounding environment information include: Obtain the surrounding environment information, including information about the lane ahead and information about surrounding obstacles; The safety value is obtained by fusing the information of the lane ahead with the information of the surrounding obstacles.

3. The lane-changing method for autonomous vehicles according to claim 2, characterized in that, The step of fusing the forward lane information with the surrounding obstacle information to obtain the safety value includes: Obtain the information about the lane ahead, including the lane guardrail, and obtain the information about surrounding obstacles, including surrounding vehicles and pedestrians; Determine whether there is a lane protection barrier in front of the lane in which the autonomous vehicle is traveling. If yes, obtain the first lane protection value; otherwise, obtain the second lane protection value. Based on the surrounding obstacle information, the moving speed and current position of the surrounding vehicles and pedestrians are obtained, and obstacle avoidance values ​​are obtained based on the moving speed and current position; The first lane protection value, the second lane protection value, and the obstacle avoidance value are weighted and processed to obtain the safety value.

4. The lane-changing method for an automated vehicle according to claim 1, characterized in that, The steps of obtaining the first driving information of the autonomous vehicle at a first moment and obtaining the first comfort value of the passenger based on the first driving information include: Acquire the first driving information, including the first driving speed, first acceleration, and first driving direction of the autonomous vehicle at the first moment; The first comfort value is obtained by fusing the first driving speed, the first acceleration, the first driving direction, and the safety value.

5. The lane-changing method for an automated vehicle according to claim 1, characterized in that, The steps of guiding the autonomous vehicle to drive according to the safety value and the preset driving route, and obtaining the second driving information at the second moment, include: determining whether the safety value is greater than the safety threshold; if so, then performing lane change processing or deceleration processing on the autonomous vehicle; if not, then the autonomous vehicle drives normally. The autonomous vehicle performs lane-changing processing based on the corresponding position coordinates of the driving route. Obtain the second driving information of the autonomous vehicle at the second time point.

6. The lane-changing method for an automated vehicle according to claim 1, characterized in that, The steps for obtaining the safety values ​​of the autonomous vehicle also include: Obtain the surrounding environment information, including lane type and violation type; Determine whether the lane in which the autonomous vehicle is permitted to drive is consistent with the lane type. If yes, obtain first permitted driving information; otherwise, obtain first prohibited driving information. Determine whether the driving status of the autonomous vehicle is consistent with the type of violation. If yes, obtain the second prohibition driving information; if no, obtain the second permission driving information. The first permitted driving information, the first prohibited driving information, the second permitted driving information, and the second prohibited driving information are fused together to obtain the safety value.

7. A lane-changing device for an autonomous vehicle, characterized in that, include: The first acquisition module is used to acquire the surrounding environment information of the autonomous vehicle and obtain the safety value of the autonomous vehicle based on the surrounding environment information. The second acquisition module is used to acquire the first driving information of the autonomous vehicle at a first moment, and to obtain the first comfort value of the passenger based on the first driving information. The lane change guidance module is used to guide the autonomous vehicle to drive according to the safety value and the preset driving route, and obtain the second driving information at the second moment. Based on the second driving information, it obtains the second driving speed, second acceleration, and second driving direction of the autonomous vehicle. It then fuses the second driving speed, second acceleration, and second driving direction with the safety value to update the first comfort value and obtain a second comfort value. It then determines whether the second comfort value is greater than a comfort threshold. If so, it performs a lane change for the autonomous vehicle; otherwise, it drives normally.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the lane-changing method for an autonomous vehicle according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the lane-changing method for an autonomous vehicle according to any one of claims 1 to 6.

Images