CN115303275A - A vehicle lane change planning method, device, computer equipment and storage medium - Google Patents

Abstract

The present application relates to a vehicle lane change planning method, device, computer equipment and storage medium. The method includes: acquiring the environmental image information of the vehicle, and obtaining the nearby lane information of the vehicle according to the environmental image information; The first steady-state speed and the second steady-state speed are obtained by a driving speed and a second driving speed, wherein the first steady-state speed is the predicted driving speed of the vehicle in the current lane, and the second steady-state speed is the prediction of the vehicle in the nearby lane Driving speed; determine whether the second steady state speed is greater than the first steady state speed;

Description

A vehicle lane change planning method, device, computer equipment and storage medium

technical field

The present invention relates to the technical field of automatic driving vehicles, in particular to a vehicle lane change planning method, device, computer equipment and storage medium.

Background technique

During the driving process of the vehicle, the driver usually changes lanes because the road ahead is blocked or his destination changes. With the development of intelligent driving technology, more and more vehicles are equipped with intelligent driving assistance systems, which provide environmental information around the vehicle to assist the driver in changing lanes. However, the existing intelligent driving assistance systems/methods can only function when the driver actually changes lanes, and cannot inform the driver in advance when the lane change should be performed and evaluate the time cost of the lane change. Especially for self-driving vehicles, it will also lead to problems such as unreasonable timing of vehicle lane changes and high time costs.

Contents of the invention

Based on this, it is necessary to address the above technical problems and provide a vehicle lane change planning method, device, computer equipment and storage medium to improve the problem of poor timing of lane change during vehicle driving.

In one aspect, a vehicle lane change planning method is provided, the vehicle lane change planning method comprising:

Obtaining the environmental image information of the vehicle, and obtaining the nearby lane information of the vehicle according to the environmental image information;

Obtaining a first traveling speed of a vehicle directly in front of the vehicle and a second traveling speed of a vehicle diagonally ahead of the vehicle according to the nearby lane information, and obtaining a second traveling speed according to the first traveling speed and the second traveling speed A steady-state speed and a second steady-state speed, wherein the first steady-state speed is the predicted speed of the vehicle in the current lane, and the second steady-state speed is the predicted speed of the vehicle in a nearby lane ;

Judging whether the second steady-state speed is greater than the first steady-state speed, and if so, performing lane-changing processing on the vehicle.

In one of the embodiments, the environment image information of the vehicle is obtained, and the step of obtaining the nearby lane information of the vehicle according to the environment image information includes:

Acquiring a first environmental image corresponding to the first moment, and obtaining first position information of the nearby vehicle and first lane type information of the nearby lane according to the first environmental image;

Obtain a second environment image corresponding to the second moment, and obtain second position information of the nearby vehicle and second lane type information of the nearby lane according to the second environment image;

The nearby lane information includes: the first location information, the first lane type information, the second location information, and the second lane type information.

In one of the embodiments, the step of obtaining the first driving speed of the vehicle directly in front of the vehicle and the second driving speed of the vehicle diagonally ahead of the vehicle according to the information of the nearby lanes includes:

According to the first position information and the second position information, the forward traveling speeds of a plurality of the vehicles directly ahead are obtained, and the first traveling speed is obtained according to the plurality of forward traveling speeds, wherein the forward traveling speeds The vehicle in front belongs to the same lane as the vehicle and is in front of the driving direction of the vehicle;

According to the first position information, the second position information, the first lane type information, and the second lane information, the oblique traveling speeds of a plurality of vehicles in front obliquely are obtained, and according to the plurality of oblique directions The driving speed obtains the second driving speed, wherein the obliquely preceding vehicle belongs to a different lane from the vehicle and is in front of the driving direction of the vehicle.

In one of the embodiments, according to the first driving speed and the second driving speed, the step of obtaining the first steady-state speed and the second steady-state speed includes:

Traversing the plurality of first driving speeds corresponding to the sampling time, and obtaining a first intermediate steady-state speed according to a preset first weight value, the mathematical expression of the first intermediate steady-state speed is:

V1 _m (t)＝w1*V1 _d (t)+(1-w1)V1 _m (t-1)

Wherein, V1 _m (t) represents the first intermediate steady-state speed, w1 represents the first weight value, t represents the corresponding moment within the sampling time, and V1 _d represents the first driving speed;

According to the first intermediate steady-state speed and a preset second weight value, traverse the plurality of first intermediate steady-state speeds corresponding to the sampling time to obtain the first steady-state speed, and the second steady-state speed The mathematical expression of a steady-state speed is:

V1 _a (t)＝w2*V1 _m (t)+(1-w2)V1 _a (t-1)

Wherein, V1 _a (t) represents the first steady-state velocity, and w2 represents the second weight value;

Traversing the plurality of second driving speeds corresponding to the sampling time, and obtaining a second intermediate steady-state speed according to the first weight value, the mathematical expression of the second intermediate steady-state speed is:

V2 _m (t)＝w1*V2 _d (t)+(1-w1)*V2 _m (t-1)

Wherein, V2 _m (t) represents the second intermediate steady-state speed, w1 represents the first weight value, t represents the corresponding moment within the sampling time, and V2 _d represents the second driving speed;

According to the second intermediate steady-state speed and the second weight value, traverse the plurality of second intermediate steady-state speeds corresponding to the sampling time to obtain the second steady-state speed, the second The mathematical expression of the steady-state speed is:

V2 _a (t)＝w2*V2 _m (t)+(1-w2)*V2 _a (t-1)

Wherein, V2 _a (t) represents the second steady-state speed, and w2 represents the second weight value.

In one of the embodiments, the steps after obtaining the nearby lane information of the vehicle further include:

Obtaining obstacle information of the nearby lane according to the nearby lane information, wherein the obstacle information includes: the size of the obstacle, the distance between the obstacle and the vehicle;

Obtaining a first drivable width of the vehicle in the current lane and a second drivable width of the nearby lane according to the obstacle information;

judging whether the first driving width is greater than the width of the vehicle; if yes, the vehicle is running normally; if not, judging whether the second driving width is greater than the width of the vehicle, and if Perform lane change processing, if not, perform deceleration processing on the vehicle.

In one of the embodiments, the steps after obtaining the nearby lane information of the vehicle further include:

Obtaining the drivable lane type corresponding to the vehicle;

Obtaining the lane type of the current lane outside the preset sampling distance;

Judging whether the drivable lane type is consistent with the lane type of the current lane; if yes, the vehicle runs normally; if not, performs lane change processing on the vehicle.

In one of the embodiments, the steps after obtaining the nearby lane information of the vehicle further include:

Acquiring the driving destination of the vehicle, and obtaining a preset driving route of the vehicle according to the driving destination;

According to the preset driving route and the nearby lane information, it is judged whether the corresponding driving lane of the vehicle outside the preset sampling distance is consistent with the current lane; if yes, the vehicle is running normally; if not, then Perform lane change processing on the vehicle.

In another aspect, a vehicle lane change planning device is provided, the vehicle lane change planning device comprising:

The first acquisition module is used to acquire the environmental image information of the vehicle, and obtain the nearby lane information of the vehicle according to the environmental image information;

The second acquisition module is used to obtain the first driving speed of the vehicle directly in front of the vehicle and the second driving speed of the vehicle obliquely ahead of the vehicle according to the information of the nearby lanes, according to the first driving speed and the The second driving speed is to obtain a first steady-state speed and a second steady-state speed, wherein the first steady-state speed is the predicted driving speed of the vehicle in the current lane, and the second steady-state speed is the predicted speed of the vehicle in the current lane. Predicted driving speed in nearby lanes;

A judging module, configured to judge whether the second steady-state speed is greater than the first steady-state speed, and if so, perform lane change processing on the vehicle.

In another aspect, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor implements the following steps when executing the computer program:

Obtaining the environmental image information of the vehicle, and obtaining the nearby lane information of the vehicle according to the environmental image information;

Obtaining a first traveling speed of a vehicle directly in front of the vehicle and a second traveling speed of a vehicle diagonally ahead of the vehicle according to the nearby lane information, and obtaining a second traveling speed according to the first traveling speed and the second traveling speed A steady-state speed and a second steady-state speed, wherein the first steady-state speed is the predicted speed of the vehicle in the current lane, and the second steady-state speed is the predicted speed of the vehicle in a nearby lane ;

Judging whether the second steady-state speed is greater than the first steady-state speed, and if so, performing lane-changing processing on the vehicle.

In yet another aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

Obtaining the environmental image information of the vehicle, and obtaining the nearby lane information of the vehicle according to the environmental image information;

Obtaining a first traveling speed of a vehicle directly in front of the vehicle and a second traveling speed of a vehicle diagonally ahead of the vehicle according to the nearby lane information, and obtaining a second traveling speed according to the first traveling speed and the second traveling speed A steady-state speed and a second steady-state speed, wherein the first steady-state speed is the predicted speed of the vehicle in the current lane, and the second steady-state speed is the predicted speed of the vehicle in a nearby lane ;

Judging whether the second steady-state speed is greater than the first steady-state speed, and if so, performing lane-changing processing on the vehicle.

According to the above-mentioned vehicle lane change planning method, device, computer equipment and storage medium, the information of the nearby lanes of the vehicle is obtained according to the environmental image information; the first driving speed of the vehicle directly in front of the vehicle and the The second running speed of the vehicle obliquely in front of the vehicle, according to the first running speed and the second running speed, obtain the first steady-state speed and the second steady-state speed; judge whether the second steady-state speed is greater than the first steady-state speed If it is the state speed, then the vehicle will change lanes, so as to solve the problems of unreasonable timing and high time cost of automatic driving vehicles.

Description of drawings

Fig. 1 is an application environment diagram of a vehicle lane change planning method in an embodiment;

Fig. 2 is a schematic flow chart of a vehicle lane change planning method in an embodiment;

Fig. 3 is a schematic flow chart of obtaining road information ahead in an embodiment;

Fig. 4 is a schematic flow chart of obtaining the first traveling speed and the second traveling speed in one embodiment;

Fig. 5 is a schematic flow chart of obtaining the first steady-state speed and the second steady-state speed in one embodiment;

Fig. 6 is a schematic flow diagram after obtaining nearby lane information in an embodiment;

Fig. 7 is a schematic flow chart after obtaining nearby lane information in another embodiment;

Fig. 8 is a schematic flow diagram after obtaining nearby lane information in another embodiment;

Fig. 9 is a structural block diagram of a vehicle lane change planning device in an embodiment;

Figure 10 is a diagram of the internal structure of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

A vehicle lane change planning method provided in this application can be applied to the application environment shown in FIG. 1 . Wherein, the terminal 102 communicates with the server 104 through the network. For example, a vehicle lane change planning method provided in the present application can be applied to a scenario in which lane changes are planned during driving of an autonomous vehicle. During the driving process of the vehicle, the driver usually changes lanes because the road ahead is blocked or his destination changes. With the development of intelligent driving technology, more and more vehicles are equipped with intelligent driving assistance systems, which provide environmental information around the vehicle to assist the driver in changing lanes. However, the existing intelligent driving assistance systems/methods can only function when the driver actually changes lanes, and cannot inform the driver in advance when the lane change should be performed and evaluate the time cost of the lane change. Especially for self-driving vehicles, it will also lead to problems such as unreasonable timing of vehicle lane changes and high time costs. Therefore, the present application acquires the environment image information of the vehicle, obtains the nearby lane information of the vehicle according to the environment image information; obtains the first driving speed of the vehicle directly in front of the vehicle and the second driving speed of the vehicle obliquely ahead of the vehicle according to the nearby lane information, Obtain the first steady-state speed and the second steady-state speed according to the first traveling speed and the second traveling speed; judge whether the second steady-state speed is greater than the first steady-state speed; The timing of lane change is unreasonable and the time cost is high. In some implementations, the terminal 102 can collect the environmental image information of the self-driving vehicle, and upload the environmental image information to the server 104 for data analysis and calculation to obtain the lane change strategy, and then the server 104 sends the lane change strategy to the terminal 102 . Among them, the terminal 102 can be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, portable wearable devices or sub-servers, and the server 104 can be an independent server or a server cluster composed of multiple servers or cloud computing platform to achieve.

In one embodiment, as shown in Figure 2, a vehicle lane change planning method is provided, comprising the following steps:

S1: Obtain the environmental image information of the vehicle, and obtain the nearby lane information of the vehicle according to the environmental image information;

S2: Obtain a first traveling speed of a vehicle directly in front of the vehicle and a second traveling speed of a vehicle diagonally ahead of the vehicle according to the nearby lane information, and according to the first traveling speed and the second traveling speed, obtaining a first steady-state speed and a second steady-state speed, wherein the first steady-state speed is the predicted speed of the vehicle in the current lane, and the second steady-state speed is the predicted speed of the vehicle in a nearby lane Driving speed;

S3: Determine whether the second steady-state speed is greater than the first steady-state speed, and if so, perform lane-changing processing on the vehicle.

Through the above steps, problems such as unreasonable timing of lane change and high time cost of autonomous driving vehicles can be improved.

Before the lane change planning for the autonomous vehicle, it is necessary to obtain the environmental image information near the vehicle. In step S1, it is exemplarily explained that the environmental image information of the vehicle is obtained, and the nearby lane information of the vehicle is obtained according to the environmental image information. For example, you can Obtain other vehicle information, lane information, and obstacle information at any angle around the vehicle through the on-board camera as environmental image information, such as obtaining video information of the front, rear, left, and right of the self-driving vehicle (current vehicle), and then follow the preset The preset period intercepts and analyzes the video in segments. In some implementation processes, the preset period can be 200 milliseconds or 500 milliseconds. The specific value is not limited here. The implementer can analyze the image according to the Real-time performance requires periodical value adjustment, and it should be noted that nearby lane information can include not only the nearby lanes of the current vehicle, but also the lane to which the current vehicle belongs. In some implementations, it can also directly follow the preset period Take photos and store the environmental image information of the current vehicle. After the environmental image information is obtained, the front and rear information of the current vehicle's lane and the front and rear information of the nearby lanes can be obtained from it. The front and rear information also includes whether there are other vehicles on the lane, the number of vehicles, and the type of lane , the shape of the lane and other information, the above information is fused to obtain the information of the nearby lanes, which is used as the data basis for the subsequent lane change planning and decision-making of the vehicle. In other implementation processes, the driving lane of the vehicle can also be obtained through the map nearby lane information.

After obtaining the information of the nearby lanes, in order to further evaluate the time cost of the vehicle changing lanes, in step S2, it is exemplarily explained that according to the information of the nearby lanes, the first driving speed of the vehicle directly in front of the vehicle and the oblique front of the vehicle are obtained. The second driving speed of the vehicle. According to the first driving speed and the second driving speed, the first steady state speed and the second steady state speed can be obtained. For example, it can be obtained that it belongs to the same lane as the current vehicle and is directly in front of the current vehicle. The driving speed of the vehicle is used as the first driving speed, and the driving speed of the oblique front vehicle that belongs to a different lane from the current vehicle and is in front of the current vehicle is obtained as the second driving speed; since the nearby lane information includes the number of nearby lanes, the number of other vehicles, The number and the position of other vehicles in the nearby lanes, so the relative position between other vehicles (vehicles directly ahead, vehicles obliquely ahead) and the current vehicle can be obtained according to the information of the nearby lanes. It should be noted that there may be more than one other vehicle , so the first driving speed and the second driving speed can actually be used as a set of driving speeds of multiple other vehicles. According to the first driving speed and the second driving speed, the average driving speed or the maximum driving speed that the current vehicle can reach within a period of time if the current vehicle continues to drive in the current lane can be predicted, that is, the first steady-state speed. The second driving speed of other vehicles in the lane can predict the average driving speed or the maximum driving speed that can be achieved within a period of time if the current vehicle changes lanes and drives in a nearby lane, that is, the second steady-state speed.

After the first steady-state speed and the second steady-state speed are obtained, the two can be compared, and the lane change planning decision is obtained according to the comparison result. In step S3, it is exemplarily explained that it is judged whether the second steady-state speed is greater than If it is the first steady-state speed, then the vehicle is changed lane. For example, when the first steady-state speed is 50km/h and the second steady-state speed is 60km/h, it can be considered that if the vehicle continues to drive in the current lane The speed that can be reached is 50km/h, which is less than the speed that can be reached by driving in the nearby lane after the vehicle changes lanes. The faster driving speed can be achieved, thus saving the driving time. However, if the first steady-state speed is 60km/h and the second steady-state speed is 50km/h, then it is considered that the current vehicle can reach a faster driving speed while continuing to drive in the current lane, wherein, km/h Representative speed unit: kilometers per hour. In this way, the current lane of the autonomous vehicle and the driving information of other vehicles in the nearby lanes can be analyzed before the actual lane change, so as to obtain the decision of lane change planning in advance, save the time and cost of the vehicle to change lanes, and avoid back and forth Repeat lane change.

In some embodiments, as shown in FIG. 3 , the environmental image information of the vehicle is acquired, and the step of obtaining the nearby lane information of the vehicle according to the environmental image information includes:

S11: Obtain a first environment image corresponding to the first moment, and obtain first position information of the nearby vehicle and first lane type information of the nearby lane according to the first environment image;

S12: Obtain a second environment image corresponding to the second moment, and obtain second position information of the nearby vehicle and second lane type information of the nearby lane according to the second environment image;

S13: The nearby lane information includes: the first location information, the first lane type information, the second location information, and the second lane type information.

As shown in Figure 3, in steps S11 to S13, it is exemplarily explained that the first environment image and the second environment image at the first moment and the second moment are obtained respectively, for example, the current moment is taken as the first moment, and the The first environment image at the first moment, wherein the first environment image can be a photo taken in real time by a camera, or an image of a certain frame in a real-time video, including the front and rear lanes of the lane where the current vehicle is located Information, vehicle information, obstacle information, according to the above information, the first position information (position coordinates) of other vehicles and the first lane type information of nearby lanes (such as truck lanes, bus lanes, emergency lanes, through lanes, etc.) can be obtained. etc.), then add 1 second or 2 seconds as the second moment on the basis of the first moment, obtain the second environment image corresponding to the second moment, and obtain the updated second position information of nearby vehicles according to the second environment image and the second lane type information of the nearby lanes. It should be noted that the first environment image and the second environment image only represent the surrounding environment images that the current vehicle can collect at different times, and because the current vehicle is in a driving state, it can The collected ambient environment images will change accordingly. This application does not limit the specific values of the first moment and the second moment. The implementer can set them according to their own real-time requirements for image acquisition. Preferably, the first moment and the second moment A moment is not just a single time point, but may be a collection of multiple time points. For example, the implementer may use more than two times as the first moment or the second moment.

As shown in FIG. 4 , in some embodiments, the step of obtaining the first traveling speed of the vehicle directly in front of the vehicle and the second traveling speed of the vehicle diagonally ahead of the vehicle according to the nearby lane information includes:

S21: Obtain the forward traveling speeds of a plurality of vehicles directly in front according to the first position information and the second position information, and obtain the first traveling speed according to the plurality of forward traveling speeds, wherein the The vehicle directly ahead belongs to the same lane as the vehicle and is in front of the driving direction of the vehicle;

S22: According to the first location information, the second location information, the first lane type information, and the second lane information, obtain the oblique traveling speeds of a plurality of vehicles obliquely ahead, and according to the plurality of The second traveling speed is obtained by obliquely traveling speed, wherein the obliquely leading vehicle and the vehicle belong to different lanes and are in front of the traveling direction of the vehicle.

As shown in FIG. 4, in steps S21 to S22, it is exemplarily explained that the forward traveling speeds of a plurality of vehicles directly ahead are obtained according to the first position information and the second position information, and the first vehicle speed is obtained according to the plurality of forward traveling speeds. a driving speed, obtaining the oblique traveling speeds of a plurality of diagonally ahead vehicles according to the first position information, the second position information, the first lane type information, and the second lane information, and obtaining the second traveling speed according to the plurality of oblique traveling speeds, For example, according to the first position information corresponding to the first moment and the second position information at the second moment, the position information of the vehicle directly in front of the current vehicle can be obtained, and multi-frame detection of multiple position information can obtain the vehicle directly ahead What needs to be explained here is that the first moment and the second moment are just descriptive words representing different moments, and there is no limit to the number of moments to be obtained, so two (two frames) can be obtained Multi-frame fusion analysis of the above forward driving speed can obtain the first driving speed of the vehicle directly ahead. It should be noted that the vehicle directly ahead and the current vehicle belong to the same lane, and the vehicle directly ahead is in front of the driving direction of the current vehicle ; and for the second driving speed, the oblique running speed of the oblique front vehicle can be obtained according to the first position information, the second position information, the first lane type, and the second lane type, and a plurality of oblique running speeds can be obtained. Multi-frame detection can obtain the second driving speed. It should be noted that the diagonally ahead vehicle and the current vehicle belong to different lanes, and the diagonally ahead vehicle is in front of the current vehicle's driving direction; The perception module on the system uses historical multi-frame information to calculate the driving speed of other vehicles, that is, the first driving speed of the vehicle directly ahead and the second driving speed of the vehicle obliquely ahead.

In order to obtain the first steady-state speed and the second steady-state speed, as shown in FIG. 5 , according to the first driving speed and the second driving speed, the step of obtaining the first steady-state speed and the second steady-state speed includes :

S31: Traversing the multiple first driving speeds corresponding to the sampling time, and obtaining a first intermediate steady-state speed according to a preset first weight value, the mathematical expression of the first intermediate steady-state speed is:

V1 _m (t)＝w1*V1 _d (t)+(1-w1)*V1 _m (t-1)

Wherein, V1 _m (t) represents the first intermediate steady-state speed, w1 represents the first weight value, t represents the corresponding moment within the sampling time, and V1 _d represents the first driving speed;

S32: According to the first intermediate steady-state speed and the preset second weight value, iterate over the plurality of first intermediate steady-state speeds corresponding to the sampling time to obtain the first steady-state speed, so The mathematical expression of the first steady-state speed is:

V1 _a (t)＝w2*V1 _m (t)+(1-w2)*V1 _a (t-1)

Wherein, V1 _a (t) represents the first steady-state velocity, and w2 represents the second weight value;

S33: Traversing the plurality of second driving speeds corresponding to the sampling time, and obtaining a second intermediate steady-state speed according to the first weight value, the mathematical expression of the second intermediate steady-state speed is:

V2 _m (t)＝w1*V2 _d (t)+(1-w1)*V2 _m (t-1)

Wherein, V2 _m (t) represents the second intermediate steady-state speed, w1 represents the first weight value, t represents the corresponding moment within the sampling time, and V2 _d represents the second driving speed;

S34: According to the second intermediate steady-state speed and the second weight value, traverse the plurality of second intermediate steady-state speeds corresponding to the sampling time to obtain the second steady-state speed, the The mathematical expression of the second steady-state speed is:

V2 _a (t)＝w2*V2 _m (t)+(1-w2)*V2 _a (t-1)

Wherein, V2 _a (t) represents the second steady-state speed, and w2 represents the second weight value.

As shown in FIG. 5, in step S31, it is exemplarily explained that the multiple first driving speeds corresponding to the sampling time are traversed, and the first intermediate steady-state speed is obtained according to the preset first weight value, for example, by Time t is a sequence, starting from t=1 to obtain the first intermediate steady-state speed, in some implementation processes, the first weight w1 can be set to 0.1, and the value range of t (sampling time) can be 2 seconds, 10 seconds , the value of V1 _m (0) is 0 at the initial moment, and then traverses from t=1 to iteratively update the value of the first intermediate steady-state speed.

As shown in Figure 5, in step S32, it is exemplarily explained that according to the first intermediate steady-state speed and the preset second weight value, a plurality of first intermediate steady-state speeds corresponding to the sampling time are traversed to obtain the first intermediate steady-state speed A steady-state speed, for example, taking time t as a sequence, starting to obtain the first steady-state speed from t=1, in some implementation processes, the first weight w2 can be set to 0.01, and the value range of t (sampling time) It can be 2 seconds or 10 seconds. At the initial moment, the value of V1 _a (0) is 0, and then traverses from t=1 to iteratively update the value of the first steady-state speed. In this way, the first steady-state speed can be obtained.

As shown in FIG. 5 , in step S33, it is exemplarily explained that the multiple second driving speeds corresponding to the sampling time are traversed, and the second intermediate steady-state speed is obtained according to the preset first weight value, for example, by Time t is a sequence, starting from t=1 to obtain the second intermediate steady-state speed, in some implementations, the first weight w1 can be set to 0.1, and the value range of t (sampling time) can be 2 seconds, 10 seconds , the value of V1 _m (0) is 0 at the initial moment, and then traverses from t=1 to iteratively update the value of the intermediate steady-state speed.

As shown in FIG. 5, in step S34, it is exemplarily explained that according to the second intermediate steady-state speed and the preset second weight value, a plurality of second intermediate steady-state speeds corresponding to the sampling time are traversed to obtain the second intermediate steady-state speed The two-stable speed, for example, takes time t as a sequence, and starts to obtain the second steady-state speed from t=1. In some implementations, the first weight w2 can be set to 0.01, and the value range of t (sampling time) It can be 2 seconds or 10 seconds. At the initial moment, the value of V2 _a (0) is 0, and then traverses from t=1 to iteratively update the value of the second steady-state speed. In this way, the second steady-state speed can be obtained, which is convenient for comparing the second steady-state speed with the first steady-state speed in the subsequent process, and reasonably considers and reduces the time cost of the vehicle changing lanes.

In some implementation processes, for self-driving vehicles with large body sizes such as trucks, it is also necessary to check whether the lane space within a certain distance in front of the target lane allows the self-driving vehicle to pass, wherein the target lane includes the current lane and nearby Lane.

As shown in Figure 6, the steps after obtaining the nearby lane information of the vehicle also include:

S41: Obtain obstacle information of the nearby lane according to the nearby lane information, wherein the obstacle information includes: the size of the obstacle, the distance between the obstacle and the vehicle;

S42: Obtain the first drivable width of the vehicle in the current lane and the second drivable width of the nearby lane according to the obstacle information;

S43: Judging whether the first driving width is larger than the width of the vehicle; if yes, the vehicle is running normally; if not, judging whether the second driving width is larger than the width of the vehicle, if yes, then If the above vehicle performs lane change processing, if not, then performs deceleration processing on the vehicle.

As shown in FIG. 6, in steps S41 to S43, it is exemplarily explained that obtaining obstacle information of nearby lanes and judging whether the current vehicle can avoid obstacles, for example, there may be accidents, construction, slow vehicles ahead of the current lane In this scenario, the current vehicle needs to slow down, stop, change lanes, etc., and the obstacle occupies part of the lane position, so it is necessary to identify the type and size of the obstacle , the distance between the obstacle and the current vehicle. At the same time, it should be noted that the obstacle may exist in front of the current lane or in front of nearby lanes. Therefore, it is necessary to obtain the first drivable width of the current vehicle in the current lane and The second drivable width of the nearby lanes, and then judge whether the first drivable width is greater than the width required for normal driving of the vehicle, if so, the current vehicle is running normally in the current lane to avoid obstacles; if not, then judge whether the second drivable width is If the width is greater than the required width for normal driving of the vehicle, if so, the current vehicle will be changed lanes, if not, the current vehicle will be forced to decelerate until it stops.

As shown in Figure 7, the steps after obtaining the nearby lane information of the vehicle also include:

S51: Obtain the drivable lane type corresponding to the vehicle;

S52: Obtain the lane type of the current lane outside the preset sampling distance;

S53: Determine whether the drivable lane type is consistent with the lane type of the current lane; if yes, the vehicle runs normally; if not, perform lane change processing on the vehicle.

As shown in FIG. 7, in steps S51 to S53, it is exemplarily explained that it is determined whether to perform lane change processing on the current vehicle according to the lane type in front of the current vehicle. For example, the lane ahead of the current vehicle may not belong to the current vehicle. The type of lane that is allowed to pass. For example, for a truck-type self-driving vehicle, the front lane may not be a truck lane or the front lane may not allow trucks to enter during the current driving time period. Identify the lane type of the current vehicle, that is, set the sampling distance, which can be set to 50 meters or 100 meters. After obtaining the lane type of the current lane outside the sampling distance, combined with the drivable lane type corresponding to the current vehicle, determine whether the two are consistent , if they are consistent, the current vehicle is driving normally; if they are inconsistent, it is necessary to identify other nearby lanes and perform lane change processing on the current vehicle, for example, execute a lane change decision to change lanes to the right lane. In this way, reasonable It can accurately identify the obstacle information ahead and obtain the lane change decision in advance.

As shown in Figure 8, the steps after obtaining the nearby lane information of the vehicle also include:

S61: Obtain the driving destination of the vehicle, and obtain a preset driving route of the vehicle according to the driving destination;

S62: According to the preset driving route and the nearby lane information, determine whether the corresponding driving lane of the vehicle outside the preset sampling distance is consistent with the current lane; if yes, the vehicle is driving normally; if not , then perform lane change processing on the vehicle.

As shown in FIG. 8, in steps S61 to S62, it is exemplarily explained that according to the preset driving route and nearby lane information, it is judged whether the corresponding driving lane of the vehicle outside the preset sampling distance is consistent with the current lane, for example, After the destination is determined or the destination is changed, there may be multiple options for the driving route. If the current vehicle needs to rely on the lower right ramp or enter a certain toll gate after driving a certain distance, it is necessary to plan the lane change in advance , to prevent lane changing in time, at this time, it is necessary to judge whether the corresponding driving lane outside the sampling distance is consistent with the current lane according to the driving path and nearby lane information. If it is consistent, the current vehicle is driving normally; The current vehicle performs lane change processing. In this way, the lane change strategy can be obtained in a timely manner in the scene where an early lane change is required due to route reasons, so as to avoid errors in the actual driving route of the current vehicle.

In some implementation processes, it is also possible to obtain the current wheel congestion in the lanes around the vehicle through interconnection with the server, cloud platform, and cloud, and plan ahead for lane changes in advance for congested road scenarios.

It should be understood that although the various steps in the flow charts of FIG. 2 to FIG. 8 are shown sequentially as indicated by the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in FIGS. 2 to 8 may include a plurality of sub-steps or stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. These sub-steps or The execution order of the stages is not necessarily performed sequentially, but may be executed alternately or alternately with at least a part of other steps or substeps of other steps or stages.

In one embodiment, as shown in FIG. 9 , a vehicle lane change planning device is provided, and the vehicle lane change planning device includes:

The first acquisition module is used to acquire the environmental image information of the vehicle, and obtain the nearby lane information of the vehicle according to the environmental image information;

The second acquisition module acquires the first driving speed of the vehicle, obtains the second driving speed of nearby vehicles of the vehicle according to the nearby lane information, and obtains according to the first driving speed and the second driving speed A first steady-state speed and a second steady-state speed, wherein the first steady-state speed is the predicted driving speed of the vehicle in the current lane, and the second steady-state speed is the predicted driving speed of the vehicle in a nearby lane speed;

A judging module, configured to judge whether the second steady-state speed is greater than the first steady-state speed, and if so, perform lane change processing on the vehicle.

In the first acquisition module, it is exemplarily explained that the environmental image information of the vehicle is acquired, and the nearby lane information of the vehicle is obtained according to the environmental image information. For example, other vehicle information, lane information, obstacle Object information is used as environmental image information, such as obtaining the video information of the front, rear, left, and right of the self-driving vehicle (current vehicle), and then segmenting and analyzing the video according to the preset cycle. In some implementation processes , the preset period can be 300 milliseconds or 600 milliseconds, and the specific value is not limited here. The implementer can adjust the period value according to the real-time requirements of image analysis, and it should be noted that nearby lanes The information can include not only the nearby lanes of the current vehicle, but also the lane to which the current vehicle belongs. In some implementations, the environmental image information of the current vehicle can be directly photographed and stored according to a preset cycle. After the environmental image information is obtained, the front and rear information of the current vehicle's lane and the front and rear information of the nearby lanes can be obtained from it. The front and rear information also includes whether there are other vehicles on the lane, the number of vehicles, and the type of lane , the shape of the lane and other information, the above information is fused to obtain the information of the nearby lanes, which is used as the data basis for the subsequent lane change planning and decision-making of the vehicle. In other implementation processes, the driving lane of the vehicle can also be obtained through the map nearby lane information.

In the second acquiring module, it is exemplarily explained that the first traveling speed of the vehicle directly in front of the vehicle and the second traveling speed of the vehicle obliquely in front of the vehicle are obtained according to the information of the nearby lanes, and according to the first traveling speed and the second traveling speed, To obtain the first steady-state speed and the second steady-state speed, for example, the speed of the vehicle in front that belongs to the same lane as the current vehicle and is in front of the current vehicle can be obtained as the first speed, and the speed of the vehicle belonging to a different lane from the current vehicle and The driving speed of the oblique front vehicle in front of the current vehicle is taken as the second driving speed; since the nearby lane information includes the number of nearby lanes, the number of other vehicles, and the positions of other vehicles in the nearby lanes, according to the nearby lane information It is possible to obtain the relative position between other vehicles (vehicle directly ahead, vehicle obliquely ahead) and the current vehicle. It should be noted that there may be more than one other vehicle, so the first driving speed and the second driving speed can actually serve as multiple other vehicles. A collection of vehicle speeds. According to the first driving speed and the second driving speed, the average driving speed or the maximum driving speed that the current vehicle can reach within a period of time if the current vehicle continues to drive in the current lane can be predicted, that is, the first steady-state speed. The second driving speed of other vehicles in the lane can predict the average driving speed or the maximum driving speed that can be achieved within a period of time if the current vehicle changes lanes and drives in a nearby lane, that is, the second steady-state speed.

In the judging module, it is exemplarily explained that it is judged whether the second steady-state speed is greater than the first steady-state speed, and if so, the vehicle is changed lane. For example, when the first steady-state speed is 40km/h, the second steady-state The state speed is 60km/h. It can be considered that if the vehicle continues to drive in the current lane, the speed that can be achieved is 40km/h, which is less than the speed that the vehicle can achieve in the nearby lane after changing lanes, which is 60km/h. When the overall route of the destination is determined, the vehicle can be changed lanes, so that the vehicle can obtain a faster driving speed, thereby saving driving time. However, if the first steady-state speed is 60km/h and the second steady-state speed is 50km/h, then it is considered that the current vehicle can reach a faster driving speed while continuing to drive in the current lane, wherein, km/h Representative speed unit: kilometers per hour. In this way, the current lane of the autonomous vehicle and the driving information of other vehicles in the nearby lanes can be analyzed before the actual lane change, so as to obtain the decision of lane change planning in advance, save the time and cost of the vehicle to change lanes, and avoid back and forth Repeat lane change.

The above-mentioned device can be applied to the scenario of planning lane changes during driving of an autonomous vehicle. Obtain the environmental image information of the vehicle through the first acquisition module, obtain the nearby lane information of the vehicle according to the environmental image information; obtain the first driving speed of the vehicle through the second acquisition module, and obtain the second driving speed of the nearby vehicles of the vehicle according to the nearby lane information , according to the first driving speed and the second driving speed, obtain the first steady-state speed and the second steady-state speed; judge whether the second steady-state speed is greater than the first steady-state speed through the judging module, and if so, change the lane of the vehicle It can solve the problems of unreasonable timing of vehicle lane change and high time cost.

For the specific limitations of the vehicle lane change planning device, please refer to the above limitation on the vehicle lane change planning method, which will not be repeated here. Each module in the above vehicle lane change planning device can be fully or partially realized by software, hardware and combinations thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure may be as shown in FIG. 10 . The computer device includes a processor, memory, network interface and database connected by a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs and databases. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the data of vehicle lane change planning. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a vehicle lane change planning method is realized.

Those skilled in the art can understand that the structure shown in Figure 10 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation to the computer equipment on which the solution of this application is applied. The specific computer equipment can be More or fewer components than shown in the figures may be included, or some components may be combined, or have a different arrangement of components.

In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the computer program, the following steps are implemented:

Obtaining the environmental image information of the vehicle, and obtaining the nearby lane information of the vehicle according to the environmental image information;

Obtaining a first traveling speed of a vehicle directly in front of the vehicle and a second traveling speed of a vehicle diagonally ahead of the vehicle according to the nearby lane information, and obtaining a second traveling speed according to the first traveling speed and the second traveling speed A steady-state speed and a second steady-state speed, wherein the first steady-state speed is the predicted speed of the vehicle in the current lane, and the second steady-state speed is the predicted speed of the vehicle in a nearby lane ;

Judging whether the second steady-state speed is greater than the first steady-state speed, and if so, performing lane-changing processing on the vehicle.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

Obtaining the environmental image information of the vehicle, and obtaining the nearby lane information of the vehicle according to the environmental image information;

Obtaining a first traveling speed of a vehicle directly in front of the vehicle and a second traveling speed of a vehicle diagonally ahead of the vehicle according to the nearby lane information, and obtaining a second traveling speed according to the first traveling speed and the second traveling speed A steady-state speed and a second steady-state speed, wherein the first steady-state speed is the predicted speed of the vehicle in the current lane, and the second steady-state speed is the predicted speed of the vehicle in a nearby lane ;

Judging whether the second steady-state speed is greater than the first steady-state speed, and if so, performing lane-changing processing on the vehicle.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any references to memory, storage, database or other media used in the various embodiments provided in the present application may include non-volatile and/or volatile memory. Nonvolatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

The above-mentioned embodiments only represent several implementation modes of the present application, and the description thereof is relatively specific and detailed, but it should not be construed as limiting the scope of the patent for the invention. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the scope of protection of the patent application should be based on the appended claims.

Claims (10)

1. A method for vehicle lane change planning, comprising:

acquiring environment image information of a vehicle, and acquiring nearby lane information of the vehicle according to the environment image information;

obtaining a first running speed of a vehicle right in front of the vehicle and a second running speed of the vehicle obliquely in front of the vehicle according to the nearby lane information, and obtaining a first steady-state speed and a second steady-state speed according to the first running speed and the second running speed, wherein the first steady-state speed is a predicted running speed of the vehicle in a current lane, and the second steady-state speed is a predicted running speed of the vehicle in a nearby lane;

and judging whether the second steady-state speed is greater than the first steady-state speed, and if so, performing lane changing processing on the vehicle.

2. The vehicle lane change planning method according to claim 1, wherein acquiring environment image information of a vehicle, and the step of acquiring nearby lane information of the vehicle based on the environment image information includes:

acquiring a first environment image corresponding to a first moment, and acquiring first position information of the nearby vehicle and first lane type information of the nearby lane according to the first environment image;

acquiring a second environment image corresponding to a second moment, and acquiring second position information of the nearby vehicle and second lane type information of the nearby lane according to the second environment image;

the nearby lane information includes: the first location information, the first lane type information, the second location information, the second lane type information.

3. The vehicle lane-change planning method according to claim 2, wherein the step of obtaining a first traveling speed of a vehicle directly in front of the vehicle and a second traveling speed of a vehicle diagonally in front of the vehicle from the nearby lane information includes:

obtaining forward running speeds of a plurality of vehicles in front according to the first position information and the second position information, and obtaining the first running speed according to the forward running speeds, wherein the vehicles in front belong to the same lane as the vehicles and are in front of the running direction of the vehicles;

and obtaining oblique driving speeds of a plurality of oblique front vehicles according to the first position information, the second position information, the first lane type information and the second lane information, and obtaining the second driving speed according to the oblique driving speeds, wherein the oblique front vehicles and the vehicles belong to different lanes and are in front of the driving direction of the vehicles.

4. The vehicle lane change planning method according to claim 1, wherein the step of obtaining a first steady-state speed and a second steady-state speed from the first traveling speed and the second traveling speed comprises:

traversing a plurality of first running speeds corresponding to the sampling time, and obtaining a first intermediate steady-state speed according to a preset first weight value, wherein the mathematical expression of the first intermediate steady-state speed is as follows:

V1 _m (t)＝w1*V1 _d (t)+(1-w1)*V1 _m (t-1)

wherein, V1 _m (t) represents the first intermediate steady-state speed, w1 represents the first weight value, t represents the corresponding time within the sampling time, V1 _d Representing the first travel speed;

traversing a plurality of first intermediate steady-state speeds corresponding to the sampling time according to the first intermediate steady-state speed and a preset second weight value to obtain the first steady-state speed, wherein the mathematical expression of the first steady-state speed is as follows:

V1 _a (t)＝w2*V1 _m (t)+(1-w2)*V1 _a (t-1)

wherein, V1 _a (t) represents said first steady state speed, w2 represents said second weight value;

traversing the plurality of second running speeds corresponding to the sampling time, and obtaining a second intermediate steady-state speed according to the first weight value, wherein the mathematical expression of the second intermediate steady-state speed is as follows:

V2 _m (t)＝w1*V2 _d (t)+(1-w1)*V2 _m (t-1)

wherein, V2 _m (t) represents the second steady-state velocity, w1 represents the first weight value, t represents the corresponding time within the sampling time, V2 _d Representing the second travel speed;

traversing a plurality of second intermediate steady-state speeds corresponding to the sampling time according to the second intermediate steady-state speeds and the second weight value to obtain the second steady-state speeds, wherein the second steady-state speeds are mathematically expressed as:

V2 _a (t)＝w2*V2 _m (t)+(1-w2)*V2 _a (t-1)

wherein, V2 _a (t) represents the second steady-state speed, and w2 represents the second weight value.

5. The vehicle lane-change planning method according to claim 1, wherein the step after obtaining the nearby lane information of the vehicle further comprises:

obtaining obstacle information of the nearby lane according to the nearby lane information, wherein the obstacle information comprises: a size of an obstacle, a distance length between the obstacle and the vehicle;

according to the obstacle information, obtaining a first travelable width of the vehicle in the current lane and a second travelable width of the vehicle in the nearby lane;

determining whether the first driving width is greater than a width of the vehicle; if so, the vehicle normally runs; if not, judging whether the second running width is larger than the width of the vehicle, if so, performing lane change processing on the vehicle, and if not, performing deceleration processing on the vehicle.

6. The vehicle lane change planning method according to claim 1, wherein the step after obtaining the nearby lane information of the vehicle further comprises:

acquiring a travelable lane type corresponding to the vehicle;

acquiring the lane type of the current lane outside a preset sampling distance;

judging whether the type of the drivable lane is consistent with that of the current lane or not; if so, the vehicle normally runs; and if not, performing lane change processing on the vehicle.

7. The vehicle lane change planning method according to claim 1, wherein the step after obtaining the nearby lane information of the vehicle further comprises:

acquiring a driving destination of the vehicle, and acquiring a preset driving path of the vehicle according to the driving destination;

judging whether a corresponding driving lane of the vehicle outside a preset sampling distance is consistent with the current lane or not according to the preset driving path and the information of the nearby lane; if so, the vehicle normally runs; and if not, performing lane change processing on the vehicle.

8. A vehicle lane change planning apparatus, comprising:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring environment image information of a vehicle and acquiring nearby lane information of the vehicle according to the environment image information;

the second obtaining module is used for obtaining a first running speed of the vehicle, obtaining a second running speed of a vehicle nearby the vehicle according to the nearby lane information, and obtaining a first steady-state speed and a second steady-state speed according to the first running speed and the second running speed, wherein the first steady-state speed is a predicted running speed of the vehicle in a current lane, and the second steady-state speed is a predicted running speed of the vehicle in a nearby lane;

and the judging module is used for judging whether the second steady-state speed is greater than the first steady-state speed or not, and if so, performing lane change processing on the vehicle.

9. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the computer program, carries out the steps of the method for vehicle lane change planning of any of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method for vehicle lane change planning of any of claims 1 to 7.

Images